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

Expressway traffic efficiency improving method based on reinforced learning variable speed-limit control

A fast road and reinforcement learning technology, which is applied to the arrangement of variable traffic instructions, traffic control systems, traffic control systems of road vehicles, etc., can solve the problems that the control strategy cannot achieve the optimal control effect, and the impact and expectations are different. , to achieve the effect of improving expressway traffic efficiency and reducing system traffic time

Inactive Publication Date: 2016-11-23
SOUTHEAST UNIV
View PDF2 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The determination of the corresponding speed limit value under different traffic flow states in the existing variable speed limit control strategy depends on the subjective determination of the engineer's experience. achieve optimal control

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
  • Expressway traffic efficiency improving method based on reinforced learning variable speed-limit control
  • Expressway traffic efficiency improving method based on reinforced learning variable speed-limit control
  • Expressway traffic efficiency improving method based on reinforced learning variable speed-limit control

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The present invention is based on the basic principle of reinforcement learning Q-learning method and the basic process of variable speed limit control strategy, and proposes a strategy for variable speed limit control on the upstream of the bottleneck road section, and detects the bottleneck road section and its upstream and downstream traffic through a traffic flow detector The training database is generated by the flow operation situation. The agent masters the optimal variable speed limit value under different traffic flow states through offline learning. In actual control, the agent perceives the real-time traffic flow state through the measured traffic flow data on the expressway. Select the optimal speed limit value corresponding to the current state to dynamically adjust the traffic flow, and use the traffic flow data and speed limit value after the control to carry out continuous training on the agent. The flow chart of the improvement method is as follows figu...

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 expressway traffic efficiency improving method based on reinforced learning variable speed-limit control. The method comprises the steps that variable speed-limit values are determined in real time according to a reinforced learning method, an intelligent body perceives the running states of traffic flows on an expressway according to traffic flow data, a speed-limit value action is selected for the current state, a return valve of state transition caused by the action is calculated, the intelligent body traverses all state-action combinations till all state-action return values are convergent, and the intelligent body acquires the optimal speed-limit value action in the different traffic flow states off line; the intelligent body automatically selects the optimal speed-limit value corresponding to the current state and issues the optimal speed-limit value according to the real-time traffic flow data, and the controlled traffic flow data and speed-limit values are transmitted to a control center, so that the intelligent body continuously learns. According to the method, the defect that in the past, the subjective arbitrariness is generated when the corresponding relation between the traffic flow state and the speed-limit values in variable speed-limit control is determined is overcome, and the anti-jamming capability of a control system is improved; the affecting law of the speed-limit values on traffic efficiency improving is continuously mined through the intelligent body, therefore, feedback regulation is conducted on the variable speed-limit values according to the real-time traffic flow data, and the road traffic efficiency of a bottleneck road section in variable speed-limit control is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation and traffic control, and in particular relates to a method for improving the traffic efficiency of expressways based on reinforcement learning variable speed limit control. Background technique [0002] Variable speed limit control, as a traffic control strategy that is more and more widely used to improve the efficiency of expressway traffic, its control effect is closely related to the method used in the process of determining the variable speed limit value. As a closed-loop structure, reinforcement learning enables the agent to continuously learn the optimal speed limit values ​​corresponding to different traffic flow states through the feedback adjustment of the control effect to the control strategy, effectively improving the effect of variable speed limit control and variable speed limit control. Control the rationality of the speed limit value. Therefore, the variable sp...

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): G08G1/09G08G1/01
CPCG08G1/09G08G1/0125G08G1/0145
Inventor 李志斌刘攀王炜徐铖铖
Owner SOUTHEAST 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