Matthew Walter received his B.S. from the University of Illinois at Urbana-Champaign in 2000 and his Ph.D. in Mechanical and Ocean Engineering from the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution. His thesis considered the problem of scaling robot mapping and localization to large unknown environments, and proposed a sparse information filter that is both scalable and that preserves estimate consistency. Matthew then joined the Computer Science and Artificial Intelligence Laboratory at MIT, where he worked as a Postdoctoral Associate and Research Scientist.
Matthew is interested in developing robots that understand their surroundings and that operate effectively with and alongside people. His research focuses on probabilistic approaches to perception and natural language understanding that enable robots to to learn rich models of the objects, places, people, and events within their environment, and that allow people to interact with robots in ways that are intuitive and safe. His work is motivated by broad applications that include assistive technology, healthcare, logistics, and manufacturing.
Dr. Walter also has a personally maintained website which can be found at http://www.ttic.edu/walter.