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

Underwater unmanned vehicle safety opportunistic routing method and device based on reinforcement learning

An unmanned vehicle and reinforcement learning technology, applied in the safety opportunity routing of underwater unmanned vehicles, the field of safety opportunity routing of underwater unmanned vehicles based on reinforcement learning, can solve small topology changes, empty nodes, and can not be autonomous Mobile and other issues, to achieve the effect of optimizing overall performance, achieving security and efficiency, and avoiding effective transmission

Active Publication Date: 2022-02-08
HARBIN ENG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention solves the problem of underwater sensor nodes that cannot move autonomously, whose topological changes are very small, and the sensor nodes only record the interactive information with neighbor nodes, and cannot move autonomously; they cannot select the meeting nodes during the movement, and realize the final information of their messages. Safe and efficient transmission and the problem of easy to cause empty nodes

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
  • Underwater unmanned vehicle safety opportunistic routing method and device based on reinforcement learning
  • Underwater unmanned vehicle safety opportunistic routing method and device based on reinforcement learning
  • Underwater unmanned vehicle safety opportunistic routing method and device based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment one, see figure 1 This embodiment will be described. A safety opportunity routing method for underwater unmanned vehicles based on reinforcement learning described in this embodiment, the method includes:

[0054] The underwater unmanned vehicle is initially screened within the node-to-communication range, and a trust evaluation model is established based on the initially screened nodes;

[0055] Establish a trust evaluation model based on the initially screened nodes for evaluation, the evaluation elements of the evaluation model are composed of two parts: direct trust value DTValue and indirect trust value ITValue;

[0056] The evaluation elements are input into the fuzzy logic system to obtain the comprehensive trust value of the evaluation node, and the comprehensive trust value of the evaluation node is updated to the dynamic table of the trust value of the meeting node;

[0057] According to the comprehensive trust value of evaluation nodes output by ...

Embodiment 2

[0059] Embodiment two, see figure 1 This embodiment will be described. This embodiment is a further limitation of the safety opportunity routing method for underwater unmanned vehicles based on reinforcement learning described in the first embodiment. In this embodiment, the underwater unmanned vehicles are within the node-to-node communication range The process of initial screening and establishing a trust evaluation model based on the initially screened nodes is as follows:

[0060] The underwater unmanned vehicle node carrying the message sends a broadcast to other nodes within the communication range, requests other nodes to feed back their node information, obtains data packets, performs initial screening according to the indirect trust value ITValue in the other party's data packet information, and selects the indirect trust value Nodes exceeding the threshold are further evaluated as candidate relay nodes.

[0061] In this embodiment, node information is obtained by p...

Embodiment 3

[0062] Embodiment three, refer to figure 2 This embodiment will be described. This embodiment is a further limitation of the safety opportunity routing method for underwater unmanned vehicles based on reinforcement learning described in Embodiment 1. In this embodiment, the evaluation elements of the direct trust value DTValue are selected as: 1. The relative distance between nodes is calculated by the time difference between sending and receiving node data packets, and the path loss is estimated by the relative distance between nodes to measure the communication quality between nodes; 2. Node familiarity; 3. Node relay ratio.

[0063] The indirect trust value DTValue guarantees the objectivity of the evaluation of the current node, each node maintains a dynamic trust value table, records the comprehensive trust value data of other nodes to itself, and the average value of the data in the dynamic trust value table is output as the indirect trust value .

[0064] In this emb...

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 underwater unmanned vehicle safety opportunistic routing method and device based on reinforcement learning, and belongs to the technical field of sensors. At present, objects of underwater exploration are sensor nodes which cannot autonomously move underwater; encountering nodes cannot be selected in a moving process; and it is likely to cause hole nodes. The invention provides an underwater unmanned vehicle safety opportunistic routing method based on reinforcement learning. The method comprises the following steps: screening nodes by an underwater unmanned vehicle for the first time in a communication range, and establishing a trust evaluation model; establishing the trust evaluation model for evaluation according to the preliminarily screened nodes; inputting evaluation elements into a fuzzy logic system, obtaining an evaluation node comprehensive trust value, and updating the evaluation node comprehensive trust value into an encountering node trust value dynamic table; and according to the evaluation node comprehensive trust value output by the fuzzy logic system, using reinforcement learning to perform routing selection, set a state-action value updating function and set a reward function. The invention is applied to the field of underwater unmanned vehicle safety opportunistic routing.

Description

technical field [0001] The invention relates to the field of safety opportunity routing for underwater unmanned vehicles, in particular to the field of safety opportunity routing for underwater unmanned vehicles based on reinforcement learning. Background technique [0002] Underwater detection and resource exploration have received widespread attention in recent years. Through underwater detection and resource exploration, underwater environment prediction, disaster forecast, and military situational awareness can be realized. The existing public invention CN112188583A "a marine environment based on reinforcement learning "Opportunistic Routing Method for Underwater Wireless Perceptual Networks", which proposes the idea of ​​combining reinforcement learning and opportunistic routing, but the target is underwater sensor nodes that cannot move autonomously, whose topology changes very little, and sensor nodes only record interactions with neighbor nodes Information cannot mov...

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): H04W40/12H04L45/02
CPCH04W40/12H04L45/08Y02D30/70
Inventor 王桐崔立佳高山陈立伟
Owner HARBIN ENG 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