CN116197918B - Manipulator control system based on action record analysis - Google Patents
Manipulator control system based on action record analysis Download PDFInfo
- Publication number
- CN116197918B CN116197918B CN202310495295.3A CN202310495295A CN116197918B CN 116197918 B CN116197918 B CN 116197918B CN 202310495295 A CN202310495295 A CN 202310495295A CN 116197918 B CN116197918 B CN 116197918B
- Authority
- CN
- China
- Prior art keywords
- manipulator
- module
- track
- programming
- node
- 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
- 230000009471 action Effects 0.000 title claims abstract description 11
- 230000033001 locomotion Effects 0.000 claims abstract description 63
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000008676 import Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000004048 modification Effects 0.000 abstract description 2
- 238000012986 modification Methods 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 2
- 230000017105 transposition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of manipulator position correction, in particular to a manipulator control system based on action record analysis. The device comprises an operation programming processing unit, a manipulator operation detection unit and a programming regulation unit. According to the invention, the working state of the manipulator is shot through the arranged manipulator operation detection unit, the three-dimensional modeling of the motion state of the manipulator is carried out according to the shot content part, the operation track of the movable node in the actual operation of the manipulator is obtained according to the content of the three-dimensional modeling, the coding track is compared with the operation track of the movable node in the actual operation of the manipulator through the programming regulation unit, whether the operation track of the manipulator changes is determined, and after the operation track of the manipulator changes, the programming regulation unit corrects the coding content, and the operation programming processing unit recodes the manipulator according to the content corrected by the programming regulation unit, so that the operation track after the modification of the manipulator meets the working requirements.
Description
Technical Field
The invention relates to the technical field of manipulator position correction, in particular to a manipulator control system based on action record analysis.
Background
The manipulator is an automatic operation device which can simulate some action functions of a human hand and an arm and is used for grabbing and carrying objects or operating tools according to fixed procedures, manual operation is replaced by the manipulator, production of products is accelerated, in the working process of the manipulator, the manipulator can execute according to a program appointed in advance, the manipulator moves according to the programming requirement, the movement track of the manipulator is fixed, and repeated and fine work can be carried out.
In the process of the manipulator in work, certain deviation can appear in the part of manipulator inside because of structural wear, and then makes the orbit of manipulator appear certain change, and the orbit of manipulator appears changing the back, can influence the precision of manipulator work, and when the manipulator was carried out is accurate during work, the orbit of manipulator orbit change can lead to the precision reduction of manipulator work, and then influences the production that produces.
When the movement track changes in the process of the manipulator work, workers cannot timely find that the workers can only observe products produced by the manipulator, so that unqualified products can be caused, and in order to reduce the unqualified quantity of the products caused by the track changes in the production process of the manipulator, the movement track of the manipulator is detected and corrected by a manipulator control system based on action record analysis, so that the manipulator can normally produce the products.
Disclosure of Invention
The present invention is directed to a robot control system based on motion log analysis, which solves the above-mentioned problems.
In order to achieve the above object, the present invention provides a robot control system based on action record analysis, comprising an operation programming processing unit, a robot operation detecting unit and a programming control unit;
the operation programming processing unit programs the operation track of the manipulator according to the task of the manipulator, and the manipulator operates according to the programmed interior;
the manipulator operation detection unit captures images of the manipulator working according to the programming content, performs three-dimensional modeling of the working state of the manipulator according to the captured images, and simultaneously searches the operation track of each node of the manipulator according to the established three-dimensional model;
the programming regulation and control unit compares the running track of each node of the manipulator, which is programmed and regulated by the running programming processing unit, with the running track of each node of the manipulator, which is found by the manipulator running detection unit, and checks the difference of the running tracks of each node of the manipulator;
the programming regulation and control unit corrects data on a programmed track of the moving manipulator according to the movement performed by the operation programming processing unit and the movement track formed by modeling of the manipulator operation detection unit, and transmits the corrected data to the operation programming processing unit, so that the operation programming processing unit corrects the movement of the manipulator according to the corrected data, meanwhile, the manipulator operation detection unit performs three-dimensional modeling on the manipulator after the data correction, and then the programming regulation and control unit determines the movement track of the manipulator.
As a further improvement of the technical scheme, the operation programming processing unit comprises a work task learning module, a manipulator operation programming module and an operation module;
the work task learning module acquires tasks to be completed by the manipulator and a path to be passed through for completing the tasks;
the manipulator operation programming module is used for programming corresponding instructions according to the operation track of the manipulator acquired by the work task learning module, wherein the programmed content is the track of the manipulator motion, and the manipulator finishes the specified operation on the object through the corresponding content of the programming;
the operation module imports the content programmed by the manipulator operation programming module into the manipulator, so that the manipulator executes the programmed content.
As a further improvement of the technical scheme, the manipulator operation detection unit comprises a manipulator operation photographing module, an operation track modeling module, an actual operation planning module and a manipulator node operation track searching module;
when the manipulator operation photographing module receives the control operation of the manipulator by the operation module, photographing the operated manipulator by a camera to obtain the working state of the manipulator and the operation condition of the manipulator during operation;
the moving track modeling module processes the image acquired by the manipulator moving photographing module and performs three-dimensional modeling of the mechanical working state according to the mechanical working state in the image;
the actual operation planning module plans the operation condition of the actual operation of the manipulator according to the models of the plurality of mechanical hand operation states modeled by the operation track modeling module;
and the manipulator node running track searching module searches the running track of each movable node of the manipulator according to the whole running track of the manipulator planned by the actual running planning module, and acquires the running track of each movable node on the manipulator after the appointed operation is completed.
As a further improvement of the technical scheme, when the running track modeling module carries out three-dimensional modeling on the manipulator, firstly, the three-dimensional coordinates of the manipulator need to be obtained, the three-dimensional coordinates of the manipulator are calculated by adopting a three-dimensional photogrammetry algorithm, and the formula content is as follows:
(1) let the three-dimensional coordinates of the manipulator beThe corresponding image points are respectively on the two imagesAnd->;
(2) Let the coordinates of the camera reference points in space be respectivelyAnd->And an internal reference matrix of the camera +.>And->;
(3) According to the principle of triangulation positioning, the following two formulas are obtained:
;
;
wherein,,and->Representing camera rotation matrix, +.>And->Representing a camera position matrix, < >>Transposition of the representative vector;
(4) acquiring the three-dimensional coordinates of the manipulator according to the two formulas in (3);
(5) Repeating the steps (1), (2), (3) and (4) to obtain the three-dimensional coordinates of each corresponding point on the manipulator.
As a further improvement of the technical scheme, after the three-dimensional coordinates of the manipulator are obtained, the manipulator is subjected to three-dimensional modeling according to the three-dimensional coordinates of the manipulator, and working state models of the manipulator at different moments are obtained.
As a further improvement of the technical scheme, after the operation track modeling module obtains the operation state models of the manipulator at different moments, the actual operation planning module performs the planning of the actual operation track of the manipulator according to the models modeled by the operation track modeling module, and the planning steps are as follows:
step one: acquiring all models of the three-dimensional modeling of the manipulator by the running track modeling module, and sequencing the models according to the photographing time of the corresponding photos of the models;
step two: and judging the motion state of the manipulator according to the sequence of the model sequencing, acquiring the motion sequence of the manipulator, and planning the actual motion condition of the manipulator according to the motion sequence of the manipulator.
As a further improvement of the technical scheme, the manipulator node running track searching module reads the actual movement condition of the manipulator planned in the actual running planning module, searches the movement state of the movable node of the manipulator according to the actual movement condition of the manipulator, and plans the running track of the movable node of the manipulator according to the found movement state of the movable node of the manipulator.
As a further improvement of the technical scheme, the programming regulation and control unit comprises a programming track searching module, a track running comparison module, a difference accounting module and a correction feedback module;
the programming track searching module acquires programming information of the manipulator operation in the manipulator operation programming module, and acquires the operation track of the movable node of the manipulator in the programming content according to the programming content;
the track operation comparison module compares the programming track of the movable node of the manipulator obtained by the programming track searching module with the operation track of the movable node of the manipulator planned by the manipulator node operation track searching module, and determines whether the two tracks have position deviation;
the difference accounting module is used for planning a comparison result of the running track of the movable node of the manipulator according to the programming track of the track running comparison module and the running track searching module of the node of the manipulator, and calculating the difference data between the two tracks;
the correction feedback module receives the data difference calculated by the difference accounting module, and calculates difference data of the movement track of the manipulator node, which is converted into a programming track by the movement track searching module of the manipulator movable node.
As a further improvement of the present technical solution, when the difference accounting module calculates the data of the difference between the two tracks, there are two cases:
case one: the programming track and the moving track of the manipulator node are not different in data between the moving track of the manipulator moving node, which is planned by the manipulator node moving track searching module, and the difference calculating module does not calculate the difference of the moving track of the manipulator moving node, which is planned by the manipulator node moving track searching module;
and a second case: the difference accounting module calculates difference data of the moving track of the manipulator node, which is planned by the moving track searching module of the manipulator movable node, converted to the programming track, and transmits the calculated difference data to the correction feedback module.
As a further improvement of the technical scheme, the operation programming processing unit further comprises an operation correction module, the operation correction module receives the difference data of the operation track of the manipulator movable node, which is converted into the programming track, and transmitted by the correction feedback module, and the difference data are transmitted to the manipulator operation programming module, the manipulator operation programming module reprograms the operation track of the manipulator according to the difference data, and transmits the programmed content to the operation module, and the operation module controls the manipulator according to the newly programmed content.
Compared with the prior art, the invention has the beneficial effects that:
in the manipulator control system based on the action record analysis, the working state of the manipulator is shot through the arranged manipulator running detection unit, the three-dimensional modeling of the motion state of the manipulator is carried out according to the shot content part, the running track of the movable node in the actual working of the manipulator is obtained according to the content of the three-dimensional modeling, the coding track is compared with the running track of the movable node in the actual working of the manipulator through the programming regulation unit, whether the running track of the manipulator changes is determined, after the running track of the manipulator changes, the programming regulation unit corrects the coding content, and the running programming processing unit recodes the manipulator according to the content corrected by the programming regulation unit, so that the running track after the manipulator is modified meets the working requirement, the problem of production of products after the running track of the manipulator deviates is avoided, and normal production of the manipulator on the products is ensured.
Drawings
FIG. 1 is an overall block diagram of embodiment 1 of the present invention;
FIG. 2 is a block diagram of an operational programming processing unit of embodiment 1 of the present invention;
FIG. 3 is a block diagram of a robot operation detection unit according to embodiment 1 of the present invention;
FIG. 4 is a block diagram of a programming control unit according to embodiment 1 of the present invention;
fig. 5 is an overall combined block diagram of embodiment 1 of the present invention.
The meaning of each reference sign in the figure is:
1. operating a programming processing unit; 11. a work task learning module; 12. the manipulator operates the programming module; 13. an operation module; 14. operating a correction module;
2. the mechanical arm operates the detection unit; 21. the mechanical arm operates a photographing module; 22. a running track modeling module; 23. an actual operation planning module; 24. the manipulator node running track searching module;
3. programming a regulation and control unit; 31. a programming track searching module; 32. track operation comparison module; 33. a difference accounting module; 34. and a correction feedback module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: in the process of the manipulator in work, certain deviation can appear in the part of manipulator inside because of structural wear, and then makes the orbit of manipulator appear certain change, and the orbit of manipulator appears changing the back, can influence the precision of manipulator work, and when the manipulator was carried out is accurate during work, the orbit of manipulator orbit change can lead to the precision reduction of manipulator work, and then influences the production that produces.
When the movement track changes in the process of the manipulator work, workers cannot timely find that the workers can only observe products produced by the manipulator, so that unqualified products can be caused, and in order to reduce the unqualified quantity of the products caused by the track changes in the production process of the manipulator, the movement track of the manipulator is detected and corrected by a manipulator control system based on action record analysis, so that the manipulator can normally produce the products.
In order to solve the above-mentioned problem of unqualified production caused by deviation of the movement track of the manipulator, the present invention provides a manipulator control system based on action record analysis, please refer to fig. 1-5, which includes an operation programming processing unit 1, a manipulator operation detecting unit 2 and a programming control unit 3;
the operation programming processing unit 1 programs the operation track of the manipulator according to the task of the manipulator operation, and the manipulator operates according to the programmed interior, so that the manipulator completes the corresponding task;
the operation programming processing unit 1 comprises a work task learning module 11, a manipulator operation programming module 12 and an operation module 13;
the work task learning module 11 acquires tasks to be completed by the manipulator and passes through paths required by the completion of the tasks, and learns the tasks to be completed by the manipulator so as to operate the programming processing unit 1 to perform corresponding programming according to the tasks to be completed by the manipulator;
the manipulator operation programming module 12 performs programming of corresponding instructions according to the operation track of the manipulator acquired by the work task learning module 11, wherein the programming content is the track of the manipulator motion, and the manipulator finishes the specified operation on the object by programming the corresponding content;
the operation module 13 imports the content programmed by the manipulator operation programming module 12 into the manipulator, so that the manipulator executes the programmed content, and the manipulator performs specified operation on the goods, namely, the code for operating the manipulator is transmitted to the manipulator through the operation module 13, so that the operation module 13 controls the operation of the manipulator.
The manipulator operation detection unit 2 captures images of the manipulator working according to the programming content, performs three-dimensional modeling of the working state of the manipulator according to the captured images, and simultaneously searches the operation track of each node of the manipulator according to the established three-dimensional model; therefore, the running track of the manipulator in reality is acquired.
The manipulator operation detection unit 2 comprises a manipulator operation photographing module 21, an operation track modeling module 22, an actual operation planning module 23 and a manipulator node operation track searching module 24;
when the manipulator operation photographing module 21 receives the control operation of the manipulator by the operation module 13, photographing the operation manipulator by a camera to obtain the working state of the manipulator and the operation condition of the manipulator during operation, and when the camera is used for photographing the operation manipulator, the operation track modeling module 22 continuously photographs the manipulator to obtain the image of the complete workflow of the manipulator;
the running track modeling module 22 processes the image acquired by the manipulator running photographing module 21 and performs three-dimensional modeling of the mechanical working state according to the mechanical working state in the image;
when the running track modeling module 22 performs three-dimensional modeling on the manipulator, firstly, three-dimensional coordinates of the manipulator need to be acquired, and three-dimensional coordinates of the manipulator are calculated by adopting a three-dimensional photogrammetry algorithm, wherein the formula comprises the following components:
(1) let the three-dimensional coordinates of the manipulator beThe corresponding image points are respectively on the two imagesAnd->;
(2) Let the coordinates of the camera reference points in space be respectivelyAnd->And an internal reference matrix of the camera +.>And->;
(3) According to the principle of triangulation positioning, the following two formulas are obtained:
;
;
wherein,,and->Representing camera rotation matrix, +.>And->Representing a camera position matrix, < >>Transposition of the representative vector;
(4) acquiring the three-dimensional coordinates of the manipulator according to the two formulas in (3);
(5) Repeating the steps (1), (2), (3) and (4) to obtain the three-dimensional coordinates of each corresponding point on the manipulator;
after the three-dimensional coordinates of the manipulator are obtained, the manipulator is subjected to three-dimensional modeling according to the three-dimensional coordinates of the manipulator, a working state model of the manipulator at different moments is obtained, the working form of the manipulator when the specified operation is executed is subjected to model building, and the working position and the working state of each time point of the manipulator can be obtained, so that the working track of the manipulator can be obtained according to the working positions and the working states of the manipulator at different time points.
The actual operation planning module 23 plans the operation condition of the actual operation of the manipulator according to the models of the operation states of the plurality of manipulators modeled by the operation track modeling module 22, and obtains the operation condition of the manipulator in the actual operation, namely, obtains the space and the operation track through which the manipulator completes the specified operation in the actual operation;
after the operation track modeling module 22 obtains the operation state models of the manipulator at different moments, the actual operation planning module 23 performs the planning of the actual operation track of the manipulator according to the models modeled by the operation track modeling module 22, and the planning steps are as follows:
step one: all models of the three-dimensional modeling of the manipulator by the running track modeling module 22 are obtained, and the models are sequenced according to the photographing time of the corresponding photos of the models;
step two: and judging the motion state of the manipulator according to the sequence of the model sequencing, acquiring the motion sequence of the manipulator, and planning the actual motion condition of the manipulator according to the motion sequence of the manipulator.
The manipulator node running track searching module 24 searches the running track of each movable node of the manipulator according to the whole running track of the manipulator planned by the actual running planning module 23, and obtains the running track of each movable node on the manipulator after the appointed operation is completed;
the manipulator node running track searching module 24 reads the actual movement condition of the manipulator planned in the actual running planning module 23, searches the movement state of the movable node of the manipulator according to the actual movement condition of the manipulator, and plans the running track of the movable node of the manipulator according to the found movement state of the movable node of the manipulator.
The programming and controlling unit 3 compares the running track of each node of the manipulator, which is programmed and regulated by the running programming processing unit 1, with the running track of each node of the manipulator, which is found by the manipulator running detection unit 2, and checks the difference of the running tracks of each node of the manipulator;
the programming regulation and control unit 3 comprises a programming track searching module 31, a track running comparison module 32, a difference accounting module 33 and a correction feedback module 34;
the programming track searching module 31 obtains programming information of the manipulator operation in the manipulator operation programming module 12, and obtains the operation track of the movable node of the manipulator in the programming content according to the programming content;
the track operation comparison module 32 compares the programming track of the manipulator movable node obtained in the programming track searching module 31 with the operation track of the manipulator movable node planned by the manipulator node operation track searching module 24, and determines whether the two tracks have position deviation;
the difference accounting module 33 calculates the data of the difference between the two tracks according to the comparison result of the track operation comparison module 32 on the programming track and the mechanical arm node operation track searching module 24 planning the operation track of the mechanical arm movable node;
the difference accounting module 33, when calculating data of a difference between two trajectories, has two cases:
case one: the programming track and the moving track of the manipulator node are not different from each other when the moving track of the manipulator movable node is planned by the manipulator node moving track searching module 24, and the difference calculating module 33 does not calculate the difference of the moving track of the manipulator movable node planned by the manipulator node moving track searching module 24;
and a second case: the programming track and the moving track of the manipulator node are calculated by the moving track searching module 24, if there is a data difference between the moving tracks of the manipulator movable nodes, the difference calculating module 33 calculates difference data of the moving track of the manipulator movable nodes, which is calculated by the moving track searching module 24, converted to the programming track, and the calculated difference data is transmitted to the correction feedback module 34;
the correction feedback module 34 receives the data difference calculated by the difference accounting module 33, and calculates difference data of the movement track of the manipulator node, which is converted into the programming track by the movement track searching module 24.
The programming regulation and control unit 3 corrects data on a programmed track of the moving manipulator according to the motion performed by the programming processing unit 1 and the motion track formed by modeling of the manipulator motion detection unit 2, and transmits the corrected data to the programming processing unit 1, so that the programming processing unit 1 corrects the motion of the manipulator according to the corrected data, meanwhile, the manipulator motion detection unit 2 performs three-dimensional modeling on the manipulator after the data correction, and then the programming regulation and control unit 3 determines the motion track of the manipulator.
The operation programming processing unit 1 further comprises an operation correction module 14, the operation correction module 14 receives the difference data of the operation track of the manipulator movable node, which is transmitted by the correction feedback module 34, planned by the manipulator node operation track searching module 24 and converted into the programming track, the difference data is transmitted to the manipulator operation programming module 12, the manipulator operation programming module 12 reprograms the track of the manipulator operation according to the difference data, the programmed content is transmitted to the operation module 13, the operation module 13 controls the manipulator according to the newly programmed content, and meanwhile, in the process of transmitting the difference data to the manipulator operation programming module 12 by the operation correction module 14, the operation correction module 14 feeds back to the operation module 13, so that the operation of the manipulator is stopped, and after the operation module 13 receives the new programming transmitted by the manipulator operation programming module 12, the manipulator is operated.
The use flow is as follows:
the working task learning module 11 acquires a working task of the manipulator, the manipulator operation programming module 12 carries out programming corresponding to the task of the manipulator, the programming is transmitted to the operation module 13, the operation module 13 controls the manipulator to work, the manipulator operation photographing module 21 photographs the working manipulator in the process of the manipulator operation, the operation track modeling module 22 models the image photographed by the manipulator operation photographing module 21, and the actual operation planning module 23 and the manipulator node operation track searching module 24 search the operation track of the manipulator movable node of the modeled manipulator;
the programming track searching module 31 receives programming data in the manipulator operation programming module 12, obtains the operation track of the manipulator movable node according to the programming data, the track operation comparison module 32 compares the track of the manipulator obtained by modeling with the track of the manipulator movable node obtained by the programming data, determines whether the two track data have differences, when the differences exist, the difference accounting module 33 calculates the track data obtained by modeling, calculates the data differences between the track data obtained by modeling and the programming data, and is corrected by the correction feedback module 34 according to the data differences in the difference accounting module 33, the corrected data are transmitted to the operation correction module 14 by the correction feedback module 34, and are fed back to the manipulator operation programming module 12 by the operation correction module 14, and simultaneously, the operation correction module 14 transmits information to the operation module 13 when the operation correction module 14 feeds back to the manipulator operation programming module 12, so that the operation module 13 stops the manipulator control;
the manipulator operation programming module 12 receives the data transmitted by the operation correction module 14, modifies programming according to the content of the data, and transmits the modified programming to the operation module 13, so that the operation module 13 controls the manipulator according to the new programming, and at the moment, the manipulator operation detection unit 2 continuously captures and models the manipulator, thereby ensuring that the real-time working state of the manipulator meets the requirement of product production.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. Manipulator control system based on action record analysis, its characterized in that: the device comprises an operation programming processing unit (1), a manipulator operation detection unit (2) and a programming regulation and control unit (3);
the operation programming processing unit (1) programs the operation track of the manipulator according to the task of the manipulator, and the manipulator operates according to the programmed interior;
the manipulator operation detection unit (2) captures images of the manipulator working according to the programming content, performs three-dimensional modeling of the mechanical working state according to the captured images, and simultaneously searches the operation track of each node of the manipulator according to the established three-dimensional model;
the programming regulation and control unit (3) compares the running track of each node of the manipulator, which is programmed and regulated by the running programming processing unit (1), with the running track of each node of the manipulator, which is found by the manipulator running detection unit (2), and checks the difference of the running tracks of each node of the manipulator;
the programming regulation and control unit (3) corrects data on a motion track of the running manipulator according to the motion performed by the programming of the running programming processing unit (1) and the motion track formed by modeling of the manipulator motion detection unit (2), the corrected data are transmitted to the running programming processing unit (1), the running programming processing unit (1) corrects the motion of the manipulator according to the corrected data, meanwhile, the manipulator motion detection unit (2) performs three-dimensional modeling on the manipulator after the data correction, and then the programming regulation and control unit (3) determines the motion track of the manipulator;
the operation programming processing unit (1) comprises a work task learning module (11), a manipulator operation programming module (12) and an operation module (13);
the work task learning module (11) acquires tasks required to be completed by the manipulator and passes through paths required to complete the tasks;
the manipulator operation programming module (12) is used for programming corresponding instructions according to the operation track of the manipulator acquired by the work task learning module (11);
the operation module (13) imports the content programmed by the manipulator operation programming module (12) into the manipulator, so that the manipulator executes the programmed content;
the manipulator running detection unit (2) comprises a manipulator running photographing module (21), a running track modeling module (22), an actual running planning module (23) and a manipulator node running track searching module (24);
when the manipulator operation photographing module (21) receives the control operation of the manipulator by the operation module (13), photographing the operated manipulator by a camera to obtain the working state of the manipulator and the operation condition of the manipulator during the operation;
the moving track modeling module (22) processes the image acquired by the manipulator moving photographing module (21) and performs three-dimensional modeling of the manipulator working state according to the manipulator working state in the image;
the actual operation planning module (23) plans the operation condition of the actual operation of the manipulator according to the models of the operation states of the plurality of manipulators modeled by the operation track modeling module (22);
the manipulator node running track searching module (24) searches the running track of each movable node of the manipulator according to the whole running track of the manipulator planned by the actual running planning module (23) and acquires the running track of each movable node on the manipulator when the specified operation is completed;
after the three-dimensional coordinates of the manipulator are obtained, carrying out three-dimensional modeling on the manipulator according to the three-dimensional coordinates of the manipulator, and obtaining working state models of the manipulator at different moments;
the programming regulation and control unit (3) comprises a programming track searching module (31), a track running comparison module (32), a difference accounting module (33) and a correction feedback module (34);
the programming track searching module (31) acquires programming information of the manipulator operation in the manipulator operation programming module (12) and acquires the operation track of the manipulator movable node in the programming content according to the programming content;
the track operation comparison module (32) compares the programming track of the movable node of the manipulator obtained in the programming track searching module (31) with the operation track of the movable node of the manipulator planned by the manipulator node operation track searching module (24) to determine whether the two tracks have position deviation;
the difference accounting module (33) plans out a comparison result of the running track of the movable node of the manipulator according to the programmed track of the track running comparison module (32) and the running track searching module (24) of the node of the manipulator, and calculates the difference data between the two tracks;
the correction feedback module (34) receives the data difference calculated by the difference calculation module (33) and calculates difference data of the movement track of the manipulator node, which is planned by the manipulator node movement track searching module (24) and converted into a programming track.
2. The robot control system based on motion log analysis of claim 1, wherein: when the running track modeling module (22) performs three-dimensional modeling on the manipulator, firstly, three-dimensional coordinates of the manipulator need to be obtained, three-dimensional coordinates of the manipulator are calculated, a three-dimensional photogrammetry algorithm is adopted, and the formula content is as follows:
(1) let the three-dimensional coordinates of the manipulator beThe corresponding pixels are +.>And;
(2) let the coordinates of the camera reference points in space be respectivelyAnd->And an internal reference matrix of the camera +.>And->;
(3) According to the principle of triangulation positioning, the following two formulas are obtained:
;
;
wherein,,and->Representing camera rotation matrix, +.>And->Representing a camera position matrix, and T represents a transpose of the vector;
(4) acquiring the three-dimensional coordinates of the manipulator according to the two formulas in the step (3);
(5) repeating the steps (1), (2), (3) and (4) to obtain the three-dimensional coordinates of each corresponding point on the manipulator.
3. The robot control system based on motion log analysis of claim 1, wherein: after the operation track modeling module (22) acquires the operation state models of the manipulator at different moments, the actual operation planning module (23) performs planning of the actual operation track of the manipulator according to the models modeled by the operation track modeling module (22), and the planning steps are as follows:
step one: all models of the manipulator subjected to three-dimensional modeling by the running track modeling module (22) are obtained, and sequencing is carried out according to the photographing time of the corresponding photos of the models;
step two: and judging the motion state of the manipulator according to the sequence of the model sequencing, acquiring the motion sequence of the manipulator, and planning the actual motion condition of the manipulator according to the motion sequence of the manipulator.
4. The robot control system based on motion log analysis of claim 3, wherein: the manipulator node running track searching module (24) reads the actual movement condition of the manipulator planned in the actual running planning module (23), searches the movement state of the movable node of the manipulator according to the actual movement condition of the manipulator, and plans the running track of the movable node of the manipulator according to the searched movement state of the movable node of the manipulator.
5. The robot control system based on motion log analysis of claim 1, wherein: the difference accounting module (33) has two cases when calculating the data of the difference between two trajectories:
case one: the programming track and the moving track of the manipulator node are not different in data between the moving track of the manipulator moving node planned by the manipulator node moving track searching module (24), and the difference calculating module (33) does not calculate the difference of the moving track of the manipulator moving node planned by the manipulator node moving track searching module (24);
and a second case: the programming track and the moving track of the manipulator node are provided with data differences between the moving tracks of the manipulator movable nodes, which are planned by the moving track searching module (24), the difference accounting module (33) calculates difference data of the moving track of the manipulator movable nodes, which are planned by the moving track searching module (24), converted into the programming track, and the calculated difference data are transmitted to the correction feedback module (34).
6. The robot control system based on motion log analysis of claim 5, wherein: the operation programming processing unit (1) further comprises an operation correction module (14), the operation correction module (14) receives the difference data of the operation track of the manipulator movable node, which is planned by the manipulator node operation track searching module (24) and transmitted by the correction feedback module (34), converted to the programming track, and transmitted to the manipulator operation programming module (12), the manipulator operation programming module (12) reprograms the track of the manipulator operation according to the difference data, and transmits the programmed content to the operation module (13), and the operation module (13) controls the manipulator according to the newly programmed content.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310495295.3A CN116197918B (en) | 2023-05-05 | 2023-05-05 | Manipulator control system based on action record analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310495295.3A CN116197918B (en) | 2023-05-05 | 2023-05-05 | Manipulator control system based on action record analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116197918A CN116197918A (en) | 2023-06-02 |
CN116197918B true CN116197918B (en) | 2023-07-21 |
Family
ID=86517684
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310495295.3A Active CN116197918B (en) | 2023-05-05 | 2023-05-05 | Manipulator control system based on action record analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116197918B (en) |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006289580A (en) * | 2005-04-13 | 2006-10-26 | Fanuc Ltd | Teaching point correcting method of program and teaching point correcting device of program |
US8706298B2 (en) * | 2010-03-17 | 2014-04-22 | Raytheon Company | Temporal tracking robot control system |
CN104175330B (en) * | 2014-08-14 | 2016-04-20 | 四川大学 | A kind of six joint industrial robot real-time servo tracking means based on aiming mechanism |
JP6497953B2 (en) * | 2015-02-03 | 2019-04-10 | キヤノン株式会社 | Offline teaching apparatus, offline teaching method, and robot system |
CN106541419B (en) * | 2016-10-13 | 2019-01-25 | 同济大学 | A kind of measurement method of robot trajectory's error |
CN106965173A (en) * | 2017-03-06 | 2017-07-21 | 浙江大学 | A kind of learning control method of back yard industry manipulator |
CN108656107B (en) * | 2018-04-04 | 2020-06-26 | 北京航空航天大学 | Mechanical arm grabbing system and method based on image processing |
CN108927807B (en) * | 2018-08-14 | 2020-08-07 | 河南工程学院 | Robot vision control method based on point characteristics |
CN112140101A (en) * | 2019-06-28 | 2020-12-29 | 鲁班嫡系机器人(深圳)有限公司 | Trajectory planning method, device and system |
CN111152229B (en) * | 2020-02-24 | 2023-08-25 | 群滨智造科技(苏州)有限公司 | Manipulator guiding method and device for 3D mechanical vision |
CN111590594B (en) * | 2020-06-22 | 2021-12-07 | 南京航空航天大学 | Robot trajectory tracking control method based on visual guidance |
CN112025772B (en) * | 2020-07-28 | 2021-11-23 | 沈阳建筑大学 | Mechanical arm autonomous calibration method based on visual measurement |
CN112060082B (en) * | 2020-08-19 | 2021-10-15 | 大连理工大学 | Online stable control humanoid robot based on bionic reinforcement learning type cerebellum model |
US20220288777A1 (en) * | 2021-03-10 | 2022-09-15 | Samsung Electronics Company, Ltd. | Parameterized Waypoint Generation on Dynamically Parented Non-Static Objects for Robotic Autonomous Tasks |
CN114643582B (en) * | 2022-05-05 | 2022-12-27 | 中山大学 | Model-free joint fault-tolerant control method and device for redundant mechanical arm |
CN115026835A (en) * | 2022-07-18 | 2022-09-09 | 上海飒智智能科技有限公司 | Method for optimizing overall performance of robot mechanical arm servo system |
-
2023
- 2023-05-05 CN CN202310495295.3A patent/CN116197918B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN116197918A (en) | 2023-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tang et al. | A framework for manipulating deformable linear objects by coherent point drift | |
Castaño et al. | Visual compliance: Task-directed visual servo control | |
Wang et al. | Collision-free trajectory planning in human-robot interaction through hand movement prediction from vision | |
Zou et al. | An end-to-end calibration method for welding robot laser vision systems with deep reinforcement learning | |
CN108161931A (en) | The workpiece automatic identification of view-based access control model and intelligent grabbing system | |
De Luca et al. | On-line estimation of feature depth for image-based visual servoing schemes | |
CN110561430B (en) | Robot assembly track optimization method and device for offline example learning | |
CN110560373B (en) | Multi-robot cooperation sorting and transporting method and system | |
CN111152229A (en) | Mechanical arm guiding method and device for 3D mechanical vision | |
CN104325268A (en) | Industrial robot three-dimensional space independent assembly method based on intelligent learning | |
CN113829343A (en) | Real-time multi-task multi-person man-machine interaction system based on environment perception | |
Zhang et al. | Deep learning-based robot vision: High-end tools for smart manufacturing | |
CN114536346A (en) | Mechanical arm accurate path planning method based on man-machine cooperation and visual detection | |
Liu et al. | A mixed perception-based human-robot collaborative maintenance approach driven by augmented reality and online deep reinforcement learning | |
CN116197918B (en) | Manipulator control system based on action record analysis | |
CN113910218A (en) | Robot calibration method and device based on kinematics and deep neural network fusion | |
Lagamtzis et al. | CoAx: Collaborative Action Dataset for Human Motion Forecasting in an Industrial Workspace. | |
CN116408790B (en) | Robot control method, device, system and storage medium | |
Wu et al. | Application of visual servoing for grasping and placing operation in slaughterhouse | |
CN114888768A (en) | Mobile duplex robot cooperative grabbing system and method based on multi-sensor fusion | |
US20210129318A1 (en) | Annotation device | |
Rego et al. | Manipulator Motion Tracking Conceptual Model | |
Martínez et al. | Visual predictive control of robot manipulators using a 3d tof camera | |
TWI788253B (en) | Adaptive mobile manipulation apparatus and method | |
CN112484730B (en) | Method and system for realizing indoor material addressing navigation based on SLAM |
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 |