ICRA'09 Paper Abstract


Paper FrB6.4

Ramachandran, Deepak (University of Illinois at Urbana Champaign), Gupta, Rakesh (Honda Research Institute USA Inc)

Smoothed Sarsa: Reinforcement Learning for Robot Delivery Tasks

Scheduled for presentation during the Regular Sessions "Learning and Adaptive Systems - II" (FrB6), Friday, May 15, 2009, 11:30−11:50, Room: 404

2009 IEEE International Conference on Robotics and Automation, May 12 - 17, 2009, Kobe, Japan

This information is tentative and subject to change. Compiled on January 21, 2022

Keywords Learning and Adaptive Systems, Autonomous Agents


Our goal in this work is to make high level decisions for mobile robots. In particular, given a queue of prioritized object delivery tasks, we wish to find a sequence of actions in real time to accomplish these tasks efficiently. We introduce a novel reinforcement learning algorithm called Smoothed Sarsa that learns a good policy for these delivery tasks by delaying the backup reinforcement step until the uncertainty in the state estimate improves. The state space is modeled by a Dynamic Bayesian Network and updated using a Region-based Particle Filter. We take advantage of the fact that only discrete (topological) representations of entity locations are needed for decision-making, to make the tracking and decision making more efficient. Our experiments show that policy search leads to faster task completion times as well as higher total reward compared to a manually crafted policy. Smoothed Sarsa learns a policy orders of magnitude faster than previous policy search algorithms. We demonstrate our results on the Player/Stage simulator and on the Pioneer robot



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2022 PaperCept, Inc.
Page generated 2022-01-21  08:32:13 PST  Terms of use