Dr. Joshua Bongard has invented robots that can self-heal. For example, they detecting a missing leg and invent a new way to continue walking.
Bongard's research article entitled, "Resilient machines through continuous self modeling," will appear in Science Magazine, Friday November 17, 2006.
Dr. Bongard is assistant professor in the Department of Computer Science at the University of Vermont in the College of Engineering and Mathematical Sciences.
"There is a need for planetary robotic rovers to be able to fix things on their own," said Bongard. "The research is essential for NASA who plan to continue using robots for planetary missions. Robots on other planets must be able to continue their mission without human intervention in the event they are damaged and cannot communicate their problem back to Earth. Our robot is able to detect -- without a camera -- that something is wrong, and teach itself to continue to walk in spite of incurred damage."
A homemade robot was used for the experiments where one robotic leg was removed. The robot is programmed to do damage assessments by moving in sequences that look playful but allow the robot to determine where damage has occurred; once identified, it then self creates a new way to move without the missing limb and therefore is able to then carry on its mission.
Dr. Bongard intends to use robot construction kits, such as Lego Mindstorms, to continue his research here at UVM, and involve undergraduate and graduate students in the process.
The research, done for NASA and the U.S. Department of Energy by Dr. Bongard while at Cornell prior to his arrival at UVM, will air on the Discovery Channel of Canada Thursday, Nov. 16 and on Discoveries This Week on the Science Channel Friday, November 17.
Dr. Bongard is available with video and pictures for media: Friday, Nov. 17 -- 9:00 - 11:00 a.m. and 12:15 to 1:15 p.m. in the Dean's Office 109 Votey Building, University of Vermont.
For more information contact:
Dr. Josh Bongard
Department of Computer Science
College of Engineering and Mathematical Sciences
University of Vermont
329 Votey Hall
33 Colchester Avenue
Burlington, VT 05405