New Connections between Motion Planning and Machine Learning Sidd Srinivasa (UW)

Abstract: Any time a robot needs to move, a motion needs to be planned. But yet roboticists often treat motion planning as a black box, and barely understand fundamental algorithms like A*. In this talk, I’ll start with some intuition about search, via the absurd analogy of amoebas. I’ll use the analogy to describe the firstever edgeoptimal A*like search algorithm we invented. I’ll then cast anytime search with experience (what we call the Experienced Piano Movers’ Problem) as an instance of Bayesian Reinforcement Learning, enabling us to derive the firstever sublinear regret bounds for anytime motion planning. I’ll end with some open problems I want you all to solve, so I can retire in peace.

Biography: Siddhartha Srinivasa is the Boeing Endowed Professor at The Paul G. Allen School of Computer Science and Engineering at the University of Washington, and an IEEE Fellow. He is a fullstack roboticist, with the goal of enabling robots to perform complex manipulation tasks under uncertainty and clutter, with and around people. To this end, he founded the Personal Robotics Lab in 2005. He was a PI on the Quality of Life Technologies NSF ERC, DARPA ARMS. RCTA and the DARPA Robotics Challenge, has built several robots (HERB, ADA, CHIMP, MuSHR), and has written software frameworks (OpenRAVE, DART) and bestpaper award winning algorithms (CBiRRT, CHOMP, BIT*, Legibility) used extensively by roboticists around the world. Sidd received a B.Tech in Mechanical Engineering from the Indian Institute of Technology Madras in 1999, and a PhD in 2005 from the Robotics Institute at Carnegie Mellon University. He played badminton and tennis for IIT Madras, captained the CMU squash team, and lately runs competitively.


“Robotics Today A series of technical talks” is a new virtual robotics seminar series. The goal of the series is to bring the robotics community together during these challenging times.The seminars are scheduled on Fridays at 1PM EDT (10AM PDT) are open to the public. The format of the seminar consists of a technical talk live captioned and streamed via Web (https://roboticstoday.github.io/watch...) and Twitter (@RoboticsSeminar), followed by an interactive discussion between the speaker and a panel of faculty, postdocs, and students that will moderate audience questions.

Website: https://roboticstoday.github.io/
Twitter:   / roboticsseminar  
Calendar: https://calendar.google.com/calendar/...

Outline
0:00 Introduction
4:20 Sidd's Talk
1:01:35 Panel Discussion
1:22:33 Concluding Remarks