MIT model explains how the brain can learn novel tasks while still remembering what it has already learned.
An MIT vehicle that effectively drives itself has been selected as a semifinalist in this year's DARPA Urban Challenge, a competition for cars and trucks that run without human help. The qualification was announced Thursday by DARPA, the central research and development organization for the Department of Defense.
The announcement means the MIT vehicle and its team of student and faculty developers will travel to an urban military training facility in Victorville, Calif., in late October to compete against 35 other robotic vehicles from across the country. In the semifinals and the finals in early November, the robots will have to execute simulated military supply missions in a mock urban area while obeying California traffic laws--without any human intervention.
"Our team is delighted to move forward to the next stage of the competition," said team leader John Leonard, professor of mechanical and ocean engineering at MIT. "I want to express my gratitude to everyone on our team for their tremendous hard work. I also want to thank all our sponsors for their generous support."
The MIT vehicle uses multiple laser range scanners, high-rate video cameras and automotive radar units to perform autonomous planning and motion control.
In the final Urban Challenge, set for Nov. 3, DARPA will award $2 million, $1 million and $500,000 awards to the top three finishers that complete the course within the six-hour time limit. Unlike the previous two competitions, this challenge will take place in an urban environment with the robotic vehicles required to autonomously operate amongst one another.
In addition to Leonard, key leaders of the MIT team include Professor Jonathan How and Associate Professor Emilio Frazzoli of the MIT Department of Aeronautics and Astronautics, Professor Seth Teller of the MIT Department of Electrical Engineering and Computer Science and Associate Professor David Barrett of Olin College.
The sponsors of Team MIT include the MIT School of Engineering, the MIT Computer Science and Artificial Intelligence Lab, MIT's Department of Electrical Engineering and Computer Science, the C.S. Draper Laboratory, the Ford-MIT Alliance, Land Rover, Quanta Computer, BAE Systems, MIT Lincoln Laboratory, MIT Information Services and Technology, South Shore Tri-Town Development Corporation, Delphi, Applanix, Mobileye, Nokia and Australia National University.