Abstract:

Due to their inherently high-dimensional configuration spaces, non-rigid objects pose a number of difficult challenges. This difficulty is exemplified by the state of the art in robotic laundry folding and robotic surgery.  In this talk I will present our work on tracking and manipulation of deformable objects, which has enabled for a range of articles to have a robot fold it, and which has enabled advances in robotic knot-tying.

Bio:

Pieter Abbeel has been on the faculty at UC Berkeley since Fall 2008, with an appointment in the Department of Electrical Engineering and Computer Sciences.  He has won various awards, including best paper awards at ICML and ICRA, and Sloan and Okawa Foundations awards. He has developed apprenticeship learning algorithms which have enabled advanced helicopter aerobatics, including maneuvers such as tic-tocs, chaos and auto-rotation, which only exceptional human pilots can perform.  His group has also enabled the first end-to-end completion of reliably picking up a laundry item and folding it.  His work has been featured in many popular press outlets, including BBC, MIT Technology Review, Discovery Channel, SmartPlanet and Wired.  His current research focuses on robotics and machine learning with a particular focus on the application areas of personal robotics, surgical robotics and connectomics.