This project addresses problems central to the design of decision-making strategies that enable computer agents to work effectively with people in heterogeneous groups that interact in carrying out complex activities. These mixed networks of people and systems arise in a wide variety of real-world applications as well as in virtual reality and simulation systems used for training. They occur in settings in which computer systems support people who are working together, those in which they act as proxies for individual people, and those in which groups of agents act autonomously (but alongside people) to carry out constituent tasks for which they are responsible. Despite mixed networks being wide spread, the design of agents that can operate in such settings has received less attention than the design of agents for multi-agent systems comprising only computer agents.
The inclusion of people in mixed networks presents novel problems for the design of autonomous agent decision-making mechanisms. This proposal focuses on the following three of these challenges, which have not been investigated sufficiently in prior work and which agent designers must address to construct systems able to work well with their human partners in mixed networks: (1) information exchange policies for agent competence and past behavior; (2) design of interruption management mechanisms for collaborative interactions; and, (3) learning and incorporation of models of social factors and organizational structures into decision-making mechanisms.