Title: Why Evolving Morphology Matters
Dr. Josh Bongard
Department of Computer Science
University of Vermont
Date: October 19, 2010
Time: 9:00 am
Room: 1279 Anthony Hall
Host: Philip McKinley
Abstract:
Biological evolution shapes the physiology and neurophysiology of animals, but in the majority of robotics projects the robot's body plan is fixed and only its neural network controller is optimized. In this talk I will describe a number of projects in which the body and brains of simulated robots are evolved in virtual (yet physically-realistic) environments. In particular I will show that this approach has a number of advantages, such as (1) the automatic design of autonomous robots; (2) automated specialization of different parts of the robot body to perform different tasks; and (3) the generation of testable biological hypotheses.
Josh Bongard is an assistant professor at the University of Vermont. He is an NSF CAREER award, MIT Technology Review TR35 and Microsoft Faculty Fellow recipient. He received his Bachelors degree in Computer Science from McMaster University, Canada, his Masters degree from the University of Sussex, UK, and his PhD from the University of Zurich, Switzerland. He served as a postdoctoral associate under Hod Lipson in the Computational Synthesis Laboratory at Cornell University from 2003 to 2006.