University Team to Build Self-Driving Car for City Streets
A team of Cornell students and faculty will receive up to $1 million in Defense Advanced Research Projects Agency (DARPA) funding to develop a vehicle capable of driving itself on city streets. The vehicle will compete in the DARPA Urban Challenge in November 2007.
Last year, the competition goal was to build a vehicle that could drive itself, without human intervention, across 132 miles of desert terrain with unpaved roads, ditches, berms, sandy ground, standing water, rocks and boulders, narrow underpasses, construction equipment, concrete safety rails, power line towers, barbed wire fences, and cattle guards.
Compared with this year, that was a piece of cake.
The new DARPA Urban Challenge, leading up to a competition in November 2007, is to build a car that can drive itself on city streets, obeying traffic laws, stopping at stop signs, navigating traffic circles, and dealing with other vehicles.
Based on an initial proposal from the team, DARPA has selected Cornell as one of 11 “Track A” participants (out of more than 60 applicants) that will receive up to $1 million in advance funding to develop their vehicles. Other teams are expected to compete in the final event–a competition that will require autonomous ground vehicles to execute simulated military supply missions safely and effectively while in a mock city environment. DARPA is the research and development agency for the U.S. Department of Defense. Its long-range goal in sponsoring the challenges is to develop robotic vehicles that can carry out dangerous missions without endangering humans.
The Cornell team has selected a Chevrolet Tahoe SUV as the basic vehicle, but the key element will be what on board collects information from video cameras, radar, lidar (light detection and ranging) and GPS (global positioning satellite) signals and processes that information into a perceptive model of the environment around the vehicle. A probabilistic model not only will show what’s happening but also make predictions about what will happen next. That information then passes to an artificial intelligence system that will send commands to the vehicle’s controls.
The DARPA funding will allow the team to contract out the physical construction of such elements as the vehicle steering and brake controls and allow the students to concentrate on sensor fusion and programming the vehicle’s intelligence. Last year’s team had to build everything from scratch.
The Cornell team of 15 students includes six members of the team that suffered a frustrating defeat in the last DARPA challenge. Although their car had passed qualifying events, a software weakness combined with an action by one of the umpires knocked it out of the final competition after only nine miles.
The Cornell team ‘s faculty advisers are from the departments of Mechanical and Aerospace Engineering, Computing, Information Science, and Business, and Computer Science.