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

Unmanned cluster task collaboration method based on multi-agent reinforcement learning

A reinforcement learning, multi-agent technology, applied in non-electric variable control, instruments, control/regulation systems, etc., can solve problems such as multiple constraints, and achieve the effect of facilitating collaboration

Pending Publication Date: 2021-11-02
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF0 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Based on the above analysis, it can be seen that multi-unmanned system mission planning is a multi-constraint and dynamic optimization problem. When the number of unmanned systems and tasks is large and the task environment is complex and changeable, it is difficult to solve it with mathematical programming methods.

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
  • Unmanned cluster task collaboration method based on multi-agent reinforcement learning
  • Unmanned cluster task collaboration method based on multi-agent reinforcement learning
  • Unmanned cluster task collaboration method based on multi-agent reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

specific example

[0154] 1. Experimental conditions and methods

[0155] The hardware platform is: Intel(R) Core(TM) i5-9400F CPU@2.90GHZ, 32GB RAM;

[0156] The software platform is: Tensorflow 1.8.0, Unity 4.6.1, gym 0.17.2;

[0157] Experimental methods: deep deterministic policy gradient (DDPG), multi-agent deep deterministic policy gradient (MADDPG), collaborative deep deterministic policy gradient algorithm (CODDPG) proposed by the present invention.

[0158] 2. Simulation content and results

[0159] A scenario with 30 defenders and 20 intruders is set, and k=3, l=3, ψ=0.3, η=3, ζ=0.5 (k is the number of defenders required to destroy an intruder, and l is The number of UAVs that a UAV can perceive, ψ, η, ζ are the correlation coefficients of rewards), such as Figure 5 shown. At this time, the defender is concentrating on eliminating the intruder coming from the lower right. The scene ends when all invaders are eliminated or any invaders enter the target area. In this scenario, the...

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 an unmanned cluster task collaboration method based on multi-agent reinforcement learning, and belongs to the technical field of unmanned cluster task planning. According to the method, the method comprises the steps of: establishing a reinforcement learning simulation environment for task planning of the multi-unmanned system based on Unity; using Gym to build the acquired information of the simulation environment into a reinforcement learning environment conforming to the specification; modeling an unmanned aerial vehicle cluster confrontation environment; using a Tensorflow deep learning library for building a multi-agent reinforcement learning environment; solving a multi-agent reinforcement learning problem by using a collaborative depth deterministic strategy gradient method; and outputting an unmanned cluster task planning result. According to the method, the prior art is greatly improved, and a better multi-unmanned-system cooperative task planning result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of unmanned swarm task planning, in particular to an unmanned swarm task coordination method based on multi-agent reinforcement learning. Background technique [0002] Unmanned systems are widely used in military and civilian fields, especially unmanned aerial vehicles, which have the characteristics of low cost, flexible maneuverability, convenient deployment, and long endurance. good choice. Due to the limited type and quantity of equipment carried by a single drone, its effectiveness is also very limited. In recent years, the development of UAVs has focused on cluster situation awareness, information sharing, cluster task planning, cluster task coordination and execution, etc. In response to the above situation, the lack of task execution capability of a single drone is made up for by using multiple drones to cooperate. Therefore, the development trend of UAV technology must be to realize multi-machine...

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 Applications(China)
IPC IPC(8): G05D1/10
CPCG05D1/104Y02T10/40
Inventor 陈彦桥王雅涵李晨阳关俊志耿虎军高峰张泽勇蔡迎哲柴兴华
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
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