Presented By: Michigan Robotics
New Perspectives on the Piano Movers' Problem
Siddhartha Srinivasa, Boeing Endowed Professor at the Paul G. Allen School of Computer Science & Engineering at the University of Washington
In 1979, Schwartz and Sharir introduced the Piano Movers' Problem --- move a piano in a cluttered home from start to goal without bumping into obstacles --- as a formalism for robot motion planning, spawning generations of research on graph search, trajectory optimization and randomized algorithms. Now, motion planning is a technology. But yet, surprisingly, there are several fundamental questions unanswered. In this talk, I will address two of them. The first, is a unifying formalism for search called LazySP [winner of the Best Paper Award at ICAPS 2018], that provides a single meta-algorithm capable of expressing several search algorithms like A, Lazy A, bidirectional A, effortlessly. This formalism enables a surprisingly easy answer to a question that has been open for decades: is there an edge-optimal A algorithm? The second is a formal connection between motion planning and machine learning, via Bayesian Active Learning [NIPS 2017, IJCAI 2018], which sets up an efficient algorithm for balancing exploration and exploitation for searching for shortest paths over graphs while exploiting the history of previous problems encountered.
Siddhartha Srinivasa is the Boeing Endowed Professor at The Paul G. Allen School of Computer Science & Engineering at the University of Washington, and an IEEE Fellow. He is a full-stack 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 ARM-S and the DARPA Robotics Challenge, has built several robots (HERB, ADA, CHIMP), and has written software frameworks (OpenRAVE, DART) and best-paper award winning algorithms (CBiRRT, CHOMP, BIT*, Legibility, LazySP) 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.
Siddhartha Srinivasa is the Boeing Endowed Professor at The Paul G. Allen School of Computer Science & Engineering at the University of Washington, and an IEEE Fellow. He is a full-stack 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 ARM-S and the DARPA Robotics Challenge, has built several robots (HERB, ADA, CHIMP), and has written software frameworks (OpenRAVE, DART) and best-paper award winning algorithms (CBiRRT, CHOMP, BIT*, Legibility, LazySP) 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.
Explore Similar Events
-
Loading Similar Events...