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

A Timed Automata Based Car Following Behavior Recognition Method

A technology of time automaton and recognition method, applied in two-dimensional position/course control and other directions

Active Publication Date: 2019-09-27
TONGJI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of model can only roughly represent the driver's car-following behavior. For unmanned vehicles, a more accurate car-following model is needed to judge and predict the behavior of surrounding vehicles

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] A timed automata-based car-following behavior recognition method first extracts vehicle-following data from a public traffic dataset (NextGeneration SIMulation, NGSIM). Based on the k-means clustering algorithm, the input parameters of the car-following model (relative distance, relative speed, and the speed of the following vehicle) are symbolized, and the timed automata learning algorithm (RTI+Learning Algorithm) is used to train the car-following model, and the following car-following model is obtained. Car model automaton. Then, the hierarchical clustering method is used to cluster the state sequence to obtain a series of sub-behavior patterns in the car-following behavior, so as to carry out more detailed sub-behavior identification and prediction of the car-following behavior. This patent is innovative and practical, and can detect the following behavior of surrounding vehicles in real time and predict the vehicle behavior.

[0033] Specific steps such as figure...

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 relates to a method for identifying car following behavior based on timed automata, which includes the following steps: S1, extract original car following data from a traffic data set, and symbolize the input parameters of the car following model; S2, use a timed automaton learning algorithm Train the car-following model to obtain the car-following model automaton; S3, use the hidden state of the car-following model automaton as the sub-state of car following, and cluster the sub-states; S4, classify the sub-states whose probability is lower than the set value Remove and then merge into multiple categories, each category corresponding to a car-following behavior; S5, obtain the actual car-following data as input, and obtain the car-following behavior through the car-following model automaton. Compared with the existing technology, this invention symbolizes multi-dimensional continuous time series and learns to generate a car-following behavior model with strong interpretability. It learns the symbols through automata, obtains hidden states, and performs clustering. It can better reflect the sub-behavior of car following.

Description

technical field [0001] The invention relates to a method for generating car-following behavior, in particular to a method for identifying car-following behavior based on time automata. Background technique [0002] An unmanned vehicle (hereinafter referred to as an unmanned vehicle) is an intelligent mobile vehicle that can replace a human driver to complete a series of driving behaviors, involving research fields of many disciplines such as environmental perception, navigation and positioning, and intelligent decision-making control. . As a new concept of modern warfare, leading the development trend of the vehicle industry, and an important platform to demonstrate the technical level of computer science, pattern recognition and artificial intelligence, unmanned vehicles have always attracted the attention of national defense, the automobile industry, universities and scientific research institutions. The purpose of unmanned vehicle research is to replace human drivers for...

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): G05D1/02
CPCG05D1/0223
Inventor 王峻郭亚锋张怡欢王亮
Owner TONGJI 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