A Constrained Motion Planning Method for Space Dual-Arm System Based on Deep Reinforcement Learning

A technology that strengthens learning and constrains movement. It is applied in the direction of program-controlled manipulators, manufacturing tools, and manipulators. It can solve the problems of mechanical arm collision damage and poor versatility, and achieve the effect of improving safety and improving versatility.

Active Publication Date: 2021-11-23
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the above-mentioned prior art, the purpose of the present invention is to provide a space dual-arm system constrained motion planning method based on deep reinforcement learning to solve the problem of poor versatility of traditional motion planning methods in the prior art and unconstrained based Problems such as collision damage of the robotic arm caused by the motion planning method of the deep reinforcement learning algorithm

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 Constrained Motion Planning Method for Space Dual-Arm System Based on Deep Reinforcement Learning
  • A Constrained Motion Planning Method for Space Dual-Arm System Based on Deep Reinforcement Learning
  • A Constrained Motion Planning Method for Space Dual-Arm System Based on Deep Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the embodiments and accompanying drawings, and the contents mentioned in the embodiments are not intended to limit the present invention.

[0060] refer to figure 1 As shown, a method for constrained motion planning of a space dual-arm system based on deep reinforcement learning of the present invention, the steps are as follows:

[0061] 1) Using the generalized Jacobian matrix to establish the kinematics model of the dual-manipulator system in free-floating space;

[0062] The kinematics model of the space dual manipulator system is established according to the following formula (1):

[0063]

[0064] in, I v 0 and I ω 0 are the velocity vector and angular velocity vector of the space manipulator base in the inertial reference system, respectively; and are the velocity vector and angular velocity vector of the firs...

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 invention discloses a constrained motion planning method for a space dual-arm system based on deep reinforcement learning. The kinematic model of the arm system is combined with the DDPG algorithm to design the motion planning algorithm of the space dual-arm system; 3) The reward function in the DDPG algorithm is designed to meet the constraints in the motion planning algorithm of the space dual-arm system, including mechanical The velocity constraints of the end-of-arm actuators and the self-collision constraints of the coordinated motion of the dual robotic arms. The invention improves the universality and safety of the motion planning algorithm.

Description

technical field [0001] The invention belongs to the technical field of motion planning of a space manipulator, and in particular relates to a constrained motion planning method for a space dual-arm system based on deep reinforcement learning. Background technique [0002] As a very effective executive mechanism in space manipulation tasks, the space manipulator has high engineering application value in space manipulation tasks such as repairing faulty satellites, removing space debris, and assembling large space structures. Due to the influence of the microgravity environment in space, there are obvious differences in the motion characteristics of the space manipulator and the ground manipulator. Specifically, the ground manipulator generally has a fixed base, while the space manipulator generally has a fixed base while the space manipulator performs tasks. are in a free-floating state. Compared with the space single-arm system, the space dual-arm system is safer and more r...

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
CPCB25J9/1607B25J9/1615B25J9/1664
Inventor 李爽李胤慷佘宇琛
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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