Reinforcement-learning-based optimization method for ecological driving behavior at an urban road intersection

A technology of reinforcement learning and optimization methods, applied in the direction of traffic signal control, data processing application, prediction, etc., can solve difficult and different traffic conditions, complex solving process and other problems

Active Publication Date: 2018-06-19
ZHEJIANG NORMAL UNIVERSITY
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods require a complex solution process and are difficult to be practically applied to different traffic conditions

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
  • Reinforcement-learning-based optimization method for ecological driving behavior at an urban road intersection
  • Reinforcement-learning-based optimization method for ecological driving behavior at an urban road intersection
  • Reinforcement-learning-based optimization method for ecological driving behavior at an urban road intersection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1 provides a method for optimizing ecological driving behavior at urban road intersections based on reinforcement learning. The driving behavior in this embodiment 1 is an ecological driving behavior mode, that is, at any time, the vehicle selects the corresponding desired action A' according to the maximum value in each column in the sub-matrix in the Q matrix t . Considering the position, speed and signal lights of the vehicle, the final action A can be obtained t . Vehicle option A t to update speed and position.

[0055] Execute in the MATLAB environment. The length of the cell is 3.5 meters, the maximum speed v max 5cell / s

[0056] (63km / h), each vehicle has 6 discrete speeds, from 0cell / s, 1cell / s, 2cell / s, 3cell / s, 4cell / s to 5cell / s, representing 0km / h, 1.6km / h, 25.2km / h, 37.8km / h, 50.4km / h and 63.0km / h. The length L of the upstream of the lane up For 40 cells (ie 140m). The length L of the downstream of the lane down For 20 cells (ie 70m)...

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 a reinforcement-learning-based optimization method for an ecological driving behavior at an urban road intersection. The method comprises the following steps: establishing a simulation platform by using a cellular automata model; placing a vehicle on the simulation platform for reinforcement learning; after reinforcement learning on the vehicle, obtaining a Q matrix; and optimizing the driving behavior of the vehicle by using the obtained Q matrix to realize ecological driving. With the evaluation method based on reinforcement learning and the microscopic simulation platform, the influences on vehicle exhaust emission and traffic characteristics by the ecological driving behavior are studied to provide useful information for improvement of the strategy of the vehicleecological driving.

Description

technical field [0001] The invention relates to a method for optimizing ecological driving behavior at urban road intersections based on reinforcement learning. Background technique [0002] With the growth of population and motor vehicles, especially the continuous increase of vehicle-kilometers, vehicle emissions have become an important issue in many countries. In 2014, total U.S. greenhouse gas emissions were 6.870 billion metric tons of carbon dioxide equivalent, about 26% of which came from transportation. In the same year, China's total vehicle emissions were 45.437 million tons, including 6.278 million tons of nitrogen oxides, 4.244 million tons of hydrocarbons, and 34.373 million tons of carbon monoxide. Such a huge amount of emissions has brought enormous environmental pressure to the earth. Based on this, a series of emission reduction strategies have been used to alleviate the environmental pressure from the transportation sector. [0003] "Eco-driving" optimi...

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): G08G1/07G06Q10/04
CPCG06Q10/04G08G1/07
Inventor 施俊庆胡永举邱欣陈林武赵雅辉
Owner ZHEJIANG NORMAL UNIVERSITY
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