Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment

Author:

Feng ShuoORCID,Yan XintaoORCID,Sun HaoweiORCID,Feng Yiheng,Liu Henry X.ORCID

Abstract

AbstractDriving intelligence tests are critical to the development and deployment of autonomous vehicles. The prevailing approach tests autonomous vehicles in life-like simulations of the naturalistic driving environment. However, due to the high dimensionality of the environment and the rareness of safety-critical events, hundreds of millions of miles would be required to demonstrate the safety performance of autonomous vehicles, which is severely inefficient. We discover that sparse but adversarial adjustments to the naturalistic driving environment, resulting in the naturalistic and adversarial driving environment, can significantly reduce the required test miles without loss of evaluation unbiasedness. By training the background vehicles to learn when to execute what adversarial maneuver, the proposed environment becomes an intelligent environment for driving intelligence testing. We demonstrate the effectiveness of the proposed environment in a highway-driving simulation. Comparing with the naturalistic driving environment, the proposed environment can accelerate the evaluation process by multiple orders of magnitude.

Funder

University of Michigan

Publisher

Springer Science and Business Media LLC

Subject

General Physics and Astronomy,General Biochemistry, Genetics and Molecular Biology,General Chemistry

Reference41 articles.

1. Federal Motor Vehicle Safety Standards. National Highway Traffic Safety Administration. Department of Transportation, United States. https://www.nhtsa.gov/laws-regulations/fmvss. (1999).

2. Jacobstein, N. Autonomous vehicles: an imperfect path to saving millions of lives. Sci. Robot. 4, eaaw8703 (2019).

3. Li, L. et al. Parallel testing of vehicle intelligence via virtual-real interaction. Sci. Robot. 4, eaaw4106 (2019).

4. Legg, S. & Hutter, M. Universal intelligence: a definition of machine intelligence. Minds Mach. 17, 391–444 (2007).

5. Schieferdecker, I., Großmann, J., Schneider, M. A. How to Safeguard AI. In (Andreas Sudmann ed) The Democratization of Artificial Intelligence 245–254 (Majuskel Medienproduktion GmbH, 2019).

Cited by 177 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Camera-in-the-loop based test scenario generation method for pedestrian collision avoidance system;Accident Analysis & Prevention;2024-11

2. A generic stochastic hybrid car-following model based on approximate Bayesian computation;Transportation Research Part C: Emerging Technologies;2024-10

3. ASQ-IT: Interactive explanations for reinforcement-learning agents;Artificial Intelligence;2024-10

4. Scalable evaluation methods for autonomous vehicles;Expert Systems with Applications;2024-09

5. Modeling Lead-Vehicle Kinematics for Rear-End Crash Scenario Generation;IEEE Transactions on Intelligent Transportation Systems;2024-09

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3