MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  How to do the right thing (1989) [156 citations — 0 self]

Download:
pdf
by Pattie Maes
Connection Science Journal
ftp://publications.ai.mit.edu/ai-publications/pdf/AIM-1180.pdf
Add To MetaCart

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

2142 A robust layered control system for a mobile robot – Brooks - 1986
501 Pengi: an implementation of a theory of activity – Agre, Chapman - 1987
315 Universal plans for reactive robots in unpredictable environments – Schoppers - 1987
292 The Society of Mind. Simon and – Minsky - 1985
249 An investigation into reactive planning in complex domains – Firby - 1987
230 Chunking in Soar: The anatomy of a general learning mechanism – Laird, Rosenbloom, et al. - 1986
177 A behavioral model of rational choice – Simon - 1955
123 The synthesis of digital machines with provable epistemic properties – Itosenschein, Kaelbling - 1986
120 An architecture for intelligent reactive systems – Kaelbling - 1987
118 The Dynamics of Action Selection – Maes - 1989
28 Case-based problem solving with a large knowledge base of learned cases – Lehnert - 1987
20 A model of reaction for planning in dynamic environments – Sanborn, Hendler - 1988
18 Distributed artificial intelligence – Huhns - 1987
16 Integrating Marker-Passing and Problem Solving: A Spreading Activation approach to Improved Choice in Planning. Lawrence Erlbaum – Hendler - 1987
4 Introduction to Artificial Intelligence – Dermort, D - 1985
3 Connectionist Problem Solving, an AI Perspective – Steels - 1989
2 Modeling Planning as an Incremental Opportunistic Process – al - 1979
1 Reactive Reasoning and Planning – Georgeif - 1987
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