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

A Reinforcement Learning Variable Duration Signal Light Control Method Based on IoT Devices

An Internet of Things device and reinforcement learning technology, applied in the computer field, can solve the problems of inaccurate modeling, control time waste, extraction, etc., to achieve rapid convergence, improve control quality, and improve the speed of learning convergence.

Active Publication Date: 2022-07-05
EAST CHINA NORMAL UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to imprecise modeling, the existing traffic light control methods based on reinforcement learning are difficult to quickly extract effective content from complex traffic information to guide the model to converge to an excellent control strategy
At the same time, in order to simplify traffic modeling, the existing methods usually set a fixed green light duration for signal lights, which actually causes a waste of control time

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
  • A Reinforcement Learning Variable Duration Signal Light Control Method Based on IoT Devices
  • A Reinforcement Learning Variable Duration Signal Light Control Method Based on IoT Devices
  • A Reinforcement Learning Variable Duration Signal Light Control Method Based on IoT Devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0091] The present invention proposes a reinforcement learning variable-duration signal light control method based on Internet of Things equipment. The following is its code implementation part (interception is important):

[0092] As shown in Code 1, this part includes the code for state acquisition of the reinforcement learning method:

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099] code 1

[0100] In the code 1, the intensity information generated by the traffic data obtained in real time is mainly given, and then the intensity information is sorted out to obtain the state of the reinforcement learning method - as the observation of the traffic condition of the intersection by the agent. The main functions are intersection_info, get_lanepressure, get_neigh_pressure, and get_state. intersection_info obtains part of the traffic data at the current intersection, including the number of vehicles on each lane, vehicle speed, vehicle location, et...

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 proposes a reinforcement learning variable-duration signal light control method based on the Internet of Things equipment, which mainly includes the following aspects: a reinforcement learning method based on the concept of "intensity" of the intersection is designed, and the data collected by the Internet of Things equipment is collected. Various real-time traffic information (such as vehicle position, speed, etc.) to control the phase selection of signal lights. At the same time, a most reasonable green light duration can be selected according to the number of vehicles in each lane. The invention can quickly converge to an excellent signal light control strategy under the condition of dynamic traffic changes, greatly shorten the learning time of the strategy and improve the control quality of the strategy.

Description

technical field [0001] The invention belongs to the field of computer technology, relates to deep reinforcement learning algorithms and signal light control problems, and particularly relates to learning and generating an effective signal light control strategy according to real-time traffic data obtainable by Internet of Things devices in a highly complex real-time traffic environment. Background technique [0002] In recent years, with the rapid increase of car ownership in our country, more and more road traffic problems have appeared frequently, such as traffic planning problems, road safety problems, road congestion problems, traffic control problems and so on. Traffic congestion has always been a key issue in designing efficient infrastructure, but it has become a prominent problem due to the rapid growth in traffic demand. In addition, traffic congestion has also brought about a series of problems such as traffic environment pollution and traffic chaos, which have ser...

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): G08G1/07G08G1/08G08G1/085G16Y40/35
CPCG08G1/07G08G1/08G08G1/085G16Y40/35Y02B20/40
Inventor 陈铭松张雯倩赵吴攀叶豫桐胡铭韩定定
Owner EAST CHINA NORMAL 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