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

Human-vehicle collision risk degree analysis method based on autonomous vehicle

A technology of automatic driving and analysis method, applied in anti-collision systems, instruments, data processing applications, etc., can solve the problems of sudden changes in street crossing behavior and low prediction accuracy of collision conflicts, and achieve specific and accurate estimates

Pending Publication Date: 2022-04-08
NANJING UNIV OF SCI & TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for judging the risk of collision between people and vehicles based on self-driving cars, which can avoid the problems of low collision conflict prediction accuracy and the inability to predict possible sudden changes in street crossing behavior caused by traditional single-modal prediction of pedestrian trajectories. The future trajectories of pedestrians are collected, and the interactive graph network of pedestrians and vehicles is constructed to improve the accuracy of collision risk prediction, enrich the predicted scenarios, provide a highly reliable and accurate judgment result of collision risk of people and vehicles, and provide decision-making for autonomous vehicles. Modules and path planning modules provide accurate data basis to further improve the intelligence of autonomous driving, improve ride comfort and safety, and promote the advancement of autonomous driving technology

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
  • Human-vehicle collision risk degree analysis method based on autonomous vehicle
  • Human-vehicle collision risk degree analysis method based on autonomous vehicle
  • Human-vehicle collision risk degree analysis method based on autonomous vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0092] combine figure 1 , a method for analyzing the risk of human-vehicle collision based on an autonomous vehicle, comprising the following steps:

[0093] Step 1. Obtain the crossing characteristics in the pedestrian crossing historical data set, including speed, acceleration and crossing heading angle, and use the Gaussian mixture clustering GMM method to construct a Gaussian mixture distribution function to represent three different pedestrian crossing habits, specifically:

[0094] Obtain the motion parameters of pedestrians crossing the street with human-vehicle game through the existing data set, and extract the characteristics of crossing the street in the historical data set of pedestrians crossing the street, including speed, acceleration and heading angle of crossing the street;

[0095] The pedestrian trajectory heading angle refers to the angle formed between the pedestrian trajectory and the curb of the road. Since China adopts the right-hand driving system, the...

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 pedestrian-vehicle collision risk degree analysis method based on an autonomous vehicle, and the method comprises the steps: dividing the street crossing behaviors into different habit types through Gaussian clustering according to the street crossing features in a pedestrian street crossing historical data set, and employing a joint probability distribution function to obtain a pedestrian-vehicle collision risk degree; an automatic driving vehicle is helped to obtain a future possible state set according to the current motion state of a pedestrian, a pedestrian-vehicle dynamic space-time relation is considered through a GCN graph convolutional neural network, a future possible trajectory set of the pedestrian is obtained, finally, the trajectory collision probability and the minimum encounter distance are considered, feature dimension reduction is performed by using a matter element extension theory, and the pedestrian collision probability is reduced. And establishing a risk degree function to realize real-time judgment of the human-vehicle collision risk degree. The method focuses on the characteristic that the pedestrian motion state has sudden change, more specifically considers the influence of the pedestrian-vehicle space-time relationship on the trajectory, improves the accuracy and credibility of the pedestrian-vehicle collision judgment result through the fusion of multiple indexes, further improves the intelligence of automatic driving, and improves the riding comfort and safety.

Description

technical field [0001] The invention belongs to the field of automatic driving decision-making algorithms, and in particular relates to an analysis method based on the risk of collision between an automatic driving vehicle and pedestrians crossing the street. Background technique [0002] The rapid development of science and technology will push the whole society towards a more intelligent direction. In recent years, self-driving car technology has developed rapidly, and companies such as Google, Tesla, and Baidu are making continuous attempts in this field. Autonomous driving is getting closer and closer to people's lives, but at the same time, people still have great doubts about driving safety. Human-vehicle conflict discrimination is a core module in autonomous driving technology. Improving the accuracy of human-vehicle conflict assessment and reducing computational complexity will more effectively ensure the safety of autonomous vehicles while driving and enhance acci...

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 Applications(China)
IPC IPC(8): G06V40/20G06Q10/06G06Q10/04G06N3/04G08G1/16G06K9/62G06V10/762
Inventor 周竹萍刘博闻汤睿尧栾泊蓉欧阳墨蓝刘洋李卫胡春钢欧婉情
Owner NANJING UNIV OF SCI & 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