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

Network Adaptive Routing Method and System for Unmanned Systems Based on Deep Reinforcement Learning

A system network and reinforcement learning technology, applied in the field of self-adaptive routing of unmanned system network, can solve the problems of mobile robot network topology frequent changes, wireless link instability, unable to provide adaptive and reliable routing decisions, etc., to achieve a good model The effect of generalization ability, good network environment changes, and reliable data forwarding

Active Publication Date: 2021-11-30
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the purpose of the present invention is to propose a method and system for self-adaptive routing of the unmanned system network based on deep reinforcement learning, so as to solve the problems caused by the high-speed movement of nodes and the wireless link in the mobile unmanned system network in the prior art. Due to the influence of unstable roads and frequent changes in the network topology of mobile robots, it is impossible to provide adaptive and reliable routing decisions.

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
  • Network Adaptive Routing Method and System for Unmanned Systems Based on Deep Reinforcement Learning
  • Network Adaptive Routing Method and System for Unmanned Systems Based on Deep Reinforcement Learning
  • Network Adaptive Routing Method and System for Unmanned Systems Based on Deep Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to solve the problems of the technologies described above, the adopted technical solution of the present invention is:

[0058] Taking unmanned machines or devices in the unmanned system network as nodes, all nodes send HELLO information packets at an adaptive time interval; any node updates the neighbor table of the node after receiving the HELLO information packets sent by its neighbor nodes The node information of the neighbor node in ;

[0059] Establish a routing strategy algorithm framework based on deep reinforcement learning;

[0060] Design a routing policy implementation method based on deep reinforcement learning.

[0061] Further, the calculation method of the time interval for the node i to send the HELLO information packet is as follows:

[0062]

[0063] Among them, T min and T max are the preset minimum and maximum time intervals, respectively. v max is the preset maximum moving speed of the node i, is the average speed of the node i....

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 present invention proposes an adaptive routing method for unmanned system networks based on deep reinforcement learning, aiming to solve the technical problems in the prior art that the high-speed movement of nodes and the frequently changing network topology cannot provide adaptive routing strategies. The method includes: all nodes send HELLO information packets at an adaptive time interval; after any node receives the HELLO information packets sent by its neighbor nodes, update the node information of the neighbor node in the neighbor table of the node; Routing strategy algorithm framework of deep reinforcement learning; design of routing strategy implementation method based on deep reinforcement learning. The invention has good model generalization ability, and can be generalized on networks with different network scales and different node moving speeds, so that the invention is more suitable for unmanned system networks with dynamic changes.

Description

technical field [0001] The invention relates to an unmanned system network adaptive routing method based on deep reinforcement learning, which belongs to the field of information technology. Background technique [0002] An unmanned system (Unmanned System) is composed of a number of necessary data processing units, sensors, automatic control units, and communication systems. It is a machine or device that can complete specific tasks autonomously without human intervention. These unmanned machines or devices can be unmanned. drones, unmanned vehicles, ground robots, underwater robots, surface robots and satellites. [0003] An unmanned system network is a network established by unmanned systems in the form of self-organization or based on network infrastructure. Among them, the unmanned system network established in the form of self-organization can give full play to the perception ability and strong computing power of the unmanned system, and can effectively adapt to netwo...

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): H04L29/08H04L12/721H04L12/727H04L12/729H04L45/121H04L45/125
CPCH04L45/125H04L45/121H04L45/124H04L67/5682H04L67/63
Inventor 刘建敏王琪徐勇军何晨涛徐亦达
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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