| Grant Title: | Human-Centered, Intelligent Agents Supporting Communication and Collaboration in Domain-Oriented Design Environments |
|---|---|
| Sponsor: | National Science Foundation |
| Principal Investigators: |
Gerhard Fischer, David Redmiles |
| Period of Support: | September 1993 - August 1996 |
Our research is exploring the embedding of intelligent agents into domain-oriented design environments with the goals of reducing the cognitive load on designers through active behavior and improving the quality of the designed artifact. Incorporating intelligent agents into design raises numerous conceptual, technical, and social issues. These issues are a consequence of mixed-initiative dialogs made possible by agents. Briefly, the conceptual issues we are investigating include shared context, control of initiative and intervention, and focus of attention. Technical problems include user manipulation of agents through an agent editor, activation of agents in a shared context, presentation of agents, and creation of shared context through specification, construction, task representations, and interaction histories. Social issues addressed by our research include the new role distributions between humans and computational agents, namely, the embedding of agents in human-centered cooperative problem solving systems supporting communication, coordination, and collaboration. These issues are being addressed by providing extended task representations and accountability through explanation.
The focus of our investigation are on indirect, long-term collaboration in the design and evolution of complex artifacts. The primary domain we consider is that of local area networks. Plans for networks need to be understood for long-term evolution (maintenance, enhancements, and modifications) by designers who were not necessarily present during the original design and implementation. Other design domains we will investigate include computer graphics software and graphic arts. A focus on design and specific design domains provides unique opportunities for investigating agent-based architectures. First, the behavior of agents can be tuned (made ``intelligent'') by a representation of a shared context which, in design, can rely on interpretations restricted by domain-orientation, partially constructed artifacts, specifications, and interaction histories. Second, agent-based architectures have the potential for supporting the representation and incremental accumulation of information over the course of a design. Finally, in design, agents support communication and collaboration among humans, requiring a human-centered approach rather than a system-centered approach to information representation and delivery.