Machine learning strategy based distance preferred optimal path selection method

A distance-first, best-path technology, applied in the field of IoT

Inactive Publication Date: 2019-06-28
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF6 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problems of path planning and path selection in the process of intelligent vehicles

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
  • Machine learning strategy based distance preferred optimal path selection method
  • Machine learning strategy based distance preferred optimal path selection method
  • Machine learning strategy based distance preferred optimal path selection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] For the Genetic Algorithm (GA), Ant Colony Optimization (ACO), Artificial Neural Networks (ANNs) and Particle Swarm Optimization (PSO), which are often used in intelligent robot path planning , compared with the design algorithm OPABRL in terms of algorithm function and performance, the advantages and disadvantages of the designed algorithm are explained by analyzing the results of the policy.

[0043] 1. Reinforcement learning prior knowledge training;

[0044] In the process of intelligent vehicle travel, the problems we have to solve include two aspects: path planning and path selection. In order to simplify the system, we first describe the reinforcement learning strategy and update rules based on prior knowledge:

[0045] Assuming that the intelligent driving vehicle has been driving on a road with a certain width, the problem of path planning can be understood as solving the problem of planning one or more roads that can reach the end point from the starting poin...

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

Provided is a machine learning strategy based distance preferred optimal path selection method (OPABRL). A local path is planned according to path direction, width, curvature road intersect and faultdetail information in practical application of an intelligent driving vehicle. A reinforced learning algorithm is known and learned to design the prior knowledge based optimal path selection method ofthe reinforced learning strategy, the searching direction for the shortest path is set in the program, and the shortest path searching process is simplified. The path optimization method can be usedto help different types of intelligent driving vehicles plan an optimal path in the traffic network with height, width and weight limits or in accident/jamming conditions smoothly. According to simulation and scene experiments, the method of the invention is higher in efficiency and practicality compared with existing ACO, GA, ANNs and PSO algorithms.

Description

【Technical field】 [0001] The invention belongs to the field of the Internet of Things, and relates to a distance-priority optimal path selection method based on a machine learning strategy. 【Background technique】 [0002] The most commonly used Q-Learning algorithm in reinforcement learning learns an overall optimal strategy by establishing an evaluation function to evaluate the quality of actions. The Markov decision process provides a theoretical framework for reinforcement learning, and its process can be described by a quaternion <S, A, P, R>, where S represents the state collection; A represents the action collection; P represents the state transition probability matrix, and That is, when the agent is in the state s at the current moment, the probability of performing action a to transfer to state s′; R represents the reward function, and That is, when the agent is in the state s, the reward that can be obtained by performing action a. The idea of ​​Q-Learnin...

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): G05D1/02G06N3/00
Inventor 张德干龚倡乐刘晓欢张婷崔玉亚宋金杰
Owner TIANJIN UNIVERSITY OF TECHNOLOGY
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