Intelligent automobile rapid test method based on Bayesian optimization

A technology of smart cars and testing methods, applied in design optimization/simulation, special data processing applications, instruments, etc., can solve problems such as the explosion of the number of concrete test scenarios, shorten the test cycle, reduce the number of tests, and ensure reliability Effect

Active Publication Date: 2019-08-30
TONGJI UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the research report of the Rand Corporation of the United States, because traffic accidents are extremely low-probability events, if it is to prove that smart cars are 20% safer than human drivers, about 100 vehicles will be needed for on-site road tests or test field tests, 24 hours a day. Test 225 years without a break, this is an extremely difficult task
[0005] On the other hand, the test scenario of a smart car is composed of multiple dynamic and static elements, and the value changes and combinations of the scene elements lead to a large explosion in the number of concrete scenarios.

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
  • Intelligent automobile rapid test method based on Bayesian optimization
  • Intelligent automobile rapid test method based on Bayesian optimization
  • Intelligent automobile rapid test method based on Bayesian optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Utilize the intelligent driving (Intelligent Driver Model, IDM) model to simulate the intelligent car planning and decision-making system, test the acceleration effect of the present invention in the scene test of the vehicle lane-changing behavior function, wherein the test vehicle is a lane-changing vehicle, and the test target is to find dangerous scenes, including Detailed steps below:

[0041] (1) First, based on the on-site traffic scene, obtain the key parameters of the vehicle’s driving scene, determine the value range and sampling interval for the key parameters, and combine the key parameters to form a parameter space:

[0042] (1.1) Based on the traffic scene, determine the key parameters of the driving scene. For the scene of lateral insertion, the key parameters include the speed of the test vehicle, the speed of the front vehicle of the natural driving vehicle, the rear speed of the natural driving vehicle, and the distance between the test vehicle and the ...

Embodiment 2

[0057] Utilize the IDM model to simulate the intelligent vehicle planning and decision-making system, test the acceleration effect of the present invention on the vehicle lane-changing behavior test, wherein the test vehicle is a lane-changing vehicle, and the test target is different from that of embodiment 1. The goal of this embodiment is to find the "boundary scene" ", Boundary scenario refers to: in this test scenario, small changes in the scene parameters will bring about changes in the final test results. This embodiment includes the following detailed steps:

[0058] (1) First, based on the on-site traffic scene, obtain the key parameters of the vehicle’s driving scene, determine the value range and sampling interval for the key parameters, and combine the key parameters to form a parameter space:

[0059] (1.1) Based on the traffic scene, determine the key parameters of the driving scene. For the scene of lateral insertion, the key parameters include the speed of 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 relates to an intelligent automobile rapid test method based on Bayesian optimization. According to the method, representative test scenes are accurately selected, the test frequency isreduced, and the safety of a large number of samples is evaluated. The method comprises the following steps: firstly, obtaining driving scene key parameters of a vehicle on the basis of on-site traffic scenes, determining a value range and a sampling interval for the key parameters, and combining the key parameters to form a parameter space; then, based on the Bayesian optimization theory, selecting appropriate classifiers and acquisition functions according to different test purposes; and finally, initializing a classifier, calculating a numerical value of an acquisition function, and selecting a next intelligent automobile test scene which is more in line with requirements according to the numerical value of the acquisition function. Compared with the prior art, the method has the advantages of reducing the test times, improving the test efficiency, ensuring the test reliability and the like.

Description

technical field [0001] The invention relates to the field of intelligent networked vehicles and intelligent transportation, in particular to a rapid test method for intelligent vehicles based on Bayesian optimization. Background technique [0002] With the rapid improvement of human's ability to collect, store, transmit, and process data, a large amount of data has accumulated in every corner of human society, and there is an urgent need for computer algorithms that can effectively analyze and utilize data, and artificial intelligence technology is just suitable for large The urgent need of the data age. As the application of artificial intelligence technology in the field of transportation, autonomous driving technology is developing rapidly. Autonomous driving technology has great potential in improving traffic efficiency and safety, and smart cars based on autonomous driving technology have broad market prospects. [0003] The automatic driving system of a smart car rel...

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): G06K9/62G06F17/50
CPCG06F30/20G06F18/214G06F18/24Y02T10/40
Inventor 孙剑周华骏徐一鸣
Owner TONGJI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap