DFKI-LT - A Continual Multiagent Planning Approach to Situated Dialogue
A Continual Multiagent Planning Approach to Situated Dialogue
1 Proceedings of the LONDIAL (The 12th SEMDIAL Workshop on Semantics and Pragmatics of Dialogue), London, United Kingdom, LONDIAL, 6/2008
Situated dialogue is usually tightly integrated with be- havior planning, physical action and perception. This paper presents an algorithmic framework, Continual Collaborative Planning (CCP), for modeling this kind of integrated behavior and shows how CCP agents nat- urally blend physical and communicative actions. For experiments with conversational CCP agents we have developed MAPSIM, a software environment that can generate multiagent simulations from formal multia- gent planning problems automatically. MAPSIM permits comparison of CCP-based dialogue strategies on a wide range of domains and problems without domain-specific programming. Despite their linguis- tic capabilities being limited MAPSIM agents can al- ready engage in fairly realistic situated dialogues. Our ongoing work is taking this approach from simulation to real human-robot interaction.
Files: BibTeX, paper-londial08-final.pdf