Abstract:

Assessment and prediction of inherent risk to the driver is a central problem for the successful deployment of driver assistance and automated driving technologies. While many effective metrics have been introduced that assess risk based on distance and time to collision, such methods have strict limitations in complex and interactive urban scenes where semantic and contextual information provides important cues in modeling perceived risk. In this talk, I will present the efforts towards a predictive model that reaches human-level perception, assessment, and prediction of risk.

Bio:

Dr. Yi-Ting Chen will be joining the Department of Computer Science at National Chiao Tung University as an Assistant Professor in Spring 2021. He was a senior scientist at Honda Research Institute USA since 2015. He was a visiting researcher at the University of California at Merced in 2014. He received his Ph.D. degree from the Department of Electrical and Computer Engineering at Purdue University in 2015 and a B.S. degree in Electronics Engineering from National Chiao Tung University, Hsinchu, Taiwan in 2009. His research interests lie in computer vision, machine learning, robotics, and behavior science, and their applications to intelligent systems.