This project is concerned with grounding in multi-modal computer-supported collaboration. In particular, we concentrate on two issues: how constructed visual/spatial references (drawing a diagram) are used during grounding and the role of grounding mechanisms in problem solving. The project will progress in three phases:
- Design or adapt a multi-modal computer-supported collaborative system.
- Use the system to study grounding behavior in computer-mediated human-human collaboration.
- Develop a human-computer collaborative system, in which a computer program can collaborate with a human, using mechanisms for grounding which are functionally equivalent to those of human-human behavior, as observed in the previous phase.
For more information on the project, take a look at the project proposal summary , or the more detailed research project proposal.
Work in Progress:
We also have a BOOTNAP project home page , which has more recent progress updates and pointers to related work. Also see our publications.- Project proposal. Also available as a 1MB non-structured PS file.
David Traum and Pierre Dillenbourg ,
Miscommunication in Multi-modal Collaboration, In working notes of the AAAI Workshop on Detecting, Repairing, And Preventing Human--Machine Miscommunication, August 1996. Draft HTML Version
- Pierre Dillenbourg, David Traum & Daniel Schneider Grounding in Multi-modal Task-Oriented Collaboration, to be presented at the EuroAI&Education Conference, October 1996. Older draft in html
