A tracking control method and system for fixed-time trajectory tracking of manipulator input saturation

A fixed time, trajectory tracking technology, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve problems such as inaccuracy and speed

Active Publication Date: 2021-06-01
UNIV OF SCI & TECH BEIJING
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these existing trajectory tracking control methods cannot overcome the inaccurate and fast problem of the trajectory tracking control of the manipulator caused by the uncertainty of the dynamic model, coupling effects and external unknown disturbance factors; therefore, it is urgent to explore an effective The trajectory tracking control technology of the manipulator

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A tracking control method and system for fixed-time trajectory tracking of manipulator input saturation
  • A tracking control method and system for fixed-time trajectory tracking of manipulator input saturation
  • A tracking control method and system for fixed-time trajectory tracking of manipulator input saturation

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0101] First of all, it needs to be explained that the artificial neural network has the ability to map the input-output relationship only by using the prior input-output information. Because the neural network has good function approximation ability, it is widely used in the control of uncertain nonlinear systems. design.

[0102] The method based on Radial Basis Function Neural Network (RBFNN) is feasible to approximate nonlinear functions with arbitrary precision under certain conditions. With no or relatively limited knowledge of system dynamics, it is possible to efficiently construct a controller to achieve mission control. There are a large number of examples of intelligent control methods such as sliding mode control, dynamic surface control, impedance control, and fuzzy logic control in engineering.

[0103] Reinforcement learning is different from supervised learning in that it is a learning method that obtains training information from the environment and is an eva...

no. 2 example

[0251] This embodiment provides a trajectory tracking control system for fixed time input saturation of a manipulator, which includes:

[0252] The expected trajectory and state data acquisition module of the mechanical arm is used to obtain the expected trajectory of the mechanical arm, and obtain the state data of the mechanical arm through the sensor of the mechanical arm;

[0253] The reinforcement learning control module is used to suppress the model uncertainty of the mechanical arm by using the reinforcement learning control algorithm according to the acquired state data;

[0254] The nonlinear anti-saturation compensator design module is used to design the nonlinear anti-saturation compensator to compensate the saturation overflow effect of the joint torque actuator in real time;

[0255] Non-singular fast terminal sliding mode controller is used to design non-singular fast terminal sliding mode controller, so that the trajectory tracking error of the manipulator joint...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides a trajectory tracking control method and system for a fixed-time input saturation of a robotic arm. The method includes: obtaining the expected trajectory of the robotic arm, and obtaining the state data of the robotic arm through a robotic arm sensor; according to the obtained state data, using reinforcement learning The control algorithm suppresses the model uncertainty of the manipulator; the nonlinear anti-saturation compensator is designed to compensate the saturation overflow effect of the joint torque actuator in real time; the non-singular fast terminal sliding mode controller is designed to make the tracking error of the manipulator joint trajectory within a fixed time Converge to the small neighborhood of the origin, and realize the desired trajectory tracking control of the input saturation fixed time of the manipulator. The method of the invention has the online learning ability of model uncertainty, so that the mechanical arm can track the trajectory accurately and quickly.

Description

technical field [0001] The invention relates to the technical field of trajectory tracking of a robotic arm, in particular to a method and system for controlling trajectory tracking of a robotic arm with input saturation at fixed time based on reinforcement learning. Background technique [0002] Manipulators are widely used in dangerous environments such as military, manufacturing, and medical environments. The trajectory tracking control technology of manipulators has always been one of the hot research directions. The movement of manipulators according to the joint trajectories set in advance is the key to realizing these complex tasks. The key to the mission; however, it is very difficult for the manipulator to track the trajectory accurately and quickly due to the uncertainty of the dynamic model, coupling effects and external unknown interference problems. [0003] In recent years, many trajectory tracking control methods have appeared, including PID control, adaptive ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): B25J9/16
CPCB25J9/1605B25J9/163B25J9/1664
Inventor 孙亮曹胜杰
Owner UNIV OF SCI & TECH BEIJING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap