CN110434854B - Redundant manipulator visual servo control method and device based on data driving - Google Patents

Redundant manipulator visual servo control method and device based on data driving Download PDF

Info

Publication number
CN110434854B
CN110434854B CN201910766494.7A CN201910766494A CN110434854B CN 110434854 B CN110434854 B CN 110434854B CN 201910766494 A CN201910766494 A CN 201910766494A CN 110434854 B CN110434854 B CN 110434854B
Authority
CN
China
Prior art keywords
joint
redundant manipulator
mechanical arm
end effector
redundant
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
Application number
CN201910766494.7A
Other languages
Chinese (zh)
Other versions
CN110434854A (en
Inventor
金龙
谢正泰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lanzhou University
Original Assignee
Lanzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lanzhou University filed Critical Lanzhou University
Priority to CN201910766494.7A priority Critical patent/CN110434854B/en
Publication of CN110434854A publication Critical patent/CN110434854A/en
Application granted granted Critical
Publication of CN110434854B publication Critical patent/CN110434854B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • B25J9/1602—Programme controls characterised by the control system, structure, architecture
    • B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
    • 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)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Numerical Control (AREA)
  • Manipulator (AREA)

Abstract

The invention provides a redundant manipulator visual servo control method and a device based on data driving, wherein the whole system adopts a virtual Jacobian matrix to assist calculation, and the method comprises the following steps: 1) Acquiring the speed information of an end effector and the joint speed information of the redundant manipulator; 2) Simulating the motion of the end effector according to the speed information and the joint speed information and obtaining a virtual Jacobian matrix; 3) Applying the virtual Jacobian matrix to design a quadratic optimization redundancy analysis scheme; 4) Converting the quadratic optimization redundancy analysis scheme into a standard quadratic programming form; 5) Solving by using a quadratic programming solver to determine a control signal of the redundant manipulator; 6) Transmitting the control signal to a lower computer controller to control the movement of the mechanical arm; the invention provides a reliable visual servo control method for the redundancy mechanical arm with unknown model, and keeps higher control precision while controlling the mechanical arm.

Description

Redundant manipulator visual servo control method and device based on data driving
Technical Field
The invention relates to the field of redundant manipulator motion planning and control based on visual servo, in particular to an inverse kinematics solving method of a redundant manipulator based on visual servo.
Background
The redundant manipulator has the characteristic that the degree of freedom is greater than the minimum degree of freedom required by a task space, and the characteristic greatly improves the flexibility of the manipulator. Thus, redundant robots can perform more complex and difficult tasks than non-redundant robots and become an essential high efficiency instrument for industrial production. The redundant manipulator vision servo comprises the whole process from vision signal processing to robot control, and can overcome the uncertainty in a robot system, a vision system and the environment, thereby greatly improving the precision of vision positioning or track tracking. Therefore, with the rapid development of robotics, computer technology, and imaging devices, robot visual servos have attracted extensive attention from researchers in various fields, and have been widely used in the fields of surgery, quality inspection, precision assembly, and the like.
Although scholars have accumulated abundant experience in robot visual servoing, the modeling of the relationship between image space and robot arm joint space and the construction of control methods still plague many researchers. It is worth noting that most existing redundant robotic arm control methods based on visual servoing do not take into account the effects of joint limitations. Once the redundant mechanical arm exceeds the joint limit, not only can the task fail, but also the service life of the mechanical arm can be shortened. In addition, the existing mechanical arm control method based on visual servo only aims at the mechanical arm with a known model, and is not suitable for the mechanical arm with an unknown model. In a long-term industrial production process, a mechanical arm model is bound to change due to abrasion, and at the moment, the existing control method cannot enable the mechanical arm to accurately complete a given task, so that the task fails and even the mechanical arm is damaged. And the data driving technology can be used for acquiring the structural information of the mechanical arm, which provides important technical support for the control of the model unknown mechanical arm. The invention provides a redundant manipulator vision servo control method and device based on data driving, which can control an unknown manipulator of a model to accurately track expected pixel coordinates and simultaneously consider joint limits. These advantages are of great practical significance for industrial production. In conclusion, the invention has novelty and practicability.
Disclosure of Invention
The invention provides a visual servo control method and a visual servo control device for a redundant manipulator based on data driving, aiming at accurately realizing the visual servo control based on images on the redundant manipulator with an unknown model and considering the joint limit of the redundant manipulator.
The embodiment of the invention provides a simulation method of a mechanical arm end effector based on data driving;
the mechanical arm end effector simulation method comprises the following steps:
acquiring the speed information and joint speed information of the mechanical arm of which the model is unknown;
simulating the mechanical arm end effector by a Jacobi matrix iteration equation and acquiring model structure information;
the jacobian matrix iteration equation is as follows:
Figure BDA0002172101170000021
wherein the content of the first and second substances,
Figure BDA0002172101170000022
a virtual jacobian matrix for the robotic arm; />
Figure BDA0002172101170000023
Is->
Figure BDA0002172101170000024
A time derivative of (a); />
Figure BDA0002172101170000025
The speed of the end effector of the redundant manipulator; />
Figure BDA0002172101170000026
The joint speed of the redundant manipulator; mu is more than 0 and is a design parameter for controlling the convergence rate of the algorithm; upper label T As a transpose of a vector or matrix.
The second aspect of the embodiments of the present invention provides a redundant manipulator end effector structure of a redundant manipulator visual servo control method based on data driving, which specifically includes:
a miniature camera is installed on the end effector of the redundant manipulator, and the camera can transmit image information in real time along with the movement of the end effector.
The third aspect of the embodiments of the present invention provides a design step of a redundant manipulator visual servo control method based on data driving, which specifically includes:
setting an optimized performance index as a joint speed norm, and determining a quadratic optimization scheme through an expected pixel coordinate, a virtual mechanical arm Jacobian matrix, an image Jacobian matrix, a joint angle limit and a joint speed limit;
converting the quadratic optimization scheme into standard quadratic programming;
solving the quadratic programming solver for the standard quadratic programming to obtain a solution result;
and determining a control signal of the redundant manipulator according to the solving result.
The fourth aspect of the embodiments of the present invention provides a quadratic optimization scheme for a data-driven redundant manipulator visual servo control method;
the quadratic optimization scheme is as follows:
the designed minimum performance index is joint velocity norm and is restricted by Jacobian equation, expected pixel coordinate and jointAngular limit, joint speed limit, i.e. minimization
Figure BDA0002172101170000031
Constrained to jacobian equation>
Figure BDA0002172101170000032
Desired pixel coordinate x = x d Articulation angle limit->
Figure BDA0002172101170000033
Joint speed limit>
Figure BDA0002172101170000034
Wherein +>
Figure BDA0002172101170000035
Velocity of pixel coordinate representing feature point, J i Representing the jacobian matrix of the image, x representing the pixel coordinates of the feature points, x d Represents the desired pixel coordinate, < > or < >>
Figure BDA0002172101170000036
Represents the joint angle of the redundant robot arm>
Figure BDA0002172101170000037
Represents the upper and lower limits of the redundant manipulator joint angle>
Figure BDA0002172101170000038
Representing the upper and lower limits of the redundant manipulator joint speed.
The fifth aspect of the embodiment of the invention provides a quadratic programming scheme of a redundant manipulator visual servo control method based on data driving;
the secondary planning is as follows:
design its performance index to be minimized
Figure BDA0002172101170000041
Is restricted to>
Figure BDA0002172101170000042
x＝x d ，
Figure BDA0002172101170000043
Wherein +>
Figure BDA0002172101170000044
ω ± represents the upper and lower limits of the synthetic double-ended constraint, their i-th elements are each defined as->
Figure BDA0002172101170000045
Figure BDA0002172101170000046
i denotes the joint number, i =1,2,3 \ 8230n, normal number k α For adjusting and ensuring a sufficiently large feasible range for the joint velocity.
A sixth aspect of the embodiments of the present invention provides a redundant manipulator visual servo control apparatus based on data driving; the control device finishes the control of tracking the expected pixel coordinates from the solver to the redundancy mechanical arm through information transmission among all modules of the control device;
the control device includes:
the redundant manipulator information acquisition module is used for acquiring joint speed information and end effector speed information of the manipulator of which the model is unknown;
the virtual Jacobian matrix construction module is used for constructing a virtual Jacobian matrix according to the joint speed information of the mechanical arm and the speed information of the end effector so as to acquire the structural information of the mechanical arm;
the expected information acquisition module is used for acquiring the pixel information of the expected characteristic points and transmitting the information to a quadratic programming solver;
the image information acquisition module is used for acquiring image pixel information of the miniature camera and transmitting the information to the quadratic programming solver;
the equation building module is used for building a Jacobian matrix equation corresponding to the target redundancy manipulator according to a preset rule and the virtual Jacobian matrix and the image Jacobian matrix;
the control signal determining module is used for determining a control signal of the target redundant manipulator according to quadratic optimization and a standard quadratic programming method under the constraints of the Jacobian matrix equation, the expected pixel coordinate, the joint angle limit and the joint speed limit;
the information transmission module is used for acquiring a control signal of the target redundant manipulator and transmitting the control signal to a lower computer;
and the redundant manipulator control module is used for controlling the target redundant manipulator according to the control signal of the target redundant manipulator so that the target redundant manipulator tracks the expected pixel coordinates.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a three-dimensional model diagram of a redundant robotic arm embodying the present invention;
FIG. 3 illustrates a redundant manipulator feature point trajectory and desired coordinates for implementing the present invention;
FIG. 4 is a diagram illustrating angular changes in a joint of a redundant manipulator embodying aspects of the present invention;
FIG. 5 is a graph illustrating how the joint velocity of a redundant manipulator may vary in accordance with the application of the present invention;
FIG. 6 is a graph of a two-norm change in simulation error for a redundant manipulator implementing the present invention;
FIG. 7 is a graph of a two-norm change in pixel error for an end effector during task performance by a redundant robotic arm embodying aspects of the present invention;
FIG. 8 is a schematic diagram of a data-driven redundant manipulator visual servo control apparatus according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of the present invention; firstly, acquiring speed information and joint speed information of an end effector of the redundant manipulator; then simulating the motion of the end effector according to the speed information and the joint speed information and obtaining a virtual Jacobian matrix; then designing a quadratic form joint velocity norm performance index to generate a quadratic form optimization analysis scheme; then converting the quadratic optimization redundancy analysis scheme into a quadratic programming form; solving by using a quadratic programming solver; and finally, the lower computer controller controls the redundant manipulator to complete the visual servo control based on the image according to the solving result.
The robot arm embodying the present invention shown in figure 2 is a spatial six degree of freedom PUMA560 robot arm. The redundant manipulator consists of six connecting rods, and consists of a first joint (1), a second joint (2), a third joint (3), a fourth joint (4), a fifth joint (5), a sixth joint (6), an end effector (7) and a miniature camera (8).
The simulation method of the mechanical arm end effector comprises the following steps:
acquiring the speed information and joint speed information of the mechanical arm unknown by the model;
simulating the mechanical arm end effector by a Jacobi matrix iteration equation and acquiring model structure information;
the jacobian matrix iteration equation is as follows:
Figure BDA0002172101170000061
wherein the content of the first and second substances,
Figure BDA0002172101170000062
a virtual jacobian matrix for the robotic arm; />
Figure BDA0002172101170000063
Is->
Figure BDA0002172101170000064
The time derivative of (a); />
Figure BDA0002172101170000065
The speed of the end effector of the redundant manipulator; />
Figure BDA0002172101170000066
The joint speed of the redundant manipulator; mu is more than 0 and is a design parameter for controlling the convergence rate of the algorithm; upper label T As a transpose of a vector or matrix.
The invention designs a vision servo quadratic form optimization scheme based on images as follows
And (3) minimizing:
Figure BDA0002172101170000067
constraint conditions are as follows:
Figure BDA0002172101170000068
X＝X d (3)
Figure BDA0002172101170000069
Figure BDA00021721011700000610
wherein the content of the first and second substances,
Figure BDA0002172101170000071
for the performance indicators of the visual servoing planning scheme, <' >>
Figure BDA0002172101170000072
Velocity of pixel coordinates representing characteristic points, J i Representing the jacobian matrix of the image, x representing the pixel coordinates of the feature points, x d Represents the desired pixel coordinate, < > or < >>
Figure BDA0002172101170000073
Represents the joint angle of the redundant robot arm>
Figure BDA0002172101170000074
Representing the angle of the joints of the redundant manipulatorLower limit,. In conjunction with>
Figure BDA0002172101170000075
Representing the upper and lower limits of the redundant manipulator joint speed.
The quadratic optimization scheme (1) - (5) for the redundant manipulator image servo with physical constraints can be described as a quadratic programming scheme as follows:
and (3) minimizing:
Figure BDA0002172101170000076
constraint conditions are as follows:
Figure BDA0002172101170000077
X＝X d (8)
Figure BDA0002172101170000078
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0002172101170000079
ω. + -. Represents the upper and lower limits of the synthetic double-ended constraint, their i-th elements being defined as ^ and ^ respectively>
Figure BDA00021721011700000710
i denotes the joint number, i =1,2,3 \ 8230n, normal number k α For adjusting and ensuring a sufficiently large feasible range for the joint velocity.
An example of a possible solver is given below (the invention is not limited to this solver example), which in turn can be equivalent to a piecewise linear projection equation set by using a gradient descent method:
Figure BDA00021721011700000711
Figure BDA00021721011700000712
wherein the content of the first and second substances,
Figure BDA00021721011700000713
delta > 0 represents an end effector pixel error feedback coefficient, superscript @>
Figure BDA00021721011700000714
Represents a pseudo-inverse operation of the matrix, mu > 0 represents a coefficient for controlling convergence, and is set ^ 4>
Figure BDA00021721011700000715
To limit the projection operation of joint variables within the joint limits.
The invention has two characteristics, firstly, the invention considers the joint limit of the joint speed layer and the joint angle layer of the redundant mechanical arm and makes up the defect that the existing mechanical arm vision servo control method does not relate to joint limit avoidance. This ensures that the redundant manipulator operates safely and smoothly, and prolongs the service life of the redundant manipulator. In addition, the invention is oriented to the mechanical arm with unknown model, simulates the real mechanical arm movement and transmits the model information of the mechanical arm through the data driving technology, is used for controlling the mechanical arm with unknown model, and provides a more effective and comprehensive control scheme.
And after a quadratic programming solution is obtained through a quadratic programming solver of the upper computer, the result is converted into a control signal required by motor driving, the motors of all joints of the redundant manipulator are driven to move through a controller of the redundant manipulator, and the redundant manipulator is controlled to complete a visual servo task.
The workflow of the present invention will now be described with reference to a specific example operation.
An MATLAB software is used for carrying out experimental simulation on the method by taking a six-degree-of-freedom PUMA560 redundant mechanical arm as an example to track the expected pixel target. The specific parameters are set as follows: δ =10, μ =10000,k α =10, joint angle limit of redundant manipulator
Figure BDA0002172101170000082
Arc, joint speed limit of redundant manipulator->
Figure BDA0002172101170000081
Radian/second, execution task time set to 8 seconds, desired pixel coordinate x d ＝[256，256]A pixel. And solving by a quadratic programming solver, and transmitting the calculated result to the redundant mechanical arm controller so as to control the motion of the redundant mechanical arm.
FIG. 3 illustrates exemplary trajectories and desired coordinates of redundant manipulator feature points for use in implementing the present invention. In fig. 3, the characteristic points corresponding to the end effector successfully track the desired pixel target, and the motion trajectory is a straight line, which embodies the feasibility and high efficiency of the invention.
Fig. 4 is a diagram of the angular change of the joints of a redundant manipulator embodying the present invention. As can be seen from fig. 4, the joint angle of the redundant manipulator is limited within the joint angle limit, which further protects the redundant manipulator.
FIG. 5 is a graph illustrating how the joint velocity of a redundant manipulator may be varied in implementing the present invention. As can be seen from fig. 5, the joint speed of the redundant manipulator is limited within the joint speed limit, further achieving the effect of protecting the redundant manipulator.
Fig. 6 is a diagram of a two-norm variation of simulation errors during task execution by a redundant manipulator implementing the present invention. The simulation error is the difference between the pose velocity of the virtual end effector and the pose velocity of the real end effector. As can be seen in FIG. 6, the simulation error of the redundant manipulator end-effector converges rapidly in the second norm at 10 -5 After seconds, converge to zero. When stable, the two-norm of the simulation error is at 10 -15 Is an order of magnitude, indicating that the virtual end effector successfully accurately simulates the motion of a real end effector.
FIG. 7 is a graph of the two-norm change in pixel error of an end effector during task performance by a redundant robotic arm embodying aspects of the present invention. From FIG. 7, it can be seen that the redundant robotic arm end effector has two exemplary pixel errorsThe number converges rapidly and to zero 1 second ago. When stable, the two-norm of the simulation error is at 10 -13 The order of magnitude of the redundant manipulator indicates that the characteristic points of the real end effector accurately track the expected pixel target, and the redundant manipulator completes the visual servo task.
FIG. 8 is a schematic diagram of a data-driven redundant manipulator visual servo control apparatus according to the present invention. As shown in fig. 8, the control device performs control of tracking the desired pixel coordinates from the solver to the redundant manipulator through information transfer between the modules of the control device;
the control device includes:
a redundant manipulator information acquiring module 801 configured to acquire joint speed information and end effector speed information of a manipulator of which the model is unknown;
a virtual jacobian matrix construction module 802, configured to construct a virtual jacobian matrix according to the joint speed information of the mechanical arm and the speed information of the end effector, so as to obtain structural information of the mechanical arm;
an expected information obtaining module 803, configured to obtain pixel information of the expected feature point, and transmit the information to a quadratic programming solver;
an image information obtaining module 804, configured to obtain image pixel information of the micro camera, and transmit the information to a quadratic programming solver;
an equation constructing module 805, configured to construct, according to the virtual jacobian matrix and the image jacobian matrix and according to a preset rule, a jacobian matrix equation corresponding to the target redundant manipulator;
a control signal determining module 806, configured to determine a control signal of the target redundant manipulator according to quadratic optimization and a standard quadratic programming method under the constraints of the jacobian matrix equation, the expected pixel coordinates, the joint angle limit, and the joint speed limit;
an information transmission module 807 for obtaining the control signal of the target redundant manipulator and transmitting the control signal to a lower computer;
and a redundant manipulator control module 808 configured to control the target redundant manipulator according to the control signal of the target redundant manipulator, so that the target redundant manipulator tracks the expected pixel coordinates.

Claims (2)

1. A redundant manipulator visual servo control method based on data driving is characterized in that a manipulator end effector is simulated according to the speed information and joint speed information of a redundant manipulator of which the model is unknown and model structure information is obtained;
the mechanical arm end effector simulation method comprises the following steps:
acquiring the speed information and joint speed information of the mechanical arm of which the model is unknown;
simulating the mechanical arm end effector by a Jacobi matrix iteration equation and acquiring model structure information;
the jacobian matrix iteration equation is as follows:
Figure FDA0004115090680000011
wherein, the first and the second end of the pipe are connected with each other,
Figure FDA0004115090680000012
a virtual jacobian matrix for the robotic arm; />
Figure FDA0004115090680000013
Is->
Figure FDA0004115090680000014
A time derivative of (a); />
Figure FDA0004115090680000015
The speed of the end effector of the redundant manipulator; />
Figure FDA0004115090680000016
For closing redundant manipulatorsSpeed is saved; mu is more than 0 and is a design parameter for controlling the convergence rate of the algorithm; superscript T is the transpose of a vector or matrix;
the end effector of the redundant manipulator is provided with a miniature camera which can transmit image information in real time along with the movement of the end effector;
determining a control signal of the redundant manipulator by using a quadratic optimization and standard quadratic programming method according to the virtual Jacobian matrix, wherein the method specifically comprises the following steps:
setting an optimized performance index as a joint speed norm, and determining a quadratic optimization scheme through an expected pixel coordinate, a virtual mechanical arm Jacobian matrix, an image Jacobian matrix, a joint angle limit and a joint speed limit; the quadratic optimization scheme is as follows: the designed minimized performance index is joint velocity norm constrained by Jacobian equation, expected pixel coordinates, joint angle limit and joint velocity limit, namely, the minimized performance index is
Figure FDA0004115090680000017
Constrained to jacobian equation>
Figure FDA0004115090680000018
Desired pixel coordinate x = xd, joint angle limit θ - ≤θ≤θ + Articulation speed limit->
Figure FDA0004115090680000019
Wherein +>
Figure FDA00041150906800000110
Velocity of pixel coordinates representing characteristic points, J i Representing the jacobian matrix of the image, x representing the pixel coordinates of the feature points, x d Representing desired pixel coordinates, theta representing the joint angle of the redundant manipulator, theta ± Upper and lower limits for representing the angle of a redundant manipulator joint>
Figure FDA0004115090680000021
Representing the upper limit and the lower limit of the joint speed of the redundancy mechanical arm;
converting the quadratic optimization scheme into standard quadratic programming, and designing the performance index to be minimized
Figure FDA0004115090680000022
Is restricted to->
Figure FDA0004115090680000023
x＝x d ，/>
Figure FDA0004115090680000024
Wherein it is present>
Figure FDA0004115090680000025
ω ± Representing the upper and lower limits of the synthetic double-ended constraint, their i-th elements being defined as
Figure FDA0004115090680000026
i denotes the joint number, i =1,2,3 \ 8230n, normal number k α A feasible region for adjusting and ensuring joint velocity;
solving the quadratic programming solver for the standard quadratic programming to obtain a solution result;
and determining a control signal of the redundant manipulator according to the solving result.
2. The vision servo control method for the redundant manipulator based on data driving as claimed in claim 1, wherein the solution result of the quadratic programming solver is converted into a control signal required by motor driving to drive each joint motor so that the redundant manipulator tracks the expected pixel coordinates.
CN201910766494.7A 2019-08-20 2019-08-20 Redundant manipulator visual servo control method and device based on data driving Active CN110434854B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910766494.7A CN110434854B (en) 2019-08-20 2019-08-20 Redundant manipulator visual servo control method and device based on data driving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910766494.7A CN110434854B (en) 2019-08-20 2019-08-20 Redundant manipulator visual servo control method and device based on data driving

Publications (2)

Publication Number Publication Date
CN110434854A CN110434854A (en) 2019-11-12
CN110434854B true CN110434854B (en) 2023-04-07

Family

ID=68436493

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910766494.7A Active CN110434854B (en) 2019-08-20 2019-08-20 Redundant manipulator visual servo control method and device based on data driving

Country Status (1)

Country Link
CN (1) CN110434854B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113442137A (en) * 2021-06-24 2021-09-28 达闼机器人有限公司 Method and device for determining joint angle of mechanical arm, storage medium and electronic equipment
CN115213905B (en) * 2022-08-02 2023-08-25 中山大学 Method and system for controlling position and pose of redundant mechanical arm and robot

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815585A (en) * 2017-01-20 2017-06-09 浙江大学 A kind of high-precision vision positioning method of complex dynamic environment hole characteristic

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4296872B2 (en) * 2003-07-24 2009-07-15 トヨタ自動車株式会社 In-vehicle engine control parameter adaptation method and control parameter adaptation apparatus
CN101804627B (en) * 2010-04-02 2011-12-07 中山大学 Redundant manipulator motion planning method
US11070813B2 (en) * 2018-06-29 2021-07-20 Intel Corporation Global motion estimation and modeling for accurate global motion compensation for efficient video processing or coding
CN109591020B (en) * 2019-01-21 2023-02-28 兰州大学 Distributed cooperative control method and device for optimizing self-adaptive maneuverability of multi-redundancy mechanical arm
CN110103225B (en) * 2019-06-04 2023-04-11 兰州大学 Data-driven method and device for controlling repeated motion of mechanical arm

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815585A (en) * 2017-01-20 2017-06-09 浙江大学 A kind of high-precision vision positioning method of complex dynamic environment hole characteristic

Also Published As

Publication number Publication date
CN110434854A (en) 2019-11-12

Similar Documents

Publication Publication Date Title
CN107490965B (en) Multi-constraint trajectory planning method for space free floating mechanical arm
Suarez et al. Compliant bimanual aerial manipulation: Standard and long reach configurations
JP7391023B2 (en) Systems and methods for learning industrial tasks by robots based on human demonstrations
CN110103225B (en) Data-driven method and device for controlling repeated motion of mechanical arm
CN109623827B (en) High-performance redundant manipulator repetitive motion planning method and device
CN107607918B (en) Robot-based cylindrical surface near-field measurement feed source positioning and focusing method
CN110434854B (en) Redundant manipulator visual servo control method and device based on data driving
Tang et al. Path tracking of a cable-driven snake robot with a two-level motion planning method
CN112207835B (en) Method for realizing double-arm cooperative work task based on teaching learning
CN110561440A (en) multi-objective planning method for acceleration layer of redundant manipulator
CN113146600A (en) Flexible robot trajectory planning method and device based on kinematics iterative learning control
Marković et al. Adaptive stiffness estimation impedance control for achieving sustained contact in aerial manipulation
Jiang et al. The state of the art of search strategies in robotic assembly
CN110561441B (en) Single 94LVI iterative algorithm for pose control of redundant manipulator
CN113146617A (en) Flexible robot dynamics modeling and track following control method and device
Zeng et al. Autonomous control design of an unmanned aerial manipulator for contact inspection
CN115122325A (en) Robust visual servo control method for anthropomorphic manipulator with view field constraint
CN113858217A (en) Multi-robot interaction three-dimensional visual pose perception method and system
CN114800523B (en) Mechanical arm track correction method, system, computer and readable storage medium
CN111872938B (en) Spatial three-dimensional large-scale kinematics simulation system and method
CN109648567B (en) Redundancy mechanical arm planning method with noise tolerance characteristic
Gu et al. Dexterous obstacle-avoidance motion control of Rope Driven Snake Manipulator based on the bionic path following
Rego et al. Manipulator motion tracking conceptual model
Fernandez et al. Multi-Surface Admittance Control Approach applied on Robotic Assembly of Large-Scale parts in Aerospace Manufacturing
Yang Research on cruise control of hydrostatic tractor based on CAN bus

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