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

Prediction method of regional flow distribution in variable traffic control scheme based on wmgirl algorithm

A technology of traffic control and flow distribution, which is applied in traffic flow detection, road vehicle traffic control system, traffic control system, etc., can solve the problem that urban roads cannot meet traffic demand, solve the problem of excessive environmental model and reduce workload , the effect of improving the accuracy

Active Publication Date: 2022-02-18
CHENGDU UNIV OF INFORMATION TECH +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous improvement of my country's comprehensive strength, many cities have hosted large-scale events one after another, and urban roads cannot meet the rapidly increasing traffic demand in a short period of 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
  • Prediction method of regional flow distribution in variable traffic control scheme based on wmgirl algorithm
  • Prediction method of regional flow distribution in variable traffic control scheme based on wmgirl algorithm
  • Prediction method of regional flow distribution in variable traffic control scheme based on wmgirl algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] like figure 1 As shown, the regional flow distribution prediction method in the variable traffic control scheme based on the WMGIRL algorithm includes the following steps:

[0107] S1. Carry out urban road network modeling in the area to be predicted, and collect driving trajectory data in the area;

[0108] S2. Based on the urban road network and driving trajectory data corresponding to the area to be predicted, the flow characteristics in the area to be predicted are extracted through the maximum entropy inverse reinforcement learning method based on multiple weights;

[0109] S3. Based on the extracted flow characteristics and the urban road network under the current traffic control scheme, process them through the forward reinforcement learning method to obtain the flow distribution prediction results of the area to be predicted.

[0110] In the above step S1, when modeling the urban road network, it actually belongs to the reasonable abstraction of all the things ...

Embodiment 2

[0218] In this embodiment, a flow simulation platform under the variable traffic control scheme built based on the above flow distribution prediction method is provided,

[0219] The platform can predict the regional flow distribution under different traffic control schemes based on the real urban road network and the data in the buckle. The framework of the flow simulation platform based on the variable traffic control scheme is as follows: figure 2 As shown, the traffic simulation platform has three sub-modules, including road network module, traffic module and algorithm module. Among them, the road network module models the urban road network within the specified range of the specified city; the flow module uses the bayonet data of a certain period of time within the specified range of the city to mine the traffic trajectory data; the algorithm module is divided into the flow feature extraction module and the flow The simulation algorithm module, in which the traffic featu...

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 a method for predicting regional traffic flow distribution under a variable traffic control scheme based on a weighted multiagent group inverse reinforcement learning algorithm——WeightedMultiagent Group Inverse Reinforcement Learning (WMGIRL), including: Network modeling, and collect the traffic trajectory data in the area; S2, based on the urban road network and traffic trajectory data corresponding to the area to be predicted, extract the traffic in the area to be predicted by using the weighted (Weighted) maximum entropy inverse reinforcement learning method Features; S3, based on the extracted traffic characteristics and the urban road network under the current traffic control scheme, use the forward reinforcement learning method based on Multiagent Group to process it, and obtain the traffic flow distribution in the area to be predicted forecast result.

Description

technical field [0001] The invention belongs to the technical field of urban traffic flow forecasting, and in particular relates to a method for predicting regional traffic distribution in a variable traffic control scheme based on WMGIRL (intra-group evolution-based multi-agent reverse reinforcement learning) algorithm. Background technique [0002] With the continuous improvement of my country's comprehensive strength, many cities have hosted large-scale events one after another, and urban roads cannot meet the rapidly increasing traffic demand in a short period of time. Therefore, the traffic police will use traffic control schemes to induce traffic to relieve road pressure. In recent years, due to the deepening of the research on urban intelligent transportation, the research on traffic guidance technology and traffic control traffic control has become the core of urban intelligent transportation. Research methods. At present, the core technology of traffic guidance tech...

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): G08G1/01G08G1/065G06Q10/04G06Q50/30
CPCG08G1/0125G08G1/0145G08G1/065G06Q10/04G06Q50/30
Inventor 郑皎凌张中雷李军吴昊昇乔少杰刘双侨
Owner CHENGDU UNIV OF INFORMATION TECH
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