published journal article

Online war-driving by compressive sensing

IEEE Trans. on Mobile Comput.

Publication Date

November 1, 2015

Author(s)

Di Wu, Dmitri Arkhipov, Yanyan Zhang, Chi Harold Liu, Amelia Regan

View published journal article

Suggested Citation

Di Wu, Dmitri I. Arkhipov, Yuan Zhang, Chi Harold Liu and Amelia C. Regan (2015) “Online war-driving by compressive sensing”, IEEE Trans. on Mobile Comput., 14(11), pp. 2349–2362. Available at: 10.1109/tmc.2015.2388475.

conference paper

End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering

2021 IEEE Intelligent Vehicles Symposium (IV)

Publication Date

July 1, 2021

Author(s)

Ruochen Jiao, Hengyi Liang, Takami Sato, Junjie Shen, Qi Alfred Chen, Qi Zhu

View conference paper

Abstract

In the development of advanced driver-assistance systems (ADAS) and autonomous vehicles, machine learning techniques that are based on deep neural networks (DNNs) have been widely used for vehicle perception. These techniques offer significant improvement on average perception accuracy over traditional methods, however have been shown to be susceptible to adversarial attacks, where small perturbations in the input may cause significant errors in the perception results and lead to system failure. Most prior works addressing such adversarial attacks focus only on the sensing and perception modules. In this work, we propose an end-to-end approach that addresses the impact of adversarial attacks throughout perception, planning, and control modules. In particular, we choose a target ADAS application, the automated lane centering system in OpenPilot, quantify the perception uncertainty under adversarial attacks, and design a robust planning and control module accordingly based on the uncertainty analysis. We evaluate our proposed approach using both public dataset and production-grade autonomous driving simulator. The experiment results demonstrate that our approach can effectively mitigate the impact of adversarial attack and can achieve 55% 90% improvement over the original OpenPilot.

Suggested Citation

Ruochen Jiao, Hengyi Liang, Takami Sato, Junjie Shen, Qi Alfred Chen and Qi Zhu (2021) “End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering”, in 2021 IEEE Intelligent Vehicles Symposium (IV), pp. 266–273. Available at: 10.1109/IV48863.2021.9575549.

published journal article

In memoriam: Frank a. Haight 1919-2006

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR

Publication Date

January 1, 2006

Author(s)

Thomas Golob, Molly I. Haight

View published journal article

Suggested Citation

Thomas F. Golob and Molly I. Haight (2006) “In memoriam: Frank a. Haight 1919-2006”, TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 9(5), pp. 383–385. Available at: 10.1016/j.trf.2006.06.007.

conference paper

Exploring the unnoticed: An analysis of voluntary and involuntary carless households in California

Proceedings of the 95th annual meeting of the transportation research board

Publication Date

January 1, 2016

Author(s)

Suman Mitra, Jean-Daniel Saphores

Abstract

Approximately 10.5 million of US households do not own cars. These households, who are often forgotten in transportation policy discussions, can be organized into two groups: voluntary and involuntary carless households. Understanding why some households decided to voluntarily forgo cars could inform policies to reduce the dependency on cars and reduce greenhouse gas emissions but understanding the plight of households who do not have access to cars is no less important as these households are at greater risk of social exclusion. Unfortunately, the knowledge of carless households is very limited so the purpose of this paper is to fill this gap. Using simple statistical tests and logit models, the authors analyze data from the 2012 California Household Travel Survey (CHTS) to better understand the characteristics of voluntary and involuntary carless households and to assess the effects of various socio-economic, residential, and land use variables on the likelihood to be carless (voluntarily or not). The authors’ results show that voluntary carless households are more likely to have a higher average household income, a better education, a higher number of employed members, and a lower number of children than their involuntary counterparts. The authors’ binary logit models emphasize the importance of land use diversity (via the land use entropy index) and of good transit service to help households voluntarily forgo their vehicles and downplay the impact of population density and pedestrian- friendly facilities.

Suggested Citation

Suman K. Mitra and Jean-Daniel M. Saphores (2016) “Exploring the unnoticed: An analysis of voluntary and involuntary carless households in California”, in Proceedings of the 95th annual meeting of the transportation research board, p. 20p.

conference paper

A Cooperative Vehicle-Intersection Control (CVIC) Algorithm Based on Vehicle-to-Infrastructure (V2I) Communications in a Connected and Autonomous Vehicle Environment

101st Annual Meeting of the Transportation Research Board

Publication Date

January 1, 2022

Wenlong Jin

View published journal article

Suggested Citation

Wen-Long Jin (2010) “A kinematic wave theory of lane-changing traffic flow”, Transportation Research Part B: Methodological, 44(8-9), pp. 1001–1021. Available at: 10.1016/j.trb.2009.12.014.