Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A multi-group robot cooperative control method and control system based on reinforcement learning

A technology of group robot and cooperative control, applied in the direction of control/regulation system, two-dimensional position/channel control, non-electric variable control, etc., can solve the problem of multi-group robot algorithm difficult to efficiently avoid information interaction, etc., to improve navigation efficiency , the effect of improving efficiency

Active Publication Date: 2021-03-12
NANJING UNIV
View PDF28 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that it is difficult for existing multi-group robot algorithms to efficiently avoid and perform information interaction when robots meet

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 multi-group robot cooperative control method and control system based on reinforcement learning
  • A multi-group robot cooperative control method and control system based on reinforcement learning
  • A multi-group robot cooperative control method and control system based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Such as figure 1 As shown, the multi-group robot cooperative control method based on reinforcement learning provided by the present invention includes the following steps:

[0049] Step 1. Rasterize the environment of the robot to obtain the environment grid, so that the channel information is converted into a finite state set, and each group of robots performs intensive learning on the environment according to the finite state set to generate a state action table;

[0050] Step 2, each robot in the group shares reinforcement learning results with each other;

[0051] Step 3: Avoidance control is performed when the robots in the groups meet, and the state-action table in each group is shared to determine the action selected by the robot in the current state, thereby further generating a set of state-actions in the entire environment;

[0052] Step 4, use the generated action set of the whole environment state to carry out collaborative control on each group of robots. ...

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 provides a multi-group robot cooperative control method and system based on reinforcement learning. The steps of the method include: generating a state-action table through reinforcement learning, sharing reinforcement learning results among the robots in the group, sharing the state-action table when encountering each other to generate a full-environment state-action set, and using the full-environment state-action set to carry out cooperative control of each group of robots. The system includes environment mapping module, intra-group learning sharing module, inter-group learning sharing module and collaborative control module. The multi-group robot cooperative control method and system learn the actions of a single robot in the corresponding state through the reinforcement learning algorithm, and based on this, interact within the group, share the learning effect of a robot group, and finally when the robots in the group meet , share all the information in the group, and perform robot avoidance to improve the efficiency of reinforcement learning; use the inter-group multi-robot transfer learning mechanism to improve the efficiency of multi-robot navigation in large-area spaces.

Description

technical field [0001] The invention relates to a multi-group robot cooperative control method and control system, in particular to a multi-group robot cooperative control method and control system based on reinforcement learning for warehousing and logistics. Background technique [0002] When traditional industrial robots gradually replace monotonous, highly repetitive, and dangerous tasks, the collaborative work of robots will gradually penetrate into various industrial fields. The collaboration between robots and robot groups is easy to manage, can effectively improve production efficiency and save time, so it is particularly widely used in warehousing and logistics. In the research of multi-group robot cooperative control system, the focus is on how to carry out effective information exchange within and between robot groups, and realize effective control of multi-group robot cooperation. [0003] The use of teams of robots can accomplish some tasks more efficiently tha...

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): G05D1/02
CPCG05D1/0212G05D1/0221G05D1/0287
Inventor 陈春林王岚刁敏敏唐开强任其成王子辉朱长青辛博
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com