Programming by demonstration of probabilistic decision making on a multi-modal service robot

In this paper we propose a process which is able to generate abstract service robot mission representations, utilized during execution for autonomous, probabilistic decision making, by observing human demonstrations. The observation process is based on the same perceptive components as used by the robot during execution, recording dialog between humans, human motion as well as objects poses. This leads to a natural, practical learning process, avoiding extra demonstration centers or kinesthetic teaching. By generating mission models for probabilistic decision making as Partially observable Markov decision processes, the robot is able to deal with uncertain and dynamic environments, as encountered in real world settings during execution. Service robot missions in a cafeteria setting, including the modalities of mobility, natural human-robot interaction and object grasping, have been learned and executed by this system.

[1]  Joelle Pineau,et al.  A formal framework for robot learning and control under model uncertainty , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[2]  David Hsu,et al.  SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces , 2008, Robotics: Science and Systems.

[3]  Joelle Pineau,et al.  Bayes-Adaptive POMDPs , 2007, NIPS.

[4]  Tamim Asfour,et al.  Combining Appearance-based and Model-based Methods for Real-Time Object Recognition and 6D Localization , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Rüdiger Dillmann,et al.  Incremental Learning of Tasks From User Demonstrations, Past Experiences, and Vocal Comments , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Paul Lamere,et al.  Sphinx-4: a flexible open source framework for speech recognition , 2004 .

[7]  Jesse Hoey,et al.  Assisting persons with dementia during handwashing using a partially observable Markov decision process. , 2007, ICVS 2007.

[8]  Rajesh P. N. Rao,et al.  Towards a Real-Time Bayesian Imitation System for a Humanoid Robot , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[9]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[10]  Joelle Pineau,et al.  Point-based value iteration: An anytime algorithm for POMDPs , 2003, IJCAI.

[11]  Leslie Pack Kaelbling,et al.  Acting Optimally in Partially Observable Stochastic Domains , 1994, AAAI.

[12]  Rüdiger Dillmann,et al.  Feature Set Selection and Optimal Classifier for Human Activity Recognition , 2007, RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication.

[13]  Panos E. Trahanias,et al.  Real-time hierarchical POMDPs for autonomous robot navigation , 2007, Robotics Auton. Syst..

[14]  Leslie Pack Kaelbling,et al.  Grasping POMDPs , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[15]  Moritz Tenorth,et al.  KNOWROB — knowledge processing for autonomous personal robots , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  E. J. Sondik,et al.  The Optimal Control of Partially Observable Markov Decision Processes. , 1971 .

[17]  Rüdiger Dillmann,et al.  Bridging the Gap of Abstraction for Probabilistic Decision Making on a Multi-Modal Service Robot , 2008, Robotics: Science and Systems.

[18]  Reid G. Simmons,et al.  Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic , 2006, AAAI.