ICRA 2011 Paper Abstract


Paper WeP112.5

Pastor, Peter (University of Southern California), Kalakrishnan, Mrinal (University of Southern California), Chitta, Sachin (Willow Garage Inc.), Theodorou, Evangelos (University of Southern California), Schaal, Stefan (University of Southern California)

Skill Learning and Task Outcome Prediction for Manipulation

Scheduled for presentation during the Regular Sessions "Learning and Adaptive Systems I" (WeP112), Wednesday, May 11, 2011, 14:40−14:55, Room 5H

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on July 14, 2020

Keywords Learning and Adaptive Systems, Failure Detection and Recovery, Dexterous Manipulation


Learning specific motor skills for real world tasks is a hard problem in robotic manipulation that often requires painstaking manual tuning and design by a human expert. In this work, we present a Reinforcement Learning based approach to acquiring new motor skills from demonstration. Our approach allows the robot to learn fine manipulation skills and significantly improve its success rate and skill level starting from a possibly coarse demonstration. Our approach aims to incorporate task domain knowledge, where appropriate, by working in a task space consistent with the constraints of a specific task. In addition, we also present an approach to using sensor feedback to learn a predictive model of task outcome. This allows our system to learn the proprioceptive sensor feedback needed to monitor subsequent executions of the task online and abort execution in the event of predicted failure. We illustrate our approach using two example tasks executed with a dual-arm manipulator: a straight and accurate pool stroke and a box flipping task using two chopsticks as tools.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-07-14  17:01:47 PST  Terms of use