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

Automatic intersection passing decision method based on convolutional neural network

A technology of convolutional neural network and decision-making method, which is applied in the field of automatic intersection traffic decision-making, can solve the problems of increased calculation time, difficult practical application, and poor effect, so as to reduce calculation time, improve average traffic speed, and improve management performance. Effect

Active Publication Date: 2021-11-23
SOUTHEAST UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The former follows the first-come-first-serve (FCFS) rule, which does not work well in practice
The latter traverses all possible traffic schemes, and conducts simulation tests for each traffic scheme to obtain vehicle evacuation time, but the calculation time increases exponentially, which brings difficulties to practical applications

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
  • Automatic intersection passing decision method based on convolutional neural network
  • Automatic intersection passing decision method based on convolutional neural network
  • Automatic intersection passing decision method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings.

[0054] The present invention designs an automatic intersection of the convolutional neural network, such as figure 1 As shown, the steps are as follows:

[0055] 1. Establish a self-automatic intersection model, using V2I communication technology to make information interaction with intelligent network vehicles within the communication range;

[0056] 2. Determine all feasible passwords based on planning trees;

[0057] 3. Collect the vehicle track data, and use the planned tree to raise all candidates, traverse each order and obtain the time consumption corresponding to each order, establish a tab for describing the traffic state and the traffic sequence, and build a tensor-time consumption database;

[0058] 4, build and train convolutional neural networks, and obtain the short-term time consumption of the tensor of the tensor as the final gener...

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 automatic intersection passing decision method based on a convolutional neural network. The method sequentially comprises the steps of: building an automatic intersection model; determining all feasible passing sequences based on a plan tree method; collecting vehicle track data, listing all candidate passing sequences by using a plan tree, traversing all the sequences and obtaining time consumption corresponding to each sequence, establishing a tensor for describing a traffic state and a passing sequence, and constructing a tensor-time consumption database; and constructing and training a convolutional neural network, and obtaining a passing sequence corresponding to the tensor with the shortest time through the trained convolutional neural network as a final passing scheme. The method can significantly reduce the calculation time, reduce the driving delay, and improve the passing speed.

Description

Technical field [0001] The present invention belongs to the field of traffic engineering, and in particular, the present invention relates to an automatic intersection. Background technique [0002] With the continuous development of wireless communications and Internet technology, artificial driving vehicles will be replaced by intelligent network vehicles. The car has received attention in the field of intelligent transportation. It is the best means of reducing driving delays in today's internationally recognized driving, improving operational efficiency, achieving energy saving and emission reduction. [0003] In fact, the key factors that truly restrict urban transportation, affect traffic safety, has always been the general order of the intersection. In the past few decades, scholars have proposed some ways to solve automatic intersection management issues, mainly including reservation-based strategies and planned strategies. The former followed the first service (FCFS) rul...

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): G08G1/0967G08G1/01G08G1/16H04W4/44G06N3/04G06N3/08
CPCG08G1/096783G08G1/0129G08G1/164H04W4/44G06N3/08G06N3/045
Inventor 张健姜夏李丹张晓亮张平刘子懿熊壮
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

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