Reinforcement learning intelligent traffic light control method and system based on Internet-of-things platform

An Internet of Things platform and signal light control technology, applied in the traffic control system of road vehicles, traffic control system, traffic signal control, etc., can solve problems such as waste of personnel costs, congestion, travel inconvenience, etc., to reduce waiting time and improve traffic Efficiency, minimize the effect of the average waiting time

Inactive Publication Date: 2021-02-26
EAST CHINA NORMAL UNIVERSITY
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traffic congestion has always been a key problem in designing efficient infrastructure, but traffic planning problems are difficult to solve due to the rapid growth of traffic demand
Congestion occurs when the number of vehicles attempting to use public transport routes exceeds the latter's capacity, and in worse cases leads to severe degradation in the use of availa

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 intelligent traffic light control method and system based on Internet-of-things platform
  • Reinforcement learning intelligent traffic light control method and system based on Internet-of-things platform
  • Reinforcement learning intelligent traffic light control method and system based on Internet-of-things platform

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0032] Example

[0033] The present invention proposes an implementation method of a reinforcement learning intelligent traffic signal light control system based on the Internet of Things platform. The following is its code implementation part (interception is important):

[0034] As shown in Code 1, this part includes the code for the method of simulating the urban road and traffic flow:

[0035] defconvert_phases(self, phases_list):

[0036]

[0037]

[0038]

[0039]

[0040]

[0041]

[0042] code 1

[0043] Three important functions are briefly listed, they are: convert_phases, get_adjacency_maxtrix, _compute_obs_inlanes, _compute_observations, the functions of these four functions are as follows:

[0044] Convert_phases transmits phase information, get_adjacency_maxtrix calculates the adjacency matrix of adjacent intersections in the case of multiple intersections, and obtains the information of surrounding intersections, _compute_obs_inlanes calculat...

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 intelligent traffic light control method based on an Internet-of-things platform. The reinforcement learning intelligent traffic light control method mainly comprises the following steps of: step 1, completing simulation of urban traffic and traffic flow through microscopic traffic simulation software; step 2, acquiring equipment state information from a simulation equipment end through a OneNET cloud platform, issuing the equipment state information to a control end by the OneNET, receiving a control command, and sending the control command to the simulation equipment end to realize information communication between the simulation traffic flow and the control end; and step 3, using a DDQN neural network model to realize real-time coordination control of traffic lights according to intersection traffic flow conditions, and minimizing average waiting time of all vehicles. A reinforcement learning agent controls each intersection, each intersection trains the corresponding reinforcement learning agent, and communication is realized by sharing information among the agents. The invention further provides a reinforcement learning intelligent traffic light control system based on an Internet-of-things platform.

Description

technical field [0001] The present invention involves digital twin technology, deep reinforcement learning algorithm, and OneNET cloud platform. In particular, it involves mapping the status of physical equipment on the Internet of Things platform, using the Internet of Things platform as a transfer platform between the device end and the control end to complete information communication, and realizing the basic control function of traffic flow at multiple intersections, that is, all traffic vehicles Intersections have the shortest average wait times. Background technique [0002] In recent years, with the development of society and economy, the number of automobiles in our country has increased rapidly, resulting in traffic jams, high frequency of traffic accidents, traffic environmental pollution, traffic chaos and a series of problems, which seriously affect the current social and economic development. and people's lives. At the same time, the construction of transporta...

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): G08G1/095G08G1/08G08G1/01G06F30/15G06F30/27G06Q10/06G06Q50/26
CPCG06Q10/06312G06Q50/26G08G1/0104G08G1/08G08G1/095G06F30/15G06F30/27
Inventor 陈铭松马言悦邵明莉赵吴攀曹鹗
Owner EAST CHINA 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