Planning under Uncertainty for Reliable Health Care Robotics

We describe a mobile robot system, designed to assist residents of an retirement facility. This system is being developed to respond to an aging population and a predicted shortage of nursing professionals. In this paper, we discuss the task of finding and escorting people from place to place in the facility, a task containing uncertainty throughout the problem. Planning algorithms that model uncertainty well such as Partially Observable Markov Decision Processes (POMDPs) do not scale tractably to most real world problems. We demonstrate an algorithm for representing real world POMDP problems compactly, which allows us to find good policies in reasonable amounts of time. We show that our algorithm is able to find moving people in close to optimal time, where the optimal policy would start with knowledge of the person’s location.

[1]  Joelle Pineau,et al.  Experiences with a mobile robotic guide for the elderly , 2002, AAAI/IAAI.

[2]  Amos Storkey,et al.  Advances in Neural Information Processing Systems 20 , 2007 .

[3]  Sebastian Thrun,et al.  Coastal Navigation with Mobile Robots , 1999, NIPS.

[4]  Thomas G. Dietterich,et al.  Editors. Advances in Neural Information Processing Systems , 2002 .

[5]  Geoffrey J. Gordon.  Generalized^2 Linear^2 Models , 2002, NIPS 2002.

[6]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[7]  Michael I. Jordan,et al.  PEGASUS: A policy search method for large MDPs and POMDPs , 2000, UAI.

[8]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[9]  Leslie Pack Kaelbling,et al.  Acting under uncertainty: discrete Bayesian models for mobile-robot navigation , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[10]  Jeff G. Schneider,et al.  Autonomous helicopter control using reinforcement learning policy search methods , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[11]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[12]  Andrew McCallum,et al.  Instance-Based Utile Distinctions for Reinforcement Learning , 1995 .

[13]  Andrew W. Moore,et al.  Variable Resolution Discretization for High-Accuracy Solutions of Optimal Control Problems , 1999, IJCAI.

[14]  Craig Boutilier,et al.  Value-Directed Compression of POMDPs , 2002, NIPS.

[15]  Sebastian Thrun,et al.  Monte Carlo POMDPs , 1999, NIPS.

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

[17]  Sebastian Thrun,et al.  Locating moving entities in indoor environments with teams of mobile robots , 2003, AAMAS '03.

[18]  Joelle Pineau,et al.  Spoken Dialog Management for Robots , 2000, ACL 2000.

[19]  Sanjoy Dasgupta,et al.  A Generalization of Principal Components Analysis to the Exponential Family , 2001, NIPS.

[20]  Geoffrey J. Gordon.  Generalized² Linear² Models , 2003, NIPS 2003.

[21]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

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

[23]  Nicholas Roy,et al.  Exponential Family PCA for Belief Compression in POMDPs , 2002, NIPS.

[24]  Milos Hauskrecht,et al.  Value-Function Approximations for Partially Observable Markov Decision Processes , 2000, J. Artif. Intell. Res..