An Intelligent Man-Machine Dialogue System Based on AI Planning
- 118 Downloads
We describe the modular architecture of a generic dialogue system that assists a user/operator in performing a task with a tool. This coaching system is named CALLIOPE after the Greek goddess of eloquence. It aims at being an active partner in an intelligent man-machine dialogue. The intelligent dimension of the coaching system is reflected by its ability to adapt to the user and the situation at hand. The CALLIOPE system contains an explicit user model and world model to situate its dialogue actions. A plan library allows it to follow loosely predetermined dialogue scenarios.
The heart of the coaching system is an AI planning module, which plans a series of dialogue actions. We present a coherent set of three dialogue or speech actions that will make up the physical form of the man-machine communication.The use of the AI planning paradigm as a basis for man-machine interaction is motivated by research in various disciplines, as e.g., AI, Cognitive Science and Social Sciences. Starting from the man-man communication metaphor, we can view the “thinking before speaking” of a human communication partner as constructing an underlying plan which is responsible for the purposiveness, the organisation and the relevance of the communication.
CALLIOPE has been fully implemented and tested on theoretical examples. At present, also three tailored versions of CALLIOPE are in operational use in different industrial application domains: operator support for remedying tasks in chemical process industry, operator support for a combined task of planning, plan execution and process control in the area of chemical process development, and thirdly decision support in production scheduling.
Unable to display preview. Download preview PDF.
- 1.J.F. Allen and C.R. Perrault, “Analysing intentions in utterances,” Artificial Intelligence, vol. 15, no.3, pp. 143-178, 1980.Google Scholar
- 2.J.A. Ambros-Ingerson and S. Steel, “Integrated planning, execution, and monitoring,” in Proceedings of AAAI 1988, 1988, pp. 65-69.Google Scholar
- 3.D.E. Appelt, “Planning English referring expressions,” Artificial Intelligence, vol. 26, pp. 1-33, 1985.Google Scholar
- 4.D. Chapman, “Planning for conjunctive goals,” Artificial Intelligence, vol. 32, pp. 333-377, 1987.Google Scholar
- 5.P.R. Cohen and C.R. Perrault, “Elements of a plan-based theory of speech acts,” Cognitive Science, vol. 3, pp. 177-212, 1979.Google Scholar
- 6.K. Dockx and R. Timmermans, “Adding a temporal dimension to expert systems working in a real-time environment,” Communication and Cognition-Artificial Intelligence, CCAI, vol. 9, nos.2-3, pp. 253-257, 1992.Google Scholar
- 7.K. Dockx and K. Meert, “Production scheduling in a chemical process environment based on a simulated annealing algorithm,” Journal A, vol. 34, pp. 41-46, 1993.Google Scholar
- 8.K. Dockx, K. Meert, and B. Kuijpers, “Production scheduling in a chemical environment based on simulated annealing,” in Proceedings of AAAI SIGMAN Workshop, New Orleans, 1994.Google Scholar
- 9.R.E. Fikes and N. Nilsson, “STRIPS: A new approach to the application of theorem proving to problem solving,” Artificial Intelligence, vol. 5, no.2, pp. 189-208, 1971.Google Scholar
- 10.E. Fink and Q. Yang, “Automatically abstracting effects of operators,” in Proceedings of the First International Conference on AI Planning Systems, 1992, pp. 243-251.Google Scholar
- 11.E. Fink and Q. Yang, “Characterizing and automatically finding primary effects in planning,” IJCAI-93, pp. 1374-1379, 1993.Google Scholar
- 12.B.J. Grosz and C.L. Sidner, “Plans for discourse,” in Intentions in Communication, edited by P.R. Cohen, J. Morgan, and M.E. Pollack, MIT Press: Cambridge, MA, pp. 417-444, 1990.Google Scholar
- 13.R.W. Hill, Jr. and W.L. Johnson, “Situated plan attribution for intelligent tutoring,” in Proceedings of the Twelfth National Conference on Artificial Intelligence, AAAI-94, 1994, pp. 499-505.Google Scholar
- 14.E. Hollnagel and D.D. Woods, “Cognitive systems engineering: New wine in new bottles,” International Journal of Man-Machine Studies, vol. 18, pp. 583-600, 1983.Google Scholar
- 15.S. Kambhampati, “On the utility of systematicity: Understanding tradeoffs between redundancy and commitment in partial-order planning,” IJCAI-93, pp. 1380-1385, 1993.Google Scholar
- 16.K. Kanev and K. Dockx, “A framework for graphically-oriented human computer interactions in intelligent operator support systems,” Comput. and Graphics, vol. 18, no.4, pp. 563-570, 1994.Google Scholar
- 17.J.D. Moore, Participating in Explanatory Dialogues. Interpreting and Responding to Questions in Context, MIT Press: Cambridge, 1995.Google Scholar
- 18.D.J. Musliner, “Using abstraction and nondeterminism to plan reaction loops,” in Proceedings of the Twelfth National Conference on Artificial Intelligence, AAAI-94, 1994, pp. 1036-1041.Google Scholar
- 19.S.H. Nwana, “Intelligent tutoring systems: An overview,” Artificial Intelligence Review, vol. 4, pp. 251-277, 1990.Google Scholar
- 20.L. Quinn and D.M. Russel, “Intelligent interfaces: User models and planners,” in Proceedings CHI' 86, April 1986, pp. 314-320.Google Scholar
- 21.J. Rasmussen, “Cognitive systems analysis for risk management,” in Proceedings of SITEF 91-International Symposium on Cognitive Interactions, 1991, pp. 24-25.Google Scholar
- 22.E. Sacerdoti, “Planning in a hierarchy of abstraction spaces,” Artificial Intelligence, vol. 5, no.2, pp. 115-135, 1975.Google Scholar
- 23.S. Steel, “The bread and butter of planning,” Artificial Intelligence Review, vol. 1, pp. 159-181, 1987.Google Scholar
- 24.L.A. Suchman, Plans and Situated Actions. The Problem of Human Machine Communication, Cambridge University Press, 1987.Google Scholar
- 25.A. Tate, J. Hendler, and M. Drummond, “A review of AI planning techniques,” in Readings in Planning, edited by J. Allen, J. Hendler, and A. Tate, Morgan Kaufmann Publishers: California, pp. 26-49, 1990.Google Scholar
- 26.P. Van Bael, “Scheduling chemical batch processes with transfer times and sequence dependent set-up times in ZW or NIS policy,” The Second International Conference on the Practical Applications of Constraint Technology, London, UK, 1996, pp. 453-464.Google Scholar
- 27.R. Wilensky, D.N. Chin, M. Luria, J. Martin, J. Mayfield, and D. Wu, “The Berkeley UNIX consultant project,” Computational Linguistics, vol. 14, no.4, pp. 35-84, 1988.Google Scholar