WO2022142808A1 - Storage robot, camera assembly and positioning method - Google Patents
Storage robot, camera assembly and positioning method Download PDFInfo
- Publication number
- WO2022142808A1 WO2022142808A1 PCT/CN2021/131015 CN2021131015W WO2022142808A1 WO 2022142808 A1 WO2022142808 A1 WO 2022142808A1 CN 2021131015 W CN2021131015 W CN 2021131015W WO 2022142808 A1 WO2022142808 A1 WO 2022142808A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- positioning image
- positioning
- window
- mirror
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000000712 assembly Effects 0.000 claims description 12
- 238000000429 assembly Methods 0.000 claims description 12
- 230000001681 protective effect Effects 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000009434 installation Methods 0.000 description 7
- 230000003247 decreasing effect Effects 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002985 plastic film Substances 0.000 description 1
- 229920006255 plastic film Polymers 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001012 protector Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
- B65G1/02—Storage devices
- B65G1/04—Storage devices mechanical
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B17/00—Details of cameras or camera bodies; Accessories therefor
- G03B17/56—Accessories
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B30/00—Camera modules comprising integrated lens units and imaging units, specially adapted for being embedded in other devices, e.g. mobile phones or vehicles
Definitions
- the present application relates to the technical field of cargo handling equipment, and in particular, to a storage robot, a camera assembly and a positioning method.
- Intelligent logistics terminals are the inevitable trend of terminal logistics development, and warehousing robots can realize intelligent logistics terminals for automated handling operations.
- the positioning and navigation of the warehouse robot mainly relies on scanning and configuring the positioning images on the ground, such as QR codes, to obtain accurate information, so as to obtain the current position of the warehouse robot.
- a window is formed on the chassis of the warehouse robot, and the window faces the surface where the positioning image is located, such as the ground.
- a stand and a camera are set on the chassis, and the fixed part of the stand is located directly above the window, and the camera is located on the stand.
- the lens of the camera is facing the window, to shoot the two-dimensional code on the ground, so that the real-time position of the warehouse robot can be obtained by analyzing the two-dimensional code.
- the distance between the fixed part of the stand and the chassis needs to be high enough during setup, which increases the height of the stand and the camera on the storage robot. space, which affects the installation of other components in the warehouse robot.
- the embodiments of the present application provide a storage robot, a camera assembly and a positioning method to overcome the problem that the existing stand and the camera occupy a large space on the height of the storage robot, thereby affecting the installation of other components in the storage robot.
- an embodiment of the present application provides a camera assembly for navigation and positioning of a warehouse robot, wherein the camera assembly includes a mirror and an image acquisition device;
- the reflector is located on the inner surface of the chassis of the warehouse robot, and the chassis has a window facing the surface where the image is positioned.
- the reflector is arranged on the side of the window and tilted toward the window, and the reflector's reflective surface faces the window.
- the image acquisition device is located in the window. On the reflected light path of the reflector, the lens of the image acquisition device is aligned with the reflecting surface.
- the projection of the reflecting surface of the reflector on the chassis at least completely covers the window.
- the image acquisition device is arranged on the side of the window.
- the camera assembly further includes at least one shading member
- the reflector includes a first edge, a second edge, a third edge and a fourth edge arranged around the axis, the first edge is located on the chassis, and one end of the shading member is arranged at least among the second edge, the third edge and the fourth edge. on any one, and the other end of the shading member extends toward the direction of the image acquisition device.
- the number of shading members is at least three;
- At least three light shielding members are respectively disposed on the second edge, the third edge and the fourth edge respectively.
- the second edge, the third edge and the fourth edge are extended with a light-shielding edge toward the direction of the image capturing device, and the light-shielding edge and the reflector are integrally formed as an integral piece;
- the light blocking edge is configured as a light blocking member.
- the image capturing device is slidably arranged on the chassis to adjust the distance between the image capturing device and the reflective surface.
- the camera assembly further includes a bracket
- the image acquisition device is arranged on the chassis through a bracket, the image acquisition device is rotatably connected to the bracket, and the lens of the image acquisition device can be rotated toward or away from the inner surface of the chassis to adjust the alignment of the lens of the image acquisition device and the reflective surface angle.
- the reflector is rotatably connected to the chassis, and the end of the reflector away from the chassis can be rotated toward or away from the inner surface of the chassis to adjust the angle between the reflector and the chassis.
- the camera assembly further includes a control unit and a drive unit;
- the driving unit is connected with the image acquisition device to drive the movement or rotation of the image acquisition device;
- the drive unit is signal-connected to the mirror to drive the mirror to rotate;
- the control unit is signal-connected with the driving unit, and controls the driving unit to work with the signal.
- the image acquisition device is a periscope camera.
- the included angle between the reflector and the chassis is 30°-60°.
- an embodiment of the present application further provides a storage robot, including a chassis and at least one set of the above-mentioned camera assemblies;
- the camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the image is positioned, the mirror of the camera assembly is arranged on one side of the window and tilted towards the direction of the window, and the reflecting surface of the mirror faces the window, and the image acquisition device is located in the window. On the reflected light path of the reflector, the lens of the image acquisition device is aligned with the reflecting surface.
- the number of windows is at least two, and the at least two windows are arranged at intervals in the moving direction of the chassis;
- the number of camera assemblies is at least two, and the at least two camera assemblies are respectively arranged corresponding to the at least two windows.
- the storage robot further includes a light-transmitting protector
- the window is configured as a light-transmitting port opened on the chassis, and the light-transmitting protection member covers the light-transmitting port.
- an embodiment of the present invention provides a positioning method, which is applied to a storage robot, where the storage robot includes a chassis and a camera assembly, the camera assembly is located on the inner surface of the chassis, and the chassis has an orientation image on the chassis.
- the mirror of the camera assembly is arranged on one side of the window and inclined toward the direction of the window, and the reflective surface of the mirror faces the window, and the image acquisition device is located in the mirror on the reflected light path of the mirror, and the lens of the image acquisition device is aligned with the reflective surface; the method includes:
- the position of the warehouse robot is determined according to the first positioning image.
- FIG. 1 is a partial structural schematic diagram of a first structure of a storage robot provided by an embodiment of the present invention
- Fig. 2 is the partial sectional view of Fig. 1;
- Fig. 3 is the light path diagram of the camera assembly and the positioning image in Fig. 1;
- FIG. 4 is a partial structural schematic diagram of a second structure of a storage robot provided by an embodiment of the present invention.
- FIG. 5 is a partial cross-sectional view of a third structure of a storage robot provided by an embodiment of the present invention.
- FIG. 6 is a partial cross-sectional view of a fourth structure of a storage robot provided by an embodiment of the present invention.
- FIG. 7 is a partial structural schematic diagram of a fifth structure of a storage robot provided by an embodiment of the present invention.
- FIG. 8 is a flowchart of steps of a positioning method according to an embodiment of the present invention.
- the positioning and navigation of warehouse robots mainly rely on scanning and configuring positioning images on the ground, such as QR codes, to obtain accurate information, thereby obtaining the current position of the warehouse robots.
- a window is formed on the chassis of the warehouse robot in the conventional technology, and the window faces the ground, that is, the window is located on the ground
- a stand and a camera are set on the chassis, and the fixed part of the stand is located directly above the window, the camera is located on the fixed part of the stand, and the lens of the camera is facing the window, so as to take pictures on the ground.
- the two-dimensional code is then parsed to obtain the real-time position of the warehouse robot, so as to realize the positioning and navigation of the warehouse robot.
- the fixed part of the stand has a light-transmitting hole, and the light-transmitting hole is located directly above the window of the chassis.
- the lens of the camera is located in the The lens can obtain positioning images on the ground, such as QR codes, through light-transmitting holes and windows.
- the positioning image information can be directly analyzed and processed by the camera to determine the position of the warehouse robot.
- the camera can also be connected with the processor. After the camera obtains the information of the positioning image, the information of the positioning image is transmitted to the processor, and the positioning image information is analyzed and processed by the processor to determine The location of the warehouse robot.
- the distance between the fixed part of the stand and the chassis needs to be high enough during setting, which increases the distance between the stand and the camera at the height of the storage robot. Occupy space, thus affecting the installation of other components in the warehouse robot.
- the embodiment of the present invention provides a storage robot and a camera assembly, wherein the camera assembly is used for the navigation and positioning of the storage robot.
- the camera assembly of the storage robot is configured to include a reflector and an image acquisition device, and the reflector is It is arranged on the inner surface of the chassis of the storage robot, and is inclined at the side of the window of the chassis, and the reflective surface of the mirror faces the window, the image acquisition device is set on the reflected light path of the mirror, and the The lens is aimed at the reflective surface, so that when the warehouse robot moves to the surface where the positioning image is located, such as a positioning image on the ground, the positioning image on the ground can be incident on the reflecting surface of the reflector through the window, and then pass the reflection of the reflector.
- the surface reflects the incident light into the lens of the image acquisition device, and then analyzes the positioning image information through the image acquisition device or other processors, and finally obtains the location of the storage robot, realizing the positioning and navigation of the storage robot.
- the camera assembly of the embodiment of the present invention reflects the positioning image of the surface where the positioning image is located into the lens of the image acquisition device through the mirror, and it is not necessary to set the image acquisition device at a higher distance from the inner surface of the chassis. It reduces the occupied size of the camera assembly in the direction perpendicular to the chassis, that is, reduces the space occupied by the camera assembly in the height direction of the storage robot, which not only avoids the impact of the installation of other components in the storage robot, but also Moreover, the height size of the entire storage robot is reduced, which facilitates the handling and storage of the storage robot.
- FIG. 1 is a partial structural schematic diagram of a first structure of a storage robot provided by an embodiment of the present invention
- FIG. 2 is a partial cross-sectional view of FIG. 1 .
- an embodiment of the present invention provides a camera assembly 120 , and the camera assembly 120 is used for positioning and navigation of the warehouse robot 100 .
- FIG. 3 is an optical path diagram of the camera assembly and the positioning image in FIG. 1 .
- the warehouse robot 100 includes a chassis 110 and a camera assembly 120 according to an embodiment of the present invention.
- the camera component 120 is used for acquiring and analyzing the positioning image 200 on the plane 300 where the positioning image of the warehouse storing goods is located, so as to determine the position of the storage robot 100 in the warehouse and realize the positioning and navigation of the storage robot 100 .
- the surface 300 where the positioning image is located may be the floor of the warehouse, or may be the surface of the shelf in the warehouse.
- the surface 300 where the positioning image is located is the floor of the warehouse, and the positioning image 200 of the corresponding position on the ground is acquired and processed by the camera component 120 to determine the warehouse.
- the specific position of the robot 100 on the ground When the storage robot 100 can move on the shelf of the warehouse during the working process, the surface 300 where the positioning image is located may be the surface of the shelf, and the positioning image 200 of the corresponding position on the shelf is acquired and processed by the camera component 120 to determine the storage The specific position of the robot 100 on the shelf.
- the positioning image 200 may be a barcode, a two-dimensional code and other images with indication. It can be understood that, in order to realize the positioning and navigation of the warehouse robot 100, different positioning images 200 are respectively set at different positions on the surface 300 where the positioning image is located, such as the ground. Accurate position of the warehouse robot 100 can be obtained by acquiring different positioning images 200 .
- the embodiment of the present invention is specifically described by taking the positioning image 200 as a two-dimensional code and the surface 300 where the positioning image is located as the ground as an example.
- the camera assembly 120 includes a mirror 121 and an image capture device 122 .
- the reflector 121 is located on the inner surface of the chassis 110 .
- the inner surface of the chassis 110 refers to the surface of the chassis 110 facing the interior of the warehouse robot 100 .
- the chassis 110 has a window 111 facing the surface 300 where the image is positioned, such as the ground, the mirror 121 is arranged on the side of the window 111 and is inclined toward the direction of the window 111, and the reflective surface of the mirror 121 (as shown in a in FIG.
- the window 111 Facing the window 111, in this way, the light of the positioning image 200 on the ground, such as the two-dimensional code, can be irradiated on the reflective surface a of the reflector 121 through the window 111, that is, when the window 111 of the warehouse robot 100 moves to the ground
- the reflecting surface a of the mirror 121 can receive the incident light of the two-dimensional code through the window 111 (as shown by b1 in FIG. 3 ).
- the size of the window 111 on the chassis 110 is usually larger than the size of the positioning image 200 such as a two-dimensional code, to ensure that each part of the positioning image 200 can be irradiated on the reflective surface a of the mirror 121 through the window 111 .
- the shape of the window 111 may be any shape such as a rectangle, a square, or a circle, and may be specifically set according to the shape of the outer contour of the positioning image 200 .
- the window 111 can be set to a circular structure.
- the shape of the window 111 may not correspond to the shape of the outer contour of the positioning image 200 , as long as the size of the window 111 is larger than the size of the positioning image 200 , the range of the window 111 can cover the positioning image 200 .
- the image acquisition device 122 is located on the reflective optical path of the reflector 121 (the optical path shown in b2 in FIG. 3 ), and the lens 1221 of the image acquisition device 122 is aligned with the reflective surface a, so that the two-dimensional The incident light b1 incident on the reflective surface a through the window 111 of the code can be reflected into the lens 1221 of the image acquisition device 122 through the reflective surface a, so that the lens 1221 of the image acquisition device 122 can receive and acquire the image information of the two-dimensional code Then, by analyzing and processing the image information, the current position of the storage robot 100 is finally determined, so as to realize the positioning and navigation of the storage robot 100 .
- the light shown by b1 in FIG. 3 is the reflected light reflected by the reflecting surface a after the two-dimensional code enters the reflecting surface a through the window 111 .
- the two-dimensional code on the ground can be irradiated on the reflecting surface a of the reflecting mirror 121 through the window 111, and then The incident light b1 of the two-dimensional code is reflected into the lens 1221 of the image acquisition device 122 by the reflective surface a of the reflecting mirror 121, and then the image information of the two-dimensional code is analyzed, and finally the position of the storage robot 100 is obtained, which realizes Positioning and navigation of the warehouse robot 100 .
- a positioning image 200 such as a two-dimensional code
- the image acquisition device 122 acquires the image information of the two-dimensional code
- the image information can be directly parsed and processed by the image acquisition device 122 to finally determine the position of the warehouse robot 100 .
- the camera assembly 120 may further include a processor (not shown in the figure), and the processor is in signal connection with the image capture device 122 .
- the image acquisition device 122 acquires the image information of the two-dimensional code
- the image information is transmitted to the processor, and the image information is analyzed and processed by the processor, and the position of the warehouse robot 100 is finally determined.
- the camera assembly 120 in the embodiment of the present invention reflects the light of the two-dimensional code on the ground into the lens 1221 of the image acquisition device 122 through the reflector 121 , and the image acquisition device 122 does not need to be set at a distance
- the higher position of the inner surface of the chassis 110 reduces the space occupied by the camera assembly 120 in the height direction of the storage robot 100 , which not only avoids the occurrence of the impact caused by the installation of other components in the storage robot 100 , but also reduces the size of the entire storage robot 100
- the height dimension is convenient for the handling and storage of the storage robot 100.
- the height direction of the storage robot 100 refers to the direction perpendicular to the chassis 110 , as shown in the y direction in FIG. 2 .
- the reflecting mirror 121 and the image collecting device 122 are disposed on the inner surface of the chassis 110, that is, the reflecting mirror 121 and the image collecting device 122 are disposed inside the storage robot 100 to protect the reflecting mirror. 121 and the image acquisition device 122 are protected from the external environment. For example, the mirror 121 and the image acquisition device 122 are prevented from being damaged by being bumped by other objects on the ground during the movement of the warehouse robot 100, thereby extending the length of the mirror 121 and the image acquisition device 122. Service life of image capture device 122 .
- the image acquisition device 122 may be a periscope camera, so as to improve the stability of telephoto shooting of the image acquisition device 122 .
- the waterproof effect of the image acquisition device 122 is improved.
- the thickness of the body is reduced while the shooting clarity is ensured, thereby reducing the space occupied by the image acquisition device 122 in the storage robot 100 .
- the embodiment of the present invention does not exclude the use of a traditional camera as the image capturing device 122 .
- the image acquisition device 122 can be arranged on the side of the window 111 during the specific setting.
- the image acquisition device 122 and the mirror 121 are respectively arranged opposite to the window 111 .
- the camera assembly 120 is concentrated near the window 111 of the chassis 110 , so as to provide suitable space for the installation of other components on the chassis 110 .
- the reflector 121 in the embodiment of the present invention may directly adopt the reflector in the prior art.
- the projection of the reflection surface a of the reflector 121 on the chassis 110 at least completely covers the window 111 .
- the outer contour of the projection area of the reflection surface a on the chassis 110 is just at the edge of the window 111, so that the incident light b1 of the two-dimensional code under the window 111 just passes through the window 111 and completely enters the reflection surface a.
- the size of the outer contour of the projection area of the reflection surface a on the chassis 110 is larger than the size of the window 111 , that is to say, the outer contour of the projection area of the reflection surface a on the chassis 110 is located at the edge of the window 111 Externally, this can further ensure that the portion of the incident light b1 of the two-dimensional code passing through the window 111 can be completely incident on the reflective surface a, thereby ensuring that the lens 1221 of the image capturing device 122 can obtain a complete two-dimensional code.
- the angle ⁇ between it and the chassis 110 may be 30°-60°, that is to say, the inclination angle ⁇ of the reflector 121 may be It is 30°-60°, so that the incident angle of the two-dimensional code (the angle between the incident light b1 incident on the two-dimensional code on the reflective surface a and the normal of the reflective surface a) is kept between 30°-60° , that is, the reflection angle (the angle between the reflected light b2 after the incident light b1 is reflected by the reflecting surface a and the normal of the reflecting surface a) is between 30° and 60°. While the distance between the lens 1221 and the chassis 110 is constant, it is ensured that the image capturing device 122 can obtain the complete information of the two-dimensional code from the reflective surface a.
- the angle ⁇ between the reflector 121 and the chassis 110 within the above-mentioned range, it not only ensures that the light of the two-dimensional code is completely incident on the reflecting surface a of the reflector 121, but also avoids the reflection.
- the mirror 121 occupies too much space in the height direction, and at the same time, it is also avoided that the included angle ⁇ is too small to affect the stability of the mirror 121 on the chassis 110 .
- the angle ⁇ between the reflector 121 and the chassis 110 can be an appropriate value such as 30°, 45° or 60°, which can be adjusted according to the distance between the lens 1221 of the reflector 121 and the chassis 110 .
- the angle ⁇ between the reflector 121 and the chassis 110 can be increased.
- the angle ⁇ between the reflector 121 and the chassis 110 can be adjusted to be small.
- FIG. 4 is a partial structural schematic diagram of the second structure of the storage robot provided by the embodiment of the present invention.
- the camera assembly 120 may further include at least one light shielding member 123 .
- the reflector 121 may be a quadrilateral structure, for example, the reflector 121 may be a rectangular structure or a square structure.
- the reflector 121 includes a first edge, a second edge, a third edge and a fourth edge arranged around the axis, wherein the first edge, the second edge, the third edge and the fourth edge are connected end to end in sequence to form a reflector Of the four edges of 121, the first edge is located on the chassis 110, one end of the shading member 123 is disposed on at least any one of the second edge, the third edge and the fourth edge, and the other end of the shading member 123 is used for image capture.
- the direction of the device 122 extends.
- the light-shielding member 123 will be described below by taking as an example that the first edge and the third edge are disposed opposite to each other, and the second edge and the fourth edge are disposed opposite to each other.
- one end of the shading member 123 is connected to the second edge, and the other end of the shading member 123 extends toward the direction of the image capturing device 122 , that is, the shading member 123 is located between the second edge of the mirror 121 and the image capturing device 122 In this way, the shading member 123 blocks the light on the second edge side of the reflector 121, preventing part of the light from entering between the reflector 121 and the image acquisition device 122 through the second edge side of the reflector 121, and causing the reflection The reflected light from the mirror 121 interferes, which affects the acquisition of accurate image information of the two-dimensional code by the image acquisition device 122 .
- the other end of the light shielding member 123 may extend to the image capture device 122.
- one end of the light shielding member 123 is located at the second edge of the mirror 121, and the other end extends to the image capture device. 122, in this way, the shading member 123 can block the plane area formed between the second edge of the mirror 121 and the image acquisition device 122, so that external light cannot enter the mirror 121 and the image from any position in the plane area. between the collection devices 122 .
- the other end of the shading member 123 that is, the end away from the mirror 121, may have a certain distance from the image capturing device 122, so that the shading member 123 can shield part of the light on the second edge side of the mirror 121 from light.
- the height of the shading member 123 is the same as the length of the edge of the reflector 121.
- the shading member 123 includes a second oppositely disposed along the height direction. One end and a second end, wherein the first end extends to the top end of the second edge, and the second end extends to the bottom end of the second edge (ie, on the chassis 110 ), so that any position of the second edge of the mirror 121 has Shading member 123 .
- the number of the shading members 123 may be at least three, and the at least three shading members 123 are respectively disposed on the second edge, the third edge and the fourth edge, that is to say, the three shading members 123 are respectively disposed on the second edge, the third edge and the fourth edge. It is blocked on the second edge, the third edge and the fourth edge side of the reflector 121, so that the three shading members 123 block the light entering from the three edge sides of the reflector 121, further improving the shading effect and ensuring the image Accuracy and clarity of the two-dimensional code information collected by the collecting device 122 .
- the shading member 123 can be a shading plate disposed on the chassis 110 when it is specifically arranged, and one end of the shading plate can be connected to the edge of the reflector 121. Of course, one end of the shading plate can only abut on the reflector 121. on the edge.
- the second edge, the third edge and the fourth edge of the reflector 121 extend toward the image capturing device 122 with a light-shielding edge, and the light-shielding edge is integrally formed with the reflector 121
- the light-shielding edge is configured as a light-shielding piece 123 .
- This arrangement not only simplifies the assembly structure of the reflector 121 and the light shielding member 123, but also improves the assembly efficiency of the entire camera assembly 120, and at the same time improves the connection strength between the reflecting mirror 121 and the light shielding member 123, so that the structure of the light shielding member 123 is more Stablize.
- FIG. 5 is a partial cross-sectional view of a third structure of a storage robot provided by an embodiment of the present invention.
- the image capturing device 122 in the embodiment of the present invention can be slidably arranged on the chassis 110 to adjust the distance between the image capturing device 122 and the reflective surface a during specific setting.
- a chute (not shown in the figure) may be provided on the chassis 110, and a sliding part (not shown in the figure) is provided at the bottom of the image capturing device 122, and the sliding part is embedded in the chute and extends along the chute. Sliding in the extending direction, so that the image capturing device 122 can slide along the chute.
- the sliding part may be a sliding block extending downward from the bottom of the image capturing device 122, and the sliding block is slidably arranged in the sliding groove.
- the sliding part may also be a roller disposed at the bottom of the image capture device 122 , and the roller is disposed in the chute so that the image capture device 122 moves more smoothly in the chute.
- the extension direction of the chute (as shown by arrow b in FIG. 5 ) is consistent with the extension direction of the reflected light path of the reflector 121 , so that when the image capture device 122 slides in the chute, the image capture device 122 is always located in the On the reflected light path of the mirror 121 , that is, the image acquisition device 122 always moves left and right along the direction of arrow b.
- the image capture device 122 can be slid to a position closer to the reflection surface a of the mirror 121 until the image captures
- the lens 1221 of the device 122 can receive the reflected light b2 of the two-dimensional code reflected by the reflective surface a, thereby ensuring that the image acquisition device 122 can obtain the complete information of the two-dimensional code.
- the image capturing device 122 can be slid to a position farther from the reflection surface a of the mirror 121 , until the lens 1221 of the image acquisition device 122 can receive the reflected light b2 reflected by the reflective surface a, thereby ensuring that the image acquisition device 122 can acquire the complete information of the two-dimensional code.
- the image acquisition device 122 can adapt to the setting angle of the mirror 121, that is, the inclination angle ⁇ of the mirror 121 is too large or too small.
- FIG. 6 is a partial cross-sectional view of the fourth structure of the storage robot provided by the embodiment of the present invention.
- the camera assembly 120 in the embodiment of the present invention may further include a bracket 124 , the image capture device 122 is disposed on the chassis 110 through the bracket 124 , the image capture device 122 is rotatably connected to the bracket 124 , and the image capture device 122 is rotatably connected to the bracket 124 .
- the lens 1221 can be rotated toward or away from the inner surface of the chassis 110 to adjust the alignment angle between the lens 1221 of the image capture device 122 and the reflective surface a (as shown by ⁇ in FIG. 6 ).
- the rotation direction of the image acquisition device 122 may refer to the direction indicated by arrow c in FIG. 6 .
- the alignment angle between the lens 1221 of the image capture device 122 and the reflection surface a refers to the distance between the line connecting the lens 1221 of the image capture device 122 and any point on the reflection surface a and the normal to the reflection surface a. angle.
- the alignment angle ⁇ between the lens 1221 of the image capturing device 122 and the reflective surface a can be adjusted by rotating the image capturing device 122 on the bracket 124 , so that the alignment angle ⁇ is consistent with the reflection angle, that is, it is ensured that the lens 1221 is finally completely and accurately aligned with the reflecting surface a, so as to ensure that the lens 1221 of the image capturing device 122 can receive the complete light of the two-dimensional code reflected by the reflecting surface a.
- the requirement for the setting of the mirror 121 is reduced, that is, it is not required to completely control the inclination angle ⁇ of the mirror 121 within a certain range.
- the bracket 124 may include a first rotating shaft 1243 , two supporting members 1241 and two fixing members 1242 .
- the two supporting members 1241 are arranged opposite to each other along the direction perpendicular to the reflected light path, and the two fixing members 1242 are respectively fixed on the inner side of the two supporting members 1241 .
- the other fixing member 1242 is arranged on the inner side of the other supporting member 1241, the bottom ends of the two supporting members 1241 are both fixed on the chassis 110, and one end of the first rotating shaft 1243 passes through one of the fixing members 1242 and is movably arranged therein.
- the other end of the first rotating shaft 1243 passes through the other fixing member 1242 and is movably arranged on the other supporting member 1241 .
- the fixing member 1242 is fixedly connected with the supporting member 1241, and the first rotating shaft 1243 can rotate around its own axis.
- the image capturing device 122 is rotatably connected to the first rotating shaft 1243 .
- one end of the image capturing device 122 is provided with a connecting portion with a through hole, and the connecting portion is sleeved on the first rotating shaft 1243 , so that the image capturing device 122 can rotate around the first rotating shaft 1243 to realize the image capturing device 122 . Rotation of the lens 1221.
- a positioning structure may be provided between at least one fixing member 1242 and the image capture device 122, and the image capture device 122 can be stabilized at any angle through the positioning structure.
- the positioning structure may be a plurality of positioning grooves or positioning holes formed on the fixing member 1242, and the plurality of positioning grooves or positioning holes are arranged at intervals along the rotation path of the image capture device 122.
- a positioning protrusion extends from one side of 122 .
- the positioning protrusion is clamped in the corresponding positioning groove or positioning hole on the fixing member 1242, thereby restricting the rotation of the image capturing device 122 and ensuring the stability of the image capturing device 122. This further ensures the clarity of the two-dimensional code received by the lens 1221 of the image capture device 122 .
- the reflector 121 in the embodiment of the present invention is rotatably connected to the chassis 110 , and the end of the reflector 121 away from the chassis 110 can be rotated in a direction close to or away from the inner surface of the chassis 110 to Adjust the angle between the reflector 121 and the chassis 110 (ie, the inclination angle ⁇ of the reflector 121 ).
- the rotation direction of the mirror 121 can be referred to as shown by arrow d in FIG. 6 .
- the reflector 121 by rotating the reflector 121 on the chassis 110, not only when the lens 1221 of the image capture device 122 is fixed, but also the reflector 121 can be rotated to adjust the inclination angle ⁇ of the reflector 121 so that the lens 1221
- the reflective surface a can be completely and accurately aligned to ensure that the lens 1221 of the image acquisition device 122 can receive the complete information of the two-dimensional code reflected by the reflective surface a, and when the camera assembly 120 is used, the mirror 121 can be rotated to the sticker.
- a second rotating shaft 125 can be set on one edge of the window 111, and one end of the mirror 121 can be movably connected to the second rotating shaft 125.
- a through hole can be opened at one end of the reflecting mirror 121, and the second rotating shaft The 125 is movably arranged in the through hole, so that the mirror 121 can be rotated around the second rotation 125 to realize the adjustment of the inclination angle ⁇ .
- the camera assembly 120 may further include a control unit and a driving unit.
- the control unit is connected with the driving unit in signal, and controls the driving unit to work with the signal.
- the driving unit may be connected with the image capturing device 122 to drive the movement or rotation of the image capturing device 122 .
- the drive unit may be connected to the image capture device 122 and set with a first drive motor, the first drive motor is used to drive the image capture device 122 to rotate around the first shaft 1243, and the control unit is used to control the first drive motor to work .
- the first drive motor may be a rotary motor.
- the control unit may send a working signal to the first drive motor, such as a rotating motor, so that the rotating motor uses the first preset parameter.
- the first drive motor such as a rotating motor
- the control unit controls the rotating motor to stop rotating, so as to ensure that the image capture device 122 can capture the two-dimensional image reflected by the mirror 121 code for complete information.
- the first preset parameter includes the rotation speed of the rotating electrical machine.
- the drive unit may be connected to the image capture device 122 and set with a second drive motor, the second drive motor is used to drive the image capture device 122 to move toward or away from the mirror 121, and the control unit is used to control the The second drive motor works.
- the second driving motor may be a stepping motor.
- the control unit may send a working signal to the second driving motor, such as a stepping motor, so that the stepping motor starts with the second preset.
- the second driving motor such as a stepping motor
- the control unit controls the stepper motor to stop moving.
- the second preset parameter includes the movement speed of the stepping motor.
- the driving unit may include a first driving motor and a second driving motor, and the first driving motor and the second driving motor are both connected to the image capturing device 122 .
- the control unit is signal-connected to the first drive motor and the second drive motor, respectively.
- the control unit may send a working signal to the first drive motor, so that the first drive motor is driven with the first preset parameters.
- the image capture device 122 rotates around the first shaft 1243 , and at the same time, the control unit sends a working signal to the second drive motor, so that the second drive motor drives the image capture device 122 toward or away from the mirror 121 with the second preset parameters.
- the direction moves until the lens 1221 of the image capture device 122 captures the complete information of the two-dimensional code reflected by the mirror 121, and the control unit controls the first drive motor and the second drive motor to stop working.
- the driving unit in the embodiment of the present invention can also be connected with the mirror 121 to drive the mirror 121 to rotate.
- the driving unit may be connected to the image capturing device 122 and provided with a third driving motor, the third driving motor is used to drive the mirror 121 to rotate around the second shaft 125 to adjust the inclination angle ⁇ of the mirror 121 .
- the third drive motor may be a rotary motor.
- the control unit may send a working signal to a third drive motor, such as a rotary motor, so that the rotary motor uses the third preset parameter.
- a third drive motor such as a rotary motor
- the mirror 121 is driven to rotate around the second shaft 125 until the image capture device 122 can capture the complete information of the two-dimensional code reflected by the mirror 121, and the control unit controls the third drive motor to stop working.
- the third preset parameter includes the rotation speed of the rotating electrical machine.
- the embodiment of the present invention effectively improves the adjustment efficiency of the mirror 121 and the image acquisition device 122 by setting the control unit and the driving unit to control the activities of the image acquisition device 122 and the mirror 121 with signals, thereby improving the operation efficiency of the entire storage robot 100 Positioning and Navigation Efficiency.
- control unit may be a controller of the prior art, and the specific circuit structure and control principle thereof may directly refer to the prior art.
- an embodiment of the present invention further provides a storage robot, which includes a chassis 110 and at least one set of camera assemblies 120 according to any of the foregoing examples.
- the camera assembly 120 is located on the inner surface of the chassis 110, and the chassis 110 has a window 111 facing the surface 300 where the image is positioned.
- the reflection surface of the mirror 121 faces the window 111
- the image capture device 122 is located on the reflected light path of the mirror 121
- the lens 1221 of the image capture device 122 is aligned with the reflection surface.
- the two-dimensional code on the ground can be irradiated to the mirror 121 through the window 111 .
- the incident light b1 of the two-dimensional code is reflected to the lens 1221 of the image acquisition device 122 through the reflecting surface a of the reflecting mirror 121, and then the image information of the two-dimensional code is analyzed, and finally the storage is obtained.
- the location of the robot 100 realizes the positioning and navigation of the warehouse robot 100 .
- the camera assembly 120 in the embodiment of the present invention reflects the light of the two-dimensional code on the ground into the lens 1221 of the image acquisition device 122 through the reflector 121 , and it is not necessary to set the image acquisition device 122 at a distance from the inner surface of the chassis 110 .
- the higher position reduces the space occupied by the camera assembly 120 in the height direction of the storage robot 100, which not only avoids the impact of the installation of other components in the storage robot 100, but also reduces the height dimension of the entire storage robot 100. The handling and storage of the storage robot 100 are facilitated.
- the window 111 in the embodiment of the present invention may be a light-transmitting port opened on the chassis 110 during specific setting.
- the storage robot according to the embodiment of the present invention may further include a light-transmitting protection member.
- the light-transmitting protective member covers the light-transmitting port to isolate the inner cavity of the storage robot 100 from the external environment, thereby ensuring that the camera assembly 120 and other components in the storage robot 100 will not be damaged by external dust and other sundries. Further, the service life of components such as the camera assembly 120 is prolonged.
- the light-transmitting protection member may include, but is not limited to, any one of a light-transmitting plastic film and a light-transmitting glass.
- FIG. 7 is a partial structural schematic diagram of a fifth structure of a storage robot provided by an embodiment of the present invention.
- the number of windows 111 may be one or more, for example, the number of windows 111 is at least two, and at least two windows 111 are arranged at intervals in the moving direction of the chassis 110 .
- the moving direction of the chassis 110 may refer to the direction shown by x in FIG. 7 .
- the number of the camera assemblies 120 is at least two, and the at least two camera assemblies 120 are respectively arranged corresponding to the at least two windows 111 .
- mirrors 121 and image acquisition devices 122 are provided on both sides of each window 111 .
- the window 111 located on the left side of the two windows 111 is referred to as the first window 1111
- the window 111 located on the right side is referred to as the second window 1112 .
- the warehouse robot 100 moves along the x-direction.
- the positioning image such as a positioning image 200 (such as a two-dimensional code) on the ground
- the two-dimensional code on the ground can be illuminated through the first window 1111 to the reflective surface a of the mirror 121 on the side of the first window 1111, and then reflect the incident light b1 of the two-dimensional code to the image on the side of the first window 1111 through the reflective surface a of the mirror 121
- the image information of the two-dimensional code is analyzed to obtain the first position where the warehouse robot 100 is located.
- the warehouse robot 100 continues to move along the x-direction.
- the second window 1112 moves to the surface 300 where the positioning image is located, such as a positioning image 200 (such as a two-dimensional code) on the ground
- the two-dimensional code on the ground can pass through the second
- the window 1112 illuminates the reflective surface a of the mirror 121 provided on the side of the second window 1112, and then reflects the incident light b1 of the two-dimensional code to the reflective surface a of the mirror 121 to the second window 1112-1.
- the image information of the two-dimensional code is analyzed to obtain the second position where the warehouse robot 100 is located.
- the determined accuracy of the position of the storage robot 100 can be obtained.
- the first position is inconsistent with the second position, it can be concluded that the determined position of the storage robot 100 is inaccurate and needs to be re-determined.
- the warehouse robot 100 can be positioned and navigated through the other camera assembly 120 , which improves the positioning reliability of the camera assemblies 120 .
- FIG. 8 is a flowchart of steps of a positioning method according to an embodiment of the present invention, including: S201 to S202:
- S201 Acquire a first positioning image in the mirror collected by the image collection device.
- the generation process of the first positioning image includes the following two stages.
- the first stage the mirror images the positioning image on the ground through the window, and the image is formed in the mirror;
- the second stage the image acquisition device collects the image in the mirror image to get the first positioning image.
- S202 Determine the position of the warehouse robot according to the first positioning image.
- the location of the warehouse robot refers to the location of the warehouse robot in the warehouse.
- the position of the warehouse robot may be determined according to the content of the first positioning image, and the content of the first positioning image at different positions is different.
- the first positioning image may include position information, so that the position information may be obtained by parsing the first positioning image.
- the first positioning image may be a two-dimensional code including location information, so that the two-dimensional code may be parsed to obtain the location information.
- the first positioning image does not include position information, so that the first positioning image can be matched with the image data preset in the database. If the matching is successful, the matched first positioning image will be stored in the database. The corresponding position is used as the position of the warehouse robot.
- the database stores several image data and corresponding position information.
- the position information corresponding to the image data in the database is used as the position corresponding to the first positioning image in the database.
- the positional relationship between the mirror, the window, and the image acquisition device can be adjusted to reacquire the first positioning image or obtain a plurality of first positioning images, so as to determine the determination according to the re-acquired first positioning image
- the position of the storage robot, or the determination of the position of the storage robot according to multiple first positioning images helps to improve positioning accuracy and success rate.
- the positional relationship may be adjusted in the following manner: adjusting the inclination angle between the mirror and the window; and/or adjusting the inclination angle between the image capture device and the window; and/or adjusting the image capture device and the mirror the distance between.
- the adjustment of the inclination angle between the reflector and the window can be realized by adjusting the degree of inclination of the reflector, and the reflector can be adjusted and fixed on the chassis. Adjusting the inclination angle between the image capture device and the window can be achieved by adjusting the inclination of the image capture device, and the image capture device can be adjusted and fixed on the chassis. Adjusting the inclination angle between the image capturing device and the window can be achieved by adjusting the position of the image capturing device, for example, installing the image capturing device on the slideway to slide the image capturing device.
- the foregoing S202 includes S2021 to S2022:
- the unrecognizable first positioning image may be caused by the distortion of the first positioning image, and the first positioning image distortion includes: a partial area of the first positioning image is missing, the first positioning image is deformed, and a partial area of the first positioning image is occluded or reflective.
- Whether the first positioning image can be identified can be determined in two ways.
- the first way is to identify the first positioning image and determine whether the first positioning image can be identified according to the recognition result; the second way is to determine whether the first positioning image is identifiable according to the degree of distortion of the first positioning image.
- the parameter determines whether the first positioning image can be identified. For details, refer to S2023 to S2025:
- the distortion degree parameter is used to represent the degree of difference between the first positioning image and the standard positioning image. It can be understood that the larger the distortion degree parameter is, the larger the difference degree is; the smaller the distortion degree parameter is, the smaller the difference degree is.
- the standard positioning image corresponds to the preset graphic, and the shape and size of the preset graphic can be set. If the shape and size of the first positioning image are inconsistent with the standard positioning image, it represents the first positioning image.
- the image is distorted, and the distortion degree parameter can be determined according to the degree of difference between the shape and size; when the shape and size of the first positioning image are consistent with the shape and size of the standard positioning image, it means that the first positioning image is not distorted.
- the distortion degree parameter of the first positioning image can be determined according to the following S20231 to S20232 or S20233 to S20235, wherein S20231 and S20232 can be used to determine whether the first positioning image is deformed or lacks an edge part, and S20233 to S20235 can be used to It is determined whether there is reflection or occlusion in the first positioning image.
- S20231 and S20232 may be performed, or only S20233 to S20235 may be performed, and the distortion degree parameters determined by S20231 and S20232 and the distortion degree parameters determined by S20233 to S20235 may be synthesized to obtain the distortion degree of the first positioning image. parameter.
- S20231 Determine the edge pixels of the first positioning image.
- the edge pixels are pixels located at the edge of the first positioning image.
- determining an edge pixel, for any pixel in the first positioning image (hereinafter referred to as a candidate pixel), it can be determined whether there is a pixel located to the left, right, below, or above the candidate pixel.
- the candidate pixel point is determined to be the edge pixel point on the left side of the first positioning image; if there is no pixel point located to the right of the candidate pixel point, the candidate pixel point is determined to be The candidate pixel point is the edge pixel point on the right side of the first positioning image; if there is no pixel point located above the candidate pixel point, the candidate pixel point is determined as the edge pixel point on the upper side of the first positioning image point; if not If there is a pixel point located below the candidate pixel point, the candidate pixel point is determined to be the lower edge pixel point of the first positioning image.
- a candidate pixel point may be an edge pixel point on at least two sides of the upper side, the left side, the lower side, and the right side.
- S20232 Determine the degree of difference between the graphics formed by the edge pixels and the preset graphics of the first positioning image, and determine the distortion degree parameter of the first positioning image.
- the distortion degree parameter may include: the degree of shape difference between the figure formed by the edge pixels and the preset figure, and the degree of size difference between the figure formed by the edge pixels and the preset figure.
- the shape difference degree and the size difference degree may be weighted as the distortion degree parameter of the first positioning image. Since the distortion when the shapes are inconsistent is usually larger, a larger weight can be set for the degree of shape difference, and a smaller weight can be set for the degree of size difference.
- the above-mentioned shape difference degree can be set to two values.
- the shape difference degree can be set as the first shape difference value;
- the degree of shape difference may be set as the second shape difference value.
- the first shape difference is greater than the second shape difference.
- a typical value situation may be that the first shape difference is a positive number, and the second shape difference may be 0.
- the above-mentioned size difference degree can be represented by the length difference, width difference, area difference, etc. between the figure formed by the edge pixels and the preset figure.
- S20233 Determine the average brightness of the first positioning image.
- the average brightness of the first positioning image may be an average value of brightness values of each pixel in the first positioning image.
- S20234 Determine a target pixel whose brightness difference from the average brightness in the first positioning image is greater than a preset brightness difference threshold.
- the brightness difference value is the absolute value of the difference between the brightness value of the pixel point and the average brightness
- the target pixel point is the pixel point in the first positioning image whose brightness difference value is greater than the preset brightness difference threshold, that is, the first positioning image Pixels that are too bright or too small. It can be understood that when multiple pixels with consecutive positions are target pixels, then multiple consecutive pixels in the position form an over-bright area or an over-dark area, an over-bright area is a reflective area, and an over-dark area is an occluded area. .
- S20235 Determine the distortion degree parameter of the first positioning image according to the target pixel point.
- the distortion degree parameter determined in S20235 is used to represent the distortion degree of the first positioning image in terms of brightness.
- the number of target pixels can be used as the distortion degree parameter; in another way, the ratio between the number of target pixels and the total number of pixels in the first positioning image can be used as the distortion degree parameter.
- the distortion degree parameters determined by the above two methods can also be converted to obtain the distortion degree parameters, but the following relationship needs to be maintained: if the number of target pixels is larger, the distortion degree parameter is larger; or, if the above ratio The larger the value, the larger the distortion level parameter.
- the position of the warehouse robot cannot be determined by recognizing the first positioning image; when When the distortion degree parameter is less than the preset distortion degree threshold, the distortion of the first positioning image can be ignored, and the first positioning image can be identified. In this case, the position of the warehouse robot can be determined by identifying the first positioning image.
- whether the first positioning image can be recognized can be determined by the distortion degree parameter, and the recognition of the first positioning image can be avoided when the first positioning image is distorted, thereby reducing the computational complexity when the first positioning image is distorted .
- the positional relationship between the mirror, the window, and the image acquisition device may be adjusted, and S201 and S2021 or S201 and S2022 may be re-executed after the adjustment.
- S201 and S2021 or S201 and S2022 may be re-executed after the adjustment.
- the above S201 includes S2011: in the process of adjusting the positional relationship among the mirror, the window, and the image acquisition device, acquire at least two first positioning images.
- the positional relationship among the mirror, the window, and the image acquisition device can be adjusted step by step.
- the inclination angle of the mirror is gradually increased or decreased by taking the unit angle as the step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image acquisition device.
- the angle between the image acquisition device and the chassis can be gradually increased or decreased by taking the unit angle as a step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image acquisition device.
- the distance between the image capture device and the mirror can be gradually increased or shortened by taking the unit length as a step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image capture device.
- At least two first positioning images may be acquired. For example, after each time the inclination angle of the mirror is increased by one unit angle, a first positioning image is collected; for another example, after each time the angle between the image acquisition device and the window is decreased by one unit angle, the first positioning image is collected A first positioning image; for another example, after each time the distance between the image acquisition device and the mirror is shortened by a unit length, a first positioning image is collected.
- At least two of the tilt angle of the mirror, the angle between the image capture device and the window, and the distance between the image capture device and the mirror can be adjusted together, and A first positioning image is acquired after an adjustment.
- At least two first positioning images can be collected through the above adjustment process, so that the position of the storage robot can be determined through the at least two first positioning images, which helps to improve the accuracy and success rate of the position of the storage robot.
- the location of the warehouse robot can be determined in the following two ways.
- one position can be determined according to each first positioning image, so that at least two positions can be obtained. If at least two positions are the same, the position is determined as the position of the storage robot; if at least two positions are different, the same position with the largest number can be obtained as the position of the storage robot. In this way, the accuracy of the position of the warehouse robot is improved.
- the distortion degree parameter of some of the first positioning images is greater than the preset distortion degree threshold, so that the part of the first positioning images cannot be recognized, and thus the position cannot be determined according to the first positioning images, the The position is determined according to the remaining first positioning images. This increases the success rate of determining the location of the warehouse robot.
- the above method further includes:
- the above-mentioned S2011 to S1025 are all processes of determining the position through the first positioning image, and the following describes the process of determining the position through the second positioning image through S2026 to S2027.
- the second positioning image is a mirror image of the first positioning image.
- S2026 Acquire a second positioning image, where the second positioning image is a mirror image corresponding to the first positioning image.
- the image in the mirror is a mirror image of the positioning image on the ground
- the first positioning image collected by the image acquisition device is the same as the image in the mirror, so the first positioning image is the positioning on the ground.
- Mirror image of the image Based on this, in order to improve the accuracy and success rate of determining the position, the mirror image of the first positioning image can be used as the second positioning image, and the second positioning image is the same as the positioning image on the ground.
- the pixel point P(x,y) in the first positioning image can be mirrored up and down to obtain the pixel point P(X-x,y) in the second image, or the second image can be obtained by mirroring left and right
- the pixel point P(x, Y-y) in .
- x and y are the row and column where the pixel point is located
- X is the total number of rows of the first positioning image
- Y is the total number of columns of the first positioning image.
- the pixels of P(X-x,y) and P(x,y) have the same value but different positions
- the pixels of P(x,Y-y) and P(x,y) have the same value but different positions.
- S2027 Determine the position of the warehouse robot according to the second positioning image.
- the position of the warehouse robot may be determined according to the content of the second positioning image, and the content of the positioning image at different positions is different.
- the second positioning image may include position information, so that the position information may be obtained by parsing the second positioning image.
- the second positioning image may be a two-dimensional code including location information, so that the two-dimensional code may be parsed to obtain the location information.
- the second positioning image does not include position information, so that the second positioning image can be matched with the image data preset in the database. If the matching is successful, the matched second positioning image will be stored in the database. The corresponding position is used as the position of the warehouse robot.
- the database stores several image data and corresponding position information.
- the position information corresponding to the image data in the database is used as the position corresponding to the second positioning image in the database.
- the position of the warehouse robot can also be determined by the first positioning image and the second positioning image. For example, both the first positioning image and the second image data are matched with the image data in the database. If one of them is successfully matched, the position information in the matched database is used as the position of the warehouse robot; if both are matched successfully And if the location information in the matched database is consistent, the location information is used as the location of the warehouse robot.
- the positional relationship between the mirror, the window, and the image acquisition device can be adjusted to re-acquire the first positioning image or acquire multiple first positioning images, so as to correspond to the first positioning images obtained again
- the position of the storage robot is determined by the second positioning image, or the position of the storage robot is determined according to the second positioning images respectively corresponding to the plurality of first positioning images, which helps to improve the positioning accuracy and success rate.
- the foregoing S2027 includes S20271 to S20272:
- the inability to identify the second positioning image may be caused by the distortion of the second positioning image
- the distortion of the second positioning image is caused by the distortion of the first positioning image
- the distortion of the second positioning image includes: The partial area of the second positioning image is missing, the second positioning image is deformed, and the partial area of the second positioning image is blocked or reflected.
- Whether the second positioning image can be identified can be determined in two ways.
- the first way is to identify the second positioning image and determine whether the second positioning image can be identified according to the recognition result; the second way is to determine whether the second positioning image can be identified according to the degree of distortion of the second positioning image
- the parameter determines whether the second positioning image can be recognized. For details, please refer to S20273 to S20275:
- the distortion degree parameter is used to indicate the degree of difference between the second positioning image and the standard positioning image. It can be understood that the larger the distortion degree parameter is, the larger the difference degree is; the smaller the distortion degree parameter is, the smaller the difference degree is.
- the standard positioning image corresponds to the preset graphics, and the shape and size of the preset graphics can be set. If the shape and size of the second positioning image are inconsistent with those of the standard positioning image, it represents the second positioning image If the image is distorted, the distortion degree parameter can be determined according to the degree of difference between the shape and size; when the shape and size of the second positioning image are consistent with the shape and size of the standard positioning image, it means that the second positioning image is not distorted.
- the distortion degree parameter of the second positioning image can be determined according to the following S202731 to S202732 or S202733 to S202735, wherein S202731 and S202732 can be used to determine whether the second positioning image is deformed or lacks an edge part, and S202733 to S202735 can be used to It is determined whether there is reflection or occlusion in the second positioning image.
- S202731 and S202732 can be executed, or only S202733 to S202735 can be executed, and the distortion degree parameters determined by S202731 and S202732 and the distortion degree parameters determined by S202733 to S202735 can be synthesized to obtain the distortion degree of the second positioning image. parameter.
- S202731 Determine the edge pixels of the second positioning image.
- the edge pixels are pixels located at the edge of the second positioning image.
- determining an edge pixel, for any pixel in the second positioning image (hereinafter referred to as a candidate pixel), it can be determined whether there is a pixel located to the left, right, below, or above the candidate pixel.
- the candidate pixel point is determined to be the edge pixel point on the left side of the second positioning image; if there is no pixel point located to the right of the candidate pixel point, then the candidate pixel point is determined The candidate pixel point is the edge pixel point on the right side of the second positioning image; if there is no pixel point located above the candidate pixel point, the candidate pixel point is determined as the edge pixel point on the upper side of the second positioning image point; if not If there is a pixel point located below the candidate pixel point, the candidate pixel point is determined to be the lower edge pixel point of the second positioning image.
- a candidate pixel point may be an edge pixel point on at least two sides of the upper side, the left side, the lower side, and the right side.
- S202732 Determine the degree of difference between the graphics formed by the edge pixels and the preset graphics of the second positioning image, and determine the distortion degree parameter of the second positioning image.
- the distortion degree parameter may include: the degree of shape difference between the figure formed by the edge pixels and the preset figure, and the degree of size difference between the figure formed by the edge pixels and the preset figure.
- the shape difference degree and the size difference degree may be weighted as a distortion degree parameter of the second positioning image. Since the distortion when the shapes are inconsistent is usually larger, a larger weight can be set for the degree of shape difference, and a smaller weight can be set for the degree of size difference.
- the above-mentioned shape difference degree can be set to two values.
- the shape difference degree can be set as the first shape difference value;
- the degree of shape difference may be set as the second shape difference value.
- the first shape difference is greater than the second shape difference.
- a typical value situation may be that the first shape difference is a positive number, and the second shape difference may be 0.
- the above-mentioned size difference degree can be represented by the length difference, width difference, area difference, etc. between the figure formed by the edge pixel points and the preset figure.
- S202733 Determine the average brightness of the second positioned image.
- the average brightness of the second positioning image may be an average value of brightness values of each pixel in the second positioning image.
- S202734 Determine a target pixel whose brightness difference from the average brightness in the second positioning image is greater than a preset brightness difference threshold.
- the brightness difference value is the absolute value of the difference between the brightness value of the pixel point and the average brightness
- the target pixel point is the pixel point in the second positioning image whose brightness difference value is greater than the preset brightness difference threshold, that is, the second positioning image. Pixels that are too bright or too small. It can be understood that when multiple pixels with consecutive positions are target pixels, then multiple consecutive pixels in the position form an over-bright area or an over-dark area, an over-bright area is a reflective area, and an over-dark area is an occluded area. .
- S202735 Determine the distortion degree parameter of the second positioning image according to the target pixel point.
- the distortion degree parameter determined in S202735 is used to represent the distortion degree of the second positioning image in terms of brightness.
- the number of target pixels can be used as the distortion degree parameter; in another way, the ratio between the number of target pixels and the total number of pixels in the second positioning image can be used as the distortion degree parameter.
- the distortion degree parameters determined by the above two methods can also be converted to obtain the distortion degree parameters, but the following relationship needs to be maintained: if the number of target pixels is larger, the distortion degree parameter is larger; or, if the above ratio The larger the value, the larger the distortion level parameter.
- the position of the warehouse robot cannot be determined by recognizing the second positioning image; when When the distortion degree parameter is less than the preset distortion degree threshold, the distortion of the second positioning image can be ignored, and the second positioning image can be identified. In this case, the position of the warehouse robot can be determined by identifying the second positioning image.
- whether the second positioning image can be recognized can be determined through the distortion degree parameter, and the recognition of the second positioning image can be avoided when the second positioning image is distorted, thereby reducing the computational complexity when the second positioning image is distorted .
- the positional relationship between the mirror, the window, and the image acquisition device can be adjusted, and S201, S2026, and S20271 or S201, S2026, and S20272 can be re-executed after the adjustment.
- S201, S2026, and S20271 or S201, S2026, and S20272 can be re-executed after the adjustment.
- the foregoing S2026 includes S20261:
- S20261 Acquire at least two second positioning images corresponding to at least two first positioning images respectively.
- the embodiment of the present invention determines the position of the storage robot by using at least two second positioning images, which helps to improve the accuracy and success rate of the position of the storage robot.
- the location of the warehouse robot can be determined in the following two ways.
- one position may be determined according to each second positioning image, so that at least two positions may be obtained. If at least two positions are the same, the position is determined as the position of the storage robot; if at least two positions are different, the same position with the largest number can be obtained as the position of the storage robot. In this way, the accuracy of the warehouse robot is improved.
- the distortion degree parameter of some of the second positioning images is greater than the preset distortion degree threshold, so that the part of the second positioning images cannot be recognized, and thus the position cannot be determined according to the second positioning images, the The position is determined from the remaining second positioning images. This increases the success rate of identifying warehouse robots.
- the above method further includes:
- An embodiment of the present invention also provides a storage robot, including a chassis and a camera assembly, the camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the image is positioned, and a reflector of the camera assembly is arranged on one side of the window and is inclined towards the direction of the window, and the reflective surface of the reflector faces the window, the image acquisition device is located on the reflected light path of the reflector, and the image acquisition device The lens of the device is aligned with the reflective surface; the image acquisition device is used for collecting the first positioning image in the reflecting mirror; and the position of the storage robot is determined according to the first positioning image.
- An embodiment of the present invention further provides another storage robot, including a chassis, a camera assembly and a processor, the camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the positioning image is located, and the camera
- the reflector of the assembly is arranged on one side of the window and is inclined toward the direction of the window, and the reflective surface of the reflector faces the window, the image acquisition device is located on the reflected light path of the reflector, and The lens of the image acquisition device is aligned with the reflective surface;
- the processor is fixed on the chassis, and the processor is used for:
- the position of the warehouse robot is determined according to the first positioning image.
- the above-mentioned image acquisition device and the above-mentioned processor can perform the steps in the above-mentioned positioning method, which will not be repeated here.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Manipulator (AREA)
Abstract
Provided are a storage robot, a camera assembly and a positioning method. The camera assembly is used for navigating and positioning the storage robot. The camera assembly of the storage robot is configured to comprise a reflecting mirror and an image acquisition device; the reflecting mirror is arranged on the inner surface of a chassis of the storage robot and is obliquely arranged at the edge of a window of the chassis with the reflecting face of the reflecting mirror facing the window; and the image acquisition device is arranged on the reflected optical path of the reflecting mirror with a lens of the image acquisition device being aligned with the reflecting face, such that the present application can obtain the position in which the storage robot is located in order to position and navigate the storage robot, and does not need to position the image acquisition device relatively high from the inner surface of the chassis, thereby reducing the amount of space occupied by the camera assembly in the height direction of the storage robot.
Description
本申请要求于2020年12月30日提交中国专利局、申请号为202023341469.1、申请名称为“仓储机器人及摄像组件”和申请号为202011630689.8、申请名称为“定位方法及仓储机器人”的中国专利申请的优先权,以及其全部内容通过引用结合在本申请中。This application is required to be submitted to the China Patent Office on December 30, 2020, the application number is 202023341469.1, the application name is "storage robot and camera assembly" and the application number is 202011630689.8, the application name is "positioning method and storage robot" Chinese patent application , and the entire contents of which are incorporated by reference in this application.
本申请涉及货物搬运设备技术领域,特别涉及一种仓储机器人、摄像组件及定位方法。The present application relates to the technical field of cargo handling equipment, and in particular, to a storage robot, a camera assembly and a positioning method.
随着人工智能技术、自动化技术、信息技术的飞速发展,末端物流的智能化程度将不断提高,智能物流终端是末端物流发展的必然趋势,而仓储机器人是可以实现智能物流终端进行自动化搬运作业的主要设备之一,从而通过仓储机器人减轻人类繁重的体力劳动。仓储机器人的定位与导航,主要是依靠扫描并配置地面上的定位图像例如二维码,以获取精确的信息,从而得到仓储机器人当前的位置。With the rapid development of artificial intelligence technology, automation technology and information technology, the intelligence of terminal logistics will continue to improve. Intelligent logistics terminals are the inevitable trend of terminal logistics development, and warehousing robots can realize intelligent logistics terminals for automated handling operations. One of the main equipment, thereby reducing the heavy manual labor of humans through warehouse robots. The positioning and navigation of the warehouse robot mainly relies on scanning and configuring the positioning images on the ground, such as QR codes, to obtain accurate information, so as to obtain the current position of the warehouse robot.
传统技术中,仓储机器人的底盘上形成有窗口,该窗口朝向定位图像所在面例如地面,同时在底盘上设置一立架和相机,且该立架的固定部位于窗口的正上方,相机位于立架的固定部上,且相机的镜头正对窗口,以拍摄地面上的二维码,从而通过对该二维码进行解析,得到仓储机器人的实时位置。In the traditional technology, a window is formed on the chassis of the warehouse robot, and the window faces the surface where the positioning image is located, such as the ground. At the same time, a stand and a camera are set on the chassis, and the fixed part of the stand is located directly above the window, and the camera is located on the stand. On the fixed part of the rack, and the lens of the camera is facing the window, to shoot the two-dimensional code on the ground, so that the real-time position of the warehouse robot can be obtained by analyzing the two-dimensional code.
然而,为了保证相机的拍摄范围能够完全覆盖二维码,在设置时,立架的固定部与底盘之间的距离需要足够高,这就增大了立架以及相机在仓储机器人高度上的占用空间,从而影响了仓储机器人中其他零部件的安装。However, in order to ensure that the shooting range of the camera can completely cover the QR code, the distance between the fixed part of the stand and the chassis needs to be high enough during setup, which increases the height of the stand and the camera on the storage robot. space, which affects the installation of other components in the warehouse robot.
发明内容SUMMARY OF THE INVENTION
本申请实施例提供一种仓储机器人、摄像组件及定位方法,以克服现 有立架以及相机在仓储机器人高度上的占用空间较大,从而影响仓储机器人中其他零部件的安装的问题。The embodiments of the present application provide a storage robot, a camera assembly and a positioning method to overcome the problem that the existing stand and the camera occupy a large space on the height of the storage robot, thereby affecting the installation of other components in the storage robot.
第一方面,本申请实施例提供一种摄像组件,用于仓储机器人的导航与定位,其中,摄像组件包括反射镜和图像采集装置;In a first aspect, an embodiment of the present application provides a camera assembly for navigation and positioning of a warehouse robot, wherein the camera assembly includes a mirror and an image acquisition device;
反射镜位于仓储机器人的底盘的内表面,底盘上具有朝向定位图像所在面的窗口,反射镜设置在窗口的侧边并往窗口的方向倾斜,且反射镜的反射面朝向窗口,图像采集装置位于反射镜的反射光路上,且图像采集装置的镜头与反射面对准。The reflector is located on the inner surface of the chassis of the warehouse robot, and the chassis has a window facing the surface where the image is positioned. The reflector is arranged on the side of the window and tilted toward the window, and the reflector's reflective surface faces the window. The image acquisition device is located in the window. On the reflected light path of the reflector, the lens of the image acquisition device is aligned with the reflecting surface.
在一种可选的实现方式中,反射镜的反射面在底盘上的投影至少完全覆盖窗口。In an optional implementation manner, the projection of the reflecting surface of the reflector on the chassis at least completely covers the window.
在一种可选的实现方式中,图像采集装置设置在窗口的侧边。In an optional implementation manner, the image acquisition device is arranged on the side of the window.
在一种可选的实现方式中,摄像组件还包括至少一个遮光件;In an optional implementation manner, the camera assembly further includes at least one shading member;
反射镜包括绕轴线设置的第一边缘、第二边缘、第三边缘和第四边缘,第一边缘位于底盘上,遮光件的一端至少设置在第二边缘、第三边缘及第四边缘中的任意一个上,且遮光件的另一端往图像采集装置的方向延伸。The reflector includes a first edge, a second edge, a third edge and a fourth edge arranged around the axis, the first edge is located on the chassis, and one end of the shading member is arranged at least among the second edge, the third edge and the fourth edge. on any one, and the other end of the shading member extends toward the direction of the image acquisition device.
在一种可选的实现方式中,遮光件的数量至少为三个;In an optional implementation manner, the number of shading members is at least three;
至少三个遮光件分别对应设置在第二边缘、第三边缘及第四边缘上。At least three light shielding members are respectively disposed on the second edge, the third edge and the fourth edge respectively.
在一种可选的实现方式中,第二边缘、第三边缘和第四边缘往图像采集装置的方向延伸有遮光边,遮光边与反射镜为一体成型的一体件;In an optional implementation manner, the second edge, the third edge and the fourth edge are extended with a light-shielding edge toward the direction of the image capturing device, and the light-shielding edge and the reflector are integrally formed as an integral piece;
遮光边被配置为遮光件。The light blocking edge is configured as a light blocking member.
在一种可选的实现方式中,图像采集装置滑动设置在底盘上,以调节图像采集装置与反射面之间的距离。In an optional implementation manner, the image capturing device is slidably arranged on the chassis to adjust the distance between the image capturing device and the reflective surface.
在一种可选的实现方式中,摄像组件还包括支架;In an optional implementation manner, the camera assembly further includes a bracket;
图像采集装置通过支架设置在底盘上,图像采集装置转动连接在支架上,且图像采集装置的镜头能够往靠近或者远离底盘内表面的方向转动,以调整图像采集装置的镜头与反射面的对准角度。The image acquisition device is arranged on the chassis through a bracket, the image acquisition device is rotatably connected to the bracket, and the lens of the image acquisition device can be rotated toward or away from the inner surface of the chassis to adjust the alignment of the lens of the image acquisition device and the reflective surface angle.
在一种可选的实现方式中,反射镜转动连接在底盘上,且反射镜远离底盘的一端能够往靠近或者远离底盘内表面的方向转动,以调节反射镜与底盘之间的夹角。In an optional implementation manner, the reflector is rotatably connected to the chassis, and the end of the reflector away from the chassis can be rotated toward or away from the inner surface of the chassis to adjust the angle between the reflector and the chassis.
在一种可选的实现方式中,摄像组件还包括控制单元和驱动单元;In an optional implementation manner, the camera assembly further includes a control unit and a drive unit;
驱动单元与图像采集装置连接,以驱动图像采集装置的移动或者转动;The driving unit is connected with the image acquisition device to drive the movement or rotation of the image acquisition device;
和/或,驱动单元与反射镜信号连接,以驱动反射镜转动;And/or, the drive unit is signal-connected to the mirror to drive the mirror to rotate;
控制单元与驱动单元信号连接,以信号控制驱动单元工作。The control unit is signal-connected with the driving unit, and controls the driving unit to work with the signal.
在一种可选的实现方式中,图像采集装置为潜望式相机。In an optional implementation manner, the image acquisition device is a periscope camera.
在一种可选的实现方式中,反射镜与底盘之间的夹角为30°-60°。In an optional implementation manner, the included angle between the reflector and the chassis is 30°-60°.
第二方面,本申请实施例还提供一种仓储机器人,包括底盘和至少一组如上所述的摄像组件;In a second aspect, an embodiment of the present application further provides a storage robot, including a chassis and at least one set of the above-mentioned camera assemblies;
摄像组件位于底盘的内表面,底盘上具有朝向定位图像所在面的窗口,摄像组件的反射镜设置在窗口的一侧并往窗口的方向倾斜,且反射镜的反射面朝向窗口,图像采集装置位于反射镜的反射光路上,且图像采集装置的镜头与反射面对准。The camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the image is positioned, the mirror of the camera assembly is arranged on one side of the window and tilted towards the direction of the window, and the reflecting surface of the mirror faces the window, and the image acquisition device is located in the window. On the reflected light path of the reflector, the lens of the image acquisition device is aligned with the reflecting surface.
在一种可选的实现方式中,窗口的数量至少为两个,至少两个窗口间隔设置在底盘的活动方向上;In an optional implementation manner, the number of windows is at least two, and the at least two windows are arranged at intervals in the moving direction of the chassis;
摄像组件的数量至少为两个,至少两个摄像组件分别与至少两个窗口对应设置。The number of camera assemblies is at least two, and the at least two camera assemblies are respectively arranged corresponding to the at least two windows.
在一种可选的实现方式中,仓储机器人还包括透光保护件;In an optional implementation manner, the storage robot further includes a light-transmitting protector;
窗口被配置为开设在底盘上的透光口,透光保护件覆盖在透光口上。The window is configured as a light-transmitting port opened on the chassis, and the light-transmitting protection member covers the light-transmitting port.
第三方面,本发明实施例提供一种定位方法,应用于仓储机器人,所述仓储机器人包括底盘和摄像组件,所述摄像组件位于所述底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述摄像组件的反射镜设置在所述窗口的一侧并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准;所述方法包括:In a third aspect, an embodiment of the present invention provides a positioning method, which is applied to a storage robot, where the storage robot includes a chassis and a camera assembly, the camera assembly is located on the inner surface of the chassis, and the chassis has an orientation image on the chassis. The mirror of the camera assembly is arranged on one side of the window and inclined toward the direction of the window, and the reflective surface of the mirror faces the window, and the image acquisition device is located in the mirror on the reflected light path of the mirror, and the lens of the image acquisition device is aligned with the reflective surface; the method includes:
获取所述图像采集装置采集的所述反射镜中的第一定位图像;acquiring a first positioning image in the mirror captured by the image capturing device;
根据所述第一定位图像确定所述仓储机器人的位置。The position of the warehouse robot is determined according to the first positioning image.
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.
图1是本发明实施例提供的仓储机器人的第一种结构的部分结构示意图;1 is a partial structural schematic diagram of a first structure of a storage robot provided by an embodiment of the present invention;
图2是图1的局部剖视图;Fig. 2 is the partial sectional view of Fig. 1;
图3是图1中摄像组件与定位图像的光路图;Fig. 3 is the light path diagram of the camera assembly and the positioning image in Fig. 1;
图4是本发明实施例提供的仓储机器人的第二种结构的部分结构示意图;4 is a partial structural schematic diagram of a second structure of a storage robot provided by an embodiment of the present invention;
图5是本发明实施例提供的仓储机器人的第三种结构的局部剖视图;5 is a partial cross-sectional view of a third structure of a storage robot provided by an embodiment of the present invention;
图6是本发明实施例提供的仓储机器人的第四种结构的局部剖视图;6 is a partial cross-sectional view of a fourth structure of a storage robot provided by an embodiment of the present invention;
图7是本发明实施例提供的仓储机器人的第五种结构的部分结构示意图;7 is a partial structural schematic diagram of a fifth structure of a storage robot provided by an embodiment of the present invention;
图8是本发明实施例示出的一种定位方法的步骤流程图。FIG. 8 is a flowchart of steps of a positioning method according to an embodiment of the present invention.
附图标记说明:Description of reference numbers:
100-仓储机器人;100 - warehousing robot;
110-底盘;110 - chassis;
111-窗口;111-window;
1111-第一窗口;1111 - the first window;
1112-第二窗口;1112 - second window;
120-摄像组件;120 - camera assembly;
121-反射镜;121 - mirror;
122-图像采集装置;122-image acquisition device;
1221-镜头;1221 - lens;
123-遮光件;123-shading piece;
124-支架;124 - bracket;
1241-支撑件;1241 - Support;
1242-固定件;1242-fixtures;
1243-第一转轴;1243 - the first shaft;
125-第二转轴;125 - the second shaft;
200-定位图像;200 - positioning image;
300-定位图像所在面。300 - Locate the face of the image.
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
目前,仓储机器人的定位与导航,主要是依靠扫描并配置地面上的定位图像例如二维码,以获取精确的信息,从而得到仓储机器人当前的位置。At present, the positioning and navigation of warehouse robots mainly rely on scanning and configuring positioning images on the ground, such as QR codes, to obtain accurate information, thereby obtaining the current position of the warehouse robots.
为了使仓储机器人能够实时获取定位图像所在面例如地面上的定位图像(例如二维码),传统技术中的仓储机器人的底盘上形成有窗口,该窗口朝向地面,也即是说,窗口位于地面的正上方,同时在底盘上设置一立架和相机,且该立架的固定部位于窗口的正上方,相机位于立架的固定部上,且相机的镜头正对窗口,以拍摄地面上的二维码,继而对该二维码进行解析,得到仓储机器人的实时位置,从而实现对该仓储机器人的定位与导航。In order to enable the warehouse robot to obtain the positioning image (such as a two-dimensional code) on the ground where the positioning image is located in real time, a window is formed on the chassis of the warehouse robot in the conventional technology, and the window faces the ground, that is, the window is located on the ground At the same time, a stand and a camera are set on the chassis, and the fixed part of the stand is located directly above the window, the camera is located on the fixed part of the stand, and the lens of the camera is facing the window, so as to take pictures on the ground. The two-dimensional code is then parsed to obtain the real-time position of the warehouse robot, so as to realize the positioning and navigation of the warehouse robot.
需要说明的是,立架的固定部上具有通光孔,该透光孔位于底盘的窗口的正上方,相机固定在该固定部上时,该相机的镜头位于透光孔内,则该相机的镜头可通过透光孔以及窗口获取到地面上的定位图像例如二维码。It should be noted that the fixed part of the stand has a light-transmitting hole, and the light-transmitting hole is located directly above the window of the chassis. When the camera is fixed on the fixed part, the lens of the camera is located in the The lens can obtain positioning images on the ground, such as QR codes, through light-transmitting holes and windows.
其中,相机获取到定位图像的信息后,可通过该相机直接对该定位图像信息进行解析处理,以确定仓储机器人的位置。当然,该相机也可以与处理器进行信号连接,当相机获取到定位图像的信息后,将该定位图像的信息传输至处理器内,通过该处理器对该定位图像信息进行解析处理,以确定仓储机器人的位置。Wherein, after the camera obtains the information of the positioning image, the positioning image information can be directly analyzed and processed by the camera to determine the position of the warehouse robot. Of course, the camera can also be connected with the processor. After the camera obtains the information of the positioning image, the information of the positioning image is transmitted to the processor, and the positioning image information is analyzed and processed by the processor to determine The location of the warehouse robot.
为了保证相机的拍摄范围能够完全覆盖定位图像例如二维码,在设置时,立架的固定部与底盘之间的距离需要足够高,这就增大了立架以及相机在仓储机器人高度上的占用空间,从而影响了仓储机器人中其他零部件的安装。In order to ensure that the shooting range of the camera can completely cover the positioning image such as the two-dimensional code, the distance between the fixed part of the stand and the chassis needs to be high enough during setting, which increases the distance between the stand and the camera at the height of the storage robot. Occupy space, thus affecting the installation of other components in the warehouse robot.
本发明实施例提供一种仓储机器人及摄像组件,其中,摄像组件用于仓储机器人的导航与定位,本发明实施例通过将仓储机器人的摄像组件设置为包括反射镜和图像采集装置,将反射镜设置在仓储机器人的底盘内表面,并倾斜设置在底盘的窗口边,且将该反射镜的反射面朝向该窗口,将图像采集装置设置在反射镜的反射光路上,且将该图像采集装置的镜头对 准反射面,这样,当仓储机器人移动至定位图像所在面例如地面的某定位图像上方时,地面上的定位图像可通过窗口入射至反射镜的反射面上,再通过该反射镜的反射面将入射光线反射至图像采集装置的镜头内,继而通过图像采集装置或者其他处理器便对该定位图像信息进行解析,最终得到仓储机器人所在位置,实现对该仓储机器人的定位与导航。The embodiment of the present invention provides a storage robot and a camera assembly, wherein the camera assembly is used for the navigation and positioning of the storage robot. In the embodiment of the present invention, the camera assembly of the storage robot is configured to include a reflector and an image acquisition device, and the reflector is It is arranged on the inner surface of the chassis of the storage robot, and is inclined at the side of the window of the chassis, and the reflective surface of the mirror faces the window, the image acquisition device is set on the reflected light path of the mirror, and the The lens is aimed at the reflective surface, so that when the warehouse robot moves to the surface where the positioning image is located, such as a positioning image on the ground, the positioning image on the ground can be incident on the reflecting surface of the reflector through the window, and then pass the reflection of the reflector. The surface reflects the incident light into the lens of the image acquisition device, and then analyzes the positioning image information through the image acquisition device or other processors, and finally obtains the location of the storage robot, realizing the positioning and navigation of the storage robot.
基于上述可知,相比于传统技术,本发明实施例的摄像组件通过反射镜将定位图像所在面的定位图像反射至图像采集装置的镜头内,无需将图像采集装置设置在距离底盘内表面较高的位置,缩小了摄像组件在垂直于底盘的方向上的占用尺寸,即缩小了摄像组件在仓储机器人高度方向上的占用空间,不仅避免了仓储机器人中其他零部件的安装造成影响的情况发生,而且缩小了整个仓储机器人的高度尺寸,方便了仓储机器人的搬运与收纳。Based on the above, it can be seen that, compared with the traditional technology, the camera assembly of the embodiment of the present invention reflects the positioning image of the surface where the positioning image is located into the lens of the image acquisition device through the mirror, and it is not necessary to set the image acquisition device at a higher distance from the inner surface of the chassis. It reduces the occupied size of the camera assembly in the direction perpendicular to the chassis, that is, reduces the space occupied by the camera assembly in the height direction of the storage robot, which not only avoids the impact of the installation of other components in the storage robot, but also Moreover, the height size of the entire storage robot is reduced, which facilitates the handling and storage of the storage robot.
以下具体对本发明实施例的仓储机器人及摄像组件的结构进行详细说明。The structure of the storage robot and the camera assembly according to the embodiment of the present invention will be described in detail below.
图1是本发明实施例提供的仓储机器人的第一种结构的部分结构示意图,图2是图1的局部剖视图。参照图1和图2所示,本发明实施例提供一种摄像组件120,该摄像组件120用于仓储机器人100的定位与导航。FIG. 1 is a partial structural schematic diagram of a first structure of a storage robot provided by an embodiment of the present invention, and FIG. 2 is a partial cross-sectional view of FIG. 1 . Referring to FIG. 1 and FIG. 2 , an embodiment of the present invention provides a camera assembly 120 , and the camera assembly 120 is used for positioning and navigation of the warehouse robot 100 .
图3是图1中摄像组件与定位图像的光路图。参照图3所示,实际应用中,该仓储机器人100包括底盘110和本发明实施例的摄像组件120。摄像组件120用于获取并解析处理存储货物的仓库的定位图像所在面300上的定位图像200,以确定仓储机器人100在仓库中的位置,实现对仓储机器人100的定位与导航。FIG. 3 is an optical path diagram of the camera assembly and the positioning image in FIG. 1 . Referring to FIG. 3 , in practical applications, the warehouse robot 100 includes a chassis 110 and a camera assembly 120 according to an embodiment of the present invention. The camera component 120 is used for acquiring and analyzing the positioning image 200 on the plane 300 where the positioning image of the warehouse storing goods is located, so as to determine the position of the storage robot 100 in the warehouse and realize the positioning and navigation of the storage robot 100 .
需要说明的是,定位图像所在面300可以是仓库的地面,也可以是仓库中货架的表面。例如,当仓储机器人100在工作过程中仅在仓库的地面上活动时,定位图像所在面300为仓库的地面,通过摄像组件120对地面上对应位置的定位图像200进行获取并处理,以确定仓储机器人100在地面上的具***置。当仓储机器人100在工作过程中可以在仓库的货架上移动时,该定位图像所在面300可以是货架的表面,通过摄像组件120对货架上对应位置的定位图像200进行获取并处理,以确定仓储机器人100在货架上的具***置。It should be noted that the surface 300 where the positioning image is located may be the floor of the warehouse, or may be the surface of the shelf in the warehouse. For example, when the warehouse robot 100 only moves on the floor of the warehouse during the working process, the surface 300 where the positioning image is located is the floor of the warehouse, and the positioning image 200 of the corresponding position on the ground is acquired and processed by the camera component 120 to determine the warehouse. The specific position of the robot 100 on the ground. When the storage robot 100 can move on the shelf of the warehouse during the working process, the surface 300 where the positioning image is located may be the surface of the shelf, and the positioning image 200 of the corresponding position on the shelf is acquired and processed by the camera component 120 to determine the storage The specific position of the robot 100 on the shelf.
其中,定位图像200可以是条码、二维码以及其他具有标示性的图像。 可以理解的是,为了实现对仓储机器人100的定位与导航,在定位图像所在面300例如地面的不同位置分别设置不同的定位图像200。通过获取不同的定位图像200,以得到仓储机器人100的准确位置。Wherein, the positioning image 200 may be a barcode, a two-dimensional code and other images with indication. It can be understood that, in order to realize the positioning and navigation of the warehouse robot 100, different positioning images 200 are respectively set at different positions on the surface 300 where the positioning image is located, such as the ground. Accurate position of the warehouse robot 100 can be obtained by acquiring different positioning images 200 .
本发明实施例具体以定位图像200为二维码,定位图像所在面300为地面为例进行说明。The embodiment of the present invention is specifically described by taking the positioning image 200 as a two-dimensional code and the surface 300 where the positioning image is located as the ground as an example.
参照图1至图3所示,摄像组件120包括反射镜121和图像采集装置122。其中,该反射镜121位于底盘110的内表面。可以理解的是,底盘110的内表面是指该底盘110朝向仓储机器人100内部的表面。底盘110上具有朝向定位图像所在面300例如地面的窗口111,反射镜121设置在窗口111的侧边并往窗口111的方向倾斜,且反射镜121的反射面(如图2中a所示)朝向窗口111,这样,地面上的定位图像200例如二维码的光线便可通过窗口111照射在反射镜121的反射面a上,也即是说,当仓储机器人100的窗口111移动至地面上的二维码正上方时,反射镜121的反射面a便可透过窗口111接收到二维码的入射光线(如图3中的b1所示)。Referring to FIG. 1 to FIG. 3 , the camera assembly 120 includes a mirror 121 and an image capture device 122 . Wherein, the reflector 121 is located on the inner surface of the chassis 110 . It can be understood that the inner surface of the chassis 110 refers to the surface of the chassis 110 facing the interior of the warehouse robot 100 . The chassis 110 has a window 111 facing the surface 300 where the image is positioned, such as the ground, the mirror 121 is arranged on the side of the window 111 and is inclined toward the direction of the window 111, and the reflective surface of the mirror 121 (as shown in a in FIG. 2 ) Facing the window 111, in this way, the light of the positioning image 200 on the ground, such as the two-dimensional code, can be irradiated on the reflective surface a of the reflector 121 through the window 111, that is, when the window 111 of the warehouse robot 100 moves to the ground When the two-dimensional code is directly above the two-dimensional code, the reflecting surface a of the mirror 121 can receive the incident light of the two-dimensional code through the window 111 (as shown by b1 in FIG. 3 ).
实际应用中,底盘110上窗口111的尺寸通常大于定位图像200例如二维码的尺寸,以保证定位图像200的各个部分均能够透过窗口111照射到反射镜121的反射面a上。In practical applications, the size of the window 111 on the chassis 110 is usually larger than the size of the positioning image 200 such as a two-dimensional code, to ensure that each part of the positioning image 200 can be irradiated on the reflective surface a of the mirror 121 through the window 111 .
另外,窗口111的形状可以是长方形、正方形及圆形等任意形状,具体可根据定位图像200的外轮廓形状进行设置。例如,当定位图像200的外轮廓形状为圆形时,该窗口111可以设置为圆形结构。窗口111的形状也可以与定位图像200的外轮廓形状不相对应,只要窗口111的尺寸大于定位图像200的尺寸,窗口111范围能涵盖定位图像200即可。In addition, the shape of the window 111 may be any shape such as a rectangle, a square, or a circle, and may be specifically set according to the shape of the outer contour of the positioning image 200 . For example, when the shape of the outer contour of the positioning image 200 is a circle, the window 111 can be set to a circular structure. The shape of the window 111 may not correspond to the shape of the outer contour of the positioning image 200 , as long as the size of the window 111 is larger than the size of the positioning image 200 , the range of the window 111 can cover the positioning image 200 .
继续参照图3所示,图像采集装置122位于反射镜121的反射光路(如图3中b2所示的光路)上,且图像采集装置122的镜头1221与反射面a对准,这样,二维码透过窗口111入射至反射面a上的入射光线b1,可通过反射面a反射至图像采集装置122的镜头1221内,使得图像采集装置122的镜头1221接收并获取到二维码的图像信息,接着通过对该图像信息进行解析并处理,最终确定仓储机器人100当前所处的位置,实现对该仓储机器人100的定位与导航。Continuing to refer to FIG. 3 , the image acquisition device 122 is located on the reflective optical path of the reflector 121 (the optical path shown in b2 in FIG. 3 ), and the lens 1221 of the image acquisition device 122 is aligned with the reflective surface a, so that the two-dimensional The incident light b1 incident on the reflective surface a through the window 111 of the code can be reflected into the lens 1221 of the image acquisition device 122 through the reflective surface a, so that the lens 1221 of the image acquisition device 122 can receive and acquire the image information of the two-dimensional code Then, by analyzing and processing the image information, the current position of the storage robot 100 is finally determined, so as to realize the positioning and navigation of the storage robot 100 .
其中,图3中b1所示的光线为二维码透过窗口111入射至反射面a后,经反射面a反射的反射光线。The light shown by b1 in FIG. 3 is the reflected light reflected by the reflecting surface a after the two-dimensional code enters the reflecting surface a through the window 111 .
当仓储机器人100移动至定位图像所在面300例如地面的某个定位图像200(例如二维码)上方时,地面上的二维码可通过窗口111照射至反射镜121的反射面a上,再通过该反射镜121的反射面a将该二维码的入射光线b1反射至图像采集装置122的镜头1221内,继而对该二维码的图像信息进行解析,最终得到仓储机器人100所在位置,实现对该仓储机器人100的定位与导航。When the warehouse robot 100 moves to the surface 300 where the positioning image is located, such as a positioning image 200 (such as a two-dimensional code) on the ground, the two-dimensional code on the ground can be irradiated on the reflecting surface a of the reflecting mirror 121 through the window 111, and then The incident light b1 of the two-dimensional code is reflected into the lens 1221 of the image acquisition device 122 by the reflective surface a of the reflecting mirror 121, and then the image information of the two-dimensional code is analyzed, and finally the position of the storage robot 100 is obtained, which realizes Positioning and navigation of the warehouse robot 100 .
其中,图像采集装置122获取到二维码的图像信息后,可直接通过该图像采集装置122对该图像信息进行解析并处理,最终确定仓储机器人100的位置。Wherein, after the image acquisition device 122 acquires the image information of the two-dimensional code, the image information can be directly parsed and processed by the image acquisition device 122 to finally determine the position of the warehouse robot 100 .
当然,在一些示例中,摄像组件120还可以包括处理器(图中未示出),该处理器与图像采集装置122信号连接。当图像采集装置122获取到二维码的图像信息后,将该图像信息传输至处理器内,通过该处理器对该图像信息进行解析并处理,最终确定仓储机器人100的位置。Of course, in some examples, the camera assembly 120 may further include a processor (not shown in the figure), and the processor is in signal connection with the image capture device 122 . After the image acquisition device 122 acquires the image information of the two-dimensional code, the image information is transmitted to the processor, and the image information is analyzed and processed by the processor, and the position of the warehouse robot 100 is finally determined.
基于上述可知,相比于传统技术,本发明实施例的摄像组件120通过反射镜121将地面的二维码的光线反射至图像采集装置122的镜头1221内,无需将图像采集装置122设置在距离底盘110内表面较高的位置,缩小了摄像组件120在仓储机器人100高度方向上的占用空间,不仅避免了仓储机器人100中其他零部件的安装造成影响的情况发生,而且缩小了整个仓储机器人100的高度尺寸,方便了仓储机器人100的搬运与收纳。Based on the above, it can be seen that, compared with the conventional technology, the camera assembly 120 in the embodiment of the present invention reflects the light of the two-dimensional code on the ground into the lens 1221 of the image acquisition device 122 through the reflector 121 , and the image acquisition device 122 does not need to be set at a distance The higher position of the inner surface of the chassis 110 reduces the space occupied by the camera assembly 120 in the height direction of the storage robot 100 , which not only avoids the occurrence of the impact caused by the installation of other components in the storage robot 100 , but also reduces the size of the entire storage robot 100 The height dimension is convenient for the handling and storage of the storage robot 100.
需要说明的是,仓储机器人100的高度方向是指垂直于底盘110的方向,如图2中的y方向所示。It should be noted that the height direction of the storage robot 100 refers to the direction perpendicular to the chassis 110 , as shown in the y direction in FIG. 2 .
另外,本发明实施例通过将反射镜121和图像采集装置122设置在底盘110的内表面,也即是说,将反射镜121和图像采集装置122设置在仓储机器人100的内部,以保护反射镜121和图像采集装置122免受外部环境的影响,例如,避免了反射镜121和图像采集装置122在仓储机器人100的移动过程中受到地面上其他物件的磕碰而损坏,进而延长了反射镜121和图像采集装置122的使用寿命。In addition, in the embodiment of the present invention, the reflecting mirror 121 and the image collecting device 122 are disposed on the inner surface of the chassis 110, that is, the reflecting mirror 121 and the image collecting device 122 are disposed inside the storage robot 100 to protect the reflecting mirror. 121 and the image acquisition device 122 are protected from the external environment. For example, the mirror 121 and the image acquisition device 122 are prevented from being damaged by being bumped by other objects on the ground during the movement of the warehouse robot 100, thereby extending the length of the mirror 121 and the image acquisition device 122. Service life of image capture device 122 .
本发明实施例中,图像采集装置122可以是潜望式相机,以提高该图像采集装置122的长焦拍摄的稳定性。同时,提高了图像采集装置122的防水效果,另外,在保证拍摄清晰度的同时缩小了机身厚度,从而缩小了该图像采集装置122在仓储机器人100内的占用空间。In this embodiment of the present invention, the image acquisition device 122 may be a periscope camera, so as to improve the stability of telephoto shooting of the image acquisition device 122 . At the same time, the waterproof effect of the image acquisition device 122 is improved. In addition, the thickness of the body is reduced while the shooting clarity is ensured, thereby reducing the space occupied by the image acquisition device 122 in the storage robot 100 .
当然,本发明实施例也不排除采用传统的相机作为图像采集装置122。Of course, the embodiment of the present invention does not exclude the use of a traditional camera as the image capturing device 122 .
如图1所示,具体设置时,图像采集装置122可以设置在窗口111的侧边,例如,当窗口111为正方形或者长方形结构时,图像采集装置122与反射镜121分别设置在窗口111相对的两个侧边缘处,这样,使得摄像组件120集中在底盘110的窗口111的附近,从而为底盘110上其他零部件的安装提供合适的空间。As shown in FIG. 1 , the image acquisition device 122 can be arranged on the side of the window 111 during the specific setting. For example, when the window 111 has a square or rectangular structure, the image acquisition device 122 and the mirror 121 are respectively arranged opposite to the window 111 . At the two side edges, in this way, the camera assembly 120 is concentrated near the window 111 of the chassis 110 , so as to provide suitable space for the installation of other components on the chassis 110 .
本发明实施例的反射镜121可以直接采用现有技术中的反射镜。具体设置时,反射镜121的反射面a在底盘110上的投影至少完全覆盖窗口111。The reflector 121 in the embodiment of the present invention may directly adopt the reflector in the prior art. In specific settings, the projection of the reflection surface a of the reflector 121 on the chassis 110 at least completely covers the window 111 .
例如,反射面a在底盘110上的投影区域的外轮廓刚好位于窗口111的边缘,使得窗口111下方的二维码的入射光线b1刚好透过窗口111完全入射至反射面a上。当然,在一些示例中,反射面a在底盘110上的投影区域的外轮廓尺寸大于窗口111的尺寸,也即是说,反射面a在底盘110上的投影区域的外轮廓位于窗口111的边缘外部,这样可进一步保证二维码的入射光线b1透过窗口111的部分能够完全入射至反射面a上,从而确保图像采集装置122的镜头1221获取到完整的二维码。For example, the outer contour of the projection area of the reflection surface a on the chassis 110 is just at the edge of the window 111, so that the incident light b1 of the two-dimensional code under the window 111 just passes through the window 111 and completely enters the reflection surface a. Of course, in some examples, the size of the outer contour of the projection area of the reflection surface a on the chassis 110 is larger than the size of the window 111 , that is to say, the outer contour of the projection area of the reflection surface a on the chassis 110 is located at the edge of the window 111 Externally, this can further ensure that the portion of the incident light b1 of the two-dimensional code passing through the window 111 can be completely incident on the reflective surface a, thereby ensuring that the lens 1221 of the image capturing device 122 can obtain a complete two-dimensional code.
参照图1至图3所示,其中,反射镜121在具体设置时,其与底盘110之间的夹角θ可以为30°-60°,也即是说,反射镜121的倾斜角度θ可以为30°-60°,使得二维码的入射角(二维码入射至反射面a上的入射光线b1与反射面a的法线之间的夹角)保持在30°-60°之间,即使得反射角(入射光线b1经反射面a反射后的反射光线b2与反射面a的法线之间的夹角)在30°-60°之间,这样,在保证图像采集装置122的镜头1221与底盘110之间的距离一定的同时,确保图像采集装置122能从反射面a上获得二维码的完整信息。Referring to FIGS. 1 to 3 , when the reflector 121 is specifically set, the angle θ between it and the chassis 110 may be 30°-60°, that is to say, the inclination angle θ of the reflector 121 may be It is 30°-60°, so that the incident angle of the two-dimensional code (the angle between the incident light b1 incident on the two-dimensional code on the reflective surface a and the normal of the reflective surface a) is kept between 30°-60° , that is, the reflection angle (the angle between the reflected light b2 after the incident light b1 is reflected by the reflecting surface a and the normal of the reflecting surface a) is between 30° and 60°. While the distance between the lens 1221 and the chassis 110 is constant, it is ensured that the image capturing device 122 can obtain the complete information of the two-dimensional code from the reflective surface a.
另外,本发明实施例通过将反射镜121与底盘110之间的夹角θ设置在上述范围内,不仅保证二维码的光线完全入射至反射镜121的反射面a上,而且避免了该反射镜121在高度方向上的占用过大的空间,同时也避免夹角θ过小而影响反射镜121在底盘110上的稳固性。In addition, in the embodiment of the present invention, by setting the angle θ between the reflector 121 and the chassis 110 within the above-mentioned range, it not only ensures that the light of the two-dimensional code is completely incident on the reflecting surface a of the reflector 121, but also avoids the reflection. The mirror 121 occupies too much space in the height direction, and at the same time, it is also avoided that the included angle θ is too small to affect the stability of the mirror 121 on the chassis 110 .
具体设置时,反射镜121与底盘110之间的夹角θ可以为30°、45°或者60°等合适的数值,具体可根据反射镜121的镜头1221与底盘110之间的距离进行调整。例如,当反射镜121的镜头1221与底盘110之间的距离较大时,可以将反射镜121与底盘110之间的夹角θ调大,相反地, 当反射镜121的镜头1221与底盘110之间的距离较小时,可以将反射镜121与底盘110之间的夹角θ调小。In specific setting, the angle θ between the reflector 121 and the chassis 110 can be an appropriate value such as 30°, 45° or 60°, which can be adjusted according to the distance between the lens 1221 of the reflector 121 and the chassis 110 . For example, when the distance between the lens 1221 of the reflector 121 and the chassis 110 is large, the angle θ between the reflector 121 and the chassis 110 can be increased. On the contrary, when the lens 1221 of the reflector 121 and the chassis 110 When the distance between them is small, the angle θ between the reflector 121 and the chassis 110 can be adjusted to be small.
这里需要说明的是,本发明实施例涉及的数值和数值范围为近似值,受制造工艺的影响,可能会存在一定范围的误差,这部分误差本领域技术人员可以认为忽略不计。It should be noted here that the numerical values and numerical ranges involved in the embodiments of the present invention are approximate values, and there may be errors in a certain range due to the influence of the manufacturing process, and those skilled in the art can consider these errors to be ignored.
图4是本发明实施例提供的仓储机器人的第二种结构的部分结构示意图。参照图4所示,本发明实施例的摄像组件120还可以包括至少一个遮光件123。FIG. 4 is a partial structural schematic diagram of the second structure of the storage robot provided by the embodiment of the present invention. Referring to FIG. 4 , the camera assembly 120 according to the embodiment of the present invention may further include at least one light shielding member 123 .
实际应用中,反射镜121可以是四边形结构,例如,该反射镜121可以是长方形结构或者正方形结构。其中,反射镜121包括绕轴线设置的第一边缘、第二边缘、第三边缘和第四边缘,其中,第一边缘、第二边缘、第三边缘和第四边缘依次首尾连接,形成反射镜121的四个边缘部,第一边缘位于底盘110上,遮光件123的一端至少设置在第二边缘、第三边缘及第四边缘中的任意一个上,且遮光件123的另一端往图像采集装置122的方向延伸。In practical applications, the reflector 121 may be a quadrilateral structure, for example, the reflector 121 may be a rectangular structure or a square structure. The reflector 121 includes a first edge, a second edge, a third edge and a fourth edge arranged around the axis, wherein the first edge, the second edge, the third edge and the fourth edge are connected end to end in sequence to form a reflector Of the four edges of 121, the first edge is located on the chassis 110, one end of the shading member 123 is disposed on at least any one of the second edge, the third edge and the fourth edge, and the other end of the shading member 123 is used for image capture. The direction of the device 122 extends.
以下具体以第一边缘和第三边缘相对设置,第二边缘与第四边缘相对设置为例,对遮光件123进行说明。The light-shielding member 123 will be described below by taking as an example that the first edge and the third edge are disposed opposite to each other, and the second edge and the fourth edge are disposed opposite to each other.
例如,遮光件123的一端连接在第二边缘上,遮光件123的另一端往图像采集装置122的方向延伸,也即是说,遮光件123位于反射镜121的第二边缘与图像采集装置122之间,这样,遮光件123对反射镜121的第二边缘侧的光线进行遮挡,避免了部分光线通过反射镜121的第二边缘侧进入反射镜121与图像采集装置122之间,而对反射镜121的反射光线进行干涉,影响图像采集装置122采集精确的二维码的图像信息的情况发生。For example, one end of the shading member 123 is connected to the second edge, and the other end of the shading member 123 extends toward the direction of the image capturing device 122 , that is, the shading member 123 is located between the second edge of the mirror 121 and the image capturing device 122 In this way, the shading member 123 blocks the light on the second edge side of the reflector 121, preventing part of the light from entering between the reflector 121 and the image acquisition device 122 through the second edge side of the reflector 121, and causing the reflection The reflected light from the mirror 121 interferes, which affects the acquisition of accurate image information of the two-dimensional code by the image acquisition device 122 .
可以理解的是,遮光件123的另一端即远离反射镜121的一端可以延伸至图像采集装置122上,例如,遮光件123的一端位于反射镜121的第二边缘,另一端延伸至图像采集装置122上,这样,遮光件123便可对反射镜121的第二边缘与图像采集装置122之间形成的平面区域进行遮挡,使得外部的光线无法从该平面区域的任意位置进入反射镜121与图像采集装置122之间。It can be understood that the other end of the light shielding member 123, that is, the end away from the mirror 121, may extend to the image capture device 122. For example, one end of the light shielding member 123 is located at the second edge of the mirror 121, and the other end extends to the image capture device. 122, in this way, the shading member 123 can block the plane area formed between the second edge of the mirror 121 and the image acquisition device 122, so that external light cannot enter the mirror 121 and the image from any position in the plane area. between the collection devices 122 .
当然,遮光件123的另一端即远离反射镜121的一端可以与图像采集装置122之间具有一定间距,这样,该遮光件123可以对反射镜121的第 二边缘侧的部分光线进行遮光。Of course, the other end of the shading member 123, that is, the end away from the mirror 121, may have a certain distance from the image capturing device 122, so that the shading member 123 can shield part of the light on the second edge side of the mirror 121 from light.
需要说明的是,遮光件123的高度与反射镜121的边缘的长度一致,例如,当反射镜121的第二边缘设置有遮光件123时,该遮光件123包括沿高度方向上相对设置的第一端和第二端,其中第一端延伸至第二边缘的顶端,第二端延伸至第二边缘的底端(即底盘110上),使得反射镜121的第二边缘的任意位置均具有遮光件123。It should be noted that the height of the shading member 123 is the same as the length of the edge of the reflector 121. For example, when the second edge of the reflector 121 is provided with the shading member 123, the shading member 123 includes a second oppositely disposed along the height direction. One end and a second end, wherein the first end extends to the top end of the second edge, and the second end extends to the bottom end of the second edge (ie, on the chassis 110 ), so that any position of the second edge of the mirror 121 has Shading member 123 .
在一些示例中,遮光件123的数量可以至少为三个,至少三个遮光件123分别对应设置在第二边缘、第三边缘及第四边缘上,也即是说,三个遮光件123分别遮挡在反射镜121的第二边缘、第三边缘及第四边缘侧,从而使得三个遮光件123对从反射镜121的三个边缘侧进入的光线进行遮挡,进一步提高了遮光效果,保证图像采集装置122采集到的二维码信息的准确度和清晰度。In some examples, the number of the shading members 123 may be at least three, and the at least three shading members 123 are respectively disposed on the second edge, the third edge and the fourth edge, that is to say, the three shading members 123 are respectively disposed on the second edge, the third edge and the fourth edge. It is blocked on the second edge, the third edge and the fourth edge side of the reflector 121, so that the three shading members 123 block the light entering from the three edge sides of the reflector 121, further improving the shading effect and ensuring the image Accuracy and clarity of the two-dimensional code information collected by the collecting device 122 .
其中,遮光件123在具体设置时,可以是设置在底盘110上的遮光板,该遮光板的一端可连接在反射镜121的边缘上,当然,遮光板的一端可以仅抵接在反射镜121的边缘上。Wherein, the shading member 123 can be a shading plate disposed on the chassis 110 when it is specifically arranged, and one end of the shading plate can be connected to the edge of the reflector 121. Of course, one end of the shading plate can only abut on the reflector 121. on the edge.
参照图4所示,在一些示例中,反射镜121的第二边缘、第三边缘和第四边缘往图像采集装置122的方向延伸有遮光边,该遮光边与反射镜121为一体成型的一体件,遮光边被配置为遮光件123。Referring to FIG. 4 , in some examples, the second edge, the third edge and the fourth edge of the reflector 121 extend toward the image capturing device 122 with a light-shielding edge, and the light-shielding edge is integrally formed with the reflector 121 The light-shielding edge is configured as a light-shielding piece 123 .
如此设置,不仅简化了反射镜121与遮光件123的装配结构,提高了整个摄像组件120的装配效率,同时提高了反射镜121与遮光件123之间的连接强度,使得遮光件123的结构更加稳定。This arrangement not only simplifies the assembly structure of the reflector 121 and the light shielding member 123, but also improves the assembly efficiency of the entire camera assembly 120, and at the same time improves the connection strength between the reflecting mirror 121 and the light shielding member 123, so that the structure of the light shielding member 123 is more Stablize.
图5是本发明实施例提供的仓储机器人的第三种结构的局部剖视图。参照图5所示,本发明实施例的图像采集装置122在具体设置时,可滑动设置在底盘110上,以调节图像采集装置122与反射面a之间的距离。FIG. 5 is a partial cross-sectional view of a third structure of a storage robot provided by an embodiment of the present invention. Referring to FIG. 5 , the image capturing device 122 in the embodiment of the present invention can be slidably arranged on the chassis 110 to adjust the distance between the image capturing device 122 and the reflective surface a during specific setting.
例如,可以在底盘110上开设滑槽(图中未示出),图像采集装置122的底部设置有滑动部(图中未示出),该滑动部嵌设在滑槽内,且沿滑槽的延伸方向滑动,从而使得图像采集装置122可沿滑槽滑动。For example, a chute (not shown in the figure) may be provided on the chassis 110, and a sliding part (not shown in the figure) is provided at the bottom of the image capturing device 122, and the sliding part is embedded in the chute and extends along the chute. Sliding in the extending direction, so that the image capturing device 122 can slide along the chute.
其中,滑动部可以是从图像采集装置122的底部往下延伸的滑块,该滑块滑设在滑槽内。在一些示例中,滑动部还可以是设置在图像采集装置122底部的滚轮,滚轮滚动设置在滑槽内,使得图像采集装置122在滑槽内的移动更加顺畅。Wherein, the sliding part may be a sliding block extending downward from the bottom of the image capturing device 122, and the sliding block is slidably arranged in the sliding groove. In some examples, the sliding part may also be a roller disposed at the bottom of the image capture device 122 , and the roller is disposed in the chute so that the image capture device 122 moves more smoothly in the chute.
需要说明的是,滑槽的延伸方向(如图5中箭头b所示)与反射镜121的反射光路的延伸方向一致,使得图像采集装置122在滑槽内滑动时,图像采集装置122始终位于反射镜121的反射光路上,即图像采集装置122始终沿着箭头b的方向左右移动。It should be noted that the extension direction of the chute (as shown by arrow b in FIG. 5 ) is consistent with the extension direction of the reflected light path of the reflector 121 , so that when the image capture device 122 slides in the chute, the image capture device 122 is always located in the On the reflected light path of the mirror 121 , that is, the image acquisition device 122 always moves left and right along the direction of arrow b.
当反射镜121的倾斜角度θ较小时,例如,当反射镜121的倾斜角度θ为25°时,可将图像采集装置122滑动至距离反射镜121的反射面a较近的位置,直至图像采集装置122的镜头1221能够接收到反射面a反射的二维码的反射光线b2,从而确保图像采集装置122能够获取二维码的完整信息。When the inclination angle θ of the mirror 121 is small, for example, when the inclination angle θ of the mirror 121 is 25°, the image capture device 122 can be slid to a position closer to the reflection surface a of the mirror 121 until the image captures The lens 1221 of the device 122 can receive the reflected light b2 of the two-dimensional code reflected by the reflective surface a, thereby ensuring that the image acquisition device 122 can obtain the complete information of the two-dimensional code.
相反地,当反射镜121的倾斜角度θ较大时,例如,当反射镜121的倾斜角度θ为75°时,可将图像采集装置122滑动至距离反射镜121的反射面a较远的位置,直至图像采集装置122的镜头1221能够接收到反射面a反射的反射光线b2,从而确保图像采集装置122能够获取二维码的完整信息。Conversely, when the inclination angle θ of the mirror 121 is large, for example, when the inclination angle θ of the mirror 121 is 75°, the image capturing device 122 can be slid to a position farther from the reflection surface a of the mirror 121 , until the lens 1221 of the image acquisition device 122 can receive the reflected light b2 reflected by the reflective surface a, thereby ensuring that the image acquisition device 122 can acquire the complete information of the two-dimensional code.
基于上述可知,通过将图像采集装置122滑设在底盘110上,以使图像采集装置122能够适应反射镜121的设置角度,即反射镜121的倾斜角度θ过大或者过小时,均可通过调节图像采集装置122与反射镜121之间的距离,以使镜头1221能够接收到反射镜121的反射面a反射的二维码的完整信息,从而不仅确保通过该摄像组件120确定仓储机器人100的位置,而且降低了反射镜121的设置要求。Based on the above, it can be seen that by sliding the image acquisition device 122 on the chassis 110, the image acquisition device 122 can adapt to the setting angle of the mirror 121, that is, the inclination angle θ of the mirror 121 is too large or too small. The distance between the image acquisition device 122 and the mirror 121, so that the lens 1221 can receive the complete information of the two-dimensional code reflected by the reflective surface a of the mirror 121, so as not only to ensure that the position of the warehouse robot 100 is determined by the camera assembly 120 , and the setting requirements of the mirror 121 are reduced.
图6是本发明实施例提供的仓储机器人的第四种结构的局部剖视图。参照图6所示,本发明实施例的摄像组件120还可以包括支架124,图像采集装置122通过支架124设置在底盘110上,图像采集装置122转动连接在支架124上,且图像采集装置122的镜头1221能够往靠近或者远离底盘110内表面的方向转动,以调整图像采集装置122的镜头1221与反射面a的对准角度(如图6中的β所示)。FIG. 6 is a partial cross-sectional view of the fourth structure of the storage robot provided by the embodiment of the present invention. Referring to FIG. 6 , the camera assembly 120 in the embodiment of the present invention may further include a bracket 124 , the image capture device 122 is disposed on the chassis 110 through the bracket 124 , the image capture device 122 is rotatably connected to the bracket 124 , and the image capture device 122 is rotatably connected to the bracket 124 . The lens 1221 can be rotated toward or away from the inner surface of the chassis 110 to adjust the alignment angle between the lens 1221 of the image capture device 122 and the reflective surface a (as shown by β in FIG. 6 ).
其中,图像采集装置122的转动方向可参照图6中箭头c所示的方向。The rotation direction of the image acquisition device 122 may refer to the direction indicated by arrow c in FIG. 6 .
需要说明的是,图像采集装置122的镜头1221与反射面a的对准角度是指该图像采集装置122的镜头1221与反射面a上任意一点的连线与反射面a的法线之间的夹角。It should be noted that the alignment angle between the lens 1221 of the image capture device 122 and the reflection surface a refers to the distance between the line connecting the lens 1221 of the image capture device 122 and any point on the reflection surface a and the normal to the reflection surface a. angle.
这样,当反射镜121以确定的倾斜角度θ固定在窗口111的一侧,可 通过在支架124上转动图像采集装置122,以调整图像采集装置122的镜头1221与反射面a的对准角度β,使得该对准角度β与反射角一致,即保证镜头1221最终完全准确地对准反射面a,从而在确保图像采集装置122的镜头1221能够接收到反射面a反射的二维码的完整光线的同时,降低了对反射镜121的设置要求,即无需要求反射镜121的倾斜角度θ完全控制在一定范围内。In this way, when the reflective mirror 121 is fixed on one side of the window 111 at the determined inclination angle θ, the alignment angle β between the lens 1221 of the image capturing device 122 and the reflective surface a can be adjusted by rotating the image capturing device 122 on the bracket 124 , so that the alignment angle β is consistent with the reflection angle, that is, it is ensured that the lens 1221 is finally completely and accurately aligned with the reflecting surface a, so as to ensure that the lens 1221 of the image capturing device 122 can receive the complete light of the two-dimensional code reflected by the reflecting surface a. At the same time, the requirement for the setting of the mirror 121 is reduced, that is, it is not required to completely control the inclination angle θ of the mirror 121 within a certain range.
具体设置时,支架124可以包括第一转轴1243、两个支撑件1241及两个固定件1242。其中,两个支撑件1241沿垂直于反射光路的方向相对设置,两个固定件1242分别固定在两个支撑件1241的内侧,换句话说,其中一个固定件1242设置在其中一个支撑件1241的内侧,另一个固定件1242设置在另一个支撑件1241的内侧,两个支撑件1241的底端均固定在底盘110上,第一转轴1243的一端穿过其中一个固定件1242并活动设置在其中一个支撑件1241上,第一转轴1243的另一端穿过另一个固定件1242并活动设置在另一个支撑件1241上。In specific settings, the bracket 124 may include a first rotating shaft 1243 , two supporting members 1241 and two fixing members 1242 . Wherein, the two supporting members 1241 are arranged opposite to each other along the direction perpendicular to the reflected light path, and the two fixing members 1242 are respectively fixed on the inner side of the two supporting members 1241 . On the inner side, the other fixing member 1242 is arranged on the inner side of the other supporting member 1241, the bottom ends of the two supporting members 1241 are both fixed on the chassis 110, and one end of the first rotating shaft 1243 passes through one of the fixing members 1242 and is movably arranged therein. On one supporting member 1241 , the other end of the first rotating shaft 1243 passes through the other fixing member 1242 and is movably arranged on the other supporting member 1241 .
可以理解的是,固定件1242与支撑件1241固定连接,第一转轴1243可绕自身的轴线转动。It can be understood that the fixing member 1242 is fixedly connected with the supporting member 1241, and the first rotating shaft 1243 can rotate around its own axis.
图像采集装置122转动连接在第一转轴1243上。例如,图像采集装置122的一端设置有具有通孔的连接部,该连接部套设在第一转轴1243上,从而使得该图像采集装置122可绕第一转轴1243转动,实现图像采集装置122的镜头1221的转动。The image capturing device 122 is rotatably connected to the first rotating shaft 1243 . For example, one end of the image capturing device 122 is provided with a connecting portion with a through hole, and the connecting portion is sleeved on the first rotating shaft 1243 , so that the image capturing device 122 can rotate around the first rotating shaft 1243 to realize the image capturing device 122 . Rotation of the lens 1221.
其中,为了保证图像采集装置122在任意角度下的稳定性,可以在至少一个固定件1242与图像采集装置122之间设置定位结构,通过该定位结构使得图像采集装置122稳固在任意角度下。Wherein, in order to ensure the stability of the image capture device 122 at any angle, a positioning structure may be provided between at least one fixing member 1242 and the image capture device 122, and the image capture device 122 can be stabilized at any angle through the positioning structure.
可以理解的是,该定位结构可以是开设在固定件1242上的多个定位槽或者定位孔,多个定位槽或者定位孔沿图像采集装置122的转动路径间隔设置,相应地,在图像采集装置122的一侧延伸出定位凸起。当图像采集装置122转动至合适角度后,该定位凸起卡设在固定件1242上对应的定位槽或者定位孔内,从而限制了图像采集装置122的转动,确保图像采集装置122的稳固性,进而保证图像采集装置122的镜头1221接收到的二维码的清晰度。It can be understood that the positioning structure may be a plurality of positioning grooves or positioning holes formed on the fixing member 1242, and the plurality of positioning grooves or positioning holes are arranged at intervals along the rotation path of the image capture device 122. Correspondingly, in the image capture device A positioning protrusion extends from one side of 122 . When the image capturing device 122 is rotated to an appropriate angle, the positioning protrusion is clamped in the corresponding positioning groove or positioning hole on the fixing member 1242, thereby restricting the rotation of the image capturing device 122 and ensuring the stability of the image capturing device 122. This further ensures the clarity of the two-dimensional code received by the lens 1221 of the image capture device 122 .
继续参照图6所示,可选地,本发明实施例的反射镜121可转动连接 在底盘110上,且反射镜121远离底盘110的一端能够往靠近或者远离底盘110内表面的方向转动,以调节反射镜121与底盘110之间的夹角(即反射镜121的倾斜角度θ)。6 , optionally, the reflector 121 in the embodiment of the present invention is rotatably connected to the chassis 110 , and the end of the reflector 121 away from the chassis 110 can be rotated in a direction close to or away from the inner surface of the chassis 110 to Adjust the angle between the reflector 121 and the chassis 110 (ie, the inclination angle θ of the reflector 121 ).
其中,反射镜121的转动方向可参照图6中d箭头所示。The rotation direction of the mirror 121 can be referred to as shown by arrow d in FIG. 6 .
本发明实施例通过将反射镜121转动连接在底盘110上,不仅在图像采集装置122的镜头1221固定的情况下,可通过转动反射镜121,以调节反射镜121的倾斜角度θ,使得镜头1221能够完全准确地对准反射面a,保证图像采集装置122的镜头1221能够接收到反射面a反射的二维码的完整信息,而且当摄像组件120使用完毕后,可将反射镜121转动至贴合在底盘110的内表面上,从而降低反射镜121在未使用状态下在仓储机器人100内的占用空间,同时也减小了仓储机器人100在活动过程中,其内部的其他零部件对反射镜121发生碰撞而损坏。In this embodiment of the present invention, by rotating the reflector 121 on the chassis 110, not only when the lens 1221 of the image capture device 122 is fixed, but also the reflector 121 can be rotated to adjust the inclination angle θ of the reflector 121 so that the lens 1221 The reflective surface a can be completely and accurately aligned to ensure that the lens 1221 of the image acquisition device 122 can receive the complete information of the two-dimensional code reflected by the reflective surface a, and when the camera assembly 120 is used, the mirror 121 can be rotated to the sticker. It is combined with the inner surface of the chassis 110, thereby reducing the space occupied by the mirror 121 in the storage robot 100 when it is not in use, and also reducing the impact of other components inside the storage robot 100 on the mirror during the movement of the storage robot 100. 121 was damaged in a collision.
具体设置时,可以在窗口111的一侧边缘设置第二转轴125,反射镜121的一端活动连接在该第二转轴125上,例如,可以在反射镜121的一端开设贯穿孔,将第二转轴125活动穿设在该贯穿孔内,从而使得该反射镜121可绕第二转动125转动,实现倾斜角度θ的调节。In the specific setting, a second rotating shaft 125 can be set on one edge of the window 111, and one end of the mirror 121 can be movably connected to the second rotating shaft 125. For example, a through hole can be opened at one end of the reflecting mirror 121, and the second rotating shaft The 125 is movably arranged in the through hole, so that the mirror 121 can be rotated around the second rotation 125 to realize the adjustment of the inclination angle θ.
可以理解的是,图像采集装置122的移动、转动以及反射镜121的转动可以根据实际需要进行手动操作。It can be understood that, the movement and rotation of the image capturing device 122 and the rotation of the mirror 121 can be manually operated according to actual needs.
在一些示例中,摄像组件120还可以包括控制单元和驱动单元。其中,控制单元与驱动单元信号连接,以信号控制驱动单元工作。In some examples, the camera assembly 120 may further include a control unit and a driving unit. Wherein, the control unit is connected with the driving unit in signal, and controls the driving unit to work with the signal.
驱动单元可以与图像采集装置122连接,以驱动图像采集装置122的移动或者转动。例如,该驱动单元可以是连接在图像采集装置122上设置第一驱动电机,该第一驱动电机用于驱动图像采集装置122绕第一转轴1243转动,控制单元用于控制该第一驱动电机工作。其中,该第一驱动电机可以是旋转电机。The driving unit may be connected with the image capturing device 122 to drive the movement or rotation of the image capturing device 122 . For example, the drive unit may be connected to the image capture device 122 and set with a first drive motor, the first drive motor is used to drive the image capture device 122 to rotate around the first shaft 1243, and the control unit is used to control the first drive motor to work . Wherein, the first drive motor may be a rotary motor.
示例性地,当图像采集装置122的镜头1221无法采集到反射镜121反射的二维码时,控制单元可向第一驱动电机例如旋转电机发送工作信号,使得该旋转电机以第一预设参数驱动图像采集装置122绕第一转轴1243转动,直至图像采集装置122的镜头1221完全对准反射面a,控制单元控制旋转电机停止转动,保证图像采集装置122能够采集到反射镜121反射的二维码的完整信息。Exemplarily, when the lens 1221 of the image capture device 122 cannot capture the two-dimensional code reflected by the mirror 121, the control unit may send a working signal to the first drive motor, such as a rotating motor, so that the rotating motor uses the first preset parameter. Drive the image capture device 122 to rotate around the first rotation axis 1243 until the lens 1221 of the image capture device 122 is completely aligned with the reflective surface a, and the control unit controls the rotating motor to stop rotating, so as to ensure that the image capture device 122 can capture the two-dimensional image reflected by the mirror 121 code for complete information.
其中,第一预设参数包括旋转电机的旋转速度。Wherein, the first preset parameter includes the rotation speed of the rotating electrical machine.
再例如,该驱动单元可以是连接在图像采集装置122上设置第二驱动电机,该第二驱动电机用于驱动图像采集装置122往靠近或者远离反射镜121的方向移动,控制单元用于控制该第二驱动电机工作。其中,该第二驱动电机可以是步进电机。For another example, the drive unit may be connected to the image capture device 122 and set with a second drive motor, the second drive motor is used to drive the image capture device 122 to move toward or away from the mirror 121, and the control unit is used to control the The second drive motor works. Wherein, the second driving motor may be a stepping motor.
示例性地,当图像采集装置122的镜头1221无法采集到反射镜121反射的二维码时,控制单元可向第二驱动电机例如步进电机发送工作信号,使得该步进电机以第二预设参数驱动图像采集装置122往靠近或者远离反射镜121的方向移动,直至图像采集装置122的镜头1221采集到反射镜121反射的二维码的完整信息,控制单元控制步进电机停止运动。Exemplarily, when the lens 1221 of the image capturing device 122 cannot capture the two-dimensional code reflected by the mirror 121, the control unit may send a working signal to the second driving motor, such as a stepping motor, so that the stepping motor starts with the second preset. Set the parameters to drive the image capture device 122 to move toward or away from the mirror 121 until the lens 1221 of the image capture device 122 captures the complete information of the two-dimensional code reflected by the mirror 121, and the control unit controls the stepper motor to stop moving.
其中,第二预设参数包括步进电机的运动速度。Wherein, the second preset parameter includes the movement speed of the stepping motor.
可以理解的是,驱动单元可以包括第一驱动电机和第二驱动电机,该第一驱动电机和第二驱动电机均连接在图像采集装置122上。控制单元分别与第一驱动电机和第二驱动电机信号连接。It can be understood that the driving unit may include a first driving motor and a second driving motor, and the first driving motor and the second driving motor are both connected to the image capturing device 122 . The control unit is signal-connected to the first drive motor and the second drive motor, respectively.
示例性地,当图像采集装置122的镜头1221无法采集到反射镜121反射的二维码时,控制单元可向第一驱动电机发送工作信号,使得该第一驱动电机以第一预设参数驱动图像采集装置122绕第一转轴1243转动,同时,该控制单元向第二驱动电机发送工作信号,使得该第二驱动电机以第二预设参数驱动图像采集装置122往靠近或者远离反射镜121的方向移动,直至图像采集装置122的镜头1221采集到反射镜121反射的二维码的完整信息,控制单元控制第一驱动电机和第二驱动电机停止工作。Exemplarily, when the lens 1221 of the image capture device 122 cannot capture the two-dimensional code reflected by the mirror 121, the control unit may send a working signal to the first drive motor, so that the first drive motor is driven with the first preset parameters. The image capture device 122 rotates around the first shaft 1243 , and at the same time, the control unit sends a working signal to the second drive motor, so that the second drive motor drives the image capture device 122 toward or away from the mirror 121 with the second preset parameters. The direction moves until the lens 1221 of the image capture device 122 captures the complete information of the two-dimensional code reflected by the mirror 121, and the control unit controls the first drive motor and the second drive motor to stop working.
另外,本发明实施例的驱动单元还可与反射镜121连接,以驱动反射镜121转动。例如,该驱动单元可以是连接在图像采集装置122上设置第三驱动电机,该第三驱动电机用于驱动反射镜121绕第二转轴125转动,以调节该反射镜121的倾斜角度θ。其中,该第三驱动电机可以是旋转电机。In addition, the driving unit in the embodiment of the present invention can also be connected with the mirror 121 to drive the mirror 121 to rotate. For example, the driving unit may be connected to the image capturing device 122 and provided with a third driving motor, the third driving motor is used to drive the mirror 121 to rotate around the second shaft 125 to adjust the inclination angle θ of the mirror 121 . Wherein, the third drive motor may be a rotary motor.
示例性地,当图像采集装置122的镜头1221无法采集到反射镜121反射的二维码时,控制单元可向第三驱动电机例如旋转电机发送工作信号,使得该旋转电机以第三预设参数驱动反射镜121绕第二转轴125转动,直至图像采集装置122能够采集到反射镜121反射的二维码的完整信息,控制单元控制第三驱动电机停止工作。Exemplarily, when the lens 1221 of the image capture device 122 cannot capture the two-dimensional code reflected by the mirror 121, the control unit may send a working signal to a third drive motor, such as a rotary motor, so that the rotary motor uses the third preset parameter. The mirror 121 is driven to rotate around the second shaft 125 until the image capture device 122 can capture the complete information of the two-dimensional code reflected by the mirror 121, and the control unit controls the third drive motor to stop working.
其中,第三预设参数包括旋转电机的旋转速度。Wherein, the third preset parameter includes the rotation speed of the rotating electrical machine.
本发明实施例通过设置控制单元和驱动单元,以信号控制图像采集装置122和反射镜121活动,有效地提高了对反射镜121与图像采集装置122的调节效率,从而提高了整个仓储机器人100的定位与导航效率。The embodiment of the present invention effectively improves the adjustment efficiency of the mirror 121 and the image acquisition device 122 by setting the control unit and the driving unit to control the activities of the image acquisition device 122 and the mirror 121 with signals, thereby improving the operation efficiency of the entire storage robot 100 Positioning and Navigation Efficiency.
需要说明的是,控制单元可以是现有技术的控制器,其具体的电路结构及控制原理可直接参照现有技术。It should be noted that the control unit may be a controller of the prior art, and the specific circuit structure and control principle thereof may directly refer to the prior art.
参照图1所示,本发明实施例还提供一种仓储机器人,包括底盘110和至少一组上述任意示例的摄像组件120。Referring to FIG. 1 , an embodiment of the present invention further provides a storage robot, which includes a chassis 110 and at least one set of camera assemblies 120 according to any of the foregoing examples.
其中,摄像组件120位于底盘110的内表面,底盘110上具有朝向定位图像所在面300的窗口111,摄像组件120的反射镜121设置在窗口111的一侧并往窗口111的方向倾斜,且反射镜121的反射面朝向窗口111,图像采集装置122位于反射镜121的反射光路上,且图像采集装置122的镜头1221与反射面对准。The camera assembly 120 is located on the inner surface of the chassis 110, and the chassis 110 has a window 111 facing the surface 300 where the image is positioned. The reflection surface of the mirror 121 faces the window 111 , the image capture device 122 is located on the reflected light path of the mirror 121 , and the lens 1221 of the image capture device 122 is aligned with the reflection surface.
参照图3所示,当仓储机器人100移动至定位图像所在面300例如地面的某个定位图像200(例如二维码)上方时,地面上的二维码可通过窗口111照射至反射镜121的反射面a上,再通过该反射镜121的反射面a将该二维码的入射光线b1反射至图像采集装置122的镜头1221内,继而对该二维码的图像信息进行解析,最终得到仓储机器人100所在位置,实现对该仓储机器人100的定位与导航。Referring to FIG. 3 , when the warehouse robot 100 moves to a surface 300 where the positioning image is located, such as a positioning image 200 (such as a two-dimensional code) on the ground, the two-dimensional code on the ground can be irradiated to the mirror 121 through the window 111 . On the reflecting surface a, the incident light b1 of the two-dimensional code is reflected to the lens 1221 of the image acquisition device 122 through the reflecting surface a of the reflecting mirror 121, and then the image information of the two-dimensional code is analyzed, and finally the storage is obtained. The location of the robot 100 realizes the positioning and navigation of the warehouse robot 100 .
相比于传统技术,本发明实施例的摄像组件120通过反射镜121将地面的二维码的光线反射至图像采集装置122的镜头1221内,无需将图像采集装置122设置在距离底盘110内表面较高的位置,缩小了摄像组件120在仓储机器人100高度方向上的占用空间,不仅避免了仓储机器人100中其他零部件的安装造成影响的情况发生,而且缩小了整个仓储机器人100的高度尺寸,方便了仓储机器人100的搬运与收纳。Compared with the traditional technology, the camera assembly 120 in the embodiment of the present invention reflects the light of the two-dimensional code on the ground into the lens 1221 of the image acquisition device 122 through the reflector 121 , and it is not necessary to set the image acquisition device 122 at a distance from the inner surface of the chassis 110 . The higher position reduces the space occupied by the camera assembly 120 in the height direction of the storage robot 100, which not only avoids the impact of the installation of other components in the storage robot 100, but also reduces the height dimension of the entire storage robot 100. The handling and storage of the storage robot 100 are facilitated.
本发明实施例的窗口111在具体设置时,可以为开设在底盘110上的透光口。为了避免外部的灰尘等杂物进入仓储机器人100的内部,本发明实施例的仓储机器人还可以包括透光保护件。该透光保护件覆盖在透光口上,以将仓储机器人100的内腔与外部环境进行隔离,从而保证仓储机器人100内的摄像组件120等部件不会受到外部灰尘等杂物的污染而损坏,进而延长摄像组件120等部件的使用寿命。The window 111 in the embodiment of the present invention may be a light-transmitting port opened on the chassis 110 during specific setting. In order to prevent external dust and other sundries from entering the interior of the storage robot 100, the storage robot according to the embodiment of the present invention may further include a light-transmitting protection member. The light-transmitting protective member covers the light-transmitting port to isolate the inner cavity of the storage robot 100 from the external environment, thereby ensuring that the camera assembly 120 and other components in the storage robot 100 will not be damaged by external dust and other sundries. Further, the service life of components such as the camera assembly 120 is prolonged.
例如,通过在透光口上覆盖透光保护件,可避免仓储机器人外部的灰尘等杂物通过透光口进入底盘内部,对反射镜的镜面以及镜头造成污染。For example, by covering the light-transmitting protection piece on the light-transmitting port, dust and other debris outside the warehouse robot can be prevented from entering the interior of the chassis through the light-transmitting port, causing contamination to the mirror surface and the lens of the reflector.
其中,透光保护件可以包括但不限于透光塑料膜及透光玻璃中的任意一种。Wherein, the light-transmitting protection member may include, but is not limited to, any one of a light-transmitting plastic film and a light-transmitting glass.
图7是本发明实施例提供的仓储机器人的第五种结构的部分结构示意图。参照图7所示,具体设置时,窗口111的数量可以是1个,也可以是多个,例如,窗口111的数量至少为两个,至少两个窗口111间隔设置在底盘110的活动方向上。其中,底盘110的活动方向可参照图7中x所示的方向。FIG. 7 is a partial structural schematic diagram of a fifth structure of a storage robot provided by an embodiment of the present invention. Referring to FIG. 7 , in specific settings, the number of windows 111 may be one or more, for example, the number of windows 111 is at least two, and at least two windows 111 are arranged at intervals in the moving direction of the chassis 110 . The moving direction of the chassis 110 may refer to the direction shown by x in FIG. 7 .
摄像组件120的数量至少为两个,至少两个摄像组件120分别与至少两个窗口111对应设置。The number of the camera assemblies 120 is at least two, and the at least two camera assemblies 120 are respectively arranged corresponding to the at least two windows 111 .
例如,在每个窗口111的两侧均设置反射镜121和图像采集装置122。For example, mirrors 121 and image acquisition devices 122 are provided on both sides of each window 111 .
参照图7所示,为了方便描述,将两个窗口111中位于左侧的窗口111为第一窗口1111,位于右侧的窗口111为第二窗口1112。Referring to FIG. 7 , for the convenience of description, the window 111 located on the left side of the two windows 111 is referred to as the first window 1111 , and the window 111 located on the right side is referred to as the second window 1112 .
仓储机器人100沿x方向活动,当第一窗口1111移动至定位图像所在面300例如地面的某个定位图像200(例如二维码)上方时,地面上的二维码可通过第一窗口1111照射至设在第一窗口1111一侧的反射镜121的反射面a上,再通过该反射镜121的反射面a将该二维码的入射光线b1反射至设在第一窗口1111一侧的图像采集装置122的镜头1221内,继而对该二维码的图像信息进行解析,得到仓储机器人100所在的第一位置。The warehouse robot 100 moves along the x-direction. When the first window 1111 moves to the surface 300 where the positioning image is located, such as a positioning image 200 (such as a two-dimensional code) on the ground, the two-dimensional code on the ground can be illuminated through the first window 1111 to the reflective surface a of the mirror 121 on the side of the first window 1111, and then reflect the incident light b1 of the two-dimensional code to the image on the side of the first window 1111 through the reflective surface a of the mirror 121 In the lens 1221 of the collecting device 122, the image information of the two-dimensional code is analyzed to obtain the first position where the warehouse robot 100 is located.
接着,仓储机器人100沿x方向继续活动,当第二窗口1112移动至定位图像所在面300例如地面的某个定位图像200(例如二维码)上方时,地面上的二维码可通过第二窗口1112照射至设在第二窗口1112一侧的反射镜121的反射面a上,再通过该反射镜121的反射面a将该二维码的入射光线b1反射至设在第二窗口1112一侧的图像采集装置122的镜头1221内,继而对该二维码的图像信息进行解析,得到仓储机器人100所在的第二位置。Next, the warehouse robot 100 continues to move along the x-direction. When the second window 1112 moves to the surface 300 where the positioning image is located, such as a positioning image 200 (such as a two-dimensional code) on the ground, the two-dimensional code on the ground can pass through the second The window 1112 illuminates the reflective surface a of the mirror 121 provided on the side of the second window 1112, and then reflects the incident light b1 of the two-dimensional code to the reflective surface a of the mirror 121 to the second window 1112-1. Then, the image information of the two-dimensional code is analyzed to obtain the second position where the warehouse robot 100 is located.
当第一位置和第二位置一致时,可得出确定的仓储机器人100所在位置的准确性。当第一位置与第二位置不一致时,可得出确定的仓储机器人100所在位置不准确,需重新确定。When the first position and the second position are consistent, the determined accuracy of the position of the storage robot 100 can be obtained. When the first position is inconsistent with the second position, it can be concluded that the determined position of the storage robot 100 is inaccurate and needs to be re-determined.
通过设置两个窗口111以及两组摄像组件120,以验证得到的仓储机 器人100所在位置的准确性。By setting two windows 111 and two sets of camera assemblies 120, the accuracy of the obtained location of the warehouse robot 100 is verified.
另外,当其中一组摄像组件120发生损坏而失效时,可通过另一个摄像组件120对仓储机器人100进行定位与导航,提高了摄像组件120的定位可靠性。In addition, when one of the camera assemblies 120 is damaged and fails, the warehouse robot 100 can be positioned and navigated through the other camera assembly 120 , which improves the positioning reliability of the camera assemblies 120 .
基于上述仓储机器人,本发明实施例提出了一种定位方法,本发明实施例的定位方法可以由仓储机器人的图像采集装置执行,也可以由仓储机器人的处理器执行。图8是本发明实施例示出的一种定位方法的步骤流程图,包括:S201至S202:Based on the above-mentioned storage robot, an embodiment of the present invention proposes a positioning method. The positioning method of the embodiment of the present invention may be executed by an image acquisition device of the storage robot, or may be executed by a processor of the storage robot. FIG. 8 is a flowchart of steps of a positioning method according to an embodiment of the present invention, including: S201 to S202:
S201:获取图像采集装置采集的反射镜中的第一定位图像。S201: Acquire a first positioning image in the mirror collected by the image collection device.
其中,第一定位图像的生成过程包括如下两个阶段,第一阶段:反射镜透过窗口对地面上的定位图像成像,在反射镜中形成图像;第二阶段:图像采集装置采集反射镜中的图像得到第一定位图像。The generation process of the first positioning image includes the following two stages. The first stage: the mirror images the positioning image on the ground through the window, and the image is formed in the mirror; the second stage: the image acquisition device collects the image in the mirror image to get the first positioning image.
S202:根据第一定位图像确定仓储机器人的位置。S202: Determine the position of the warehouse robot according to the first positioning image.
其中,仓储机器人的位置是指仓储机器人在仓库中的位置。仓储机器人的位置可以根据第一定位图像的内容确定,不同位置的第一定位图像的内容不同。Among them, the location of the warehouse robot refers to the location of the warehouse robot in the warehouse. The position of the warehouse robot may be determined according to the content of the first positioning image, and the content of the first positioning image at different positions is different.
在第一种示例中,第一定位图像中可以包括位置信息,从而可以从第一定位图像中解析得到位置信息。例如,第一定位图像可以为包括位置信息的二维码,从而可以将二维码进行解析得到位置信息。In the first example, the first positioning image may include position information, so that the position information may be obtained by parsing the first positioning image. For example, the first positioning image may be a two-dimensional code including location information, so that the two-dimensional code may be parsed to obtain the location information.
在第二种示例中,第一定位图像不包括位置信息,从而可以将第一定位图像与数据库中预设的图像数据进行匹配,若匹配成功,则将匹配到的第一定位图像在数据库中对应的位置作为仓储机器人的位置。In the second example, the first positioning image does not include position information, so that the first positioning image can be matched with the image data preset in the database. If the matching is successful, the matched first positioning image will be stored in the database. The corresponding position is used as the position of the warehouse robot.
其中,数据库中存储有若干图像数据以及对应的位置信息,当匹配成功时,将数据库中该图像数据对应的位置信息为第一定位图像在数据库中对应的位置。The database stores several image data and corresponding position information. When the matching is successful, the position information corresponding to the image data in the database is used as the position corresponding to the first positioning image in the database.
在本发明实施例中,可以通过调整反射镜、窗口和图像采集装置之间的位置关系,以重新获取第一定位图像或获取多个第一定位图像,以根据重新获取的第一定位图像确定仓储机器人的位置,或根据多个第一定位图像确定仓储机器人的位置,有助于提高定位准确度和成功率。In this embodiment of the present invention, the positional relationship between the mirror, the window, and the image acquisition device can be adjusted to reacquire the first positioning image or obtain a plurality of first positioning images, so as to determine the determination according to the re-acquired first positioning image The position of the storage robot, or the determination of the position of the storage robot according to multiple first positioning images, helps to improve positioning accuracy and success rate.
可选地,可以通过如下方式调整位置关系:调整反射镜与窗口之间的倾斜角度;和/或,调整图像采集装置与窗口之间的倾斜角度;和/或,调 整图像采集装置与反射镜之间的距离。Optionally, the positional relationship may be adjusted in the following manner: adjusting the inclination angle between the mirror and the window; and/or adjusting the inclination angle between the image capture device and the window; and/or adjusting the image capture device and the mirror the distance between.
在本发明实施例中,调整反射镜与窗口之间的倾斜角度可以通过调整反射镜的倾斜程度来实现,反射镜可调整的固定在底盘上。调整图像采集装置与窗口之间的倾斜角度可以通过调整图像采集装置的倾斜程度来实现,图像采集装置可调整的固定在底盘上。调整图像采集装置与窗口之间的倾斜角度可以通过调整图像采集装置的位置来实现,例如,将图像采集装置安装于滑道上,以滑动图像采集装置。In the embodiment of the present invention, the adjustment of the inclination angle between the reflector and the window can be realized by adjusting the degree of inclination of the reflector, and the reflector can be adjusted and fixed on the chassis. Adjusting the inclination angle between the image capture device and the window can be achieved by adjusting the inclination of the image capture device, and the image capture device can be adjusted and fixed on the chassis. Adjusting the inclination angle between the image capturing device and the window can be achieved by adjusting the position of the image capturing device, for example, installing the image capturing device on the slideway to slide the image capturing device.
可选地,在本发明实施例的一种示例中,上述S202包括S2021至S2022:Optionally, in an example of the embodiment of the present invention, the foregoing S202 includes S2021 to S2022:
S2021:当判断第一定位图像无法识别,则调整反射镜、窗口和图像采集装置之间的位置关系,并根据调整之后采集的第一定位图像确定仓储机器人的位置。S2021: When it is determined that the first positioning image cannot be identified, adjust the positional relationship between the mirror, the window and the image acquisition device, and determine the position of the storage robot according to the first positioning image collected after the adjustment.
其中,第一定位图像无法识别可以是第一定位图像失真引起的,第一定位图像失真包括:第一定位图像部分区域缺失、第一定位图像变形、第一定位图像部分区域被遮挡或反光。Wherein, the unrecognizable first positioning image may be caused by the distortion of the first positioning image, and the first positioning image distortion includes: a partial area of the first positioning image is missing, the first positioning image is deformed, and a partial area of the first positioning image is occluded or reflective.
第一定位图像是否可以识别可以通过两种方式确定,第一种方式,识别第一定位图像,根据识别结果确定第一定位图像是否可以识别;第二种方式,根据第一定位图像的失真程度参数确定第一定位图像是否可以识别,具体可以参照S2023至S2025:Whether the first positioning image can be identified can be determined in two ways. The first way is to identify the first positioning image and determine whether the first positioning image can be identified according to the recognition result; the second way is to determine whether the first positioning image is identifiable according to the degree of distortion of the first positioning image. The parameter determines whether the first positioning image can be identified. For details, refer to S2023 to S2025:
S2023:确定第一定位图像的失真程度参数。S2023: Determine a distortion degree parameter of the first positioning image.
其中,失真程度参数用于表示第一定位图像与标准定位图像之间的差异程度。可以理解的是,失真程度参数越大,代表差异程度越大;失真程度参数越小,代表差异程度越小。The distortion degree parameter is used to represent the degree of difference between the first positioning image and the standard positioning image. It can be understood that the larger the distortion degree parameter is, the larger the difference degree is; the smaller the distortion degree parameter is, the smaller the difference degree is.
在实际应用中,标准定位图像对应预设图形,预设图形的形状、尺寸可以设定,若第一定位图像的形状、尺寸与标准定位图像之间的形状、尺寸不一致,则代表第一定位图像失真,失真程度参数可以根据形状、尺寸之间的差异程度确定;当第一定位图像的形状、尺寸与标准定位图像之间的形状、尺寸均一致,则代表第一定位图像未失真。In practical applications, the standard positioning image corresponds to the preset graphic, and the shape and size of the preset graphic can be set. If the shape and size of the first positioning image are inconsistent with the standard positioning image, it represents the first positioning image. The image is distorted, and the distortion degree parameter can be determined according to the degree of difference between the shape and size; when the shape and size of the first positioning image are consistent with the shape and size of the standard positioning image, it means that the first positioning image is not distorted.
可选地,可以根据如下S20231至S20232或S20233至S20235确定第一定位图像的失真程度参数,其中,S20231和S20232可以用于确定第一定位图像是否变形或缺失边缘部分,S20233至S20235可以用于确定第一定位图像是否存在反光或遮挡。在实际应用中,可以仅执行S20231和 S20232,也可以仅执行S20233至S20235,还可以将S20231和S20232确定的失真程度参数与S20233至S20235确定的失真程度参数进行综合得到第一定位图像的失真程度参数。可以理解的是,当S20231和S20232确定的失真程度参数与S20233至S20235确定的失真程度参数均不为0时,确定第一定位图像不仅确实边缘部分还存在反光或遮挡,第一定位图像的失真较严重。Optionally, the distortion degree parameter of the first positioning image can be determined according to the following S20231 to S20232 or S20233 to S20235, wherein S20231 and S20232 can be used to determine whether the first positioning image is deformed or lacks an edge part, and S20233 to S20235 can be used to It is determined whether there is reflection or occlusion in the first positioning image. In practical applications, only S20231 and S20232 may be performed, or only S20233 to S20235 may be performed, and the distortion degree parameters determined by S20231 and S20232 and the distortion degree parameters determined by S20233 to S20235 may be synthesized to obtain the distortion degree of the first positioning image. parameter. It can be understood that when the distortion degree parameters determined by S20231 and S20232 and the distortion degree parameters determined by S20233 to S20235 are not 0, it is determined that not only the edge part of the first positioning image is indeed reflective or occluded, the distortion of the first positioning image is more serious.
S20231:确定第一定位图像的边缘像素点。S20231: Determine the edge pixels of the first positioning image.
其中,边缘像素点为位于第一定位图像的边缘位置的像素点。在确定边缘像素点时,可以针对第一定位图像中的任意像素点(后续称为候选像素点),确定是否存在位于该候选像素点左方、右方、下方、上方的像素点。若不存在位于该候选像素点左方的像素点,则确定该候选像素点为该第一定位图像在左边的边缘像素点;若不存在位于该候选像素点右方的像素点,则确定该候选像素点为该第一定位图像在右边的边缘像素点;若不存在位于该候选像素点上方的像素点,则确定该候选像素点为该第一定位图像在上边的边缘像素点;若不存在位于该候选像素点下方的像素点,则确定该候选像素点为该第一定位图像在下边的边缘像素点。The edge pixels are pixels located at the edge of the first positioning image. When determining an edge pixel, for any pixel in the first positioning image (hereinafter referred to as a candidate pixel), it can be determined whether there is a pixel located to the left, right, below, or above the candidate pixel. If there is no pixel point located to the left of the candidate pixel point, the candidate pixel point is determined to be the edge pixel point on the left side of the first positioning image; if there is no pixel point located to the right of the candidate pixel point, the candidate pixel point is determined to be The candidate pixel point is the edge pixel point on the right side of the first positioning image; if there is no pixel point located above the candidate pixel point, the candidate pixel point is determined as the edge pixel point on the upper side of the first positioning image point; if not If there is a pixel point located below the candidate pixel point, the candidate pixel point is determined to be the lower edge pixel point of the first positioning image.
可以理解的是,一个候选像素点可以是在上边、左边、下边、右边其中至少两个边的边缘像素点。It can be understood that a candidate pixel point may be an edge pixel point on at least two sides of the upper side, the left side, the lower side, and the right side.
S20232:确定边缘像素点所形成的图形与第一定位图像的预设图形之间的差异程度,确定第一定位图像的失真程度参数。S20232: Determine the degree of difference between the graphics formed by the edge pixels and the preset graphics of the first positioning image, and determine the distortion degree parameter of the first positioning image.
其中,失真程度参数可以包括:边缘像素点所形成的图形与预设图形之间的形状差异程度、边缘像素点所形成的图形与预设图形之间的尺寸差异程度。可选地,可以将形状差异程度和尺寸差异程度进行加权作为第一定位图像的失真程度参数。由于形状不一致时的失真通常较大,从而可以对形状差异程度设置较大的权重,对尺寸差异程度设置较小的权重。The distortion degree parameter may include: the degree of shape difference between the figure formed by the edge pixels and the preset figure, and the degree of size difference between the figure formed by the edge pixels and the preset figure. Optionally, the shape difference degree and the size difference degree may be weighted as the distortion degree parameter of the first positioning image. Since the distortion when the shapes are inconsistent is usually larger, a larger weight can be set for the degree of shape difference, and a smaller weight can be set for the degree of size difference.
上述形状差异程度可以设定为两种取值,当边缘像素点所形成的图形与预设图形之间的形状不一致时,形状差异程度可以设定为第一形状差值;当边缘像素点所形成的图形与预设图形之间的形状一致时,形状差异程度可以设定为第二形状差值。其中,第一形状差值大于第二形状差值。一种典型的取值情况可以为第一形状差值为一个正数,第二形状差值可以为0。The above-mentioned shape difference degree can be set to two values. When the shapes formed by the edge pixels are inconsistent with the preset shapes, the shape difference degree can be set as the first shape difference value; When the shapes of the formed graphics and the preset graphics are consistent, the degree of shape difference may be set as the second shape difference value. Wherein, the first shape difference is greater than the second shape difference. A typical value situation may be that the first shape difference is a positive number, and the second shape difference may be 0.
上述尺寸差值程度可以用边缘像素点所形成的图形与预设图形之间的 长度差、宽度差、面积差等表示。The above-mentioned size difference degree can be represented by the length difference, width difference, area difference, etc. between the figure formed by the edge pixels and the preset figure.
S20233:确定第一定位图像的平均亮度。S20233: Determine the average brightness of the first positioning image.
其中,第一定位图像的平均亮度可以是第一定位图像中各个像素点的亮度值的平均值。Wherein, the average brightness of the first positioning image may be an average value of brightness values of each pixel in the first positioning image.
S20234:确定第一定位图像中与平均亮度之间的亮度差值大于预设亮度差阈值的目标像素点。S20234: Determine a target pixel whose brightness difference from the average brightness in the first positioning image is greater than a preset brightness difference threshold.
其中,亮度差值是像素点的亮度值与平均亮度之间的差值的绝对值,目标像素点是第一定位图像中亮度差值大于预设亮度差阈值的像素点,即第一定位图像中亮度过大或过小的像素点。可以理解的是,当位置连续的多个像素点均为目标像素点,则该位置连续的多个像素点形成过亮区域或过暗区域,过亮区域为反光区域,过暗区域为遮挡区域。The brightness difference value is the absolute value of the difference between the brightness value of the pixel point and the average brightness, and the target pixel point is the pixel point in the first positioning image whose brightness difference value is greater than the preset brightness difference threshold, that is, the first positioning image Pixels that are too bright or too small. It can be understood that when multiple pixels with consecutive positions are target pixels, then multiple consecutive pixels in the position form an over-bright area or an over-dark area, an over-bright area is a reflective area, and an over-dark area is an occluded area. .
S20235:根据目标像素点确定第一定位图像的失真程度参数。S20235: Determine the distortion degree parameter of the first positioning image according to the target pixel point.
可以理解的是,S20235确定的失真程度参数用于表示第一定位图像在亮度上的失真程度。It can be understood that the distortion degree parameter determined in S20235 is used to represent the distortion degree of the first positioning image in terms of brightness.
在一种方式中,可以将目标像素点的数目作为失真程度参数;在另一种方式中,可以将目标像素点的数目与第一定位图像中像素点的总数目之间的比值作为失真程度参数。In one way, the number of target pixels can be used as the distortion degree parameter; in another way, the ratio between the number of target pixels and the total number of pixels in the first positioning image can be used as the distortion degree parameter.
当然,还可以对上述两种方式确定的失真程度参数分别进行转换之后得到失真程度参数,但需要保持如下关系:若目标像素点的数目越多,则失真程度参数越大;或,若上述比值越大,则失真程度参数越大。Of course, the distortion degree parameters determined by the above two methods can also be converted to obtain the distortion degree parameters, but the following relationship needs to be maintained: if the number of target pixels is larger, the distortion degree parameter is larger; or, if the above ratio The larger the value, the larger the distortion level parameter.
S2024:若第一定位图像的失真程度参数大于预设失真程度阈值,判断第一定位图像无法被识别。S2024: If the distortion degree parameter of the first positioning image is greater than the preset distortion degree threshold, determine that the first positioning image cannot be identified.
S2025:当判断第一定位图像的失真程度参数小于或等于预设失真程度阈值时,判断第一定位图像能被识别。S2025: When it is determined that the distortion degree parameter of the first positioning image is less than or equal to the preset distortion degree threshold, determine that the first positioning image can be identified.
可以理解的是,失真程度参数大于预设失真程度阈值时,第一定位图像失真严重,第一定位图像无法被识别,在这种情况下无法通过识别第一定位图像确定仓储机器人的位置;当失真程度参数小于预设失真程度阈值时,第一定位图像失真可以忽略,第一定位图像可以被识别,在这种情况下可以通过识别第一定位图像确定仓储机器人的位置。It can be understood that when the distortion degree parameter is greater than the preset distortion degree threshold, the first positioning image is seriously distorted, and the first positioning image cannot be recognized. In this case, the position of the warehouse robot cannot be determined by recognizing the first positioning image; when When the distortion degree parameter is less than the preset distortion degree threshold, the distortion of the first positioning image can be ignored, and the first positioning image can be identified. In this case, the position of the warehouse robot can be determined by identifying the first positioning image.
本发明实施例可以通过失真程度参数确定第一定位图像是否可以识别,可以在第一定位图像失真的情况下避免对第一定位图像的识别,从而降低 了第一定位图像失真时的计算复杂度。In the embodiment of the present invention, whether the first positioning image can be recognized can be determined by the distortion degree parameter, and the recognition of the first positioning image can be avoided when the first positioning image is distorted, thereby reducing the computational complexity when the first positioning image is distorted .
S2022:当判断第一定位图像能被识别,根据第一定位图像确定仓储机器人的位置。S2022: When it is determined that the first positioning image can be recognized, determine the position of the warehouse robot according to the first positioning image.
可以理解的是,当第一定位图像无法识别时,无法准确的确定仓储机器人的位置。本发明实施例可以调整反射镜、窗口和图像采集装置之间的位置关系,并在调整之后重新执行S201和S2021或S201和S2022。当S201重新获取的第一定位图像可以识别时,进入S2022确定仓储机器人的位置;当S201重新获取的第一定位图像不可以识别时,进入S2021继续调整位置关系,如此循环,直至第一定位图像能被识别。It is understandable that when the first positioning image cannot be identified, the position of the warehouse robot cannot be accurately determined. In this embodiment of the present invention, the positional relationship between the mirror, the window, and the image acquisition device may be adjusted, and S201 and S2021 or S201 and S2022 may be re-executed after the adjustment. When the first positioning image re-acquired in S201 can be recognized, enter S2022 to determine the position of the warehouse robot; when the first positioning image re-acquired in S201 cannot be recognized, enter S2021 to continue to adjust the positional relationship, and so on until the first positioning image can be identified.
其中,根据第一定位图像确定仓储机器人的位置可以参照S202中确定位置的详细说明,在此不再赘述。Wherein, for determining the position of the warehouse robot according to the first positioning image, reference may be made to the detailed description of determining the position in S202, which will not be repeated here.
可选地,在本发明实施例的一种示例中,上述S201包括S2011:在调整反射镜、窗口和图像采集装置之间的位置关系的过程中,采集至少两个第一定位图像。Optionally, in an example of the embodiment of the present invention, the above S201 includes S2011: in the process of adjusting the positional relationship among the mirror, the window, and the image acquisition device, acquire at least two first positioning images.
在本发明实施例中,可以逐步调整反射镜、窗口和图像采集装置之间的位置关系。例如,以单位角度为步长,逐步增大或减小反射镜的倾斜角度,以达到调整反射镜、窗口和图像采集装置之间的位置关系的目的。又例如,可以以单位角度为步长,逐步增大或减少图像采集装置与底盘之间的角度,以达到调整反射镜、窗口和图像采集装置之间的位置关系的目的。又例如,可以以单位长度为步长,逐步增大或缩短图像采集装置与反射镜之间的距离,以达到调整反射镜、窗口和图像采集装置之间的位置关系的目的。In this embodiment of the present invention, the positional relationship among the mirror, the window, and the image acquisition device can be adjusted step by step. For example, the inclination angle of the mirror is gradually increased or decreased by taking the unit angle as the step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image acquisition device. For another example, the angle between the image acquisition device and the chassis can be gradually increased or decreased by taking the unit angle as a step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image acquisition device. For another example, the distance between the image capture device and the mirror can be gradually increased or shortened by taking the unit length as a step, so as to achieve the purpose of adjusting the positional relationship between the mirror, the window and the image capture device.
在上述调整过程中,可以采集至少两个第一定位图像。例如,在每次将反射镜的倾斜角度增大一个单位角度之后,均采集一个第一定位图像;又例如,在每次将图像采集装置与窗口之间的角度减少一个单位角度之后,均采集一个第一定位图像;再例如,在每次将图像采集装置与反射镜之间的距离缩短一个单位长度之后,均采集一个第一定位图像。During the above adjustment process, at least two first positioning images may be acquired. For example, after each time the inclination angle of the mirror is increased by one unit angle, a first positioning image is collected; for another example, after each time the angle between the image acquisition device and the window is decreased by one unit angle, the first positioning image is collected A first positioning image; for another example, after each time the distance between the image acquisition device and the mirror is shortened by a unit length, a first positioning image is collected.
可以理解的是,在实际应用中,可以将反射镜的倾斜角度、图像采集装置与窗口之间的角度、图像采集装置与反射镜之间的距离,三者中的至少两个一起调整,并在一次调整之后采集一个第一定位图像。It can be understood that, in practical applications, at least two of the tilt angle of the mirror, the angle between the image capture device and the window, and the distance between the image capture device and the mirror can be adjusted together, and A first positioning image is acquired after an adjustment.
本发明实施例通过上述调整过程可以采集至少两个第一定位图像,从 而可以通过至少两个第一定位图像确定仓储机器人的位置,有助于提高仓储机器人的位置的准确度和成功率。具体可以通过如下两种方式确定仓储机器人的位置。In this embodiment of the present invention, at least two first positioning images can be collected through the above adjustment process, so that the position of the storage robot can be determined through the at least two first positioning images, which helps to improve the accuracy and success rate of the position of the storage robot. Specifically, the location of the warehouse robot can be determined in the following two ways.
在第一种方式中,可以根据每个第一定位图像确定一个位置,从而可以得到至少两个位置。若至少两个位置均相同,则确定该位置为仓储机器人的位置;若至少两个位置不同,则可以获取数量最多的相同位置作为仓储机器人的位置。如此,提高了仓储机器人位置的准确度。In the first manner, one position can be determined according to each first positioning image, so that at least two positions can be obtained. If at least two positions are the same, the position is determined as the position of the storage robot; if at least two positions are different, the same position with the largest number can be obtained as the position of the storage robot. In this way, the accuracy of the position of the warehouse robot is improved.
在第二种方式中,若其中部分第一定位图像的失真程度参数大于预设失真程度阈值,导致这部分第一定位图像无法被识别,进而无法根据这部分第一定位图像确定位置,则可以根据其余第一定位图像确定位置。如此提高了确定仓储机器人位置的成功率。In the second method, if the distortion degree parameter of some of the first positioning images is greater than the preset distortion degree threshold, so that the part of the first positioning images cannot be recognized, and thus the position cannot be determined according to the first positioning images, the The position is determined according to the remaining first positioning images. This increases the success rate of determining the location of the warehouse robot.
可选地,在本发明实施例的一种示例中,上述方法还包括:Optionally, in an example of the embodiment of the present invention, the above method further includes:
当通过S202确定位置失败,调整反射镜、窗口和图像采集装置之间的位置关系,并重新执行S201,以根据调整之后采集的第一定位图像确定仓储机器人的位置。如此,可以有效提高确定仓储机器人的位置的成功率。When determining the position through S202 fails, adjust the positional relationship between the mirror, the window and the image acquisition device, and perform S201 again to determine the position of the warehouse robot according to the first positioning image collected after adjustment. In this way, the success rate of determining the position of the warehouse robot can be effectively improved.
上述S2011至S1025均为通过第一定位图像确定位置的过程,下面通过S2026至S2027介绍通过第二定位图像确定位置的过程。第二定位图像是第一定位图像的镜像图像。The above-mentioned S2011 to S1025 are all processes of determining the position through the first positioning image, and the following describes the process of determining the position through the second positioning image through S2026 to S2027. The second positioning image is a mirror image of the first positioning image.
S2026:获取第二定位图像,第二定位图像为第一定位图像对应的镜像图像。S2026: Acquire a second positioning image, where the second positioning image is a mirror image corresponding to the first positioning image.
可以理解的是,反射镜中的图像是地面上的定位图像的镜像图像,而图像采集装置采集的第一定位图像与反射镜中的图像是相同的,从而第一定位图像为地面上的定位图像的镜像图像。基于此,为了提高确定位置的准确度和成功率,可以将第一定位图像的镜像图像作为第二定位图像,第二定位图像与地面上的定位图像相同。It can be understood that the image in the mirror is a mirror image of the positioning image on the ground, and the first positioning image collected by the image acquisition device is the same as the image in the mirror, so the first positioning image is the positioning on the ground. Mirror image of the image. Based on this, in order to improve the accuracy and success rate of determining the position, the mirror image of the first positioning image can be used as the second positioning image, and the second positioning image is the same as the positioning image on the ground.
在获取第二定位图像时,可以将第一定位图像中的像素点P(x,y)通过上下镜像得到第二图像中的像素点P(X-x,y),或经过左右镜像得到第二图像中的像素点P(x,Y-y)。其中,x、y分别为像素点所在的行和列,X为第一定位图像的总行数,Y为第一定位图像的总列数。P(X-x,y)与P(x,y)的像素点取值相同但位置不同,P(x,Y-y)与P(x,y)的像素点取值相同但位置不同。When acquiring the second positioning image, the pixel point P(x,y) in the first positioning image can be mirrored up and down to obtain the pixel point P(X-x,y) in the second image, or the second image can be obtained by mirroring left and right The pixel point P(x, Y-y) in . Wherein, x and y are the row and column where the pixel point is located, X is the total number of rows of the first positioning image, and Y is the total number of columns of the first positioning image. The pixels of P(X-x,y) and P(x,y) have the same value but different positions, and the pixels of P(x,Y-y) and P(x,y) have the same value but different positions.
S2027:根据第二定位图像确定仓储机器人的位置。S2027: Determine the position of the warehouse robot according to the second positioning image.
其中,仓储机器人的位置可以根据第二定位图像的内容确定,不同位置的定位图像的内容不同。The position of the warehouse robot may be determined according to the content of the second positioning image, and the content of the positioning image at different positions is different.
在第一种示例中,第二定位图像中可以包括位置信息,从而可以从第二定位图像中解析得到位置信息。例如,第二定位图像可以为包括位置信息的二维码,从而可以将二维码进行解析得到位置信息。In the first example, the second positioning image may include position information, so that the position information may be obtained by parsing the second positioning image. For example, the second positioning image may be a two-dimensional code including location information, so that the two-dimensional code may be parsed to obtain the location information.
在第二种示例中,第二定位图像不包括位置信息,从而可以将第二定位图像与数据库中预设的图像数据进行匹配,若匹配成功,则将匹配到的第二定位图像在数据库中对应的位置作为仓储机器人的位置。In the second example, the second positioning image does not include position information, so that the second positioning image can be matched with the image data preset in the database. If the matching is successful, the matched second positioning image will be stored in the database. The corresponding position is used as the position of the warehouse robot.
其中,数据库中存储有若干图像数据以及对应的位置信息,当匹配成功时,将数据库中该图像数据对应的位置信息为第二定位图像在数据库中对应的位置。The database stores several image data and corresponding position information. When the matching is successful, the position information corresponding to the image data in the database is used as the position corresponding to the second positioning image in the database.
在实际应用中,还可以第一定位图像和第二定位图像确定仓储机器人的位置。例如,将第一定位图像、第二图像数据均与数据库中的图像数据进行匹配,若其中一个匹配成功,则将匹配到的数据库中的位置信息作为仓储机器人的位置;若两个均匹配成功并且匹配到的数据库中的位置信息一致,则将该位置信息作为仓储机器人的位置。In practical applications, the position of the warehouse robot can also be determined by the first positioning image and the second positioning image. For example, both the first positioning image and the second image data are matched with the image data in the database. If one of them is successfully matched, the position information in the matched database is used as the position of the warehouse robot; if both are matched successfully And if the location information in the matched database is consistent, the location information is used as the location of the warehouse robot.
在本发明实施例中,可以通过调整反射镜、窗口和图像采集装置之间的位置关系,以重新获取第一定位图像或获取多个第一定位图像,以根据重新获取的第一定位图像对应的第二定位图像确定仓储机器人的位置,或根据多个第一定位图像分别对应的第二定位图像确定仓储机器人的位置,有助于提高定位准确度和成功率。In this embodiment of the present invention, the positional relationship between the mirror, the window, and the image acquisition device can be adjusted to re-acquire the first positioning image or acquire multiple first positioning images, so as to correspond to the first positioning images obtained again The position of the storage robot is determined by the second positioning image, or the position of the storage robot is determined according to the second positioning images respectively corresponding to the plurality of first positioning images, which helps to improve the positioning accuracy and success rate.
在本发明实施例的一种示例中,上述S2027包括S20271至S20272:In an example of the embodiment of the present invention, the foregoing S2027 includes S20271 to S20272:
S20271:当判断第二定位图像无法识别,则调整反射镜、窗口和图像采集装置之间的位置关系,并根据调整之后采集的第一定位图像对应的第二定位图像确定仓储机器人的位置。S20271: When it is determined that the second positioning image cannot be identified, adjust the positional relationship between the mirror, the window and the image acquisition device, and determine the position of the warehouse robot according to the second positioning image corresponding to the first positioning image collected after adjustment.
其中,第二定位图像无法识别可以是第二定位图像失真引起的,第二定位图像的失真是第一定位图像的失真引起的,与第一定位图像的失真对应,第二定位图像失真包括:第二定位图像部分区域缺失、第二定位图像变形、第二定位图像部分区域被遮挡或反光。Wherein, the inability to identify the second positioning image may be caused by the distortion of the second positioning image, the distortion of the second positioning image is caused by the distortion of the first positioning image, and corresponding to the distortion of the first positioning image, the distortion of the second positioning image includes: The partial area of the second positioning image is missing, the second positioning image is deformed, and the partial area of the second positioning image is blocked or reflected.
第二定位图像是否可以识别可以通过两种方式确定,第一种方式,识别第二定位图像,根据识别结果确定第二定位图像是否可以识别;第二种 方式,根据第二定位图像的失真程度参数确定第二定位图像是否可以识别,具体可以参照S20273至S20275:Whether the second positioning image can be identified can be determined in two ways. The first way is to identify the second positioning image and determine whether the second positioning image can be identified according to the recognition result; the second way is to determine whether the second positioning image can be identified according to the degree of distortion of the second positioning image The parameter determines whether the second positioning image can be recognized. For details, please refer to S20273 to S20275:
S20273:确定第二定位图像的失真程度参数。S20273: Determine a distortion degree parameter of the second positioning image.
其中,失真程度参数用于表示第二定位图像与标准定位图像之间的差异程度。可以理解的是,失真程度参数越大,代表差异程度越大;失真程度参数越小,代表差异程度越小。The distortion degree parameter is used to indicate the degree of difference between the second positioning image and the standard positioning image. It can be understood that the larger the distortion degree parameter is, the larger the difference degree is; the smaller the distortion degree parameter is, the smaller the difference degree is.
在实际应用中,标准定位图像对应预设图形,预设图形的形状、尺寸可以设定,若第二定位图像的形状、尺寸与标准定位图像之间的形状、尺寸不一致,则代表第二定位图像失真,失真程度参数可以根据形状、尺寸之间的差异程度确定;当第二定位图像的形状、尺寸与标准定位图像之间的形状、尺寸均一致,则代表第二定位图像未失真。In practical applications, the standard positioning image corresponds to the preset graphics, and the shape and size of the preset graphics can be set. If the shape and size of the second positioning image are inconsistent with those of the standard positioning image, it represents the second positioning image If the image is distorted, the distortion degree parameter can be determined according to the degree of difference between the shape and size; when the shape and size of the second positioning image are consistent with the shape and size of the standard positioning image, it means that the second positioning image is not distorted.
可选地,可以根据如下S202731至S202732或S202733至S202735确定第二定位图像的失真程度参数,其中,S202731和S202732可以用于确定第二定位图像是否变形或缺失边缘部分,S202733至S202735可以用于确定第二定位图像是否存在反光或遮挡。在实际应用中,可以仅执行S202731和S202732,也可以仅执行S202733至S202735,还可以将S202731和S202732确定的失真程度参数与S202733至S202735确定的失真程度参数进行综合得到第二定位图像的失真程度参数。可以理解的是,当S202731和S202732确定的失真程度参数与S202733至S202735确定的失真程度参数均不为0时,确定第二定位图像不仅确实边缘部分还存在反光或遮挡,第二定位图像的失真较严重。Optionally, the distortion degree parameter of the second positioning image can be determined according to the following S202731 to S202732 or S202733 to S202735, wherein S202731 and S202732 can be used to determine whether the second positioning image is deformed or lacks an edge part, and S202733 to S202735 can be used to It is determined whether there is reflection or occlusion in the second positioning image. In practical applications, only S202731 and S202732 can be executed, or only S202733 to S202735 can be executed, and the distortion degree parameters determined by S202731 and S202732 and the distortion degree parameters determined by S202733 to S202735 can be synthesized to obtain the distortion degree of the second positioning image. parameter. It can be understood that when the distortion degree parameters determined by S202731 and S202732 and the distortion degree parameters determined by S202733 to S202735 are not 0, it is determined that the second positioning image not only has reflections or occlusions at the edges, and the second positioning image is distorted. more serious.
S202731:确定第二定位图像的边缘像素点。S202731: Determine the edge pixels of the second positioning image.
其中,边缘像素点为位于第二定位图像的边缘位置的像素点。在确定边缘像素点时,可以针对第二定位图像中的任意像素点(后续称为候选像素点),确定是否存在位于该候选像素点左方、右方、下方、上方的像素点。若不存在位于该候选像素点左方的像素点,则确定该候选像素点为该第二定位图像在左边的边缘像素点;若不存在位于该候选像素点右方的像素点,则确定该候选像素点为该第二定位图像在右边的边缘像素点;若不存在位于该候选像素点上方的像素点,则确定该候选像素点为该第二定位图像在上边的边缘像素点;若不存在位于该候选像素点下方的像素点,则确定该候选像素点为该第二定位图像在下边的边缘像素点。The edge pixels are pixels located at the edge of the second positioning image. When determining an edge pixel, for any pixel in the second positioning image (hereinafter referred to as a candidate pixel), it can be determined whether there is a pixel located to the left, right, below, or above the candidate pixel. If there is no pixel point located to the left of the candidate pixel point, the candidate pixel point is determined to be the edge pixel point on the left side of the second positioning image; if there is no pixel point located to the right of the candidate pixel point, then the candidate pixel point is determined The candidate pixel point is the edge pixel point on the right side of the second positioning image; if there is no pixel point located above the candidate pixel point, the candidate pixel point is determined as the edge pixel point on the upper side of the second positioning image point; if not If there is a pixel point located below the candidate pixel point, the candidate pixel point is determined to be the lower edge pixel point of the second positioning image.
可以理解的是,一个候选像素点可以是在上边、左边、下边、右边其中至少两个边的边缘像素点。It can be understood that a candidate pixel point may be an edge pixel point on at least two sides of the upper side, the left side, the lower side, and the right side.
S202732:确定边缘像素点所形成的图形与第二定位图像的预设图形之间的差异程度,确定第二定位图像的失真程度参数。S202732: Determine the degree of difference between the graphics formed by the edge pixels and the preset graphics of the second positioning image, and determine the distortion degree parameter of the second positioning image.
其中,失真程度参数可以包括:边缘像素点所形成的图形与预设图形之间的形状差异程度、边缘像素点所形成的图形与预设图形之间的尺寸差异程度。可选地,可以将形状差异程度和尺寸差异程度进行加权作为第二定位图像的失真程度参数。由于形状不一致时的失真通常较大,从而可以对形状差异程度设置较大的权重,对尺寸差异程度设置较小的权重。The distortion degree parameter may include: the degree of shape difference between the figure formed by the edge pixels and the preset figure, and the degree of size difference between the figure formed by the edge pixels and the preset figure. Optionally, the shape difference degree and the size difference degree may be weighted as a distortion degree parameter of the second positioning image. Since the distortion when the shapes are inconsistent is usually larger, a larger weight can be set for the degree of shape difference, and a smaller weight can be set for the degree of size difference.
上述形状差异程度可以设定为两种取值,当边缘像素点所形成的图形与预设图形之间的形状不一致时,形状差异程度可以设定为第一形状差值;当边缘像素点所形成的图形与预设图形之间的形状一致时,形状差异程度可以设定为第二形状差值。其中,第一形状差值大于第二形状差值。一种典型的取值情况可以为第一形状差值为一个正数,第二形状差值可以为0。The above-mentioned shape difference degree can be set to two values. When the shapes formed by the edge pixels are inconsistent with the preset shapes, the shape difference degree can be set as the first shape difference value; When the shapes of the formed graphics and the preset graphics are consistent, the degree of shape difference may be set as the second shape difference value. Wherein, the first shape difference is greater than the second shape difference. A typical value situation may be that the first shape difference is a positive number, and the second shape difference may be 0.
上述尺寸差值程度可以用边缘像素点所形成的图形与预设图形之间的长度差、宽度差、面积差等表示。The above-mentioned size difference degree can be represented by the length difference, width difference, area difference, etc. between the figure formed by the edge pixel points and the preset figure.
S202733:确定所第二定位图像的平均亮度。S202733: Determine the average brightness of the second positioned image.
其中,第二定位图像的平均亮度可以是第二定位图像中各个像素点的亮度值的平均值。Wherein, the average brightness of the second positioning image may be an average value of brightness values of each pixel in the second positioning image.
S202734:确定第二定位图像中与平均亮度之间的亮度差值大于预设亮度差阈值的目标像素点。S202734: Determine a target pixel whose brightness difference from the average brightness in the second positioning image is greater than a preset brightness difference threshold.
其中,亮度差值是像素点的亮度值与平均亮度之间的差值的绝对值,目标像素点是第二定位图像中亮度差值大于预设亮度差阈值的像素点,即第二定位图像中亮度过大或过小的像素点。可以理解的是,当位置连续的多个像素点均为目标像素点,则该位置连续的多个像素点形成过亮区域或过暗区域,过亮区域为反光区域,过暗区域为遮挡区域。The brightness difference value is the absolute value of the difference between the brightness value of the pixel point and the average brightness, and the target pixel point is the pixel point in the second positioning image whose brightness difference value is greater than the preset brightness difference threshold, that is, the second positioning image. Pixels that are too bright or too small. It can be understood that when multiple pixels with consecutive positions are target pixels, then multiple consecutive pixels in the position form an over-bright area or an over-dark area, an over-bright area is a reflective area, and an over-dark area is an occluded area. .
S202735:根据目标像素点确定第二定位图像的失真程度参数。S202735: Determine the distortion degree parameter of the second positioning image according to the target pixel point.
可以理解的是,S202735确定的失真程度参数用于表示第二定位图像在亮度上的失真程度。It can be understood that the distortion degree parameter determined in S202735 is used to represent the distortion degree of the second positioning image in terms of brightness.
在一种方式中,可以将目标像素点的数目作为失真程度参数;在另一种方式中,可以将目标像素点的数目与第二定位图像中像素点的总数目之 间的比值作为失真程度参数。In one way, the number of target pixels can be used as the distortion degree parameter; in another way, the ratio between the number of target pixels and the total number of pixels in the second positioning image can be used as the distortion degree parameter.
当然,还可以对上述两种方式确定的失真程度参数分别进行转换之后得到失真程度参数,但需要保持如下关系:若目标像素点的数目越多,则失真程度参数越大;或,若上述比值越大,则失真程度参数越大。Of course, the distortion degree parameters determined by the above two methods can also be converted to obtain the distortion degree parameters, but the following relationship needs to be maintained: if the number of target pixels is larger, the distortion degree parameter is larger; or, if the above ratio The larger the value, the larger the distortion level parameter.
S20274:若第二定位图像的失真程度参数大于预设失真程度阈值,判断第二定位图像无法被识别。S20274: If the distortion degree parameter of the second positioning image is greater than the preset distortion degree threshold, determine that the second positioning image cannot be identified.
S20275:当判断第二定位图像的失真程度参数小于或等于预设失真程度阈值,判断第二定位图像能被识别。S20275: When it is determined that the distortion degree parameter of the second positioning image is less than or equal to the preset distortion degree threshold, determine that the second positioning image can be identified.
可以理解的是,失真程度参数大于预设失真程度阈值时,第二定位图像失真严重,第二定位图像无法被识别,在这种情况下无法通过识别第二定位图像确定仓储机器人的位置;当失真程度参数小于预设失真程度阈值时,第二定位图像失真可以忽略,第二定位图像可以被识别,在这种情况下可以通过识别第二定位图像确定仓储机器人的位置。It can be understood that when the distortion degree parameter is greater than the preset distortion degree threshold, the second positioning image is seriously distorted, and the second positioning image cannot be recognized. In this case, the position of the warehouse robot cannot be determined by recognizing the second positioning image; when When the distortion degree parameter is less than the preset distortion degree threshold, the distortion of the second positioning image can be ignored, and the second positioning image can be identified. In this case, the position of the warehouse robot can be determined by identifying the second positioning image.
本发明实施例可以通过失真程度参数确定第二定位图像是否可以识别,可以在第二定位图像失真的情况下避免对第二定位图像的识别,从而降低了第二定位图像失真时的计算复杂度。In the embodiment of the present invention, whether the second positioning image can be recognized can be determined through the distortion degree parameter, and the recognition of the second positioning image can be avoided when the second positioning image is distorted, thereby reducing the computational complexity when the second positioning image is distorted .
S20272:当判断第二定位图像能被识别,根据第二定位图像确定仓储机器人的位置。S20272: When it is determined that the second positioning image can be recognized, determine the position of the warehouse robot according to the second positioning image.
可以理解的是,当第二定位图像无法识别时,无法准确的确定仓储机器人的位置。本发明实施例可以调整反射镜、窗口和图像采集装置之间的位置关系,并在调整之后重新执行S201、S2026、S20271或S201、S2026、S20272。当S201重新获取的第一定位图像对应的第二定位图像可以识别时,进入S20272确定仓储机器人的位置;当S201重新获取的第一定位图像对应的第二定位图像不可以识别时,进入S20271继续调整位置关系,如此循环,直至第二定位图像能被识别。It can be understood that when the second positioning image cannot be identified, the position of the warehouse robot cannot be accurately determined. In this embodiment of the present invention, the positional relationship between the mirror, the window, and the image acquisition device can be adjusted, and S201, S2026, and S20271 or S201, S2026, and S20272 can be re-executed after the adjustment. When the second positioning image corresponding to the first positioning image re-acquired in S201 can be identified, go to S20272 to determine the position of the warehouse robot; when the second positioning image corresponding to the first positioning image re-acquired in S201 cannot be identified, go to S20271 to continue The positional relationship is adjusted, and this cycle is repeated until the second positioning image can be identified.
其中,根据第二定位图像确定仓储机器人的位置可以参照S2027中确定位置的详细说明,在此不再赘述。Wherein, to determine the position of the warehouse robot according to the second positioning image, reference may be made to the detailed description of determining the position in S2027, which will not be repeated here.
可选地,在本发明实施例的一种示例中,基于上述S2011,上述S2026包括S20261:Optionally, in an example of the embodiment of the present invention, based on the foregoing S2011, the foregoing S2026 includes S20261:
S20261:获取至少两个第一定位图像分别对应的至少两个第二定位图像。S20261: Acquire at least two second positioning images corresponding to at least two first positioning images respectively.
可以理解的是,在S2011中,通过调整反射镜、窗口和图像采集装置之间的位置关系的过程中,采集了至少两个第一定位图像,从而基于每个第一定位图像可以获取到一个对应的第二定位图像,即得到至少两个第二定位图像。It can be understood that, in S2011, in the process of adjusting the positional relationship between the mirror, the window and the image acquisition device, at least two first positioning images are collected, so that one can be obtained based on each first positioning image. The corresponding second positioning images, that is, at least two second positioning images are obtained.
本发明实施例通过至少两个第二定位图像确定仓储机器人的位置,有助于提高仓储机器人的位置的准确度和成功率。具体可以通过如下两种方式确定仓储机器人的位置。The embodiment of the present invention determines the position of the storage robot by using at least two second positioning images, which helps to improve the accuracy and success rate of the position of the storage robot. Specifically, the location of the warehouse robot can be determined in the following two ways.
在第一种方式中,可以根据每个第二定位图像确定一个位置,从而可以得到至少两个位置。若至少两个位置均相同,则确定该位置为仓储机器人的位置;若至少两个位置不同,则可以获取数量最多的相同位置作为仓储机器人的位置。如此,提高了仓储机器人的准确度。In the first manner, one position may be determined according to each second positioning image, so that at least two positions may be obtained. If at least two positions are the same, the position is determined as the position of the storage robot; if at least two positions are different, the same position with the largest number can be obtained as the position of the storage robot. In this way, the accuracy of the warehouse robot is improved.
在第二种方式中,若其中部分第二定位图像的失真程度参数大于预设失真程度阈值,导致这部分第二定位图像无法被识别,进而无法根据这部分第二定位图像确定位置,则可以根据其余第二定位图像确定位置。如此提高了确定仓储机器人的成功率。In the second method, if the distortion degree parameter of some of the second positioning images is greater than the preset distortion degree threshold, so that the part of the second positioning images cannot be recognized, and thus the position cannot be determined according to the second positioning images, the The position is determined from the remaining second positioning images. This increases the success rate of identifying warehouse robots.
可选地,在本发明实施例的一种示例中,上述方法还包括:Optionally, in an example of the embodiment of the present invention, the above method further includes:
当判断第二定位图像确定位置失败,调整反射镜、窗口和图像采集装置之间的位置关系,并重新执行S201和S2026,以根据调整之后获取的第二定位图像确定仓储机器人的位置。如此,可以有效提高确定仓储机器人的位置的成功率。When judging that the second positioning image fails to determine the position, adjust the positional relationship between the mirror, the window and the image acquisition device, and re-execute S201 and S2026 to determine the position of the warehouse robot according to the second positioning image obtained after adjustment. In this way, the success rate of determining the position of the warehouse robot can be effectively improved.
本发明实施例还提供了一种仓储机器人,包括底盘和摄像组件,所述摄像组件位于所述底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述摄像组件的反射镜设置在所述窗口的一侧并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准;所述图像采集装置用于采集反射镜中的第一定位图像;根据第一定位图像确定仓储机器人的位置。An embodiment of the present invention also provides a storage robot, including a chassis and a camera assembly, the camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the image is positioned, and a reflector of the camera assembly is arranged on one side of the window and is inclined towards the direction of the window, and the reflective surface of the reflector faces the window, the image acquisition device is located on the reflected light path of the reflector, and the image acquisition device The lens of the device is aligned with the reflective surface; the image acquisition device is used for collecting the first positioning image in the reflecting mirror; and the position of the storage robot is determined according to the first positioning image.
本发明实施例还提供了另一种仓储机器人,包括底盘、摄像组件和处理器,所述摄像组件位于所述底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述摄像组件的反射镜设置在所述窗口的一侧并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装 置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准;所述处理器固定于所述底盘上,所述处理器用于:An embodiment of the present invention further provides another storage robot, including a chassis, a camera assembly and a processor, the camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the positioning image is located, and the camera The reflector of the assembly is arranged on one side of the window and is inclined toward the direction of the window, and the reflective surface of the reflector faces the window, the image acquisition device is located on the reflected light path of the reflector, and The lens of the image acquisition device is aligned with the reflective surface; the processor is fixed on the chassis, and the processor is used for:
获取所述图像采集装置采集的所述反射镜中的第一定位图像;acquiring a first positioning image in the mirror captured by the image capturing device;
根据所述第一定位图像确定所述仓储机器人的位置。The position of the warehouse robot is determined according to the first positioning image.
基于上述两种仓储机器人,上述图像采集装置和上述处理器可以执行前述定位方法中的步骤,在此不再赘述。Based on the above-mentioned two storage robots, the above-mentioned image acquisition device and the above-mentioned processor can perform the steps in the above-mentioned positioning method, which will not be repeated here.
最后应说明的是:以上各实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述各实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. scope.
Claims (36)
- 一种摄像组件,用于仓储机器人的导航与定位,其特征在于,所述摄像组件包括反射镜和图像采集装置;A camera assembly for navigation and positioning of a warehouse robot, characterized in that the camera assembly includes a reflector and an image acquisition device;所述反射镜位于所述仓储机器人的底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述反射镜设置在所述窗口的侧边并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准。The reflector is located on the inner surface of the chassis of the warehouse robot, the chassis has a window facing the surface where the image is positioned, the reflector is arranged on the side of the window and is inclined toward the direction of the window, and The reflecting surface of the reflecting mirror faces the window, the image capturing device is located on the reflected light path of the reflecting mirror, and the lens of the image capturing device is aligned with the reflecting surface.
- 根据权利要求1所述的摄像组件,其特征在于,所述反射镜的反射面在所述底盘上的投影至少完全覆盖所述窗口。The camera assembly according to claim 1, wherein the projection of the reflection surface of the reflector on the chassis at least completely covers the window.
- 根据权利要求1所述的摄像组件,其特征在于,所述图像采集装置设置在所述窗口的侧边。The camera assembly according to claim 1, wherein the image acquisition device is disposed on the side of the window.
- 根据权利要求1所述的摄像组件,其特征在于,所述摄像组件还包括至少一个遮光件;The camera assembly according to claim 1, wherein the camera assembly further comprises at least one shading member;所述反射镜包括绕轴线设置的第一边缘、第二边缘、第三边缘和第四边缘,所述第一边缘位于所述底盘上,所述遮光件的一端至少设置在所述第二边缘、第三边缘及第四边缘中的任意一个上,且所述遮光件的另一端往所述图像采集装置的方向延伸。The reflector includes a first edge, a second edge, a third edge and a fourth edge arranged around the axis, the first edge is located on the chassis, and one end of the light shielding member is at least arranged on the second edge , any one of the third edge and the fourth edge, and the other end of the light shielding member extends toward the direction of the image capturing device.
- 根据权利要求4所述的摄像组件,其特征在于,所述遮光件的数量至少为三个;The camera assembly according to claim 4, wherein the number of the light shielding members is at least three;至少三个所述遮光件分别对应设置在所述第二边缘、所述第三边缘及所述第四边缘上。At least three of the light shielding elements are respectively disposed on the second edge, the third edge and the fourth edge, respectively.
- 根据权利要求5所述的摄像组件,其特征在于,所述第二边缘、所述第三边缘和所述第四边缘往所述图像采集装置的方向延伸有遮光边,所述遮光边与所述反射镜为一体成型的一体件;The camera assembly according to claim 5, wherein the second edge, the third edge and the fourth edge have a light-shielding edge extending toward the image capturing device, and the light-shielding edge and the The reflecting mirror is an integral piece formed in one piece;所述遮光边被配置为所述遮光件。The light-shielding edge is configured as the light-shielding member.
- 根据权利要求1所述的摄像组件,其特征在于,所述图像采集装置滑动设置在所述底盘上,以调节所述图像采集装置与所述反射面之间的距离。The camera assembly according to claim 1, wherein the image capturing device is slidably arranged on the chassis to adjust the distance between the image capturing device and the reflective surface.
- 根据权利要求1所述的摄像组件,其特征在于,所述摄像组件还包 括支架;The camera assembly according to claim 1, wherein the camera assembly further comprises a bracket;所述图像采集装置通过所述支架设置在所述底盘上,所述图像采集装置转动连接在所述支架上,且所述图像采集装置的镜头能够往靠近或者远离所述底盘内表面的方向转动,以调整所述图像采集装置的镜头与所述反射面的对准角度。The image capture device is disposed on the chassis through the bracket, the image capture device is rotatably connected to the bracket, and the lens of the image capture device can be rotated toward or away from the inner surface of the chassis , to adjust the alignment angle between the lens of the image acquisition device and the reflective surface.
- 根据权利要求1所述的摄像组件,其特征在于,所述反射镜转动连接在所述底盘上,且所述反射镜远离所述底盘的一端能够往靠近或者远离所述底盘内表面的方向转动,以调节所述反射镜与所述底盘之间的夹角。The camera assembly according to claim 1, wherein the reflector is rotatably connected to the chassis, and the end of the reflector away from the chassis can be rotated toward or away from the inner surface of the chassis , to adjust the angle between the reflector and the chassis.
- 根据权利要求7-9任一项所述的摄像组件,其特征在于,所述摄像组件还包括控制单元和驱动单元;The camera assembly according to any one of claims 7-9, wherein the camera assembly further comprises a control unit and a drive unit;所述驱动单元与所述图像采集装置连接,以驱动所述图像采集装置的移动或者转动;和/或,所述驱动单元与所述反射镜连接,以驱动所述反射镜转动;The driving unit is connected with the image capturing device to drive the movement or rotation of the image capturing device; and/or the driving unit is connected with the reflecting mirror to drive the reflecting mirror to rotate;所述控制单元与所述驱动单元信号连接,以信号控制所述驱动单元工作。The control unit is signal-connected with the driving unit, and controls the driving unit to work with a signal.
- 根据权利要求1-9任一项所述的摄像组件,其特征在于,所述图像采集装置为潜望式相机。The camera assembly according to any one of claims 1-9, wherein the image acquisition device is a periscope camera.
- 根据权利要求1-9任一项所述的摄像组件,其特征在于,所述反射镜与所述底盘之间的夹角为30°-60°。The camera assembly according to any one of claims 1-9, wherein the angle between the reflector and the chassis is 30°-60°.
- 一种仓储机器人,其特征在于,包括底盘和至少一组如权利要求1-12任一项所述的摄像组件;A storage robot, characterized in that it comprises a chassis and at least one set of camera assemblies according to any one of claims 1-12;所述摄像组件位于所述底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述摄像组件的反射镜设置在所述窗口的一侧并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准。The camera assembly is located on the inner surface of the chassis, the chassis has a window facing the surface where the image is positioned, the mirror of the camera assembly is arranged on one side of the window and is inclined toward the direction of the window, and The reflecting surface of the reflecting mirror faces the window, the image capturing device is located on the reflected light path of the reflecting mirror, and the lens of the image capturing device is aligned with the reflecting surface.
- 根据权利要求13所述的仓储机器人,其特征在于,所述窗口的数量至少为两个,至少两个所述窗口间隔设置在所述底盘的活动方向上;The storage robot according to claim 13, wherein the number of the windows is at least two, and at least two of the windows are arranged at intervals in the moving direction of the chassis;所述摄像组件的数量至少为两个,至少两个所述摄像组件分别与至少两个所述窗口对应设置。The number of the camera assemblies is at least two, and the at least two camera assemblies are respectively arranged corresponding to the at least two windows.
- 根据权利要求13所述的仓储机器人,其特征在于,所述仓储机器人还包括透光保护件;The storage robot according to claim 13, wherein the storage robot further comprises a light-transmitting protective member;所述窗口被配置为开设在所述底盘上的透光口,所述透光保护件覆盖在所述透光口上。The window is configured as a light-transmitting opening opened on the chassis, and the light-transmitting protection member covers the light-transmitting opening.
- 一种定位方法,其特征在于,应用于仓储机器人,所述仓储机器人包括底盘和摄像组件,所述摄像组件位于所述底盘的内表面,所述底盘上具有朝向定位图像所在面的窗口,所述摄像组件的反射镜设置在所述窗口的一侧并往所述窗口的方向倾斜,且所述反射镜的反射面朝向所述窗口,所述图像采集装置位于所述反射镜的反射光路上,且所述图像采集装置的镜头与所述反射面对准;所述方法包括:A positioning method is characterized in that, it is applied to a storage robot, and the storage robot includes a chassis and a camera assembly, the camera assembly is located on the inner surface of the chassis, and the chassis has a window facing the surface where the positioning image is located, so the The mirror of the camera assembly is arranged on one side of the window and is inclined toward the direction of the window, and the reflective surface of the mirror faces the window, and the image acquisition device is located on the reflected light path of the mirror , and the lens of the image acquisition device is aligned with the reflective surface; the method includes:获取所述图像采集装置采集的所述反射镜中的第一定位图像;acquiring a first positioning image in the mirror captured by the image capturing device;根据所述第一定位图像确定所述仓储机器人的位置。The position of the warehouse robot is determined according to the first positioning image.
- 根据权利要求16所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to claim 16, wherein the determining the position of the warehouse robot according to the first positioning image comprises:当判断所述第一定位图像无法识别,则调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系,并根据调整之后采集的第一定位图像确定所述仓储机器人的位置。When it is judged that the first positioning image cannot be identified, the positional relationship between the mirror, the window and the image acquisition device is adjusted, and the position of the warehouse robot is determined according to the first positioning image collected after adjustment. .
- 根据权利要求17所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to claim 17, wherein the determining the position of the warehouse robot according to the first positioning image comprises:当判断所述第一定位图像能被识别,根据所述第一定位图像确定所述仓储机器人的位置。When it is determined that the first positioning image can be identified, the position of the warehouse robot is determined according to the first positioning image.
- 根据权利要求17所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to claim 17, wherein the determining the position of the warehouse robot according to the first positioning image comprises:确定所述第一定位图像的失真程度参数;determining the distortion degree parameter of the first positioning image;若所述第一定位图像的失真程度参数大于预设失真程度阈值,判断所述第一定位图像无法被识别。If the distortion degree parameter of the first positioning image is greater than a preset distortion degree threshold, it is determined that the first positioning image cannot be identified.
- 根据权利要求18所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to claim 18, wherein the determining the position of the warehouse robot according to the first positioning image comprises:确定所述第一定位图像的失真程度参数;determining the distortion degree parameter of the first positioning image;当判断所述第一定位图像的失真程度参数小于或等于预设失真程度阈 值时,判断所述第一定位图像能被识别。When it is determined that the distortion degree parameter of the first positioning image is less than or equal to a preset distortion degree threshold, it is determined that the first positioning image can be identified.
- 根据权利要求16所述的方法,其特征在于,所述获取所述图像采集装置采集的所述反射镜中的第一定位图像,包括:The method according to claim 16, wherein the acquiring the first positioning image in the mirror acquired by the image acquisition device comprises:在调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系的过程中,采集至少两个第一定位图像。During the process of adjusting the positional relationship between the mirror, the window and the image acquisition device, at least two first positioning images are acquired.
- 根据权利要求16所述的方法,其特征在于,所述方法还包括:The method of claim 16, wherein the method further comprises:当判断所述第一定位图像确定位置失败,调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系,并根据调整之后采集的第一定位图像确定所述仓储机器人的位置。When judging that the first positioning image fails to determine the position, adjust the positional relationship between the mirror, the window and the image acquisition device, and determine the position of the warehouse robot according to the first positioning image collected after adjustment .
- 根据权利要求16所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to claim 16, wherein the determining the position of the warehouse robot according to the first positioning image comprises:获取第二定位图像,所述第二定位图像为所述第一定位图像对应的镜像图像;acquiring a second positioning image, where the second positioning image is a mirror image corresponding to the first positioning image;根据所述第二定位图像确定所述仓储机器人的位置。The position of the warehouse robot is determined according to the second positioning image.
- 根据权利要求23所述的方法,其特征在于,所述根据所述第二定位图像确定所述仓储机器人的位置,包括:The method according to claim 23, wherein the determining the position of the warehouse robot according to the second positioning image comprises:当判断所述第二定位图像无法识别,则调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系,并根据调整之后采集的第一定位图像对应的第二定位图像确定所述仓储机器人的位置。When it is determined that the second positioning image cannot be identified, the positional relationship between the mirror, the window and the image acquisition device is adjusted, and the second positioning image corresponding to the first positioning image collected after the adjustment is determined. The location of the warehouse robot.
- 根据权利要求23所述的方法,其特征在于,所述根据所述第二定位图像确定所述仓储机器人的位置,包括:The method according to claim 23, wherein the determining the position of the warehouse robot according to the second positioning image comprises:当判断所述第二定位图像能被识别,根据所述第二定位图像确定所述仓储机器人的位置。When it is determined that the second positioning image can be identified, the position of the warehouse robot is determined according to the second positioning image.
- 根据权利要求24所述的方法,其特征在于,所述根据所述第二定位图像确定所述仓储机器人的位置,包括:The method according to claim 24, wherein the determining the position of the warehouse robot according to the second positioning image comprises:确定所述第二定位图像的失真程度参数;determining a distortion degree parameter of the second positioning image;若所述第二定位图像的失真程度参数大于预设失真程度阈值,判断所述第二定位图像无法被识别。If the distortion degree parameter of the second positioning image is greater than a preset distortion degree threshold, it is determined that the second positioning image cannot be identified.
- 根据权利要求25所述的方法,其特征在于,所述根据所述第二定位图像确定所述仓储机器人的位置,包括:The method according to claim 25, wherein the determining the position of the warehouse robot according to the second positioning image comprises:确定所述第二定位图像的失真程度参数;determining a distortion degree parameter of the second positioning image;当判断所述第二定位图像的失真程度参数小于或等于预设失真程度阈值,判断所述第二定位图像能被识别。When it is determined that the distortion degree parameter of the second positioning image is less than or equal to a preset distortion degree threshold, it is determined that the second positioning image can be identified.
- 根据权利要求23所述的方法,其特征在于,所述获取所述图像采集装置采集的所述反射镜中的第一定位图像,包括:The method according to claim 23, wherein the acquiring the first positioning image in the mirror acquired by the image acquisition device comprises:在调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系的过程中,采集至少两个所述第一定位图像;in the process of adjusting the positional relationship between the mirror, the window and the image acquisition device, acquiring at least two of the first positioning images;所述获取第二定位图像,包括:The acquiring the second positioning image includes:获取至少两个所述第一定位图像分别对应的至少两个第二定位图像。At least two second positioning images respectively corresponding to at least two of the first positioning images are acquired.
- 根据权利要求23所述的方法,其特征在于,所述方法还包括:The method of claim 23, wherein the method further comprises:当判断所述第二定位图像确定位置失败,调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系,并根据调整之后获取的第二定位图像确定所述仓储机器人的位置。When judging that the second positioning image fails to determine the position, adjust the positional relationship between the mirror, the window and the image acquisition device, and determine the position of the warehouse robot according to the second positioning image obtained after adjustment .
- 根据权利要求16至22任一项所述的方法,其特征在于,所述根据所述第一定位图像确定所述仓储机器人的位置,包括:The method according to any one of claims 16 to 22, wherein the determining the position of the warehouse robot according to the first positioning image comprises:将所述第一定位图像与数据库预设的图像数据进行匹配;matching the first positioning image with the image data preset in the database;若匹配成功,则将匹配到的所述第一定位图像在所述数据库中对应的位置作为所述仓储机器人的位置。If the matching is successful, the corresponding position of the matched first positioning image in the database is used as the position of the warehouse robot.
- 根据权利要求23至29任一项所述的方法,其特征在于,所述根据所述第二定位图像确定所述仓储机器人的位置,包括:The method according to any one of claims 23 to 29, wherein the determining the position of the warehouse robot according to the second positioning image comprises:将所述第一定位图像和/或所述第二定位图像与数据库预设的图像数据进行匹配;matching the first positioning image and/or the second positioning image with image data preset in the database;若匹配成功,则将匹配到的所述第一定位图像和/或所述第二定位图像在所述数据库中对应的位置作为所述仓储机器人的位置。If the matching is successful, the corresponding position of the matched first positioning image and/or the second positioning image in the database is used as the position of the warehouse robot.
- 根据权利要求19或20所述的方法,其特征在于,所述确定所述第一定位图像的失真程度参数,包括:The method according to claim 19 or 20, wherein the determining the distortion degree parameter of the first positioning image comprises:确定所述第一定位图像的边缘像素点;determining the edge pixels of the first positioning image;确定所述边缘像素点所形成的图形与所述第一定位图像的预设图形之间的差异程度,确定所述第一定位图像的失真程度参数。The degree of difference between the graphics formed by the edge pixels and the preset graphics of the first positioning image is determined, and the distortion degree parameter of the first positioning image is determined.
- 根据权利要求19或20所述的方法,其特征在于,所述确定所述第一定位图像的失真程度参数,包括:The method according to claim 19 or 20, wherein the determining the distortion degree parameter of the first positioning image comprises:确定所述第一定位图像的平均亮度;determining the average brightness of the first positioning image;确定所述第一定位图像中与所述平均亮度之间的亮度差值大于预设亮度差阈值的目标像素点;determining a target pixel whose brightness difference between the first positioning image and the average brightness is greater than a preset brightness difference threshold;根据所述目标像素点确定所述第一定位图像的失真程度参数。The distortion degree parameter of the first positioning image is determined according to the target pixel point.
- 根据权利要求26或27所述的方法,其特征在于,所述确定所述第二定位图像的失真程度参数,包括:The method according to claim 26 or 27, wherein the determining the distortion degree parameter of the second positioning image comprises:确定所述第二定位图像的边缘像素点;determining the edge pixels of the second positioning image;确定所述边缘像素点所形成的图形与所述第二定位图像的预设图形之间的差异程度,确定所述第二定位图像的失真程度参数。The degree of difference between the graphics formed by the edge pixels and the preset graphics of the second positioning image is determined, and the distortion degree parameter of the second positioning image is determined.
- 根据权利要求26或27所述的方法,其特征在于,所述确定所述第二定位图像的失真程度参数,包括:The method according to claim 26 or 27, wherein the determining the distortion degree parameter of the second positioning image comprises:确定所述第二定位图像的平均亮度;determining the average brightness of the second positioning image;确定所述第二定位图像中与所述平均亮度之间的亮度差值大于预设亮度差阈值的目标像素点;determining a target pixel whose brightness difference from the average brightness in the second positioning image is greater than a preset brightness difference threshold;根据所述目标像素点确定所述第二定位图像的失真程度参数。The distortion degree parameter of the second positioning image is determined according to the target pixel point.
- 根据权利要求17至22、24至29中任一项所述的方法,其特征在于,所述调整所述反射镜、所述窗口和所述图像采集装置之间的位置关系,包括:The method according to any one of claims 17 to 22 and 24 to 29, wherein the adjusting the positional relationship between the mirror, the window and the image acquisition device comprises:调整所述反射镜与所述窗口之间的倾斜角度;和/或,adjusting the angle of inclination between the mirror and the window; and/or,调整所述图像采集装置与所述窗口之间的倾斜角度;和/或,adjusting the angle of inclination between the image capture device and the window; and/or,调整所述图像采集装置与所述反射镜之间的距离。Adjust the distance between the image capture device and the mirror.
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011630689.8 | 2020-12-30 | ||
CN202011630689.8A CN112698539A (en) | 2020-12-30 | 2020-12-30 | Positioning method and warehousing robot |
CN202023341469.1U CN214191209U (en) | 2020-12-30 | 2020-12-30 | Storage robot and camera shooting assembly |
CN202023341469.1 | 2020-12-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022142808A1 true WO2022142808A1 (en) | 2022-07-07 |
Family
ID=82260178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/131015 WO2022142808A1 (en) | 2020-12-30 | 2021-11-16 | Storage robot, camera assembly and positioning method |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2022142808A1 (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204964854U (en) * | 2015-08-27 | 2016-01-13 | 丁雪勤 | High pixel module of making a video recording |
CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
CN206339868U (en) * | 2016-12-21 | 2017-07-18 | 深圳若步智能科技有限公司 | A kind of automatic guided vehicle vision positioning device |
CN107065853A (en) * | 2016-12-21 | 2017-08-18 | 深圳若步智能科技有限公司 | A kind of merchandising machine people system and its method of work |
CN110018688A (en) * | 2019-04-11 | 2019-07-16 | 清华大学深圳研究生院 | The automatic guide vehicle localization method of view-based access control model |
CN110850872A (en) * | 2019-10-31 | 2020-02-28 | 深圳市优必选科技股份有限公司 | Robot inspection method and device, computer readable storage medium and robot |
CN112698539A (en) * | 2020-12-30 | 2021-04-23 | 深圳市海柔创新科技有限公司 | Positioning method and warehousing robot |
CN214191209U (en) * | 2020-12-30 | 2021-09-14 | 深圳市海柔创新科技有限公司 | Storage robot and camera shooting assembly |
-
2021
- 2021-11-16 WO PCT/CN2021/131015 patent/WO2022142808A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204964854U (en) * | 2015-08-27 | 2016-01-13 | 丁雪勤 | High pixel module of making a video recording |
CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
CN206339868U (en) * | 2016-12-21 | 2017-07-18 | 深圳若步智能科技有限公司 | A kind of automatic guided vehicle vision positioning device |
CN107065853A (en) * | 2016-12-21 | 2017-08-18 | 深圳若步智能科技有限公司 | A kind of merchandising machine people system and its method of work |
CN110018688A (en) * | 2019-04-11 | 2019-07-16 | 清华大学深圳研究生院 | The automatic guide vehicle localization method of view-based access control model |
CN110850872A (en) * | 2019-10-31 | 2020-02-28 | 深圳市优必选科技股份有限公司 | Robot inspection method and device, computer readable storage medium and robot |
CN112698539A (en) * | 2020-12-30 | 2021-04-23 | 深圳市海柔创新科技有限公司 | Positioning method and warehousing robot |
CN214191209U (en) * | 2020-12-30 | 2021-09-14 | 深圳市海柔创新科技有限公司 | Storage robot and camera shooting assembly |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7839431B2 (en) | Image processing system and method for improving repeatability | |
US20230100386A1 (en) | Dual-imaging vision system camera, aimer and method for using the same | |
US11240436B2 (en) | Machine vision system and method with steerable mirror | |
US7768572B2 (en) | Iris recognition camera for an iris recognition system and a method of operation for an iris recognition camera | |
US7733412B2 (en) | Image pickup apparatus and image pickup method | |
EP3839610A1 (en) | Machine vision system and method with steerable mirror | |
US6606458B2 (en) | Automatic framing camera | |
US20140078345A1 (en) | System for capturing a document in an image signal | |
EP1936477A1 (en) | Position information detection device, position information detection method, and position information detection program | |
US9646188B1 (en) | Imaging module and reader for, and method of, expeditiously setting imaging parameters of an imager based on the imaging parameters previously set for a default imager | |
US20190020850A1 (en) | Information Handling System Integrated Multi-Angle Camera | |
CN112698539A (en) | Positioning method and warehousing robot | |
CN111818264B (en) | Image acquisition system | |
EP4217912A1 (en) | Machine vision system and method with on-axis aimer and distance measurement assembly | |
US11790656B2 (en) | Machine vision system and method with steerable mirror | |
WO2022142808A1 (en) | Storage robot, camera assembly and positioning method | |
CN214191209U (en) | Storage robot and camera shooting assembly | |
CN113273176B (en) | Automated movie production using image-based object tracking | |
CN113124830A (en) | Method and equipment for testing imaging optical gradient of camera module | |
US8302867B2 (en) | Symbol reading device, symbol reading method and program recording medium to control focus based on size of captured symbol | |
US20220014682A1 (en) | System and method for extending depth of field for 2d vision system cameras in the presence of moving objects | |
EP4359994A1 (en) | Machine vision system and method with steerable mirror | |
JP3691802B2 (en) | Automatic framing camera | |
CN214045751U (en) | Liquid lens assembly and terminal equipment | |
CN117835039A (en) | Image acquisition device, control method and device thereof, storage medium and image pickup apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21913551 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21913551 Country of ref document: EP Kind code of ref document: A1 |