Distinguished Lecture: Development of a Self-Driving Car

Date: 
Thursday, March 12, 2009 - 3:01pm

UCSB COMPUTER SCIENCE DEPARTMENT PRESENTS
DISTINGUISHED LECTURE:
MONDAY, APRIL 6, 2009
3:00 – 3:30 Reception
3:30 – 4:30 Talk
Engineering Sciences Building, Room 1001

HOST: Subhash Suri

SPEAKER: SETH TELLER
Professor, Electrical Engineering and Computer Science Department and Artificial Intelligence Laboratory, MIT

Title: Development of a Self-Driving Car

Abstract:

In May 2006 we formed a team to compete in DARPA’s 2006-2007 “Urban Challenge,” the goal of which was to develop a passenger vehicle capable of safe, robust autonomous driving in city traffic. Over the following eighteen months, we built the team up to roughly twenty-five faculty, students, and technical staff, acquired more than a half-million dollars worth of sensors and mobile computers and data storage systems, assembled two autonomous vehicles, wrote (and discarded) hundreds of thousands of lines of new code, and tested our system extensively in various public and closed road networks around the country.

This talk surveys some of the issues that arose in the project, including systems design, sensor choice, environment/surround representation, codification of driving rules, algorithm development, and testing methods. We’ll show lots of real data and examples of our algorithms doing reasonable and not-so-reasonable things. We will describe our experiences through the final stages of the competition late this year. Finally, we’ll attempt to identify some of the lessons we learned from the project.

Bio:

Prof. Seth Teller joined the MIT EECS Department and Computer Science and Artificial Intelligence Laboratory in 1994. He heads the Robotics, Vision and Sensor Networks group there, where his lab focuses on developing robots, assistive technology and hand-held devices with situational awareness, i.e., a useful representation of their surroundings. His recent projects include a self-driving
car, a robotic forklift, a voice-commandable autonomous wheelchair, a body-worn navigation assistant for people with visual disabilities, and a hand-held indoor navigation assistant.