Automatic drive vehicle test scene construction method based on traffic accident case deconstruction, and test method

A traffic accident and test scene technology, applied in character and pattern recognition, instruments, data processing applications, etc., can solve problems such as the inability to respond well to complex traffic environment logic adaptability, and achieve synergy and complexity enhancement. Effect

Inactive Publication Date: 2018-11-06
TRAFFIC MANAGEMENT RES INST OF THE MIN OF PUBLIC SECURITY
View PDF3 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And the testing of basic functions such as emergency braking and adaptive cruise control of autonomous driving has been gradually improved, but such test methods are mostly based on hardware performance testing of autonomous driving vehicles, which cannot well reflect the complex traffic environment faced by autonomous driving measurements. Therefore, it is necessary to construct a test scenario that can reflect the dangerous scenarios in the typical road traffic environment in my country, cover more common accidents and illegal scenarios, and standardize the test scenarios that can comprehensively reflect the adaptability of autonomous vehicles to the traffic environment

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 drive vehicle test scene construction method based on traffic accident case deconstruction, and test method
  • Automatic drive vehicle test scene construction method based on traffic accident case deconstruction, and test method
  • Automatic drive vehicle test scene construction method based on traffic accident case deconstruction, and test method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with specific drawings and embodiments.

[0036] The self-driving vehicle test scene construction method and test method based on the deconstruction of traffic accident cases proposed by the present invention include:

[0037] (1) By analyzing the characteristics of the real traffic scene, extract the scene elements for the test of the self-driving vehicle;

[0038] Feature analysis is based on traffic accident cases, and case types include files, videos, etc.; analysis steps include data preprocessing, complexity analysis, and feature comparison of scene elements;

[0039] Step 1.1, data preprocessing: classify the scene elements, combine the driving behavior of real vehicles, and form a case sheet for each traffic accident case; as shown in Table 1;

[0040] The classification of scene elements includes: accident causes, accident objects, accident areas, and environmental conditions; the accident ca...

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 provides an automatic drive vehicle test scene construction method based on traffic accident case deconstruction. The method comprises the following steps of (1) extracting scene elements used for testing an automatic drive vehicle by analyzing characteristics of a real traffic scene; (2) arranging a test scene of the automatic drive vehicle, thereby generating test cases used for testing the automatic driving vehicle; and (3) arranging a test scene collaborative control system. The scene elements and typical features are analyzed and extracted through clustering analysis, and important parameters in the real traffic scene are converted into test parameters in combination with cause analysis, so that an automatic drive urban complex traffic scene safety adaptability test evaluation method suitable for industrial development and third-party certification evaluation is constructed.

Description

technical field [0001] The invention belongs to the technical field of self-driving vehicle performance testing, in particular to a method for constructing a test scene of a self-driving vehicle and a testing method based on the deconstruction of traffic accident cases. Background technique [0002] According to the level of autonomous driving ability, automatic driving can be divided into five levels, level 1 is driving assistance, level 2 is partial automatic driving, level 3 is conditional automatic driving, level 4 is highly automatic driving, and level 5 is fully automatic driving. Among them, automatic driving systems with intelligence levels 1 and 2 mainly rely on humans to monitor the driving environment, while automatic driving systems with intelligence levels 3 to 5 use computer systems to monitor the driving environment. With the improvement of the intelligence level of autonomous driving, the intelligent system gradually reaches and has the driving level of a hum...

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): G06Q50/26G06K9/62
CPCG06Q50/26G06F18/23G06F18/24
Inventor 孙巍应朝阳潘汉中范志翔穆文浩严慈磊
Owner TRAFFIC MANAGEMENT RES INST OF THE MIN OF PUBLIC SECURITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products