Abstract

This paper presents a novel approach to the problem of action selection for an autonomous agent. An agent is viewed as a collection of com- petence modules. Action selection is modeled as an emergent property of an activation/inhibition dynamics among these modules. A con- crete action selection algorithm is presented and a detailed account of the results is given. This algorithm combines characteristics of both traditional planners and reactive systems: it produces fast and robust activity in a tight interaction loop with the environment, while at the same time allowing for some prediction and planning to take place. It provides global parameters, which one can use to tune the action selection behavior to the characteristics of the task environment. As such one can smoothly trade off goal-orientedness for situation-orientedness, bias towards ongoing plans (inertia) for adaptivity, thoughtfulness for speed, and adjust its sensitivity to goal conflicts.

Citations

2441	A robust layered control system for a mobile robot - Brooks - 1986
530	Pengi: An implementation of a theory of activity - Agre, Chapman - 1987
435	A Behavioral Model of Rational Choice - Simon - 1955
405	Reactive Reasoning and Planning - Georgeff, Lansky - 1987
365	The Society of Mind (Simon and - Minsky - 1986
306	Universal plans for reactive robots in unpredictable environments - Schoppers - 1987
246	Chunking in Soar: The anatomy of a general learning mechanism - Laird, Rosenbloom, et al. - 1986
241	An investigation into reactive planning in complex domains - Firby - 1987
124	The synthesis of digital machines with provable epistemic properties - Rosenschein, Kaelbling - 1986
118	The dynamics of action selection - Maes - 1989
115	An Architecture for Intelligent Reactive Systems - Kaelbling - 1987
25	Case-based problem solving with a Large Knowledge Based of Learned Cases - Lehnert - 1987
17	A model of reaction for planning in dynamic environments - Sanborn, Hendler - 1988
17	Integrating Marker-Passing and Problem Solving: A Spreading Activation Approach to Improved Choice in Planning - Hendler - 1987
15	Distributed artificial intelligence - Huhns - 1987
3	Introduction to Artificial Intelligence - Dermort, D - 1985
2	Reactive reasoning and planning - Georgeif - 1987
2	Connectionist Problem Solving, an AI Perspective - Steels - 1989
1	Modeling Planning as an Incremental Opportunistic Process - al - 1979
1	Integrating Marker-Passing and Problem Solving, A Spreading Activation Approach to Improved Choice in Planning. Lawrence Erlbaum Ass - Hentiler - 1988
1	The Synthesis of Digital Machines with Prowable Epistemic Properties - Rosenschein - 1987
1	Pengi: An Implementation of aTheory of Activity - Agre - 1987