CN109176605A - Robot data collection layer structure - Google Patents
Robot data collection layer structure Download PDFInfo
- Publication number
- CN109176605A CN109176605A CN201810823071.XA CN201810823071A CN109176605A CN 109176605 A CN109176605 A CN 109176605A CN 201810823071 A CN201810823071 A CN 201810823071A CN 109176605 A CN109176605 A CN 109176605A
- Authority
- CN
- China
- Prior art keywords
- kinect
- robot
- data collection
- layer structure
- camera
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The present invention discloses a kind of robot data collection layer structure, and supporting table is mounted on the trunk frame top of robot, and Kinect and IP Camera group are successively removably fixed in supporting table from bottom to top;The shell bottom face part outwardly convex of Kinect is formed at least two guide posts, and supporting table top end face part is recessed inwardly the guide groove for being formed with and matching with guide post;IP Camera group includes at least two IP Cameras, and the housing top end face part of Kinect, which is recessed inwardly, is formed at least two ring-shaped slide slots;IP Camera is horizontally disposed and middle part is formed with rotation axis straight down, and rotation the tip of the axis is rotatably connected on the shell of Kinect;The side movable end of IP Camera is formed with sliding bar straight down, and sliding bar bottom end can be slidably embedded in ring-shaped slide slot and can be fastened by locating part and positioned.Robot data collection layer structure assembling is compact, acquisition angles adjust efficient and convenient, flexibility height.
Description
Technical field
The present invention relates to robot fields, and in particular, to a kind of robot data collection layer structure.
Background technique
With the development of industrial automation, machine intelligence is received more and more attention, and wherein intelligent robot is even more quilt
It is known as following mainstream development direction.
And robot will once move, just inevitably involve understanding to environment, path planning, autonomous positioning,
Avoidance and anticollision etc., and the understanding and robot autonomous localization to environment be other function basis and primary research
Direction.
Existing researcher and application device realize robot autonomous localization using GPS, known using being manually entered
Environmental map and fabric structure figure replace robot autonomous study and building map, but it has following defect: firstly,
GPS positioning is only applicable to outdoor environment, is not suitable for indoor scene;Secondly, civilian GPS location precision is inadequate, machine is not achieved
The operating accuracy requirement of device people;Then, the mode that map is manually entered is not suitable for the scene that environment can change, such as: road envelope
Stifled, someone or article account for, original road is disconnected etc. by digging;Then, the mode that map is manually entered limits the work model of robot
It encloses, robot can only work in portion in the range that map determines, often changing a working environment, to require an accurate map defeated
Enter;Finally, the mode that map is manually entered causes robot that can not work in the environment and scene of no electronics shelves map.
Between above-mentioned various problem, the robot autonomous localization and environmental map of view-based access control model are constructed so that intelligent machine
The one important problem to be solved in device human hair exhibition road.Therefore, it is necessary to pass through visible image capturing head, binocular camera, laser thunder
Up to the information of the sensors such as rangefinder acquisition local environment, machine learning, mathematical modeling, image procossing and pattern-recognition etc. are used
Technology automatically analyzes and understands the environment that robot is presently in, it is established that environmental map, and make robot at any time can be
The current location of oneself is determined in the map.Moreover, the map established is also provided to other equipment or personnel use,
It will work in the present context use for robot future.As it can be seen that the mobility of robot data collection layer structure and flexibility are just
It is particularly significant.
Summary of the invention
The object of the present invention is to provide a kind of robot data collection layer structure, robot data collection layer structure assemblings
Compact, acquisition angles adjust efficient and convenient, flexibility height.
To achieve the goals above, the present invention provides a kind of robot data collection layer structure, including supporting table,
Kinect and IP Camera group;Wherein,
Supporting table is mounted on the trunk frame top of robot, and Kinect and IP Camera group are successively removable from bottom to top
It is fixed in supporting table with unloading;
The shell bottom face part outwardly convex of Kinect is formed at least two guide posts, supporting table top end face part to
Sunken inside is formed with the guide groove matched with guide post;
IP Camera group includes at least two IP Cameras, and the housing top end face part of Kinect is recessed inwardly to be formed
There are at least two ring-shaped slide slots;
IP Camera is horizontally disposed and middle part is formed with rotation axis straight down, and rotation the tip of the axis is rotatably coupled
On the shell of Kinect;The side movable end of IP Camera is formed with sliding bar straight down, and sliding bar bottom end is slidably
Ground is embedded in ring-shaped slide slot and can be fastened by locating part and positioned.
Preferably, two mutual poses of IP Camera are constant, and binocular vision sensing is constituted after calibration and is set
It is standby.
Preferably, the data of Kinect turn the USB3.0 that USB adapter is directly connected on the processor of robot by L and connect
Mouthful, for directly acquiring color video, deep video and infrared video.
Preferably, IP Camera accesses the router of robot interior by twisted pair, and processor is accessed from router
It accesses IP Camera and carries out video acquisition.
Preferably, one of guide post is round guide post, and corresponding guide groove is provided in round guide groove;Separately
One guide post is diamond shape guide post, and corresponding guide groove is set as diamond shape guide groove.
Preferably, the shell bottom face of Kinect is laid with one layer of buffer layer.
Preferably, buffer layer is spongy layer.
Preferably, rotation the tip of the axis is formed with universal ball end, is formed on the shell of Kinect and universal ball end activity
The universal ball-and-socket being embedded.
According to the above technical scheme, supporting table is mounted on to the trunk frame top of robot, Kinect and network shooting
Head group is successively removably fixed in supporting table from bottom to top;In this way, can individually be dismantled between each component repair and
Cleaning.And the shell bottom face part outwardly convex of Kinect is formed at least two guide posts, supporting table top end face part to
Sunken inside is formed with the guide groove matched with guide post.In this way, between Kinect and supporting table assembling be will not be because of direction
Mistake is adjusted repeatedly and is wasted time, and the stability when assembling positioning is mobile followed by robot is higher, will not occur
Dislocation.IP Camera group includes at least two IP Cameras, and the housing top end face part of Kinect, which is recessed inwardly, to be formed with
At least two ring-shaped slide slots;IP Camera is horizontally disposed and middle part is formed with rotation axis straight down, rotates the tip of the axis
It is rotatably connected on the shell of Kinect;The side movable end of IP Camera is formed with sliding bar straight down, sliding
Bar bottom end can be slidably embedded in ring-shaped slide slot and can be fastened by locating part and positioned.It can be according to need using the design
Unclamp locating part, driving sliding bar is slided along ring-shaped slide slot, pre- to drive IP Camera one end to turn to around rotation axis
It, then can fixed network camera direction using locating part repositioning if position.In adjustment process, two cameras
Not only the synchronous acquisition of same direction may be implemented, but also the synchronous acquisition and aggregation process of different directions may be implemented, significantly
Whole capture acquisition range is expanded, so that the data obtained after processing are more accurate.
Other features and advantages of the present invention will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
The drawings are intended to provide a further understanding of the invention, and constitutes part of specification, with following tool
Body embodiment is used to explain the present invention together, but is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the structural representation of the robot data collection layer structure in a kind of embodiment provided according to the present invention
Figure.
Description of symbols
1- supporting table 2-Kinect
3- IP Camera 4- ring-shaped slide slot
5- rotation axis 6- sliding bar
Specific embodiment
Below in conjunction with attached drawing, detailed description of the preferred embodiments.It should be understood that this place is retouched
The specific embodiment stated is merely to illustrate and explain the present invention, and is not intended to restrict the invention.
In the present invention, in the absence of explanation to the contrary, the noun of locality that " upper and lower, forward and backward " etc. is included in the term
Only represent orientation of the term under normal service condition, or be those skilled in the art understand that be commonly called as, and be not construed as pair
The limitation of the term.
Referring to Fig. 1, the present invention provides a kind of robot data collection layer structure, including supporting table 1, Kinect2 and network
Camera group;Wherein,
Supporting table 1 is mounted on the trunk frame top of robot, and Kinect2 and IP Camera group successively may be used from bottom to top
It is releasably fixed in supporting table 1;
The shell bottom face part outwardly convex of Kinect2 is formed at least two guide posts, 1 top end face part of supporting table
Be recessed inwardly the guide groove for being formed with and matching with guide post;
IP Camera group includes at least two IP Cameras 3, and the housing top end face part of Kinect2 is recessed inwardly shape
At there is at least two ring-shaped slide slots 4;
IP Camera 3 is horizontally disposed and middle part is formed with rotation axis 5 straight down, and the end of rotation axis 5 is rotationally
It is connected on the shell of Kinect2;The side movable end of IP Camera 3 is formed with sliding bar 6,6 bottom of sliding bar straight down
End can be slidably embedded in ring-shaped slide slot 4 and can be fastened by locating part and positioned.
Through the above technical solutions, supporting table 1 to be mounted on to the trunk frame top of robot, Kinect2 and network are taken the photograph
It is successively removably fixed in supporting table 1 from bottom to top as first 3 groups;It is tieed up in this way, can individually be dismantled between each component
It repairs and clears up.And the shell bottom face part outwardly convex of Kinect2 is formed at least two guide posts, 1 top end face of supporting table
Partially be recessed inwardly the guide groove for being formed with and matching with guide post.In this way, between Kinect2 and supporting table 1 assembling be will not
It wastes time because anisotropy adjusts repeatedly, and the stability when assembling positioning is mobile followed by robot is higher,
It will not misplace.3 groups of IP Camera include at least two IP Cameras 3, and the housing top end face part of Kinect2 is inside
Recess is formed at least two ring-shaped slide slots 4;IP Camera 3 is horizontally disposed and middle part is formed with rotation axis 5 straight down,
The end of rotation axis 5 is rotatably connected on the shell of Kinect2;The side movable end of IP Camera 3 shape straight down
At there is sliding bar 6,6 bottom end of sliding bar can be slidably embedded in ring-shaped slide slot 4 and can be fastened by locating part and positioned.It adopts
It can according to need release locating part with the design, driving sliding bar 6 is slided along ring-shaped slide slot 4, to drive IP Camera 3
One end turns to predeterminated position around rotation axis 5, then can 3 direction of fixed network camera using locating part repositioning.
In adjustment process, the synchronous acquisition of same direction had not only been may be implemented in two cameras, but also different directions may be implemented
Synchronous acquisition and aggregation process, expand whole capture acquisition range significantly, so that the data obtained after processing are more accurate.
In the present embodiment, in order to enable the capture collection effect of IP Camera 3 is more preferable, it is preferable that two networks
The mutual pose of camera 3 is constant, and binocular vision sensing equipment is constituted after calibration.
It is directly connected on the processor of robot further, it is preferable to which the data of Kinect2 turn USB adapter by L
USB3.0 interface, for directly acquiring color video, deep video and infrared video.
IP Camera 3 accesses the router of robot interior by twisted pair, and processor is from router access net
Network camera 3 carries out video acquisition.
In addition, in order to play the limit effect mutually formed between guide post and guide groove as much as possible, it is preferable that wherein
One guide post is round guide post, and corresponding guide groove is provided in round guide groove;Another guide post is led for diamond shape
Xiang Zhu, corresponding guide groove are set as diamond shape guide groove.
When the robot data collection layer structure is squeezed or is jolted by external force in assembling or use process, meeting
It collides with adjacent contact surface, both in order to prevent impaired deformation occurs is unfavorable for subsequent assembly use, it is preferable that
The shell bottom face of Kinect2 is laid with one layer of buffer layer.
Above-mentioned buffer layer can be any flexible material common in this field and be made, but from convenient for materials and drop
From the point of view of low use replacement cost, it is preferable that buffer layer is spongy layer.
In addition, in order to enable the bigger wider model of the acquisition angles of the robot data collection layer structure, further optimizes
Adjust the flexibility during angle, it is preferable that the end of rotation axis 5 is formed with universal ball end, is formed on the shell of Kinect2
There is the universal ball-and-socket being embedded with universal ball end activity.
It is described the prefered embodiments of the present invention in detail above in conjunction with attached drawing, still, the present invention is not limited to above-mentioned realities
The detail in mode is applied, within the scope of the technical concept of the present invention, a variety of letters can be carried out to technical solution of the present invention
Monotropic type, these simple variants all belong to the scope of protection of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the present invention to it is various can
No further explanation will be given for the combination of energy.
In addition, various embodiments of the present invention can be combined randomly, as long as it is without prejudice to originally
The thought of invention, it should also be regarded as the disclosure of the present invention.
Claims (8)
1. a kind of robot data collection layer structure, which is characterized in that including supporting table (1), Kinect (2) and IP Camera
Group;Wherein,
The supporting table (1) is mounted on the trunk frame top of the robot, the Kinect (2) and the IP Camera
Group is successively removably fixed on the supporting table (1) from bottom to top;
The shell bottom face part outwardly convex of the Kinect (2) is formed at least two guide posts, supporting table (1) top
End face part is recessed inwardly the guide groove for being formed with and matching with the guide post;
The IP Camera group includes at least two IP Cameras (3), the housing top end face part of the Kinect (2) to
Sunken inside is formed at least two ring-shaped slide slots (4);
The IP Camera (3) is horizontally disposed and middle part is formed with rotation axis (5) straight down, the end of the rotation axis (5)
End is rotatably connected on the shell of (2) the Kinect;The side movable end of the IP Camera (3) shape straight down
At having sliding bar (6), sliding bar (6) bottom end can be slidably embedded in the ring-shaped slide slot (4) and can pass through limit
Position part fastening positioning.
2. robot data collection layer structure according to claim 1, which is characterized in that two IP Cameras
(3) mutual pose is constant, and binocular vision sensing equipment is constituted after calibration.
3. robot data collection layer structure according to claim 1, which is characterized in that the data of the Kinect (2)
Turn the USB3.0 interface that USB adapter is directly connected on the processor of the robot by L, for directly acquiring colored view
Frequently, deep video and infrared video.
4. robot data collection layer structure according to claim 3, which is characterized in that the IP Camera (3) is logical
Cross the router that twisted pair accesses the robot interior, the processor is from network shooting described in the router access
Head (3) carries out video acquisition.
5. robot data collection layer structure according to claim 1, which is characterized in that one of them described guide post is
Round guide post, the corresponding guide groove are provided in round guide groove;Another described guide post is diamond shape guide post,
The corresponding guide groove is set as diamond shape guide groove.
6. robot data collection layer structure according to claim 1, which is characterized in that the shell of the Kinect (2)
Bottom face is laid with one layer of buffer layer.
7. robot data collection layer structure according to claim 6, which is characterized in that the buffer layer is spongy layer.
8. robot data collection layer structure according to claim 1, which is characterized in that the end of the rotation axis (5)
It is formed with universal ball end, is formed with the universal ball-and-socket being embedded with the universal ball end activity on the shell of the Kinect (2).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810823071.XA CN109176605A (en) | 2018-07-25 | 2018-07-25 | Robot data collection layer structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810823071.XA CN109176605A (en) | 2018-07-25 | 2018-07-25 | Robot data collection layer structure |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109176605A true CN109176605A (en) | 2019-01-11 |
Family
ID=64936860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810823071.XA Withdrawn CN109176605A (en) | 2018-07-25 | 2018-07-25 | Robot data collection layer structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109176605A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202582585U (en) * | 2012-03-07 | 2012-12-05 | 陶重犇 | Indoor multipurpose experimental platform for mobile robot |
CN104536445A (en) * | 2014-12-19 | 2015-04-22 | 深圳先进技术研究院 | Mobile navigation method and system |
KR20150097049A (en) * | 2014-02-17 | 2015-08-26 | 경북대학교 산학협력단 | self-serving robot system using of natural UI |
CN106652026A (en) * | 2016-12-23 | 2017-05-10 | 安徽工程大学机电学院 | Three-dimensional space automatic calibration method based on multi-sensor fusion |
CN206389477U (en) * | 2017-01-20 | 2017-08-08 | 深圳市中保国安实业有限公司 | Camera adjusts fixing device and video monitoring system |
-
2018
- 2018-07-25 CN CN201810823071.XA patent/CN109176605A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202582585U (en) * | 2012-03-07 | 2012-12-05 | 陶重犇 | Indoor multipurpose experimental platform for mobile robot |
KR20150097049A (en) * | 2014-02-17 | 2015-08-26 | 경북대학교 산학협력단 | self-serving robot system using of natural UI |
CN104536445A (en) * | 2014-12-19 | 2015-04-22 | 深圳先进技术研究院 | Mobile navigation method and system |
CN106652026A (en) * | 2016-12-23 | 2017-05-10 | 安徽工程大学机电学院 | Three-dimensional space automatic calibration method based on multi-sensor fusion |
CN206389477U (en) * | 2017-01-20 | 2017-08-08 | 深圳市中保国安实业有限公司 | Camera adjusts fixing device and video monitoring system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN205219101U (en) | Service robot of family | |
Lee et al. | Wearable RGBD indoor navigation system for the blind | |
US9552056B1 (en) | Gesture enabled telepresence robot and system | |
CN108885459A (en) | Air navigation aid, navigation system, mobile control system and mobile robot | |
Hyams et al. | Cooperative navigation of micro-rovers using color segmentation | |
JP2007098567A (en) | Autonomous control type robot and its control device | |
US20210325889A1 (en) | Method of redefining position of robot using artificial intelligence and robot of implementing thereof | |
Valenti et al. | An autonomous flyer photographer | |
CN108965812A (en) | Robot panoramic view data acquisition layer structure | |
CN206399422U (en) | Multifunctional vision sensor and mobile robot | |
JP6134894B2 (en) | Robot control system and robot | |
CN106671101A (en) | Intelligent shooting robot | |
Li et al. | Multiple RGB-D sensor-based 3-D reconstruction and localization of indoor environment for mini MAV | |
CN109176605A (en) | Robot data collection layer structure | |
CN111531560B (en) | Patrol and examine robot applied to indoor and outdoor environment of transformer substation | |
CN109079855A (en) | Robot data collection layer | |
CN108838998A (en) | Novel robot data collection layer structure | |
ES2895461T3 (en) | Object recognition procedure and system by analyzing digital image signals of a scene | |
JP2006051864A (en) | Automatic flight controlling system, and automatic flight controlling method | |
CN109202931A (en) | Robot head parts | |
CN108838997A (en) | Novel wooden robot | |
CN110271015A (en) | A kind of adjustable active vision SLAM mobile platform of video camera posture | |
CN109304716A (en) | Robot system and sharing method are shared by a kind of sharing robot | |
CN109164800A (en) | Highly machine personal data acquisition layer | |
Carnegie et al. | A human-like semi autonomous mobile security robot |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190111 |