Scaling Up Decision Theoretic Planning to Planetary Rover Problems

Abstract Because of communication limits, planetary rovers must op- erate autonomously during consequent durations. The abil- ity to plan under uncertainty is one of the main components of autonomy. Previous approaches to planning under uncer- tainty in NASA applications are not able to address the chal- lenges of hture missions, because several apparent lim- its. On another side, decision theory provides a solid princi- pled framework for reasoning about uncertainty and rewards. Unfortunately, there are several obstacles to a direct appli- cation of decision-theoretic techniques to the rover domain. This paper focuses on the issues of structure and concurrency, and continuous state variables. We describes two techniques currently under development that address specifically these issues and allow scaling-up decision theoretic solution tech- niques io pianetary rover planning problems involving a small number of goals. Introduction There are many problems inherent in direct human con- trol of remote devices such as planet exploratory rovers and satellites: (i) Communication takes significant time.

[1]  Robert Givan,et al.  Model Minimization in Markov Decision Processes , 1997, AAAI/IAAI.

[2]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[3]  Craig Boutilier,et al.  Stochastic dynamic programming with factored representations , 2000, Artif. Intell..

[4]  Ronen I. Brafman,et al.  Structured Reachability Analysis for Markov Decision Processes , 1998, UAI.

[5]  Avrim Blum,et al.  Fast Planning Through Planning Graph Analysis , 1995, IJCAI.

[6]  Michael L. Littman,et al.  Exact Solutions to Time-Dependent MDPs , 2000, NIPS.

[7]  Tara Estlin,et al.  Continuous planning and execution for an autonomous Mars Rover , 2002 .

[8]  Tara Estlin,et al.  Continuous Planning and Execution for an Autonomous Rover , 2002 .

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

[10]  David E. Smith,et al.  Optimal Limited Contingency Planning , 2002, UAI.

[11]  David E. Smith,et al.  Incremental Contingency Planning , 2003 .

[12]  P. Pandurang Nayak,et al.  Remote Agent: To Boldly Go Where No AI System Has Gone Before , 1998, Artif. Intell..

[13]  Zhengzhu Feng,et al.  Dynamic Programming for Structured Continuous Markov Decision Problems , 2004, UAI.

[14]  David E. Smith,et al.  Integrated Demonstration of Instrument Placement , Robust Execution and Contingent Planning , 2003 .

[15]  Nathanael Hyafil,et al.  Conformant Probabilistic Planning via CSPs , 2003, ICAPS.

[16]  David E. Smith,et al.  Planning Under Continuous Time and Resource Uncertainty: A Challenge for AI , 2002, AIPS Workshop on Planning for Temporal Domains.

[17]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.

[18]  David E. Smith,et al.  Conformant Graphplan , 1998, AAAI/IAAI.

[19]  Michael L. Littman,et al.  Incremental Pruning: A Simple, Fast, Exact Method for Partially Observable Markov Decision Processes , 1997, UAI.

[20]  Jesse Hoey,et al.  SPUDD: Stochastic Planning using Decision Diagrams , 1999, UAI.

[21]  Nicola Muscettola,et al.  Planning in Interplanetary Space: Theory and Practice , 2000, AIPS.

[22]  John L. Bresina,et al.  Just-In-Case Scheduling , 1994, AAAI.

[23]  Jim Blythe,et al.  Decision-Theoretic Planning , 1999, AI Mag..