Abstract: Complex robot tasks require a combination of abstractions and algorithms: discrete, geometric, dynamic, or probabilistic. Disconnected or implicit representations limit robots' ability to plan.  We identify integrated combinatorial and geometric needs to plan everyday tasks and develop an integrated task and motion planning system.  Then, we address a key challenge of implicit configuration space representations to explicitly identify feasible and infeasible motion.  In related projects, we use physics-based communication models to plan multi-robot networks, apply formal representations for human-robot interaction, and explore computationally efficient and robust kinematic representations.

Bio: Neil T. Dantam is an Assistant Professor of Computer Science at the Colorado School of Mines.  His research focuses on robot planning and manipulation.  Previously, Neil was a Postdoctoral Research Associate in Computer Science at Rice University working with Prof. Lydia Kavraki and Prof. Swarat Chaudhuri.  Neil received a Ph.D. in Robotics from Georgia Tech, advised by Prof. Mike Stilman, and B.S. degrees in Computer Science and Mechanical Engineering from Purdue University.
His research program is supported by the NSF, NASA, ARL, and ONR.  He has worked at iRobot Research and MIT Lincoln Laboratory.