Unmanned aerial vehicle full-area reconnaissance path planning method of unsupervised learning type neural network

An unsupervised learning and neural network technology, applied in the field of intelligent decision-making of unmanned systems, can solve the problem of missing target information search and other problems, and achieve the effect of good transferability and versatility

Active Publication Date: 2020-07-10
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not consider the missing problem of target information search, that is, it do

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 aerial vehicle full-area reconnaissance path planning method of unsupervised learning type neural network
  • Unmanned aerial vehicle full-area reconnaissance path planning method of unsupervised learning type neural network
  • Unmanned aerial vehicle full-area reconnaissance path planning method of unsupervised learning type neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0091] The present invention adopts the unsupervised training method of the neural network through the genetic algorithm to complete the regional coverage path planning task, mainly including: 1. Constructing the environmental model, the UAV model and the environmental threat constraint model; 2. Setting the threat assessment index, for Evaluate the flight efficiency of the UAV during the execution of the mission; 3. Construct the neural network model, set the adaptive function, and then construct the neural network unsupervised learning model; 4. Based on the constructed global model, train the neural network; 5 .Load the offline learning results of maps with known environmental information, and verify and apply online the maps with unknown environmental information.

[0092] Specifically, model the grid digital map and UAV motion model, use the nonlin...

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 provides an unmanned aerial vehicle full-area reconnaissance path planning method of the unsupervised learning type neural network. Neural network parameters for controlling maneuveringof the unmanned aerial vehicle are obtained through iterative offline learning, so that the unmanned aerial vehicle can reconnaissance the whole area as quickly as possible on the premise of autonomously avoiding threats. Meanwhile, the maneuvering decision neural network obtained by the method has good mobility and universality in different terrains, and a new solution is provided for the unmanned aerial vehicle in intelligent path planning and autonomous maneuvering decision directions. The method is simple, convenient and efficient, the problem of re-planning or re-planning of the unmannedaerial vehicle due to environmental information change is effectively reduced, and the training time cost is effectively saved.

Description

technical field [0001] The invention relates to the field of intelligent decision-making of unmanned systems, in particular to a path planning method for unmanned aerial vehicles. Background technique [0002] With the acceleration of computer processing speed, the improvement of automation, the reduction of sensor size and other related technologies, the application value of unmanned aerial vehicles in map mapping, target search, power inspection and forest fire prevention has continued to increase. In view of the problems that UAVs need to autonomously avoid obstacles when performing reconnaissance missions, it is an important functional requirement to provide UAVs with path planning capabilities, and it is a prerequisite for realizing autonomous decision-making of unmanned systems to perform complex tasks. For many reasons, the autonomous flight of drones still faces great challenges in the field of intelligent decision-making. On the one hand, the limitations of existin...

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
IPC IPC(8): G05D1/10
CPCG05D1/101
Inventor 李波杨志鹏马浩万开方甘志刚越凯强
Owner NORTHWESTERN POLYTECHNICAL UNIV
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