CN115933706B - Robot charging method and device, robot and robot system - Google Patents
Robot charging method and device, robot and robot system Download PDFInfo
- Publication number
- CN115933706B CN115933706B CN202310075460.XA CN202310075460A CN115933706B CN 115933706 B CN115933706 B CN 115933706B CN 202310075460 A CN202310075460 A CN 202310075460A CN 115933706 B CN115933706 B CN 115933706B
- Authority
- CN
- China
- Prior art keywords
- robot
- charging
- charging pile
- sensor data
- matching result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application discloses a robot charging method, a device, a robot and a robot system, after detecting that the robot needs to be charged, sensor data acquired by the robot through a camera and a laser radar are acquired, the sensor data are matched with the characteristics of a preset number of charging piles, the preset number is not less than 2, a target characteristic matching result is obtained, if the number of matched characteristics indicated in the target characteristic matching result is equal to 1, the preliminary position of the charging piles is determined based on the acquired sensor data, the robot is controlled to move to the preliminary position, and the steps of data acquisition and characteristic matching are repeated after the robot moves to the preliminary position. If the number of the matched features is not less than 2, determining the final position of the charging pile based on the acquired sensor data, and controlling the robot to move to the final position so as to realize pile charging. According to the scheme, the searching efficiency is considered, and the identification accuracy of the charging pile is considered.
Description
Technical Field
The application relates to the technical field of intelligent robots, in particular to a robot charging method, a robot charging device, a robot and a robot system.
Background
Along with the progress of science and technology, more and more intelligent robots are applied to the work and the life of people. Examples are intelligent sweeping robots, transfer robots, companion robots, etc.
The intelligent robots can realize established operations such as autonomous movement, cleaning, carrying, illumination and the like, and bring great convenience to users. Generally, the intelligent robot is provided with a built-in power module, so that the intelligent robot can be separated from a charging device to work, but the built-in power module has limited power supply capacity due to the limitation of the size of the body, so that before the electric quantity of the power module is exhausted, the intelligent robot is required to accurately return to a charging pile to realize autonomous charging, and the hands of a user are thoroughly liberated.
In the prior art, characteristic marks such as reflective strips and the like are generally arranged on the surface of the charging pile. When the intelligent robot moves, surrounding environment data are perceived, and when the perceived environment data are detected to be matched with the characteristic identifiers, the charging pile is detected, and then the intelligent robot moves towards the charging pile to charge. However, the working environment where the intelligent robot is located may be complex and variable, and articles similar to the feature identifiers arranged on the surface of the charging pile often appear in the environment, so that the intelligent robot misjudges the position of the charging pile.
Disclosure of Invention
In view of the above problems, the present application is provided to provide a method, an apparatus, a robot and a robot system for charging a robot, so as to improve the inspection accuracy of the position of a charging pile while considering the efficiency of searching the charging pile. The specific scheme is as follows:
in a first aspect, a robot charging method is provided, including:
after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar;
matching the sensor data with a preset number of charging pile features to obtain a target feature matching result, wherein the preset number is not less than 2;
if the target feature matching result shows that the number of the matched features is equal to 1, determining a preliminary position of the charging pile based on the sensor data, controlling the robot to move to the preliminary position, and returning to execute the step of acquiring the sensor data acquired by the robot through the camera and the laser radar;
and if the target feature matching result shows that the number of the matched features is not less than 2, determining the final position of the charging pile based on the sensor data, and controlling the robot to move to the final position so as to realize pile charging.
In a second aspect, there is provided a robot charging apparatus comprising:
the sensor data acquisition unit is used for acquiring sensor data acquired by the robot through the camera and the laser radar after detecting that the robot needs to be charged;
the characteristic matching unit is used for matching the sensor data with the characteristics of the charging piles of a preset number to obtain a target characteristic matching result, wherein the preset number is not less than 2;
the preliminary position determining unit is used for determining the preliminary position of the charging pile based on the sensor data if the number of the matched features is equal to 1 in the target feature matching result, controlling the robot to move to the preliminary position, and returning to the step of executing the sensor data acquired by the sensor data acquiring unit through the camera and the laser radar;
and the final position determining unit is used for determining the final position of the charging pile based on the sensor data and controlling the robot to move to the final position so as to realize pile charging if the number of the matched features is not less than 2 in the target feature matching result.
In a third aspect, a robot is provided, comprising: the robot comprises a robot body, a power module, a camera, a laser radar, a memory and a processor, wherein the power module, the camera, the laser radar, the memory and the processor are arranged on the robot body;
The memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the robot charging method as described above.
In a fourth aspect, a robot system is provided, including the robot and a charging stake;
the charging pile comprises a charging groove, and a power supply interface is arranged in the charging groove and is used for being matched with a charging interface on the robot to charge the robot;
at least two materials with different retroreflection coefficients are arranged in the charging groove.
By means of the technical scheme, after the fact that the robot needs to be charged is detected, sensor data acquired by the robot through the camera and the laser radar are acquired, the sensor data are matched with the charging pile features of the preset quantity, the target feature matching result is obtained, and the preset quantity is not less than 2, namely, at least 2 charging pile features are designed. If the number of the matched features is equal to 1 in the target feature matching result, the preliminary position of the charging pile, namely the approximate position of the charging pile, can be determined based on the acquired sensor data, and is used as a path planning guide for searching the charging pile, on the basis, the robot is controlled to move to the preliminary position, and the steps of acquiring the sensor data and matching the features of the charging pile are repeatedly executed in the moving process or after the robot moves to the preliminary position, so that the pile searching efficiency is ensured. If the target feature matching result shows that the number of the matched features is not less than 2, the final position of the charging pile can be determined based on the acquired sensor data, and the robot is controlled to move to the final position so as to realize pile charging. Obviously, the identity of the charging pile is verified through the characteristic comparison of the charging piles of more than 2, the final position of the charging pile is determined, the identification accuracy of the charging pile is ensured, and misjudgment is avoided.
In summary, the application designs more than 2 types of charging pile features, through feature matching, if 1 feature is matched, the preliminary position of the charging pile is determined to serve as a path planning guide for searching the charging pile, more charging pile features are continuously matched to improve the confidence coefficient of the charging pile identification in the process that the robot reaches the preliminary position or after the robot reaches the preliminary position, and when more than 2 feature matching is determined, the final position of the charging pile can be determined, so that the searching efficiency is considered, and the accuracy of the charging pile identification is considered.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 is a schematic flow chart of a robot charging method according to an embodiment of the present disclosure;
FIG. 2 illustrates a schematic layout of two materials with different retroreflectivity;
fig. 3 is another flow chart of a robot charging method according to an embodiment of the present disclosure;
Fig. 4 is a schematic structural diagram of a robot charging device according to an embodiment of the present disclosure;
fig. 5 is a schematic hardware structure of a robot according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The application provides a robot charging method which can be suitable for various intelligent robots such as cleaning robots, transfer robots, shopping guide robots and the like which charge by means of charging piles. The robot body is provided with a power module for supporting the autonomous movement and work of the robot. The body can be further provided with a camera and a laser radar for collecting sensor data of surrounding environment, such as collecting environment image data through the camera, collecting point cloud data, reflected light intensity data and the like through the laser radar. The robot moves out of the charging pile and then performs given work such as cleaning, carrying, explaining, lighting and the like. When the robot receives the charging signal, the robot needs to return to the charging pile for automatic charging, so that the robot can be guaranteed to rapidly and accurately identify the charging pile and further realize pile charging, and the use convenience of the robot is concerned.
The application provides a robot charging method which is used for realizing autonomous searching and identifying a charging pile by a robot leaving the pile and returning to the charging pile for autonomous charging. The method can be realized based on the robot, and can also be realized under the control of other control ends (such as a server, a cloud end and the like) or under the cooperation of other control ends and the robot.
Next, as described in connection with fig. 1, the robot charging method of the present application may include the steps of:
and step S100, after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through the camera and the laser radar.
Specifically, it may be determined that the robot needs to be charged after receiving the charging signal. The charging signal may be an instruction from a user, or may be a charging signal sent when the electric quantity of the charging module of the robot is too low to reach a certain threshold value.
Be provided with camera and laser radar on the robot, after detecting that the robot needs to charge, can gather sensor data through camera and laser radar. The sensor data collected by the camera can comprise environment image data, and the sensor data collected by the laser radar can comprise point cloud data, reflected light intensity data and the like.
In the step, after the robot is detected to be charged, sensor data acquired by the camera and the laser radar in a static state or in a moving process of the robot can be acquired.
Wherein, under the static state, the method can comprise the following steps: after detecting that the robot needs to be charged, the stationary state of the robot at the current position may further include: after detecting that the robot needs to be charged, controlling the robot to move according to a set rule, and stopping the robot in a static state after the robot moves to a set position.
The moving process may include: and after detecting that the robot needs to be charged, controlling the robot to move and roam in the working environment according to a set rule. The movement rules may specifically be movement along the map boundary, or preferably within a set area (e.g. movement in living room may be preferred when the robot is a sweeping robot).
In addition, after the robot is detected to be charged, the robot can be controlled to move towards the preset charging pile position, and sensor data acquired by the robot through a camera or a laser radar in the moving process are acquired.
The preset charging pile position may be a starting point position of a current driving path of the robot, or a registered charging pile position in a global map of the robot, or a potential charging pile position determined based on sensor data acquired by a camera and a laser radar in a moving process before the robot needs to be charged.
It can be understood that the robot can record the running track after starting and running out from the charging pile, so that the starting position of the running track can be used as the preset charging pile position.
In addition, the robot needs to establish a global map of the environment before first use, and the charging pile positions can be marked in the global map to serve as registered charging pile positions. The registered charging pile position can be updated at any time later if global map updating is involved. In this embodiment, the charging pile position registered in the global map may be used as a preset charging pile position.
In another case, after the robot is driven out of the charging pile, the potential charging pile position can be determined and stored in real time through sensor data acquired by a camera and a laser radar in the moving working process. And when the robot is detected to need to be charged, the robot can be controlled to move towards the potential charging pile position.
And step S110, matching the acquired sensor data with the characteristics of the charging piles of a preset number to obtain a target characteristic matching result, wherein the preset number is not less than 2.
Specifically, the application presets at least 2 charging pile features for identifying the identity of the charging pile from different angles. On this basis, sensor data acquired by a camera and a laser radar can be matched with each charging pile feature to obtain a target feature matching result, the target feature matching result comprises whether each preset charging pile feature is successfully matched, and the matching is performed through a plurality of different charging pile features, so that the recognition accuracy of the charging piles is improved through more feature matching.
Step S120, determining the number of matched features in the target feature matching result, if the number is equal to 0, returning to execute step S100, if the number is equal to 1, executing step S130 described below, and if the number is not less than 2, executing step S140 described below.
If the number of the matched features is equal to 0 in the target feature matching result, it indicates that the sensor data acquired by the current camera and the laser radar are not matched with any one of the charging pile features, that is, the charging pile is not found, so that the step S100 can be returned to continue to acquire the sensor data, that is, continue to search the charging pile.
If the number of matched features in the target feature matching result is equal to 1, it indicates that the currently acquired sensor data matches a certain preconfigured charging pile feature, and considering the complexity of the working environment of the robot, other objects other than the charging pile may exist in the surrounding environment, which are similar to certain charging pile features, that is, the confidence of preconfigured different charging pile features may be different, and when the number of matched features is determined to be 1, it indicates that the current sensor data may find a charging pile, so that step S130 described below may be executed to determine the preliminary position of the charging pile as a path planning guide for searching the charging pile.
If the number of the matched features is not less than 2 in the target feature matching result, it is indicated that the currently acquired sensor data is matched with the features of the plurality of preconfigured charging piles, and the confidence of identifying the charging piles is high at this time, so that the step of determining the final position of the charging piles in step S140 described below can be performed.
And step 130, determining the preliminary position of the charging pile based on sensor data acquired by the camera and the laser radar, and controlling the robot to move towards the preliminary position.
Specifically, when the collected sensor data matches 1 preconfigured charging pile feature, a preliminary location of the charging pile may be determined based on the sensor data.
After controlling the robot to move to the preliminary position or move to the preliminary position, the step of acquiring the sensor data in the step S100 may be continuously performed, and the step of acquiring the sensor data and matching with the pre-configured charging pile features may be continuously performed, so as to improve the number of matching features and improve the confidence degree of identifying the charging pile.
And step 140, determining the final position of the charging pile based on the sensor data acquired by the camera and the laser radar, and controlling the robot to move towards the final position so as to realize pile entering charging.
Specifically, when the collected sensor data matches more than 2 pre-configured charging stake features, it may be determined that the confidence that the charging stake is found at this time is already high, and thus the final position of the charging stake may be determined based on the collected sensor data. At this time, the steps of sensor data acquisition, charging pile feature matching and the like are not required to be executed.
According to the robot charging method, after the fact that the robot needs to be charged is detected, sensor data acquired by the robot through the camera and the laser radar are acquired, the sensor data are matched with the charging pile features of the preset quantity, the target feature matching result is obtained, and the preset quantity is not less than 2, namely, at least 2 charging pile features are designed. If the number of the matched features is equal to 1 in the target feature matching result, the preliminary position of the charging pile, namely the approximate position of the charging pile, can be determined based on the acquired sensor data, and is used as a path planning guide for searching the charging pile, on the basis, the robot is controlled to move to the preliminary position, and the steps of acquiring the sensor data and matching the features of the charging pile are repeatedly executed in the moving process or after the robot moves to the preliminary position, so that the pile searching efficiency is ensured. If the target feature matching result shows that the number of the matched features is not less than 2, the final position of the charging pile can be determined based on the acquired sensor data, and the robot is controlled to move to the final position so as to realize pile charging. Obviously, the identity of the charging pile is verified through the characteristic comparison of the charging piles of more than 2, the final position of the charging pile is determined, the identification accuracy of the charging pile is ensured, and misjudgment is avoided.
In summary, the application designs more than 2 types of charging pile features, through feature matching, if 1 feature is matched, the preliminary position of the charging pile is determined to serve as a path planning guide for searching the charging pile, more charging pile features are continuously matched to improve the confidence coefficient of the charging pile identification in the process that the robot reaches the preliminary position or after the robot reaches the preliminary position, and when more than 2 feature matching is determined, the final position of the charging pile can be determined, so that the searching efficiency is considered, and the accuracy of the charging pile identification is considered.
Further optionally, considering that the placement posture of the charging pile may affect the pile charging of the robot, the preliminary position of the charging pile is determined based on the sensor data in the above step, and the preliminary posture of the charging pile is further determined, and the preliminary posture is obtained by combining the preliminary posture and the preliminary position, that is, the position information and the posture information of the charging pile are determined simultaneously.
The process of determining the preliminary position and the gesture of the charging pile based on the sensor data can be to position the azimuth and the gesture of the charging pile based on the shooting angle of the camera, and further to measure the distance of the charging pile based on the laser radar, so that the preliminary position and the gesture of the charging pile can be obtained.
On the basis, the process of controlling the robot to move to the preliminary position may include: and controlling the robot to move to a set distance position right in front of the charging pile indicated by the initial pose.
Similarly, while the final position of the charging pile is determined based on the sensor data in the above step, the final posture of the charging pile may be further determined, and the final posture is obtained by combining the final posture and the final position, that is, the position information and the posture information of the charging pile are determined at the same time.
On the basis, the process of controlling the robot to move to the final position may include: and controlling the robot to move to a set distance position right in front of the charging pile indicated by the final pose. After the robot moves to a position right in front of the charging pile by a set distance, the robot can execute subsequent pile entering actions.
In some embodiments of the present application, the process of matching the sensor data with the preset number of charging pile features in the aforementioned step S110 is further described.
In this embodiment, an optional arrangement manner of the charging pile features is provided, specifically, the preset number of charging pile features may include two types, which are respectively: the appearance characteristic of the charging pile and the internal characteristic of the charging groove of the charging pile, namely, the charging pile is identified from the integral appearance angle of the charging pile and the internal angle of the charging groove respectively.
The number of appearance features of the charging pile and the number of internal features of the charging groove are not strictly limited, and the number of the overall charging pile features is not less than 2.
On this basis, the process of step S110 may specifically include:
s1, matching sensor data acquired by a camera with appearance characteristics of a charging pile to obtain a first characteristic matching result.
Specifically, the charging post appearance features may include features of external shape, color, pattern, etc. of the charging post as a whole. Therefore, in the step, the sensor data acquired by the camera is matched with the appearance characteristics of the charging pile, so as to judge whether the camera shoots an object with the matched appearance characteristics of the charging pile currently.
The sensor data collected by the camera may include image data, that is, the image data collected by the camera is matched with appearance features of the charging pile, so as to determine whether the appearance features of the charging pile are successfully matched, and a first feature matching result is obtained.
S2, matching the sensor data acquired by the laser radar with the internal features of the charging tank to obtain a second feature matching result, and forming the target feature matching result by the first feature matching result and the second feature matching result.
In particular, the charging slot internal features are used to characterize the charging slot internal features of the charging post, the number of which may be one or more, examples such as charging slot internal features may include: charging tank internal structure characteristics, charging tank internal material characteristics and the like.
In order to better identify the internal characteristics of the charging slot, in the step, sensor data acquired by the laser radar are matched with the internal characteristics of the charging slot of the charging pile, and a second characteristic matching result is obtained. Specifically, the data such as the point cloud and the reflected light intensity collected by the laser radar can be matched with the internal features of the charging slot to determine whether the internal features of the charging slot are successfully matched, and a second feature matching result is obtained.
And finally, forming a final target feature matching result by the first feature matching result and the second feature matching result.
In this embodiment, two different types of characteristics of the charging pile, namely, two types of characteristics of appearance characteristics of the charging pile and internal characteristics of the charging groove are illustrated, so that the charging pile can be matched from two different angles of the whole appearance of the charging pile and the internal characteristics of the charging groove, and the recognition accuracy of the charging pile is improved.
In some embodiments of the present application, the process of matching the sensor data acquired by the camera with the appearance feature of the charging pile in the step S1 to obtain the first feature matching result is described.
The sensor data collected by the camera may be ambient image data. In this embodiment, an image recognition algorithm may be used to calculate the matching degree between the environmental image data collected by the camera and the appearance features of the pre-configured charging pile. And if the matching degree exceeds the set matching degree threshold, confirming that the appearance characteristics of the charging pile are matched, otherwise, confirming that the appearance characteristics of the charging pile are not matched, and taking the matching result of the appearance characteristics of the charging pile as a first characteristic matching result.
Specifically, the charging pile recognition model can be trained by using the charging pile appearance image in advance, and then the environment image data acquired by the camera can be input into the charging pile recognition model to obtain the confidence coefficient of the charging pile contained in the environment image data output by the model, and if the confidence coefficient exceeds a set threshold, the environment image is matched with the appearance characteristics of the pre-configured charging pile, namely, the charging pile exists in the environment image.
The appearance characteristics of the charging pile can comprise the combination of appearance shapes, colors, patterns and the like.
In some embodiments of the present application, the process of matching the sensor data acquired by the lidar with the internal feature of the charging slot in the step S2 to obtain the second feature matching result is described.
In this embodiment, two different charging slot internal features are introduced, respectively: the internal structural characteristics of the charging tank and the internal material characteristics of the charging tank.
On the basis, the method and the device can match the point cloud data acquired by the laser radar with the internal structural characteristics of the charging tank, and obtain an internal structural characteristic matching result.
And matching the object reflected light intensity data acquired by the laser radar with the internal material characteristics of the charging tank to obtain an internal material characteristic matching result.
And taking the internal structural feature matching result and/or the internal material feature matching result as a second feature matching result.
Specifically, in this embodiment, only the internal structural feature may be selected as the internal feature of the charging slot, only the internal material feature may be selected as the internal feature of the charging slot, or both the internal structural feature and the internal material feature may be selected as the internal feature of the charging slot.
The finally obtained second feature matching result may include one or both of an internal structural feature matching result and an internal material feature matching result.
In this embodiment, the in-process of filling electric pile is being looked for, matches filling electric pile appearance characteristic promptly, matches simultaneously again filling electric pile's charging groove inner structure characteristic and/or inside material characteristic, matches through the characteristic to multiple difference, can enough promote and seek stake efficiency, has promoted the rate of accuracy of filling electric pile discernment again, reduces the misrecognition.
Further, in order to improve the identification degree of the material characteristics inside the charging groove, at least two materials with different retroreflection coefficients can be arranged inside the charging groove of the charging pile in advance in the embodiment of the application. The two materials with different retroreflection coefficients can be distributed at intervals. The layout of the two materials with different retroreflectivity can be shown in fig. 2. The material A and the material B with different retroreflection coefficients are included, and the sizes and the intervals of the two materials can be different.
On this basis, the process of matching the object reflected light intensity data acquired by the laser radar with the internal material characteristics of the charging tank to obtain the internal material characteristic matching result can include:
and matching the object reflected light intensity data acquired by the laser radar with the material characteristics of at least two materials with different retroreflection coefficients to obtain an internal material matching result.
In some embodiments of the present application, another robot charging method is provided, as shown in fig. 3, which may include the steps of:
and step 200, after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through the camera and the laser radar.
And S210, respectively matching the sensor data acquired by the camera and the laser radar with the appearance characteristics of the charging pile and the internal characteristics of the charging tank to obtain a target characteristic matching result.
Specifically, sensor data acquired by a camera can be matched with pre-configured appearance features of the charging pile, and a first feature matching result is obtained.
And matching the sensor data acquired by the laser radar with the internal features of the charging slot of the pre-configured charging pile to obtain a second feature matching result, wherein the first feature matching result and the second feature matching result form a target feature matching result.
Step S220, determining the number of matched features in the target feature matching result, if the number is equal to 0, returning to execute step S200, if the number is equal to 1, executing step S230, and if the number is not less than 2, executing step S250.
Step S230, determining whether the matched features match the appearance features of the charging pile, if not, executing step S240, and if yes, executing step S250.
Specifically, when the number of the matched features is equal to 1 as indicated in the target feature matching result, whether the matched features are matched with the appearance features of the charging pile is further judged.
In this embodiment, the preconfigured charging pile features are divided into two types, the first type is the appearance feature of the charging pile, and the second type is the internal feature of the charging slot.
Because it is not common that the whole appearance of the robot working environment is similar to that of the charging pile, if the sensor data captured and collected by the camera is matched with the appearance feature of the pre-configured charging pile, the confidence of the type of feature is relatively high, so that the searching of the charging pile can be directly determined, and the step of determining the final position of the charging pile in step S250 can be performed.
Further, some articles similar to the charging slot may exist in the robot working environment, such as a vertically placed basin, and the point cloud obtained after the laser radar scanning is similar to the U-shaped structure of the charging slot. In addition, some articles carrying bright and dark stripes or alternatively composed of two materials with different reflective intensities can cause intensity variation of reflected light intensity received by the laser radar, so that the charging pile is misjudged. Therefore, if the 1 matched features are not matched with the appearance features of the charging pile, it means that the 1 matched features belong to a matching with an internal feature of a charging slot (for example, a matching with an internal structural feature of the charging slot or a matching with an internal material feature of the charging slot), and at this time, the confidence of the 1 matched features is not high enough, the following step S240 may be executed, where the step of determining the preliminary position of the charging pile is performed as a path planning guide for searching the charging pile.
And step 240, determining the preliminary position of the charging pile based on sensor data acquired by the camera and the laser radar, and controlling the robot to move towards the preliminary position.
After the robot is controlled to move to the preliminary position or move to the preliminary position, the step of obtaining the sensor data in the step S200 is continuously carried out, and the step of matching the sensor data with the pre-configured charging pile features is continuously carried out, so that the number of the matched features is increased, and the confidence of identifying the charging pile is increased.
And step S250, determining the final position of the charging pile based on sensor data acquired by the camera and the laser radar, and controlling the robot to move towards the final position so as to realize pile entering charging.
Specifically, in this embodiment, when it is determined that the number of matched features in the target feature matching result is more than 2, and when the number of matched features is 1 and belongs to matching with the appearance feature of the charging pile, the confidence that the charging pile is identified is high may be considered, and the final position of the charging pile may be determined based on the collected sensor data.
According to the robot charging method provided by the embodiment, the charging pile features are divided into two types, wherein the first type is the appearance feature of the charging pile, the second type is the charging groove internal feature (including the charging groove internal structural feature, the charging groove internal material feature and the like) of the charging pile, and if the first type feature is matched with or more than 2 of the second type features are matched with each other, the final position of the charging pile can be confirmed. If the first type of features are not matched, only 1 of the second type of features are matched, the preliminary position of the charging pile can be calculated, the robot is controlled to move towards the preliminary position, and after the robot moves in the moving process or moves to the preliminary position, sensor data are continuously acquired to perform feature matching until the final position of the charging pile is confirmed.
The charging pile features of different types have different confidence degrees, such as appearance features of the charging pile of the first type, and articles which are long like the charging pile in the whole appearance in the working environment of the robot are not common, so that the confidence degrees of the appearance features of the charging pile of the first type are higher. The second type of charging tank internal characteristics are acquired through a laser radar, and the shape of part of articles in a robot working environment obtained through laser radar modeling is similar to the shape of the charging tank internal structure, or the change of the reflected light intensity of part of articles received through the laser radar is similar to the material characteristics of the charging tank internal, so that misjudgment is easy to occur. Thus, the confidence of the second type of charging slot internal features is relatively low.
Although the confidence of the appearance characteristics of the charging pile of the first layer is higher, the characteristics are acquired through the camera, and the view angle of the camera is usually smaller (for example, the view angle of the RGB depth camera is generally only about 100 degrees), so that the efficiency of searching the charging pile in the environment simply by means of the camera is lower. Therefore, in the embodiment, the internal features of the second type of charging slot are further overlapped, the second type of features are detected through the laser radar, the field angle of the laser radar on the robot can reach 300-360 degrees, and the searching efficiency is high. In this embodiment, when it is detected that some of the internal features of the second type charging slots are matched, a preliminary position of the charging pile can be generated as a path planning guide for searching the charging pile, and after the charging pile moves to the preliminary position or moves to the preliminary position, other features are continuously searched again to improve the confidence level until more than 2 internal features of the second type charging slots are matched or appearance features of the first type charging pile are matched are searched, and then the final position of the charging pile is confirmed, so that both pile searching efficiency and accuracy of charging pile identification can be considered.
The following describes a robot charging device provided in the embodiments of the present application, and the robot charging device described below and the robot charging method described above may be referred to correspondingly to each other.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a charging device for a robot according to an embodiment of the present application.
As shown in fig. 4, the apparatus may include:
a sensor data acquisition unit 11, configured to acquire sensor data acquired by the robot through the camera and the laser radar after detecting that the robot needs to be charged;
a feature matching unit 12, configured to match the sensor data with a preset number of charging pile features, to obtain a target feature matching result, where the preset number is not less than 2;
a preliminary position information determining unit 13, configured to determine a preliminary position of the charging pile based on the sensor data if the number of matched features is equal to 1 in the target feature matching result, control the robot to move to the preliminary position, and return to executing the step of the sensor data acquiring unit acquiring sensor data acquired by the robot through the camera and the laser radar;
and a final position information determining unit 14, configured to determine a final position of the charging pile based on the sensor data if the number of matched features is not less than 2 in the target feature matching result, and control the robot to move to the final position so as to implement pile-in charging.
Optionally, the foregoing preset number of charging pile features may include two types of features including an appearance feature of a charging pile and an internal feature of a charging slot of the charging pile, on this basis, a process of matching the sensor data with the preset number of charging pile features by the foregoing feature matching unit to obtain a target feature matching result may include:
matching the sensor data acquired by the camera with the appearance characteristics of the charging pile to obtain a first characteristic matching result;
and matching the sensor data acquired by the laser radar with the internal features of the charging tank to obtain a second feature matching result, wherein the first feature matching result and the second feature matching result form the target feature matching result.
Optionally, the foregoing charging tank internal feature may include a charging tank internal structural feature and a charging tank internal material feature, on this basis, the process of matching the sensor data collected by the laser radar with the charging tank internal feature of the charging pile to obtain a second feature matching result may include:
matching the point cloud data acquired by the laser radar with the internal structural characteristics of the charging slot of the charging pile to obtain an internal structural characteristic matching result;
And/or the number of the groups of groups,
matching the object reflected light intensity data acquired by the laser radar with the internal material characteristics of the charging slot of the charging pile to obtain an internal material characteristic matching result;
and taking the internal structural feature matching result and/or the internal material feature matching result as a second feature matching result.
Optionally, the process of matching the sensor data collected by the camera with the appearance feature of the charging pile by the feature matching unit may include:
calculating the matching degree between the environmental image data acquired by the camera and the appearance characteristics of the charging pile by adopting an image recognition algorithm;
and if the matching degree exceeds the set matching degree threshold, confirming that the appearance characteristics of the charging pile are matched, otherwise, confirming that the appearance characteristics of the charging pile are not matched.
Optionally, the apparatus of the present application may further include:
and the matching feature type determining unit is used for determining whether the matched features are matched with the appearance features of the charging pile after determining that the number of the matched features is equal to 1 in the target feature matching result, if so, executing the step of the final position information determining unit, and if not, executing the step of the preliminary position information determining unit.
Optionally, at least two materials with different retroreflection coefficients are arranged in the charging groove of the charging pile. The process of matching the object reflected light intensity data acquired by the laser radar with the internal material characteristics of the charging slot of the charging pile by the feature matching unit to obtain an internal material characteristic matching result may include:
and matching the object reflected light intensity data acquired by the laser radar with the material characteristics of the at least two materials with different retroreflection coefficients to obtain an internal material matching result.
Optionally, the process of acquiring the sensor data acquired by the robot through the camera and the laser radar after the sensor data acquiring unit detects that the robot needs to be charged may include:
after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar in the moving process;
or after detecting that the robot needs to be charged, acquiring sensor data acquired by the camera and the laser radar of the robot in a static state.
Optionally, the process of acquiring the sensor data acquired by the robot through the camera and the laser radar during the moving process by the sensor data acquiring unit may include:
Controlling the robot to move towards a preset charging pile position, and acquiring sensor data acquired by the robot through a camera and a laser radar in the moving process;
the preset charging pile position is a starting point position of a current driving path of the robot, or a registered charging pile position in a global map of the robot, or a potential charging pile position determined by the robot based on sensor data acquired by a camera and a laser radar in a moving process before charging is required.
Optionally, the preliminary location information determining unit is further configured to determine, in the target feature matching result, a preliminary pose of the charging pile based on the sensor data when the number of matched features is equal to 1, and obtain a preliminary pose of the charging pile from the preliminary pose and the preliminary location. On the basis, the process of controlling the robot to move to the preliminary position may include: and controlling the robot to move to a set distance position right in front of the charging pile indicated by the initial pose.
Optionally, the final position information determining unit is further configured to determine, when the number of matched features is not less than 2 in the target feature matching result, a final pose of the charging pile based on the sensor data, and obtain a final pose of the charging pile from the final pose and the final position. On the basis, the process of controlling the robot to move to the final position may include: and controlling the robot to move to a set distance in front of the charging pile indicated by the final pose.
The robot charging device provided by the embodiment of the application can be applied to robots such as cleaning robots, transfer robots, shopping guide robots and the like. Alternatively, fig. 5 shows a block diagram of a hardware structure of the robot, and referring to fig. 5, the hardware structure of the robot may include: a robot body (not shown in the figure), a power module 1, a camera 2, a laser radar 3, a memory 4, a processor 5 and a communication bus 6 which are arranged on the robot body;
in the embodiment of the application, the number of the power supply module 1, the camera 2, the laser radar 3, the memory 4, the processor 5 and the communication bus 6 is at least one. The power module 1 supplies power to the other modules. The camera 2, the laser radar 3, the memory 4 and the processor 5 complete communication with each other through the communication bus 6;
the processor 5 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 4 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory) or the like, such as at least one magnetic disk memory;
Wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar;
matching the sensor data with a preset number of charging pile features to obtain a target feature matching result, wherein the preset number is not less than 2;
if the target feature matching result shows that the number of the matched features is equal to 1, determining a preliminary position of the charging pile based on the sensor data, controlling the robot to move to the preliminary position, and returning to execute the step of acquiring the sensor data acquired by the robot through the camera and the laser radar;
and if the target feature matching result shows that the number of the matched features is not less than 2, determining the final position of the charging pile based on the sensor data, and controlling the robot to move to the final position so as to realize pile charging.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the application also provides a storage medium, which may store a program adapted to be executed by a processor, the program being configured to:
After detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar;
matching the sensor data with a preset number of charging pile features to obtain a target feature matching result, wherein the preset number is not less than 2;
if the target feature matching result shows that the number of the matched features is equal to 1, determining a preliminary position of the charging pile based on the sensor data, controlling the robot to move to the preliminary position, and returning to execute the step of acquiring the sensor data acquired by the robot through the camera and the laser radar;
and if the target feature matching result shows that the number of the matched features is not less than 2, determining the final position of the charging pile based on the sensor data, and controlling the robot to move to the final position so as to realize pile charging.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the application also provides a robot system, which comprises the robot introduced by the embodiment and the charging pile matched with the robot.
The charging pile comprises a charging groove, and a power supply interface is arranged in the charging groove and used for being matched with a charging interface on the robot to charge the robot.
At least two materials with different retroreflection coefficients can be arranged in the charging groove and used for improving the identification degree of the internal characteristics of the charging groove.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and may be combined according to needs, and the same similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. A robot charging method, comprising:
after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar;
matching the sensor data with a preset number of charging pile features to obtain a target feature matching result, wherein the preset number is not less than 2;
if the target feature matching result shows that the number of the matched features is equal to 1, determining a preliminary position of the charging pile based on the sensor data, controlling the robot to move to the preliminary position, and returning to execute the step of acquiring the sensor data acquired by the robot through the camera and the laser radar;
If the target feature matching result shows that the number of the matched features is not less than 2, determining the final position of the charging pile based on the sensor data, and controlling the robot to move to the final position so as to realize pile charging;
the charging pile features of the preset number comprise appearance features of charging piles and charging groove internal features of the charging piles;
the process of matching the sensor data with the preset number of charging pile features to obtain a target feature matching result comprises the following steps:
matching the sensor data acquired by the camera with the appearance characteristics of the charging pile to obtain a first characteristic matching result;
and matching the sensor data acquired by the laser radar with the internal features of the charging tank to obtain a second feature matching result, wherein the first feature matching result and the second feature matching result form the target feature matching result.
2. The method of claim 1, wherein the charging tank internal features include charging tank internal structural features and charging tank internal material features;
the sensor data acquired by the laser radar is matched with the internal characteristics of the charging tank to obtain a second characteristic matching result, and the method comprises the following steps:
Matching the point cloud data acquired by the laser radar with the internal structural characteristics of the charging tank to obtain an internal structural characteristic matching result;
and/or the number of the groups of groups,
matching the object reflected light intensity data acquired by the laser radar with the internal material characteristics of the charging tank to obtain an internal material characteristic matching result;
and using the internal structural feature matching result and/or the internal material feature matching result as the second feature matching result.
3. The method of claim 1, wherein the step of determining the position of the substrate comprises,
after determining that the number of matched features is equal to 1 in the target feature matching result, before determining the preliminary position of the charging pile, the method further comprises:
and if the matched characteristic is determined to be matched with the appearance characteristic of the charging pile, executing the step of determining the final position of the charging pile, otherwise, executing the step of determining the preliminary position of the charging pile.
4. The method of claim 1, wherein the matching the sensor data collected by the camera with the appearance feature of the charging pile comprises:
calculating the matching degree between the environmental image data acquired by the camera and the appearance characteristics of the charging pile by adopting an image recognition algorithm;
And if the matching degree exceeds the set matching degree threshold, confirming that the appearance characteristics of the charging pile are matched, otherwise, confirming that the appearance characteristics of the charging pile are not matched.
5. The method of claim 2, wherein at least two materials with different retroreflection coefficients are arranged inside the charging groove of the charging pile;
the object reflected light intensity data acquired by the laser radar is matched with the internal material characteristics of the charging tank to obtain an internal material characteristic matching result, and the method comprises the following steps:
and matching the object reflected light intensity data acquired by the laser radar with the material characteristics of the at least two materials with different retroreflection coefficients to obtain an internal material matching result.
6. The method of any of claims 1-5, wherein acquiring sensor data acquired by the robot via the camera and the lidar after detecting that the robot needs to be charged comprises:
after detecting that the robot needs to be charged, acquiring sensor data acquired by the robot through a camera and a laser radar in the moving process;
or after detecting that the robot needs to be charged, acquiring sensor data acquired by the camera and the laser radar of the robot in a static state.
7. The method of claim 6, wherein the acquiring sensor data acquired by the robot through the camera and lidar during movement comprises:
controlling the robot to move towards a preset charging pile position, and acquiring sensor data acquired by the robot through a camera and a laser radar in the moving process;
the preset charging pile position is a starting point position of a current driving path of the robot, or a registered charging pile position in a global map of the robot, or a potential charging pile position determined by the robot based on sensor data acquired by a camera and a laser radar in a moving process before charging is required.
8. The method of any of claims 1-5, wherein if the target feature matches, indicating that the number of matched features is equal to 1, the method further comprises:
determining a preliminary gesture of the charging pile based on the sensor data, and obtaining a preliminary gesture from the preliminary gesture and the preliminary position;
the controlling the robot to move to the preliminary position includes:
controlling the robot to move to a set distance in front of the charging pile indicated by the initial pose;
If the number of the matched features is not less than 2 in the target feature matching result, the method further comprises:
determining a final posture of the charging pile based on the sensor data, and obtaining a final posture from the final posture and the final position;
the controlling the robot to move to the final position includes:
and controlling the robot to move to a set distance in front of the charging pile indicated by the final pose.
9. A robotic charging device, comprising:
the sensor data acquisition unit is used for acquiring sensor data acquired by the robot through the camera and the laser radar after detecting that the robot needs to be charged;
the characteristic matching unit is used for matching the sensor data with the characteristics of the charging piles of a preset number to obtain a target characteristic matching result, wherein the preset number is not less than 2;
the preliminary position determining unit is used for determining the preliminary position of the charging pile based on the sensor data if the number of the matched features is equal to 1 in the target feature matching result, controlling the robot to move to the preliminary position, and returning to the step of executing the sensor data acquired by the sensor data acquiring unit through the camera and the laser radar;
The final position determining unit is used for determining the final position of the charging pile based on the sensor data and controlling the robot to move to the final position so as to realize pile charging if the number of the matched features is not less than 2 in the target feature matching result;
the charging pile features of the preset number comprise appearance features of charging piles and charging groove internal features of the charging piles;
the process of matching the sensor data with the preset number of charging pile features by the feature matching unit to obtain a target feature matching result comprises the following steps:
matching the sensor data acquired by the camera with the appearance characteristics of the charging pile to obtain a first characteristic matching result;
and matching the sensor data acquired by the laser radar with the internal features of the charging tank to obtain a second feature matching result, wherein the first feature matching result and the second feature matching result form the target feature matching result.
10. A robot, comprising: the robot comprises a robot body, a power module, a camera, a laser radar, a memory and a processor, wherein the power module, the camera, the laser radar, the memory and the processor are arranged on the robot body;
The memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the robot charging method according to any one of claims 1 to 8.
11. A robotic system comprising the robot of claim 10 and a charging stake;
the charging pile comprises a charging groove, and a power supply interface is arranged in the charging groove and is used for being matched with a charging interface on the robot to charge the robot;
at least two materials with different retroreflection coefficients are arranged in the charging groove.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310075460.XA CN115933706B (en) | 2023-02-07 | 2023-02-07 | Robot charging method and device, robot and robot system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310075460.XA CN115933706B (en) | 2023-02-07 | 2023-02-07 | Robot charging method and device, robot and robot system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115933706A CN115933706A (en) | 2023-04-07 |
| CN115933706B true CN115933706B (en) | 2023-07-25 |
Family
ID=86550985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310075460.XA Active CN115933706B (en) | 2023-02-07 | 2023-02-07 | Robot charging method and device, robot and robot system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115933706B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980320A (en) * | 2017-05-18 | 2017-07-25 | 上海思岚科技有限公司 | Robot charging method and device |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107040000A (en) * | 2016-02-04 | 2017-08-11 | 梁彦云 | Multifunctional DC charging pile |
| CN106239504B (en) * | 2016-07-29 | 2019-05-07 | 北京小米移动软件有限公司 | cleaning robot and control method thereof |
| KR101897730B1 (en) * | 2016-12-30 | 2018-09-12 | 엘지전자 주식회사 | Charging stating for robot cleaner |
| CN207257426U (en) * | 2017-09-29 | 2018-04-20 | 深圳悉罗机器人有限公司 | Charging pile and intelligent mobile robot identification charging pile system |
| CN108596084A (en) * | 2018-04-23 | 2018-09-28 | 宁波Gqy视讯股份有限公司 | A kind of charging pile automatic identifying method and device |
| CN111427361B (en) * | 2020-04-21 | 2023-08-08 | 浙江欣奕华智能科技有限公司 | Recharging method, recharging device and robot |
| CN113778068A (en) * | 2020-05-22 | 2021-12-10 | 苏州科瓴精密机械科技有限公司 | Self-moving device and charging station docking method and device, self-moving device, system and readable storage medium |
| CN114077246A (en) * | 2020-08-21 | 2022-02-22 | 苏州三六零机器人科技有限公司 | Recharging method and device for sweeping robot, sweeping robot and readable medium |
| CN112198871A (en) * | 2020-09-02 | 2021-01-08 | 创新工场(北京)企业管理股份有限公司 | Method and apparatus for autonomous charging of mobile robot |
| CN112467828A (en) * | 2020-11-12 | 2021-03-09 | 上海姜歌机器人有限公司 | Robot charging method and device |
| CN112947440A (en) * | 2021-02-06 | 2021-06-11 | 湖南擎谱数字科技有限公司 | Charging seat searching method for automatic charging of robot |
| CN113485357A (en) * | 2021-07-29 | 2021-10-08 | 山东新一代信息产业技术研究院有限公司 | Automatic pile returning and charging system and method for indoor robot |
| CN113696180A (en) * | 2021-08-31 | 2021-11-26 | 千里眼(广州)人工智能科技有限公司 | Robot automatic recharging method and device, storage medium and robot system |
| CN115097830A (en) * | 2022-06-23 | 2022-09-23 | 江苏眸视机器人科技有限公司 | Charging docking method and device, electronic equipment and storage medium |
-
2023
- 2023-02-07 CN CN202310075460.XA patent/CN115933706B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980320A (en) * | 2017-05-18 | 2017-07-25 | 上海思岚科技有限公司 | Robot charging method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115933706A (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106308685B (en) | cleaning robot and control method thereof | |
| CN108256574B (en) | Robot positioning method and device | |
| CN111989544B (en) | System and method for indoor vehicle navigation based on optical target | |
| CN111700546B (en) | Cleaning method of mobile robot and mobile robot | |
| CN107945233B (en) | Visual floor sweeping robot and refilling method thereof | |
| CN109901590B (en) | Recharging control method of desktop robot | |
| CN111743450B (en) | Recharging method for movable device and movable device | |
| Thompson et al. | A probabilistic model of human motion and navigation intent for mobile robot path planning | |
| CN108062098B (en) | Map construction method and system for intelligent robot | |
| CN106239504B (en) | cleaning robot and control method thereof | |
| CN108983761B (en) | Method and system for searching charging device by robot and robot | |
| CN113116224B (en) | Robot and control method thereof | |
| KR102024094B1 (en) | A moving-robot using artificial intelligence and a controlling method for the same | |
| CN113675923B (en) | Charging method, charging device and robot | |
| US10436878B2 (en) | Localising portable apparatus | |
| US20200334887A1 (en) | Mobile robots to generate occupancy maps | |
| WO2019113859A1 (en) | Machine vision-based virtual wall construction method and device, map construction method, and portable electronic device | |
| CN111625007A (en) | Method for identifying dynamic obstacle and mobile robot | |
| JP2019159520A (en) | Autonomous mobile device, autonomous mobile method and program | |
| CN111964680A (en) | Real-time positioning method of inspection robot | |
| US20210271257A1 (en) | Information processing device, optimum time estimation method, self-position estimation method, and record medium recording computer program | |
| CN115933706B (en) | Robot charging method and device, robot and robot system | |
| CN113536820B (en) | Position identification method and device and electronic equipment | |
| CN117077081A (en) | Human body pointing prediction method, device, robot and storage medium | |
| CN212044739U (en) | Positioning device and robot based on inertial data and visual characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |