Abstract
Planetary rovers are small unmanned vehicles equipped with cameras and a variety of sensors used for scientific experiments. They must operate under tight constraints over such resources as operation time, power, storage capacity, and communication bandwidth. Moreover, the limited computational resources of the rover limit the complexity of on-line planning and scheduling. We describe two decision-theoretic approaches to maximize the productivity of planetary rovers: one based on adaptive planning and the other on hierarchical reinforcement learning. Both approaches map the problem into a Markov decision problem and attempt to solve a large part of the problem off-line, exploiting the structure of the plan and independence between plan components. We examine the advantages and limitations of these techniques and their scalability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bapna, D., Rollins, E., Murphy, J., Maimone, E., Whittaker, W., and Wetter-green, D.: The Atacama Desert Trek: Outcomes. IEEE International Conference on Robotics and Automation (ICRA-98) (1998) 597–604
Bernstein, D.S., and Zilberstein, S.: Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control. European Conference on Planning (2001)
Bernstein, D.S., Zilberstein, S., Washington, R., and Bresina, J.L.: Planetary Rover Control as a Markov Decision Process. Sixth International Symposium on Artificial Intelligence, Robotics, and Automation in Space (2001)
Boutilier, C., Dean, T., and Hanks, S.: Decision-Theoretic Planning: Structural Assumptions and Computational Leverage. Journal of Artificial Intelligence Research 1 (1999) 1–93
Boyan, J.A., and Littman, M.L.: Exact Solutions to Time-Dependent MDPs. Advances in Neural Information Processing Systems MIT Press, Cambridge, MA (2001)
Bresina, J.L., Golden, K., Smith, D.E., and Washington, R.: Increased Flexibility and Robustness of Mars Rovers. Fifth International Symposium on Artificial Intelligence, Robotics and Automation in Space (1999)
Bresina, J.L., and Washington, R.: Expected Utility Distributions for Flexible, Contingent Execution. AAAI-2000 Workshop: Representation Issues for Real-World Planning Systems (2000)
Bresina, J.L., and Washington, R.: Robustness Via Run-Time Adaptation of Contingent Plans. AAAI Spring Symposium on Robust Autonomy (2001)
Bresina, J.L., Bualat, M., Fair, M., Washington, R., and Wright, A.: The K9 On-Board Rover Architecture. European Space Agency (ESA) Workshop on On-Board Autonomy (2001)
Cardon, S., Mouaddib, A.-I., Zilberstein, S., and Washington, R.: Adaptive Control of Acyclic Progressive Processing Task Structures. Seventeenth International Joint Conference on Artificial Intelligence (2001) 701–706
Christian, D., Wettergreen, D., Bualat, M., Schwehr, K., Tucker, D., and Zbinden, E.: Field Experiments with the Ames Marsokhod Rover. Field and Service Robotics Conference (1997)
Dean, T., and Boddy, M.: An Analysis of Time-Dependent Planning. Seventh National Conference on Artificial Intelligence (1988) 49–54
Dean, T., and Lin, S.-H.: Decomposition Techniques for Planning in Stochastic Domains. Fourteenth International Joint Conference on Artificial Intelligence (1995) 1121–1127
Estlin, T., Gray, A., Mann, T., Rabideau, G., Castano, R., Chien, S., and Mjol-sness, E.: An Integrated System for Multi-Rover Scientific Exploration. Sixteenth National Conference on Artificial Intelligence (1999) 541–548
Fikes, R., and Nilsson, N.: Strips: A New Approach to the Application of Theorem Proving to Problem Solving. Artificial Intelligence 2 (1971) 189–208
Foreister, J.-P., and Varaiya, P.: Multilayer Control of Large Markov Chains. IEEE Transactions on Automatic Control 23(2) (1978) 298–304
Fukunaga, A., Rabideau, G., Chien, S., Yan, D.: Toward an Application Framework for Automated Planning and Scheduling. International Symposium on Artificial Intelligence, Robotics and Automation for Space (1997)
Green, C.: Application of Theorem Proving to Problem Solving. First International Joint Conference on Artificial Intelligence (1969) 219–239
Hansen, E.A., and Zilberstein, S.: LAO*: A Heuristic Search Algorithm that Finds Solutions with Loops. Artificial Intelligence 129(1–2) (2001) 35–62
Hauskrecht, M., Meuleau, N., Kaelbling, L.P., Dean, T., and Boutilier, C.: Hierarchical Solution of Markov Decision Processes Using Macro-Actions. Fourteenth International Conference on Uncertainty in Artificial Intelligence (1998)
Kaelbling, L., Littman, M., and Cassandra, A.: Planning and Acting in Partially Observable Stochastic Domains. Artificial Intelligence 101(1–2) (1998) 99–134
Limonadi, D.: Smart Lander Reference Surface Scenario and Reference Vehicle Description. Jet Propulsion Laboratory Interoffice Memorandum, November 2 (2001)
Mishkin, A.H., Morrison, J.C., Nguyen, T.T., Stone, H.W., Cooper, B.K., and Wilcox, B.H.: Experiences with Operations and Autonomy of the Mars Pathfinder Microrover. IEEE Aerospace Conference (1998)
Mouaddib, A.-I., and Zilberstein, S.: Optimal Scheduling of Dynamic Progressive Processing. Thirteenth Biennial European Conference on Artificial Intelligence (1998) 449–503
Muscettola, N., Nayak, P.P., Pell, B., and Williams, B.C.: Remote Agent: To Boldly Go Where No AI System Has Gone Before. Artificial Intelligence 103(1–2) (1998) 5–47
Parr, R.: Flexible Decomposition Algorithms for Weakly-Coupled Markov Decision Problems. Fourteenth International Conference on Uncertainty in Artificial Intelligence (1998)
Puterman, M.L.: Markov Decision Processes-Discrete Stochastic Dynamic Programming. John Wiley & Sons, Inc., New York, NY (1994)
Sacerdoti, E.D.: Planning in a Hierarchy of Abstraction Spaces. Artificial Intelligence 5(2) (1974) 115–135
Simmons, R., and Koenig, S.: Probabilistic Robot Navigation in Partially Observable Environments. Fourteenth International Joint Conference on Artificial Intelligence (1995) 1080–1087
Stoker, C, R.oush, T., and Cabrol, N.: Personal communication (2001)
Sutton, R.S., and Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)
Sutton, R.S., Precup, D., and Singh, S.: Between MDPs and Semi-MDPs: Learning, Planning, and Representing Knowledge at Multiple Temporal Scales. Artificial Intelligence, 112 (2000) 181–211
Watkins, C.: Learning from Delayed Rewards. PhD Thesis, Cambridge University, Cambridge, England (1989)
Wellman, M.P., Larson, K., Ford, M., and Wurman, P.R.: Path Planning under Time-Dependent Uncertainty. Eleventh Conference on Uncertainty in Artificial Intelligence (1995) 532–539.
Zilberstein, S., and Mouaddib, A.-I.: Reactive Control of Dynamic Progressive Processing. Sixteenth International Joint Conference on Artificial Intelligence (1999) 1268–1273
Zilberstein, S., and Mouaddib, A.-I.: Adaptive Planning and Scheduling of On-Board Scientific Experiments. European Space Agency (ESA) Workshop on On-Board Autonomy (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zilberstein, S., Washington, R., Bernstein, D.S., Mouaddib, AI. (2002). Decision-Theoretic Control of Planetary Rovers. In: Beetz, M., Hertzberg, J., Ghallab, M., Pollack, M.E. (eds) Advances in Plan-Based Control of Robotic Agents. Lecture Notes in Computer Science(), vol 2466. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-37724-7_16
Download citation
DOI: https://doi.org/10.1007/3-540-37724-7_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00168-3
Online ISBN: 978-3-540-37724-5
eBook Packages: Springer Book Archive