Performance Evaluation of a Lane Correction Module Stress Test: A Field Test of Tesla Model 3

Author:

Lancelot Jonathan1ORCID,Rimal Bhaskar1ORCID,Dennis Edward1ORCID

Affiliation:

1. The Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USA

Abstract

This paper is designed to explicate and analyze data acquired from experimental field tests of a Tesla Model 3 lane correction module within the vehicle’s Autopilot Suite, a component of Tesla OS. The initial problem was discovered during a nominal drive of the Tesla Model 3, where after a random number of lane correction events, the lane correction module shuts down, issues a visual disable warning on the touchscreen, and control of the vehicle is given to the driver until the next drive. That development was considered problematic, as the driver can be caught off guard or may be medically disabled and unable to respond. During a controlled stress test, a more severe issue was discovered. After a random number of lane correction events, the lane correction module shuts down without warning, then stays activated after the test driver corrects the vehicle’s trajectory. This is considered a fatal error in the system and adds a dangerous element to an otherwise standard feature in a modern automotive vehicle. The results established that the number of events needed to trigger a fatal error without warning is unpredictable. Our results also demonstrate that the system is inconsistent.

Publisher

MDPI AG

Subject

Computer Networks and Communications

Reference23 articles.

1. Schofield, K. (2005). Automotive Lane Change Aid. (No. US6882287B2), Patent, Available online: https://patents.google.com/patent/US6882287B2/en.

2. Tesla (2022, December 05). Model 3 Owner’s Manual. Available online: https://www.tesla.com/ownersmanual/model3/en_jo/GUID-ADA05DFF-963D-477D-9A51-FA8C8F6429F1.html.

3. USDOT (2022, February 21). USDOT Releases 2016 Fatal Traffic Crash Data, Available online: https://www.nhtsa.gov/press-releases/usdot-releases-2016-fatal-traffic-crash-data/.

4. Tesla (2022, December 05). Exclusive Tesla Faces U.S. Criminal Probe over Self-Driving Claims. Available online: https://www.reuters.com/legal/exclusive-tesla-faces-us-criminal-probe-over-self-driving-claims-sources-2022-10-26/.

5. Corrado, R. (2023, March 15). ‘Defects’ Keep Subaru’s Emergency Braking, Lane Keep Assist Systems from Working as Advertised, Class Action Claims. Available online: https://www.classaction.org/blog/defects-keep-subarus-emergency-braking-lane-keep-assist-systems-from-working-as-advertised-class-action-claims.

Cited by 3 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

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