How to Do the Right Thing

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 competence modules. Action selection is modelled as an emergent property of an activation/inhibition dynamics among these modules. A concrete 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 provides global parameters, which one can use to tune the action selection behavior along several criteria, such as goal orientedness versus situation orientedness, bias towards ongoing plans versus adaptivity, and sensitivity to goal conflicts and 'thoughtfulness' versus speed. Keywords: Action selection; Planning; Autonomous agents; Control architectures; Artificial intelligence; Decision making; Spreading activation algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA220031

Entities

People

  • Pattie Maes

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Autonomous Agents
  • California
  • Computational Science
  • Computations
  • Control Systems
  • Dynamics
  • Equations
  • Fault Tolerance
  • Heat Of Activation
  • Hybrid Systems
  • Language
  • Learning
  • Lisp Programming Language
  • Mathematical Models
  • Models
  • Simulations

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks