CN110065064A - A kind of robot sorting control method - Google Patents
A kind of robot sorting control method Download PDFInfo
- Publication number
- CN110065064A CN110065064A CN201810069509.XA CN201810069509A CN110065064A CN 110065064 A CN110065064 A CN 110065064A CN 201810069509 A CN201810069509 A CN 201810069509A CN 110065064 A CN110065064 A CN 110065064A
- Authority
- CN
- China
- Prior art keywords
- target object
- robot
- control method
- location information
- target
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- 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
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- 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)
- Multimedia (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of robots to sort control method, comprising: constructs the target tracking model of robot and the visual signature map of target object, and determines initial position of the initial target object on the visual signature map;Target object image is acquired and is handled, physical location of the laser scanning target object on the visual signature map is passed through;The mode of operation of robot is detected and identified with the method for image procossing, the target object under acquisition device people's operating process, and the target object is obtained in the location information at the moment;It is accurately positioned the distance between machine people and target object, and target object state is predicted, the location information to target object in subsequent time is predicted;The running track of the end effector of planning robot;The end effector of control robot is acted according to the motion profile planned.
Description
Technical field
The present invention relates to robotic technology fields more particularly to a kind of robot to sort control method.
Background technique
The combination of industrial robot and vision is following developing direction, at present in the vision of industrial robot field application
System is generally divided into two classes: one kind is using smart camera, i.e. camera and processor integrates, and vision algorithm operates in place
It manages in device, smart camera configures upper computer software module, may be implemented to calculate in smart camera by upper computer software module
Method input parameter does corresponding configuration;It is to use general industry camera, and configure PC machine there are also one kind, general camera only has camera
And camera lens, without processor, vision algorithm is operated in above PC machine.
Two class vision systems respectively have advantage and disadvantage: the first kind is relatively high using smart camera integrated level, but due to camera size
It cannot do very greatly, have higher requirements in this way for the size of processor, processing capacity, heat dissipation etc., increase the cost of camera, separately
Outside, this smart camera size and weight are bigger, if being placed on robot end, design robot end and bear a heavy burden
It is a test, application is more inconvenient;It is another kind of high without smart camera using general industry camera integrated level, but due to list
It is solely configured to the PC machine of algorithm operation, although computing capability is stronger, cost and smart camera are similar.
Industrial robot can apish partial act, according to different execution programs, track and require realize grab automatically
The electro-mechanical system of workpiece and operational instrument is taken, carries, it has the characteristics that intelligent and automation, can significantly improve life
Efficiency is produced, is improved working conditions, the application of industrial robot will greatly improve the technical level of China's manufacturing industry, automation journey
Degree, product competitiveness, promote manufacturing transition and upgrade, bring the raising of entire industrial level;Robot vision technology is exactly
The video conversion of optical electron system photographs at electronic image and is transmitted to computer system progress image procossing, is realized to object
The identification of the features such as color, size, shape, the position of body, and recognition result is sent to computer to control other executing agencies
The industrial system of execution, since it has, non-contact, accuracy of identification is high, speed is fast, high degree of automation, easy and other are
The features such as system is integrated, has been widely used at present in light industry, chemical industry, weaving, medical treatment, electronics, automobile and other industries, by robot and machine
Device vision system combines, and is a kind of very promising application.
Industrial robot can be used for flexible sorting, but this in flexible sort process, and the accuracy of robot is not
Often there is deviation in height, causes the inaccuracy of segregating articles, affects the progress of production.
Therefore, accuracy of the robot in flexible sort process how is improved, becomes those skilled in the art and urgently solves
Technical problem certainly.
Summary of the invention
The object of the present invention is to provide a kind of robots to sort control method, can be improved robot in flexible sort process
In accuracy, enable robot to be accurately sorted to target object.
To achieve the goals above, the present invention provides a kind of robots to sort control method, comprising the following steps:
The target tracking model of robot and the visual signature map of target object are constructed, and determines initial target object described
Initial position on visual signature map;
Target object image is acquired and is handled, reality of the laser scanning target object on the visual signature map is passed through
Border position;
The mode of operation of robot is detected and identified with the method for image procossing, the mesh under acquisition device people's operating process
Object is marked, and obtains the target object in the location information at the moment;
It is accurately positioned the distance between machine people and target object, and target object state is predicted, is existed to target object
The location information of subsequent time is predicted;
Track the position of target object next state value and subsequent time in time according to prediction result;
According to the status information of the current state information of target object and prediction, the position at current location information and lower a moment is believed
Breath, the running track of the end effector of planning robot;
The end effector of control robot is acted according to the motion profile planned.
Preferably, target object image is acquired and is handled by visual sensor.
Preferably, before target object image is acquired and is handled, robot is obtained by visual sensor
The location information and status information of end effector, to determine the initial position message and initial shape of the end effector of robot
State.
Preferably, the visual sensor obtains the two width scene images for containing the target object, then passes through two-value
After change, edge extracting, the detection of profile boundary rectangle, ellipses detection, oval similarity calculation, oval center of gravity calculation, described in acquisition
The parallax of the target object in two width scene images, to obtain the status information of target object.
Preferably, the physical location by laser scanning target object on the visual signature map, comprising: logical
Three laser scanners are crossed, the location information of target object are obtained by triangulation, and location information is marked in the view
Feel on characteristics map.
Preferably, the visual sensor establishes mesh based on the track algorithm of robot working background color combining and edge
Mark tracing model;And it is detected and is identified to the target object under the mode of operation of robot using frame differential method;
Calculate the distance between robot and target object;Motion state based on Kalman filtering algorithm prediction target object.
Preferably, the running track of the end effector of the planning robot;It include: that the motion profile is straight by three
" door " zag trajectory of line segment process, the height of " door " zag trajectory are higher than the height of barrier.
Robot provided by the invention sorts control method, passes through acquisition robot, the original state of target object and just
The beginning position and status information and location information at lower a moment, accurately cooks up the motion profile of end effector of robot, enough
Accuracy of the robot in flexible sort process is improved, robot is enabled accurately to be sorted to target object.
Detailed description of the invention
Fig. 1 is a kind of flow diagram for specific embodiment that robot provided by the invention sorts control method.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Fig. 1 is please referred to, Fig. 1 is a kind of process for specific embodiment that robot provided by the invention sorts control method
Schematic diagram.
As shown in Figure 1, the present invention provides a kind of robots to sort control method, include the following steps.
The target tracking model of robot and the visual signature map of target object are constructed, and determines that initial target object exists
Initial position on the visual signature map;
Target object image is acquired and is handled, reality of the laser scanning target object on the visual signature map is passed through
Border position;
The mode of operation of robot is detected and identified with the method for image procossing, the mesh under acquisition device people's operating process
Object is marked, and obtains the target object in the location information at the moment;
It is accurately positioned the distance between machine people and target object, and target object state is predicted, is existed to target object
The location information of subsequent time is predicted;
Track the position of target object next state value and subsequent time in time according to prediction result;
According to the status information of the current state information of target object and prediction, the position at current location information and lower a moment is believed
Breath, the running track of the end effector of planning robot;
The end effector of control robot is acted according to the motion profile planned.
In specific scheme, target object state includes the posture of target object and the motion state of target object, such as
Shape, movement velocity, acceleration of motion of target object etc..
Robot provided by the invention sorts control method, passes through acquisition robot, the original state of target object and just
The beginning position and status information and location information at lower a moment, accurately cooks up the motion profile of end effector of robot, enough
Accuracy of the robot in flexible sort process is improved, robot is enabled accurately to be sorted to target object.
In preferred scheme, target object image is acquired and is handled by visual sensor.
In preferred scheme, before target object image is acquired and is handled, machine is obtained by visual sensor
The location information and status information of the end effector of device people, with determine robot end effector initial position message and
Original state.
In preferred scheme, the visual sensor obtains the two width scene images for containing the target object, then passes through
After crossing binaryzation, edge extracting, the detection of profile boundary rectangle, ellipses detection, oval similarity calculation, oval center of gravity calculation, obtain
The parallax of the target object in the two width scene image is obtained, to obtain the status information of target object.
In preferred scheme, the physical location by laser scanning target object on the visual signature map,
It include: the location information of target object to be obtained by triangulation, and location information label is existed by three laser scanners
On the visual signature map.
In preferred scheme, track algorithm of the visual sensor based on robot working background color combining and edge
Establish target tracking model;And using frame differential method to the target object under the mode of operation of robot carry out detection and
Identification;Calculate the distance between robot and target object;Movement shape based on Kalman filtering algorithm prediction target object
State.
In preferred scheme, the running track of the end effector of the planning robot;Include: the motion profile by
" door " zag trajectory of three straightway processes, the height of " door " zag trajectory are higher than the height of barrier.This scheme
It can allow robot smoothly across barrier, in case robot is influenced by barrier during the motion.
Structure, feature and effect of the invention, the above institute are described in detail based on the embodiments shown in the drawings
Only presently preferred embodiments of the present invention is stated, but the present invention does not limit the scope of implementation as shown in the drawings, it is all according to structure of the invention
Think made change or equivalent example modified to equivalent change, when not going beyond the spirit of the description and the drawings,
It should all be within the scope of the present invention.
Claims (7)
1. a kind of robot sorts control method, which comprises the following steps:
The target tracking model of robot and the visual signature map of target object are constructed, and determines initial target object described
Initial position on visual signature map;
Target object image is acquired and is handled, reality of the laser scanning target object on the visual signature map is passed through
Border position;
The mode of operation of robot is detected and identified with the method for image procossing, the mesh under acquisition device people's operating process
Object is marked, and obtains the target object in the location information at the moment;
It is accurately positioned the distance between machine people and target object, and target object state is predicted, is existed to target object
The location information of subsequent time is predicted;
Track the position of target object next state value and subsequent time in time according to prediction result;
According to the status information of the current state information of target object and prediction, the position at current location information and lower a moment is believed
Breath, the running track of the end effector of planning robot;
The end effector of control robot is acted according to the motion profile planned.
2. robot according to claim 1 sorts control method, which is characterized in that by visual sensor to target pair
As image is acquired and is handled.
3. robot according to claim 2 sorts control method, which is characterized in that adopted to target object image
Before collection and processing, the location information and status information of the end effector of robot are obtained, by visual sensor with determination
The initial position message and original state of the end effector of robot.
4. robot according to claim 3 sorts control method, which is characterized in that the visual sensor acquisition contains
Two width scene images of the target object, then by binaryzation, edge extracting, the detection of profile boundary rectangle, ellipses detection,
After oval similarity calculation, oval center of gravity calculation, the parallax of the target object in the two width scene image is obtained, to obtain
Obtain the status information of target object.
5. robot according to claim 1 sorts control method, which is characterized in that described to pass through laser scanning target pair
As the physical location on the visual signature map, comprising: by three laser scanners, obtain target by triangulation
The location information of object, and by location information label on the visual signature map.
6. robot according to claim 3 sorts control method, which is characterized in that the visual sensor is based on machine
The track algorithm at people's working background color combining and edge establishes target tracking model;And using frame differential method to machine
Target object under the mode of operation of people is detected and is identified;Calculate the distance between robot and target object;It is based on
The motion state of Kalman filtering algorithm prediction target object.
7. robot according to claim 1 sorts control method, which is characterized in that hold the end of the planning robot
The running track of row device;It include: " door " zag trajectory of the motion profile by three straightway processes, " door " the font rail
The height of mark is higher than the height of barrier.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810069509.XA CN110065064A (en) | 2018-01-24 | 2018-01-24 | A kind of robot sorting control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810069509.XA CN110065064A (en) | 2018-01-24 | 2018-01-24 | A kind of robot sorting control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110065064A true CN110065064A (en) | 2019-07-30 |
Family
ID=67365581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810069509.XA Pending CN110065064A (en) | 2018-01-24 | 2018-01-24 | A kind of robot sorting control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110065064A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111804605A (en) * | 2020-07-13 | 2020-10-23 | 东莞市恒明机器人自动化有限公司 | Automatic packing unit of injection molding machine |
CN114083533A (en) * | 2021-11-09 | 2022-02-25 | 广州富港生活智能科技有限公司 | Data processing method and device based on mechanical arm |
WO2023124735A1 (en) * | 2021-12-31 | 2023-07-06 | 广东美的白色家电技术创新中心有限公司 | Robot control method, apparatus and system and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4633414A (en) * | 1982-11-26 | 1986-12-30 | Hitachi, Ltd. | Robot operation control system |
CN101226640A (en) * | 2007-12-21 | 2008-07-23 | 西北工业大学 | Method for capturing movement based on multiple binocular stereovision |
CN101434066A (en) * | 2008-10-20 | 2009-05-20 | 北京理工大学 | Method and platform for predicating teleoperation of robot |
CN106610666A (en) * | 2015-10-22 | 2017-05-03 | 沈阳新松机器人自动化股份有限公司 | Assistant robot based on binocular vision, and control method of assistant robot |
CN107206601A (en) * | 2014-10-24 | 2017-09-26 | 费洛有限公司 | Customer service robot and related systems and methods |
CN107363837A (en) * | 2017-09-08 | 2017-11-21 | 桂林加宏汽车修理有限公司 | A kind of method of manipulator control system and control machinery hand captures object |
-
2018
- 2018-01-24 CN CN201810069509.XA patent/CN110065064A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4633414A (en) * | 1982-11-26 | 1986-12-30 | Hitachi, Ltd. | Robot operation control system |
CN101226640A (en) * | 2007-12-21 | 2008-07-23 | 西北工业大学 | Method for capturing movement based on multiple binocular stereovision |
CN101434066A (en) * | 2008-10-20 | 2009-05-20 | 北京理工大学 | Method and platform for predicating teleoperation of robot |
CN107206601A (en) * | 2014-10-24 | 2017-09-26 | 费洛有限公司 | Customer service robot and related systems and methods |
CN106610666A (en) * | 2015-10-22 | 2017-05-03 | 沈阳新松机器人自动化股份有限公司 | Assistant robot based on binocular vision, and control method of assistant robot |
CN107363837A (en) * | 2017-09-08 | 2017-11-21 | 桂林加宏汽车修理有限公司 | A kind of method of manipulator control system and control machinery hand captures object |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111804605A (en) * | 2020-07-13 | 2020-10-23 | 东莞市恒明机器人自动化有限公司 | Automatic packing unit of injection molding machine |
CN111804605B (en) * | 2020-07-13 | 2021-03-19 | 东莞市恒明机器人自动化有限公司 | Automatic packing unit of injection molding machine |
CN114083533A (en) * | 2021-11-09 | 2022-02-25 | 广州富港生活智能科技有限公司 | Data processing method and device based on mechanical arm |
CN114083533B (en) * | 2021-11-09 | 2024-04-09 | 广州富港生活智能科技有限公司 | Data processing method and device based on mechanical arm |
WO2023124735A1 (en) * | 2021-12-31 | 2023-07-06 | 广东美的白色家电技术创新中心有限公司 | Robot control method, apparatus and system and storage medium |
CN116408790A (en) * | 2021-12-31 | 2023-07-11 | 广东美的白色家电技术创新中心有限公司 | Robot control method, device, system and storage medium |
CN116408790B (en) * | 2021-12-31 | 2024-07-16 | 广东美的白色家电技术创新中心有限公司 | Robot control method, device, system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Controlling object hand-over in human–robot collaboration via natural wearable sensing | |
Romero-Ramire et al. | Fractal markers: A new approach for long-range marker pose estimation under occlusion | |
US20220016765A1 (en) | Method and system for object grasping | |
EP3951643A1 (en) | Gesture trajectory recognition method, based on hand speed and trajectory distribution, for following robot | |
Bhuyan et al. | Hand pose recognition using geometric features | |
CN110065064A (en) | A kind of robot sorting control method | |
KR20210076962A (en) | Smart car motion control method and device, device and storage medium | |
Chao et al. | Deep learning‐based grasp‐detection method for a five‐fingered industrial robot hand | |
Kim et al. | An Innovative Automated Robotic System based on Deep Learning Approach for Recycling Objects. | |
US11478922B2 (en) | Robot teaching device and robot system | |
Michel et al. | Gesture recognition supporting the interaction of humans with socially assistive robots | |
KR20120089948A (en) | Real-time gesture recognition using mhi shape information | |
CN115070781A (en) | Object grabbing method and two-mechanical-arm cooperation system | |
D'Avella et al. | Multimodal grasp planner for hybrid grippers in cluttered scenes | |
El-Sawah et al. | A framework for 3D hand tracking and gesture recognition using elements of genetic programming | |
Liu et al. | Latest developments of gesture recognition for human–robot collaboration | |
Chang et al. | Real-time object coordinate detection and manipulator control using rigidly trained convolutional neural networks | |
Lei et al. | An investigation of applications of hand gestures recognition in industrial robots | |
Bose et al. | In-situ enhanced anchor-free deep CNN framework for a high-speed human-machine interaction | |
Terreran et al. | Multi-view human parsing for human-robot collaboration | |
Li et al. | Tactile Sensing, Skill Learning, and Robotic Dexterous Manipulation | |
Zoghlami et al. | Tracking body motions in order to guide a robot using the time of flight technology. | |
Algabri et al. | Online boosting-based target identification among similar appearance for person-following robots | |
Wang et al. | Robust grasp detection with incomplete point cloud and complex background | |
Sileo | Collaborative and Cooperative Robotics Applications using Visual Perception |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190730 |
|
RJ01 | Rejection of invention patent application after publication |