Building the Next-Generation Safety System for Scooters

Thursday Nov. 15, 2012

Hsin-Mu (Michael) Tsai (NTU)


Scooters (a type of motorcycles) are one of most commonly used transportation means in Taiwan, Japan, Italy, and several other Asian and European countries. In Taiwan, approximately 70% of the vehicles are scooters. However, limited by the low cost nature of them, there is almost no new safety features added to the product in the past 10 years, during which numerous new safety features, at higher costs, have become standardized for cars. As a result, scooters contribute to more and more fatalities in accidents; for example, in Taiwan 63% of the fatalities in the accidents involve scooters. It is therefore crucial to develop a new generation of safety systems which are low-cost, effective in avoiding common accidents, and can be utilized by scooters.

The key ingredients in the new safety system are “reliable V2V communications” and “vehicle behavior prediction models.” The former enable scooters and cars to exchange information about themselves and what they observe from their surroundings, while the latter can predict certain key vehicle behaviors from the raw sensor readings of both the scooter itself and the neighboring vehicles. In the talk, I will present how some of our latest development of these two components can be used to avoid several most common types of scooter accidents.


Hsin-Mu (Michael) Tsai is an assistant professor in Department of Computer Science and Information Engineering and Graduate Institute of Networking and Multimedia at National Taiwan University. He received his B.S.E in Computer Science and Information Engineering from National Taiwan University in 2002, and his M.S. and Ph.D. in Electrical and Computer Engineering from Carnegie Mellon University in

2006 and 2010, respectively. During his Ph.D. studies, he was part of the General Motors – Carnegie Mellon Collaborative Research Laboratory and spent four summers (2005-2009) as an intern researcher in the Electrical and Controls Integration Laboratory at General Motors Research and Development where he worked on intra-car wireless channel measurements as well as the design of intra-car wireless sensor networks. Dr. Tsai’s research interests include vehicular networking and communications, wireless channel and link measurements, vehicle safety systems, and visible light communications. He is currently the principle investigator of the project “Extend the Safety Shield – An Early Warning System for Vehicles” in the Intel-NTU Connected Context Computing Center.

Back to the seminar page