Vision and Learning for Active Safety

ECE Seminar: Vision and Learning for Active Safety


Starts at: February 28, 2013 4:30 PM

Ends at: 5:30 PM

Location: Pittsburgh Campus: Scaife Auditorium (Room 125), Refreshments at 4pm. - Silicon Valley campus: Rm 118, Building 23 at 1:30 PST

Speaker: Mohan M Trivedi

Affiliation: University of California at San Diego, professor of Electrical and Computer Engineering and founding director of the Computer Vision and Robotics Research Laboratory

Link to Abstract

Link to Audio

Link to Video (1)

Details:

If you would like to meet with Prof. Trivedi during his visit to CMU on Thursday, Feb. 28th please email Kelley Conley.

Abstract:
Designing fully autonomous robotic vehicles which can drive on roads does not require models of drivers and how they interact with vehicles. In contrast, design of intelligent driver assistance systems, especially those for active safety that prevent accidents, requires understanding of human behavior , modeling of human-vehicle interaction and prediction of human intent. We will present an overview of a "human-centered" framework for a distributed intelligent system with the driver, vehicle and environment as three key components. We will emphasize the need and the implications of utilizing an holistic approach where driving in a naturalistic context is observed over long periods to learn driving behavior and to predict driver intentions and interactivity patterns. The presentation will include discussion of selected ongoing studies and will conclude with some pointers to important outstanding research challenges.

Bio:
Mohan Trivedi is a professor of Electrical and Computer Engineering and founding director of the Computer Vision and Robotics Research Laboratory at the University of California at San Diego. He has also established LISA: Laboratory for Intelligent and Safe Automobiles at UCSD. Currently, Trivedi and his team are pursuing research in intelligent vehicles, machine perception, machine learning, multimodal interfaces, driver assistance, active safety and intelligent transportation systems.. Two of his students were awarded Best Dissertation Awards by the IEEE ITS Society (Dr. Shinko Cheng 2008 and Dr. Brendan Morris 2010). Most recently Dr. Anup Doshi's dissertation was selected as the UCSD's top dissertation entry and was judged among the five finalists by the Western Association of Graduate Schools (WAGS). Trivedi's team has played a key role in several major research collaborative initiatives. These include human-centered vehicle collision avoidance systems, vision based passenger protection system for "smart airbags and several vision systems for transportation and homeland security applications. He serves regularly as a consultant to industry and government agencies in the USA and abroad.