AAAI Spring Symposium on Lessons Learned from Implemented Software Architectures for Physical Agents, March 27-29, 1995, Stanford University, California, USA
This paper describes an architecture for controlling autonomous agents, building on previous work addressing reactive and deliberative control methods. The proposed multi-layered architecture allows a resource-bounded, goal-directed agent to reason predicatively about potential conflicts by constructing causal theories which explain other agents' observed behaviours and hypothesize their goals and intentions; at the same time it enables the agent to operate autonomously and to react promptly to changes in its real-time physical environment. A number of criteria which influenced the design and implementation of the architecture, in particular its action control component, are also discussed.
Proceedings of the AAAI Spring Symposium on Lessons Learned from Implemented Software Architectures for Physical Agents.