Home Home Home

CCAT Research Review

March 23, 2020 - 4:30pm
Sponsor: CCAT Research Review
CCAT Research Review
March 24, 2020
2:00-3:00 PM EST
Free Webinar
Please join us for the CCAT Research Review webinar, presenting:

Dr. Yiheng Feng and Dr. Shuo Feng

Safety Assessment of Highly Automated Driving Systems – A New Framework

Dr. Yiheng Feng is an assistant research scientist at the University of Michigan Transportation Research Institute (UMTRI). He received his Ph.D. from the Department of Systems and Industrial Engineering at the University of Arizona in 2015. His research mainly focuses on smart transportation systems, including traffic control with connected and automated vehicles (CAVs), cybersecurity of transportation infrastructure and CAV testing and evaluation. His research articles have appeared in major transportation journals, such as Transportation Research Part B, Part C, IEEE transactions on ITS, and top security conferences such as NDSS. He has been the PI and co-PI for multiple federal and industry-funded research projects including NSF, USDOT, USDOE and Ford Motor Company. Dr. Shuo Feng received the bachelor’s and Ph.D. degrees from the Department of Automation, Tsinghua University, China, in 2014 and 2019, respectively. He was also a visiting Ph.D. student in Civil and Environmental Engineering with the University of Michigan, Ann Arbor, MI, USA, from 2017 to 2019, where he is currently a research fellow. His current research interests include testing, evaluation, and optimization of connected and automated vehicles.

There are three major safety assessment methods for transportation researchers: simulation, test track, and public roads. Test tracks provide a safe, cost-effective testing environment, but they typically cannot provide a level of background traffic that may be necessary for testing. Dr. Yiheng and Shuo Feng of U-M will present on a new safety assessment framework to address these limitations. First, an augmented reality testing platform is constructed to create simulated traffic within test tracks that can interact with real, automated driving systems. Second, a testing scenario library generation (TSLG) method is developed to systematically generate sets of critical scenarios under different operational design domains (ODDs). This free webinar will include a Q&A session. You can read the abstract for this project here, and can register for this free webinar below.