Self-Directed Cooperative Planetary Rovers

Sponsored by:
NASA, Aerospace Technology Enterprise

Principal Investigator: Shlomo Zilberstein
Co-Investigators: Eric Hansen, Victor Lesser, and Rich Washington
Collaborators: Francois Charpillet and Abdel-Illah Mouaddib
RAs: Raphen Becker, Daniel Bernstein, Max Horstmann, and Zhengzhu Feng

Project Description

Planetary rovers are unmanned vehicles equipped with cameras and a variety of scientific sensors. They have proved to be a cost-effective mechanism in space exploration and will continue to play a major role in future NASA missions. Recent rover missions, such as Sojourner's Mars exploration, have suffered from total reliance on ground-based commanding and employed on-board autonomy only to safely follow uplinked commands. The inherent uncertainty that characterizes exploration of new environments and the limited communication bandwidth and time delays increase the risk of execution failures and rover downtime.

This project focuses on the question of how to best utilize the rover's resources in the face of the above difficulties. Our approach is to equip the rovers with pre-compiled control polices for making fast decisions on such issues as: how to best perform a given task given a set of alternatives; when the quality of the result is satisfactory; how to react to failure; how many times to retry to perform a certain operation; and how to best allocate limited resources to the entire set of activities over a certain window of operation.

To achieve these goals we are developing and evaluating several fundamental technologies, focused on the basic need to carefully manage the limited computational resources, power, and communication capabilities of the rover. First, we are enriching the rover plan language to describe different methods to achieve each sub-goal and the associated costs and expected quality. We are also providing the system with a model of the uncertainty about the outcome of actions and the resources they consume. Off-line reinforcement learning algorithms are used to construct control policies to choose among the alternative plan options at run-time. These choices are sensitive to the importance of the task, what has been achieved so far, the remaining workload, and the available resources. Second, we are examining the viability of a multi-rover design and its implications on system complexity, autonomy, reliability, and scientific return. Finally, we are building an execution architecture that exploits preliminary on-board data interpretation in order to assess the quality of the collected data and provide feedback to the planner.

Related Publications

  • Automated Conversion and Simplification of Plan Representations.

    M. Allen and S. Zilberstein. ICAPS Workshop on Connecting Planning Theory with Practice, Whistler, BC, 2004. [abs] [bib] [pdf]

  • Dynamic Programming for Decentralized POMDPs.

    D.S. Bernstein, E.A. Hansen, S. Zilberstein, and C. Amato. AAAI Spring Symposium on Bridging the Multi-Agent and Multi-Robot Research Gap, Stanford, California, 2004. [abs] [bib] [pdf]

  • Automated Generation of Understandable Contingency Plans.

    M. Horstmann and S. Zilberstein. Poster presented at the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), 1518-1519, Acapulco, Mexico, 2003. [abs] [bib] [pdf]

  • Transition-Independent Decentralized Markov Decision Processes.

    R. Becker, S. Zilberstein, V. Lesser, and C.V. Goldman. Proceedings of the Second International Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 41-48, Melbourne, Australia, 2003. (Best Paper Award) [abs] [bib] [pdf]

  • Optimizing Information Exchange in Cooperative Multi Agent Systems.

    C.V. Goldman and S. Zilberstein. Proceedings of the Second International Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 137-144, Melbourne, Australia, 2003. [abs] [bib] [pdf]

  • Automated Generation of Understandable Contingency Plans.

    M. Horstmann and S. Zilberstein. ICAPS Workshop on Planning Under Uncertainty and Incomplete Information, Trento, Italy, 2003. [abs] [bib] [pdf]

  • The Complexity of Decentralized Control of Markov Decision Processes.

    D.S. Bernstein, R. Givan, N. Immerman, and S. Zilberstein. Mathematics of Operations Research, 27(4):819-840, 2002. [abs] [bib] [pdf]

  • Decision-Theoretic Control of Planetary Rovers

    S. Zilberstein, R. Washington, D.S. Bernstein, and A.I. Mouaddib. In M. Beetz et al. (Eds.), Plan-Based control of Robotic Agents, LNAI, No. 2466, 270-289, 2002. [abs] [bib] [pdf]

  • Adaptive Control of Acyclic Progressive Processing Task Structures

    S. Cardon, A.I. Mouaddib, S. Zilberstein, and R. Washington. Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), 701-706, Seattle, Washington, 2001. [abs] [bib] [pdf]

  • Communication Decisions in Multi-agent Cooperation: Model and Experiments

    P. Xuan, V. Lesser, and S. Zilberstein. Proceedings of the Fifth International Conference on Autonomous Agents (AGENTS), 616-623, Montreal, Canada, 2001. [abs] [bib] [pdf]

  • Planetary Rover Control as a Markov Decision Process

    D.S. Bernstein, S. Zilberstein, R. Washington, and J. Bresina. The Sixth International Symposium on Artificial Intelligence, Robotics and Automation in Space, Montreal, Canada, 2001. [abs] [bib] [pdf]

  • Optimal Scheduling of Progressive Processing Tasks

    S. Zilberstein and A.I. Mouaddib. International Journal of Approximate Reasoning, 25(3):169-186, 2000. [abs] [bib] [pdf]

  • Optimizing Resource Utilization in Planetary Rovers

    S. Zilberstein and A.I. Mouaddib. Proceedings of the Second NASA International Workshop on Planning and Scheduling for Space, 163-168, 2000. [abs] [bib] [pdf]

  • Reactive Control of Dynamic Progressive Processing

    S. Zilberstein and and A.I. Mouaddib. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI), 1268-1273, Stockholm, Sweden, 1999. [abs] [bib] [pdf]
UMass Amherst