Unmanned cluster evolution system and method based on meta-action sequence reinforcement learning

A reinforcement learning, meta-action technology, applied in control/regulation systems, combustion engines, non-electric variable control, etc., can solve problems such as difficulty in building an unmanned swarm decision-making model, poor environmental adaptability, and lack of evolutionary ability, to promote The effect of transformation, strong generalization ability, and overcoming construction difficulties

Pending Publication Date: 2022-05-17
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the current unmanned swarm decision-making model construction difficulties, poor environmental adaptability, lack of evolution ability, etc., the present invention provides an unmanned swarm evolution system and method based on meta-action sequence reinforcement learning. The present invention has strong generalization Capability, high robustness when dealing with complex dynamic scenes

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 evolution system and method based on meta-action sequence reinforcement learning
  • Unmanned cluster evolution system and method based on meta-action sequence reinforcement learning
  • Unmanned cluster evolution system and method based on meta-action sequence reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0033] An unmanned swarm evolution system based on meta-action sequence reinforcement learning, including six main components: unmanned swarm simulation environment, swarm strategy model library, effectiveness evaluation module, situation awareness module, swarm strategy evolution module and swarm decision-making module. Some functions are described as follows:

[0034] Unmanned swarm simulation environment: Provide models of various types of unmanned systems such as drones, unmanned vehicles, and unmanned ships, and can import multiple types of 3D environment models, and provide unmanned system drivers and environmental information reading interfaces to support unmanned Simulation and deduction of intelligent algorithms such as swarm cooperative flight, unmanned swarm mission planning, and deep reinforcement learning.

[0035] Swarm strategy model library: ...

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 evolution system and method based on meta-action sequence reinforcement learning, and belongs to the field of unmanned cluster autonomous task collaboration. According to the method, firstly, a plurality of tasks faced by an unmanned cluster are decomposed into basic meta-actions, a mapping relation between environment information and a meta-action sequence is constructed through an estimation network, a task efficiency evaluation index is used as a reward function of reinforcement learning, and self-adaptive reinforcement learning is carried out through a plurality of scenes, so that the evolution of unmanned cluster task capability is realized. The system has strong generalization ability, and has high robustness when coping with complex dynamic scenes.

Description

technical field [0001] The invention belongs to the field of unmanned swarm autonomous task coordination, in particular to an unmanned swarm evolution system and method based on meta-action sequence reinforcement learning. Background technique [0002] At present, the demand for unmanned operations is rising sharply in various fields. The traditional unmanned autonomous system model of a single platform is gradually restricted from playing its due role in more scenarios due to its low anti-risk ability and single task type. New technologies are sought The breakthrough is the only way to maintain the advantage of unmanned. Among them, the use of existing unmanned units to build "unmanned swarms", where different units with limited capabilities work together to complete complex tasks and achieve low-cost, low-risk, and high-efficiency mission goals, can represent the development trend of the future unmanned system field . The unmanned swarm system is composed of a certain nu...

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): G05D1/00
CPCG05D1/0088Y02T10/40
Inventor 柴兴华耿虎军张小龙陈彦桥牛韶源李晨阳高峰关俊志王雅涵彭会湘陈勇宗茂
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
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