CITRIS People and Robots hosts a weekly seminar series every Monday afternoon jointly with UC Berkeley’s “Design of Robotics and Embedded systems, Analysis, and Modeling” Seminars (DREAMS).
SPEAKER: Matthew Walter
BIO: Matthew Walker is an assistant professor and director of the Robot Intelligence through Perception Laboratory (RIPL) at the Toyota Technological Institute at Chicago (TTI-Chicago), a philanthropically endowed academic computer science institute located on the University of Chicago campus. Walker also holds a part-time faculty appointment in the Department of Computer Science at the University of Chicago.
Prior to joining TTI-Chicago, Walker was a research scientist in the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT), where he worked with Seth Teller. He received his PhD from the Joint Program between MIT and the Woods Hole Oceanographic Institution, under the supervision of John Leonard.
Walker’s thesis considered the problem of scaling robotic mapping and localization to larger unknown environments. I studied feature-based algorithms for simultaneous localization and mapping (SLAM) whereby a robot builds a map of the world while concurrently estimating its position in the map. His thesis work proposed a sparse information filter algorithm that is scalable and also preserves estimate consistency. The approach maintains a Gaussian probability distribution over the robot and map states, and takes advantage of insights into the natural structure of this model for SLAM. The Exactly Sparse Extended Information Filter (ESEIF) exploits a sparse parametrization of this distribution to reduce the computational and memory costs from quadratic to linear in the map’s size. In addition to the gains in efficiency, a primary contribution of the algorithm is its ability to achieve sparsity in a principled, yet simple way that preserves consistency. For more information, please see the IJRR paper or his thesis.