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

Construction Method of Driver's Longitudinal Car Following Behavior Model Based on Deep Reinforcement Learning

A reinforcement learning and driver technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as randomness and complexity of difficult driver following behavior

Active Publication Date: 2021-10-29
XIAMEN UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this model is made by linear or non-linear fitting based on the state information of the following car, which is difficult to truly reflect the randomness and complexity of the driver's following behavior.

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
  • Construction Method of Driver's Longitudinal Car Following Behavior Model Based on Deep Reinforcement Learning
  • Construction Method of Driver's Longitudinal Car Following Behavior Model Based on Deep Reinforcement Learning
  • Construction Method of Driver's Longitudinal Car Following Behavior Model Based on Deep Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0039] The schematic flow chart of the driver's longitudinal car-following behavior model of the present invention is as follows: figure 1 shown. Firstly, collect the data of the driver’s car-following behavior that conforms to the characteristics of Chinese roads, and give the key parameters representing the benchmark information of the driver’s behavior. Secondly, build a deep neural network structure of the driver’s longitudinal car-following behavior model to effectively solve the problem of driver’s car-following behavior. The decision-making problem in the continuous action space in the behavior process, and then, the training method of the driver's longitudinal car-following behavior model based on deep reinforcement learning is designed to realize the verification and evaluation of the driver's longitudinal car-following behavior model. The s...

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

A method for constructing a driver's longitudinal following behavior model based on deep reinforcement learning belongs to the field of automotive intelligent safety and automatic driving. Based on the actual road conditions in China, collect the vehicle status information and surrounding environment information during the driving process of the driver that conforms to the characteristics of the Chinese road, statistically analyze the collected data, and give the behavior characteristics and influencing factors of the driver's driving process . Determine the benchmark information that characterizes the actions taken by the driver at a certain moment, and establish a mathematical model that describes the iterative relationship of the driver's following behavior state. Design the neural network structure of the driver's longitudinal car-following behavior model based on the competitive Q network framework. Design the driver's longitudinal car-following behavior learning process based on the neural network of the competitive Q network architecture. Design a training method for a driver's longitudinal following behavior model based on deep reinforcement learning. It can accurately describe the characteristics of the driver's car-following behavior under different working conditions, and realize the reproducibility of the driver's car-following behavior.

Description

technical field [0001] The invention belongs to the field of automobile intelligent safety and automatic driving, and in particular relates to a method for constructing a driver's longitudinal car-following behavior model based on deep reinforcement learning. Background technique [0002] In the future, drivers will play an important role in the driving tasks of smart cars. In order to reduce the driver's driving burden, improve the driver's driving ability and acceptance of the intelligent driving system, it is necessary to conduct in-depth research on the driver's driving habits. Establishing a driver model that accurately reflects the driver's following behavior is of great significance for the development of control strategies for intelligent driving systems. [0003] In recent years, from different perspectives, such as traffic engineering perspective, human factors engineering perspective, etc., or based on different theories, using different research methods to study...

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): G08G1/0967G06N3/08G06N3/04
CPCG08G1/096725G06N3/08G06N3/048G06N3/045
Inventor 郭景华李文昌王靖瑶王班肖宝平
Owner XIAMEN 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