Reference: Hayes-Roth, B.; Pfleger, K.; Morignot, P.; & Lalanda, P. Plans and Behavior in Intelligent Agents. Knowledge Systems Laboratory, March, 1995.
Abstract: An "intelligent agent" is a versatile and adaptive computer system that performs divers cognitive and physical behaviors in its efforts to achieve multiple goals in a dynamic, uncertain task environment. In this paper, we address the question: How should plans influence the cognitive and physical behavior of intelligent agents? In contrast to the well-known model of plans as executable programs, we propose that intelligent agents can make better use of plans that simply describe their intended behavior. This kind of model has been discussed by other researchers, but it has not been operationalized in an agree-upon way. We instantiate this model with operational definitions of plans, planning, and plan following. We present an agent architecture for using such plans to guide an agent's cognitive and physical behaviors. Experimental results from a simulated office surveillance robot demonstrate several important capabilities engendered by our approach: (a) coordination of diverse cognitive and physical behaviors to achieve multiple goals; (b) robust goal-directed improvisation over a range of situation-enabled behaviors; and (c) ready exploitation of asynchronously learned knowledge and behavioral capabilities.
Full paper available as ps.