Learning and Adaptation for Crisis Planning

By their very nature, crises place overwhelming demands on the human planners who must cope with them. This new research effort aims to develop intelligent advisory systems that will assist humans in responding to complex crises. The basic approach involves retrieving an appropriate plan from a preexisting plan library, adapting this plan to the current situation, and tracking it during implementation, adapting it further as the need arises. As with image analysis, the advisory nature of the system supports collection of users' decisions, which in turn provides training data for learning. Over time, the advisory system should come to reflect each user's preferences, and thus greatly reduce the overall time needed to select and adapt a given plan. A longer-term goal of the project is to use learning methods to acquire coordination strategies among different planners, and thus to reduce the number of conflicts that arise during the crisis-planning process.

This work is funded by the Office of Naval Research through Grant N000014-96-1-1221.

Related Publications

Gervasio, M. T., Iba, W., & Langley, P. (1999). Learning user evaluation functions for adaptive scheduling assistance. Proceedings of the Sixteenth International Conference on Machine Learning. Bled, Slovenia. [368K] (Abstract)

Iba, W. & Gervasio, M. (1999). Adapting to user preferences in crisis response. Proceedings of the 1999 Conference on Intelligent User Interfaces. Redondo Beach, CA. [66K] (Abstract)

Langley, P. & Fehling, M. (1998). The experimental study of adaptive user interfaces (Technical Report 98-3). Institute for the Study of Learning and Expertise, Palo Alto, CA. [100K]

Iba, W., Gervasio, M., Langley, P., & Sage, S. (1998). Evaluating computational assistance for crisis response. Proceedings of the Twentieth Annual Meeting of the Cognitive Science Society. Madison, WI. [95K] (Abstract)

Gervasio, M. T., Iba, W., & Langley, P. (1998). Learning to Predict User Operations for Adaptive Scheduling. Proceedings of the Fifteenth National Conference on Artificial Intelligence (pp. 721-726). Madison, WI. [319K] (Abstract)

Gervasio, M. T., Iba, W., & Langley, P. (1998). Case-based seeding for an interactive crisis response assistant. Case-Based Reasoning Integrations: Papers from the 1998 Workshop (Technical Report WS-98-15) (pp. 61-66) AAAI Press, American Association for Artificial Intelligence. Madison, WI. [519K] (Abstract)

Gervasio, M., Iba, W., Langley, P., & Sage, S. (1998). Interactive adaptation for crisis response. Working Notes of the AIPS-98 Workshop on Interactive and Collaborative Planning (pp. 29-36). Pittsburgh, PA. [561K] (Abstract)

Gervasio, M. T. (1998). Adaptive mixed-initiative systems for decision-theoretic crisis response. Interactive and Mixed-Initiative Decision Theoretic Systems: Papers from the 1998 AAAI Spring Symposium (Technical Report SS-98-03) (pp. 53-54). AAAI Press, American Association for Artificial Intelligence. Stanford, CA. [172K] (HTML)

Gervasio, M. T. & Iba, W. (1997). Crisis response planning: a task analysis (extended abstract). Proceedings of the Nineteenth Annual Conference of the Cognitive Science Society (p. 929). Stanford, CA. [29K] (HTML)

Iba, W. & Gervasio, M. T. (1997). Crisis response planning: a task analysis. Preliminary technical report. [289K]

HOME