Plans and Behavior in Intelligent Agents

Plans and Behavior in Intelligent Agents Barbara Hayes-Roth, Karl Pfleger, Philippe Morignot, and Philippe Lalanda Abstract An intelligent agent is a versatile and adaptive system that performs diverse behaviors in its efforts to achieve multiple goals in a dynamic, uncertain environment. In this paper, we address the question: How should plans influence the 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 abstractly describe their intended behavior. This idea has been discussed by other researchers, but it has not been operationalized. 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 behaviors. Experimental results from an office robot in different scenarios demonstrate important capabilities engendered by our approach: (a) coordination of diverse behaviors to achieve multiple goals; (b) robust improvisation of goal-directed behavior over a range of situations; and (c) ready exploitation of asynchronously acquired knowledge and behavioral capabilities.