CN114932557A - Adaptive admittance control method based on energy consumption under kinematic constraint - Google Patents
Adaptive admittance control method based on energy consumption under kinematic constraint Download PDFInfo
- Publication number
- CN114932557A CN114932557A CN202210729992.6A CN202210729992A CN114932557A CN 114932557 A CN114932557 A CN 114932557A CN 202210729992 A CN202210729992 A CN 202210729992A CN 114932557 A CN114932557 A CN 114932557A
- Authority
- CN
- China
- Prior art keywords
- damping
- energy consumption
- interaction
- admittance
- velocity
- 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.)
- Granted
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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
Abstract
The invention discloses an adaptive admittance control method based on energy consumption under kinematic constraint, belonging to the field of human-computer loop interaction. The minimum criterion of energy consumption in the human-computer ring interaction process is provided, an admittance control law is designed on the basis of comprehensively considering the interaction force and the movement speed of the robot, damping parameters are updated, and the flexibility and the safety of the human-computer ring interaction are improved. The quality parameter range of the admittance controller is given according to the kinematic constraint of the robot, the speed, the acceleration and the variable acceleration limit of the robot are considered, and the safety of the robot system is improved. The admittance controller converts the acting force into the pose correction quantity of the tail end of the mechanical arm, and the pose correction quantity is superposed on the input of the robot system, and the robot motion control is realized through the position controller. The method can make the robot well conform to the intention of an operator, reduce the man-machine interaction force, improve the precision of the contact force with the environment, prevent the instability of the interaction process caused by the undersize admittance parameters, and improve the flexibility and the safety of the man-machine loop interaction.
Description
Technical Field
The invention relates to the technical field of man-machine loop interaction, in particular to an energy consumption-based adaptive admittance control method under kinematic constraint.
Background
Human-computer interaction is that an operator pulls a mechanical arm to complete specific movement, and most commonly human-computer teaching is performed. The cooperative mechanical arm can independently realize track reproduction from receiving teaching, and various human-computer loop interaction modes exist in the whole process. In order to make the interaction process more compliant and safe, the robot needs to have the ability to adapt to the intentions of the operator and the risks that may arise in the interaction.
The traditional admittance control method has the problems of poor flexibility and poor safety. In the prior art, a human-computer cooperation system control method based on intention identification of chinese patent CN112276944A estimates the intention of a human by using a neural network identification system, and although the method reduces the interaction force of human-computer cooperation, the method does not consider the constraint conditions of the mechanical arm itself, and cannot ensure the safety of the mechanical arm system. The method for controlling the compliance force of the mechanical arm based on the fuzzy reinforcement learning of the Chinese patent CN107053179B adopts the fuzzy reinforcement learning algorithm and completes the active following task of the mechanical arm by online learning and training the real-time adjustment strategy of admittance parameters, but the method has low convergence speed and reduces the compliance of man-machine cooperation. The adaptive man-machine cooperative control method based on the optimal admittance parameters, disclosed by the chinese patent CN113352322A, finds the optimal admittance parameters and introduces the assisting power into the admittance control equation in an integral reinforcement learning manner, but the method requires a large amount of data training and is only suitable for specific tasks.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a self-adaptive admittance control method considering energy consumption under kinematic constraint, and the flexibility and the safety of a human-computer loop interaction process are improved.
In order to achieve the purpose, the invention adopts the following technical scheme that:
an adaptive admittance control method based on energy consumption under kinematic constraint considers a man-machine ring interaction process, establishes a capability consumption minimum criterion according to interaction force and a robot movement speed, designs an admittance control law, and updates damping parameters.
Preferably, the damping update formula of the man-machine interaction admittance controller is as follows:
wherein b is the updated damping value, b 0 Is an initial damping value, e is a natural constant, α is a parameter, f h Is the force exerted on the robotic arm, and v is the velocity of the robotic arm in Cartesian space.
Preferably, the damping coefficient of the admittance controller for human-computer interaction is updated based on the minimum energy consumption criterion in the human-computer loop interaction process, and the specific method is as follows:
s11, energy consumption in the process of man-machine interaction can be represented by the following formula;
wherein f is h Is the force applied to the robotic arm, v is the velocity of the robotic arm in cartesian space;
s12, considering the relation between energy consumption and damping, minimizing the energy consumption in the interactive process, and calculating the partial derivative of the energy to the damping;
wherein f is h Is the acting force applied on the mechanical arm, and v is the velocity of the mechanical arm in Cartesian space;
s13, obtaining the damping coefficient b of the admittance controller according to the operation force f applied on the mechanical arm h And the relational expression of the motion speed v of the mechanical arm in the Cartesian space, wherein the damping updating formula is as follows:
wherein b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, α is the parameter;
s14, knowing the speed of the robot arm itself
Acceleration of a vehicle
And variable acceleration
According to the operating force f h And a damping coefficient b for the damping coefficient,
setting the value range of the quality parameter m
The subscript min represents a minimum value, i.e., a lower limit, and the subscript max represents a maximum value, i.e., an upper limit.
Preferably, the damping update formula of the machine-ring interactive admittance controller is as follows:
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is ambient velocity, b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, and α is the parameter.
Preferably, the damping coefficient of the admittance controller in the machine loop interaction is updated based on the energy consumption minimum criterion, and the specific method is as follows:
s21, energy consumption in the process of interaction between the mechanical arm and the environment can be represented by the following formula;
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is the ambient velocity;
s22, in order to minimize the energy consumption in the interaction process, the partial derivative of the energy to the damping is obtained;
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space, v e Is the ambient velocity;
s23 deviation of damping coefficient b from admittance controller with contact force
And speed deviation
The machine-ring interactive admittance controller damping updating expression is as follows:
wherein, the first and the second end of the pipe are connected with each other,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space, v e Is the ambient velocity, b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, α is the parameter;
s24, knowing the robot arm speed
Acceleration of a vehicle
And variable acceleration
According to the deviation of the applied force
Damping coefficient b and ambient velocity
Ambient acceleration
And ambient variation of acceleration
Setting the value range of the quality parameter m
Wherein the content of the first and second substances,
the subscript min represents the minimum, i.e., lower limit, and the subscript max represents the maximum, i.e., upper limit.
The invention has the advantages that:
(1) the invention provides an energy consumption minimum criterion in the human-computer ring interaction process, an admittance control law is designed on the basis of comprehensively considering interaction force and the movement speed of a robot, damping parameters are updated, the damping coefficient exponentially decreases along with the force applied by an operator and the movement speed of a mechanical arm at the beginning stage of the human-computer ring interaction, and the flexibility of the human-computer ring cooperation is improved; the damping coefficient is kept at a smaller value in the motion process, so that the energy consumption in the cooperation process is reduced; when the mechanical arm needs to execute fine work or stop motion emergently, the damping coefficient can exponentially rise, and the control precision and the safety of the mechanical arm are improved.
(2) The invention also gives the mass parameter range of the admittance controller according to the kinematic constraint of the robot, considers the limits of the speed, the acceleration and the variable acceleration of the robot arm, prevents the instability of the motion of the robot arm caused by the undersize admittance parameter and ensures the motion safety of the robot arm system.
(3) The self-adaptive admittance control method ensures that the mechanical arm can identify the movement intention of an operator in the human-computer loop cooperation process, and improves the flexibility of the mechanical arm system.
Drawings
FIG. 1 is a block diagram of the adaptive admittance control of the present invention.
FIG. 2 is a diagram of the trajectory tracking effect of the adaptive admittance of the present invention.
Fig. 3 is a graph showing the change of the damping coefficient in the X direction according to the present invention.
Fig. 4 is a graph showing the variation of the damping coefficient in the Y direction according to the present invention.
The English meaning in the drawings is as follows:
desired traj-desired track, actual traj-track.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a method for controlling adaptive admittance based on energy consumption in human-computer interaction under kinematic constraint includes the following steps:
s1: and modeling the mechanical arm. Building a kinematic model of the mechanical arm in Simulink;
s2: generation of the desired trajectory. Planning a track on an XY plane of a task space, wherein the track is used as an expected track for the track tracking of the mechanical arm in the later period;
s3: and (4) acquiring a force signal. According to the actual motion trail x and the expected motion trail x of the mechanical arm d Calculating the force f between the robot arm and the operator h And (3) feedback control for the admittance controller, wherein k in formula (1) is the set environmental stiffness parameter.
f h ＝k(x-x d ) (1)
S4: and (4) considering the energy consumption in an impedance expression, minimizing the energy consumption in the man-machine interaction process, and solving the relation between an energy function and damping, wherein the relation is shown in formulas (2) and (3).
S5: and updating the damping coefficient. Collecting the speed v of the mechanical arm in the Cartesian space, and obtaining the acting force f according to the step S3 h On-line calculation of damping coefficient
Wherein b is 0 Is an initial damping value, e is a natural constant, α is a parameter, f h Is the force exerted on the robotic arm, and v is the velocity of the robotic arm in cartesian space.
S6: and (4) admittance control. Impedance parameters m, b and force f h Substituting into formula
And calculating the displacement correction quantity of the tail end of the mechanical arm. Wherein
Respectively the acceleration and velocity of the mechanical arm in cartesian space.
S7: and controlling the motion of the mechanical arm. Superposing the displacement correction quantity delta x calculated by the admittance controller on the initial target position x d Obtaining a reference position x of the mechanical arm r As shown in equation (4). x is the number of r And obtaining the expected motion angle of each joint of the mechanical arm through inverse kinematics solution, and realizing motion control on the mechanical arm through a position controller.
x r ＝x d +Δx (4)
Fig. 2 is a diagram of the track following effect of adaptive admittance control, the solid line is the desired track desired traj, the dotted line is the following track actual traj, and the desired track and the following track of the present invention coincide. Fig. 3 and 4 are graphs showing changes in the damping coefficient in the X and Y directions, respectively.
The invention is not to be considered as limited to the specific embodiments shown and described, but is to be understood to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. An adaptive admittance control method based on energy consumption under kinematic constraint is characterized in that a human-computer loop interaction process is considered, a capability consumption minimum criterion is established according to interaction force and robot movement speed, an admittance control law is designed, and damping parameters are updated.
2. The adaptive admittance control method based on energy consumption under kinematic constraint according to claim 1, wherein the damping of the human-computer interaction admittance controller updates the formula as follows:
where b is the updated damping value, b 0 Is an initial damping value, e is a natural constant, α is a parameter, f h Is the force exerted on the robotic arm, and v is the velocity of the robotic arm in cartesian space.
3. The adaptive admittance control method based on energy consumption under kinematic constraint according to claim 1 or 2, wherein the damping coefficient of the admittance controller for human-computer interaction is updated based on the energy consumption minimum criterion of the human-computer loop interaction process, and the specific method is as follows:
s11, energy consumption in the process of man-machine interaction can be represented by the following formula;
wherein, f h Is the force applied to the robotic arm, v is the velocity of the robotic arm in cartesian space;
s12, considering the relation between energy consumption and damping, minimizing the energy consumption in the interactive process, and calculating the partial derivative of the energy to the damping;
wherein, f h Is the force applied to the robotic arm, v is the velocity of the robotic arm in cartesian space;
s13, obtaining the damping coefficient b of the admittance controller according to the operation force f applied on the mechanical arm h And the relational expression of the motion speed v of the mechanical arm in the Cartesian space, wherein the damping updating formula is as follows:
where b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, α is the parameter;
s14, knowing the speed of the robot arm itself
Acceleration of a vehicle
And variable acceleration
In response to the operating force f h And a damping coefficient b for the damping of the vibration,
setting the value range of the quality parameter m
The subscript min represents a minimum value, i.e., a lower limit, and the subscript max represents a maximum value, i.e., an upper limit.
4. The adaptive admittance control method based on energy consumption under kinematic constraint according to claim 1, wherein the damping update formula of the machine-loop interactive admittance controller is as follows:
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is ambient velocity, b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, and α is the parameter.
5. The adaptive admittance control method based on energy consumption under kinematic constraint according to claim 1 or 4, wherein the damping coefficient of the admittance controller in the machine loop interaction is updated based on the energy consumption minimum criterion, and the specific method is as follows:
s21, energy consumption in the process of interaction between the mechanical arm and the environment can be represented by the following formula;
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is the ambient velocity;
s22, in order to minimize the energy consumption in the interaction process, the partial derivative of the energy to the damping is obtained;
wherein the content of the first and second substances,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is the ambient velocity;
s23 deviation of damping coefficient b from admittance controller with contact force
And speed deviation
The relationship expression of (2) and the admittance controller damping updating expression of machine ring interaction are as follows:
wherein, the first and the second end of the pipe are connected with each other,
f e is the actual contact force between the mechanical arm and the environment, f d Is the expected contact force between the robot arm and the environment, v is the velocity of the robot arm in Cartesian space e Is the ambient velocity, b is the updated damping value, b 0 Is the initial damping value, e is the natural constant, α is the parameter;
s24, knowing the robot arm speed
Acceleration of a vehicle
And variable acceleration
According to the applied force deviation
Damping coefficient b and ambient velocity
Ambient acceleration
And ambient variation of acceleration
Setting quality parametersValue range of m
Wherein the content of the first and second substances,
the subscript min represents the minimum, i.e., lower limit, and the subscript max represents the maximum, i.e., upper limit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210729992.6A CN114932557B (en) | 2022-06-24 | 2022-06-24 | Self-adaptive admittance control method based on energy consumption under kinematic constraint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210729992.6A CN114932557B (en) | 2022-06-24 | 2022-06-24 | Self-adaptive admittance control method based on energy consumption under kinematic constraint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114932557A true CN114932557A (en) | 2022-08-23 |
| CN114932557B CN114932557B (en) | 2023-07-28 |
Family
ID=82869178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210729992.6A Active CN114932557B (en) | 2022-06-24 | 2022-06-24 | Self-adaptive admittance control method based on energy consumption under kinematic constraint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114932557B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5023808A (en) * | 1987-04-06 | 1991-06-11 | California Institute Of Technology | Dual-arm manipulators with adaptive control |
| WO2015137877A1 (en) * | 2014-03-14 | 2015-09-17 | National University Of Singapore | Gait rehabilitation apparatus |
| CN105242533A (en) * | 2015-09-01 | 2016-01-13 | 西北工业大学 | Variable-admittance teleoperation control method with fusion of multi-information |
| US20160067061A1 (en) * | 2014-08-15 | 2016-03-10 | Honda Motor Co., Ltd | Integral admittance shaping for an exoskeleton control design framework |
| CN107053179A (en) * | 2017-04-21 | 2017-08-18 | 哈尔滨思哲睿智能医疗设备有限公司 | A kind of mechanical arm Compliant Force Control method based on Fuzzy Reinforcement Learning |
| CN109249394A (en) * | 2018-09-27 | 2019-01-22 | 上海电气集团股份有限公司 | Robot control method and system based on admittance control algorithms |
| CN109366488A (en) * | 2018-12-07 | 2019-02-22 | 哈尔滨工业大学 | A kind of superimposed oscillation power Cartesian impedance control method of object manipulator assembly |
| CN109910005A (en) * | 2019-03-04 | 2019-06-21 | 上海电气集团股份有限公司 | Change admittance control method and system for robot |
| CN110597072A (en) * | 2019-10-22 | 2019-12-20 | 上海电气集团股份有限公司 | Robot admittance compliance control method and system |
| CN110977974A (en) * | 2019-12-11 | 2020-04-10 | 遨博（北京）智能科技有限公司 | Admittance control method, device and system for avoiding singular position type of robot |
| CN111230873A (en) * | 2020-01-31 | 2020-06-05 | 武汉大学 | Teaching learning-based collaborative handling control system and method |
| CN111281743A (en) * | 2020-02-29 | 2020-06-16 | 西北工业大学 | Self-adaptive flexible control method for exoskeleton robot for upper limb rehabilitation |
| US20200206943A1 (en) * | 2019-01-02 | 2020-07-02 | Research & Business Foundation Sungkyunkwan University | Apparatus and method for controlling robot |
| CN111660307A (en) * | 2020-05-27 | 2020-09-15 | 华中科技大学 | Robot operation high-assistance precision virtual clamp control method and system |
| CN111660306A (en) * | 2020-05-27 | 2020-09-15 | 华中科技大学 | Robot variable admittance control method and system based on operator comfort |
| CN112276944A (en) * | 2020-10-19 | 2021-01-29 | 哈尔滨理工大学 | Man-machine cooperation system control method based on intention recognition |
| JP2021117918A (en) * | 2020-01-29 | 2021-08-10 | 株式会社人機一体 | Drive unit having admittance control |
| CN113352322A (en) * | 2021-05-19 | 2021-09-07 | 浙江工业大学 | Adaptive man-machine cooperation control method based on optimal admittance parameters |
| CN113568313A (en) * | 2021-09-24 | 2021-10-29 | 南京航空航天大学 | Variable admittance auxiliary large component assembly method and system based on operation intention identification |
| CN113733105A (en) * | 2021-10-18 | 2021-12-03 | 哈尔滨理工大学 | Cooperative mechanical arm fuzzy variable admittance control system and method based on human intention recognition |
| WO2022007358A1 (en) * | 2020-07-08 | 2022-01-13 | 深圳市优必选科技股份有限公司 | Impedance control method and apparatus, impedance controller, and robot |
| CN114406983A (en) * | 2021-12-06 | 2022-04-29 | 中国科学院深圳先进技术研究院 | Adaptive admittance control method and related device for lower limb exoskeleton robot |
-
2022
- 2022-06-24 CN CN202210729992.6A patent/CN114932557B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5023808A (en) * | 1987-04-06 | 1991-06-11 | California Institute Of Technology | Dual-arm manipulators with adaptive control |
| WO2015137877A1 (en) * | 2014-03-14 | 2015-09-17 | National University Of Singapore | Gait rehabilitation apparatus |
| US20160067061A1 (en) * | 2014-08-15 | 2016-03-10 | Honda Motor Co., Ltd | Integral admittance shaping for an exoskeleton control design framework |
| CN105242533A (en) * | 2015-09-01 | 2016-01-13 | 西北工业大学 | Variable-admittance teleoperation control method with fusion of multi-information |
| CN107053179A (en) * | 2017-04-21 | 2017-08-18 | 哈尔滨思哲睿智能医疗设备有限公司 | A kind of mechanical arm Compliant Force Control method based on Fuzzy Reinforcement Learning |
| CN109249394A (en) * | 2018-09-27 | 2019-01-22 | 上海电气集团股份有限公司 | Robot control method and system based on admittance control algorithms |
| CN109366488A (en) * | 2018-12-07 | 2019-02-22 | 哈尔滨工业大学 | A kind of superimposed oscillation power Cartesian impedance control method of object manipulator assembly |
| US20200206943A1 (en) * | 2019-01-02 | 2020-07-02 | Research & Business Foundation Sungkyunkwan University | Apparatus and method for controlling robot |
| CN109910005A (en) * | 2019-03-04 | 2019-06-21 | 上海电气集团股份有限公司 | Change admittance control method and system for robot |
| CN110597072A (en) * | 2019-10-22 | 2019-12-20 | 上海电气集团股份有限公司 | Robot admittance compliance control method and system |
| CN110977974A (en) * | 2019-12-11 | 2020-04-10 | 遨博（北京）智能科技有限公司 | Admittance control method, device and system for avoiding singular position type of robot |
| JP2021117918A (en) * | 2020-01-29 | 2021-08-10 | 株式会社人機一体 | Drive unit having admittance control |
| CN111230873A (en) * | 2020-01-31 | 2020-06-05 | 武汉大学 | Teaching learning-based collaborative handling control system and method |
| CN111281743A (en) * | 2020-02-29 | 2020-06-16 | 西北工业大学 | Self-adaptive flexible control method for exoskeleton robot for upper limb rehabilitation |
| CN111660307A (en) * | 2020-05-27 | 2020-09-15 | 华中科技大学 | Robot operation high-assistance precision virtual clamp control method and system |
| CN111660306A (en) * | 2020-05-27 | 2020-09-15 | 华中科技大学 | Robot variable admittance control method and system based on operator comfort |
| WO2022007358A1 (en) * | 2020-07-08 | 2022-01-13 | 深圳市优必选科技股份有限公司 | Impedance control method and apparatus, impedance controller, and robot |
| CN112276944A (en) * | 2020-10-19 | 2021-01-29 | 哈尔滨理工大学 | Man-machine cooperation system control method based on intention recognition |
| CN113352322A (en) * | 2021-05-19 | 2021-09-07 | 浙江工业大学 | Adaptive man-machine cooperation control method based on optimal admittance parameters |
| CN113568313A (en) * | 2021-09-24 | 2021-10-29 | 南京航空航天大学 | Variable admittance auxiliary large component assembly method and system based on operation intention identification |
| CN113733105A (en) * | 2021-10-18 | 2021-12-03 | 哈尔滨理工大学 | Cooperative mechanical arm fuzzy variable admittance control system and method based on human intention recognition |
| CN114406983A (en) * | 2021-12-06 | 2022-04-29 | 中国科学院深圳先进技术研究院 | Adaptive admittance control method and related device for lower limb exoskeleton robot |
Non-Patent Citations (1)
| Title |
|---|
| 杨静宜等: "基于特征深度学习的机器人协调操作感知控制", 《计算机仿真》, vol. 38, no. 1, pages 307 - 311 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114932557B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111660306B (en) | Robot variable admittance control method and system based on operator comfort | |
| US11772264B2 (en) | Neural network adaptive tracking control method for joint robots | |
| CN110450156B (en) | Optimal design method of self-adaptive fuzzy controller of multi-degree-of-freedom mechanical arm system | |
| Mueller et al. | Iterative learning of feed-forward corrections for high-performance tracking | |
| CN105773623A (en) | SCARA robot trajectory tracking control method based on prediction indirect iterative learning | |
| CN113601512B (en) | General avoidance method and system for singular points of mechanical arm | |
| CN111249005A (en) | Puncture surgical robot compliance control system | |
| CN112338913B (en) | Trajectory tracking control method and system of multi-joint flexible mechanical arm | |
| CN107160396A (en) | A kind of robot vibration controller and method based on track optimizing | |
| JPH06131009A (en) | Feedback controller | |
| CN107085432B (en) | Target track tracking method of mobile robot | |
| CN113199477B (en) | Baxter mechanical arm track tracking control method based on reinforcement learning | |
| CN115256401A (en) | Space manipulator shaft hole assembly variable impedance control method based on reinforcement learning | |
| CN107511830B (en) | Adaptive adjustment realization method for parameters of five-degree-of-freedom hybrid robot controller | |
| CN114932557A (en) | Adaptive admittance control method based on energy consumption under kinematic constraint | |
| CN112936277A (en) | Underwater robot-manipulator system fixed time trajectory tracking method | |
| WO2023116129A1 (en) | Compliant force control method and system for collaborative robot | |
| CN109176529B (en) | Self-adaptive fuzzy control method for coordinated movement of space robot | |
| Stulp et al. | Reinforcement learning of impedance control in stochastic force fields | |
| Mitrovic et al. | Adaptive optimal control for redundantly actuated arms | |
| Lange et al. | Iterative self-improvement of force feedback control in contour tracking. | |
| CN114063621A (en) | Wheeled robot formation tracking and obstacle avoidance control method | |
| CN114879508A (en) | Grinding robot path tracking control method based on model prediction control | |
| CN114397810A (en) | Four-legged robot motion control method based on adaptive virtual model control | |
| Macnab | Neural-adaptive backstepping for flexible-joint robots with neither extra parameters, extra networks, nor robust terms |
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 |