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

Multi-Agent based robot combined search system by reinforcement learning

A technology of reinforcement learning and joint search, applied in the field of multi-robot joint target search, to achieve the effects of preventing collisions, improving search efficiency, and speeding up search speed

Active Publication Date: 2014-12-10
JIANGSU TOM PACKAGING MACHINERY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Designing the entire system with traditional centralized control or hierarchical control will encounter some insurmountable difficulties

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
  • Multi-Agent based robot combined search system by reinforcement learning
  • Multi-Agent based robot combined search system by reinforcement learning
  • Multi-Agent based robot combined search system by reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to further explain the technical means and effects that the present invention adopts to achieve the intended purpose of the invention, below in conjunction with the accompanying drawings and preferred embodiments, the specific implementation, structure, features and effects of the present invention will be described in detail as follows: rear.

[0039] The research background of the present invention is as figure 1 As shown, in real life, it is often necessary to use robots to complete search tasks, such as the search for fire ignition points, radioactive substances or odor sources, etc. The search environment usually contains obstacles (walls, etc.), and the search target position is also unknown. .

[0040] The overall structure diagram of the reinforcement learning algorithm involved in the robot joint search system based on multi-agent reinforcement learning is as follows figure 2 As shown in Fig. 1, the robot Agent obtains state values ​​from the search...

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 relates to a multi-robot combined target search system, and in particular relates to a multi-Agent based robot combined search system by reinforcement learning. The system provided by the invention performs search on the condition of uncertain target location and uses a reinforcement learning algorithm which can not only accelerate the search speed, but also improve the search efficiency, thus effectively avoiding the problems of robots hitting a wall and collision among the robots and the like. The system is especially applied to search in dangerous regions or regions that human cannot reach, thereby the purposes of saving the search time, expanding the search region and better protecting personal and property safety and the like can be reached.

Description

technical field [0001] The invention relates to a multi-robot joint target search method, in particular to a multi-robot joint target search method based on multi-Agent reinforcement learning. Background technique [0002] Target localization and search in an unknown environment is a very suitable problem for mobile robots to solve. This automated method saves more time and resources than other search methods, and is particularly suitable for searching areas that are dangerous or inaccessible to humans. At present, multi-robot joint search technology is becoming an important direction in the field of robot research. [0003] A multi-robot system usually needs to be composed of several specialized subsystems that have both division of labor and cooperation, coordination and competition. Designing the whole system with traditional centralized control or layered control will encounter some insurmountable difficulties. The emergence of multi-agent technology provides a new id...

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): G06F15/18
Inventor 倪建军刘明华范新南谭宪军
Owner JIANGSU TOM PACKAGING MACHINERY
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