Seminar

 
Abstract
The high degree of mobility on the road generates a growing need for assuring safety, comfortability, and efficiency while driving. Recent advances in self-driving vehicles and intelligent transportation systems will maximize the safety and comfortability for future vehicles, yet it is required to develop new technologies and services that interact directly with drivers and passengers inside the vehicle cabin. This talk 1) overviews recent trends in smart vehicles as well as emerging services, e.g., smart air conditioning and heat, self-adjusting seats, prevention of driving while distracted (DWD), for future vehicles; 2) discusses how state-of-the-art techniques in artificial intelligence and machine learning can be applied to make our driving safe and comfortable; and 3) introduces two recent results of our work related to this topic. First, we present a solution, called Automatic Identification of Driver’s Smartphone (AIDS), for DWD prevention. Texting or browsing web on a smartphone while driving significantly increases the risk of car accidents. There have been a number of proposals for the prevention of distracted driving, but none of them has addressed its important challenges completely and effectively. To remedy this deficiency, we present AIDS, which identifies a driver’s smartphone by analyzing and fusing the phone’s sensory information related to common vehicle-riding activities before the vehicle leaves its parked spot. Second, we present a new way of checking norm operations, called BAD (Brake Anomaly Detection), for in-vehicle networks. For better controllability and energy-efficiency, more vehicle and research literature have been covering them under the name of vehicle misbehavior. BAD detects any vehicle misbehavior in the Brake-by-Wire system. We focus on the braking system since it is a prototypical safety-critical and cyber-physical system. We propose a new method for constructing norm models of braking and show how anomalies are detected by BAD using the constructed models.
 
Short Bio
Taejoon Park is currently a Full Professor in the Department of Robotics Engineering at Hanyang University, Gyeonggi-do, Korea. Prior to joining Hanyang University, he was an Associate Professor at Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, Korea from Feb. 2011 to Feb. 2015, an Assistant Professor at Korea Aerospace University, Gyeonggi-do, Korea from Sep. 2008 to Feb. 2011, a Principal Research Engineer at Samsung Electronics, Gyeonggi-do, Korea from Apr. 2005 to Apr. 2008, and a Research Engineer at LG Electronics, Seoul, Korea from Feb. 1994 to Jun. 2000 (promoted to a Senior Research Engineer in 2000). He received the Ph.D. degree (under the supervision of Prof. Kang G. Shin) in Electrical Engineering and Computer Science from the University of Michigan, Ann Arbor, MI, USA in 2005, the M.S. degree in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), Taejon, Korea in 1994, and the B.S. degree (summa cum laude) in Electrical Engineering from Hongik University, Seoul, Korea in 1992. His current research interests are in Cyber-Physical Systems (CPS) and Artificial Intelligence (AI) with emphasis on deep learning, and their applications to robots, vehicles, and factories. He has authored or coauthored 130+ papers/patents including essential patents for the DVD standard, 6 of which were cited 100+ times. He has an h-index of 17 with 1700+ cumulative citations according to Google scholar. He is a member of IEEE and ACM.