Abstract: The fields of AI and robotics have made great improvements in many individual subfields, including in motion planning, symbolic planning, reasoning under uncertainty, perception, and learning.
Our goal is to develop an integrated approach to solving very large problems that are hopelessly intractable to solve optimally. We make a number of approximations during planning, including serializing subtasks, factoring distributions, and determinizing stochastic dynamics, but regain robustness and effectiveness through a continuous state-estimation and replanning process.
I will describe our application of these ideas to an end-to-end mobile manipulation system, as well as ideas for current and future work on improving correctness and efficiency through learning.
Bio: Leslie Pack Kaelbling is the Panasonic Professor of Computer Science and Engineering at MIT, where she has been a faculty member since 1999. She has an undergraduate degree in Philosophy and a PhD in Computer Science from Stanford University, and previously held positions at Brown University, Teleos Research, and SRI International. Her goal is to make intelligent robots: she did some of the earliest work on reinforcement learning and partially observable Markov decision processes in robotics, and she is currently focused on integrating geometric, probabilistic, and logical reasoning.
Kaelbling is the founder of the Journal of Machine Learning Research, a recipient of the 1997 IJCAI Computers and Thought Award, and a Fellow of the AAAI. She is not a robot.
*There will be a reception on the second floor atrium following the talk.