Supervenient Hierarchies of Behaviors: Lessons Learned from a Vacuuming Robot

Abstract

In this paper, the authors describe the use of behavior hierarchies based on "merging" two models of multi-layer architecture: the supervenience model and the subsumption model. The behavior hierarchy approach allows them to use the robustness of reactivity in behavior design. It also encourages the design of modular behaviors that can be reused or, more importantly, recalibrated in different situations. They argue that behavior hierarchies extend researchers' ability to design and program effective solutions that do not require any explicit planning. They also describe ongoing work in using this model for integrating planning and reacting. This work is being used in support of an implemented system in which an autonomous mobile robot performs a vacuuming task.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 1994
Accession Number
ADA445811

Entities

People

  • James Hendler
  • Oliver Seeliger

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Classification
  • Computer Science
  • Computers
  • Hierarchies
  • Information Operations
  • Lessons Learned
  • Maryland
  • Military Research
  • Universities

Fields of Study

  • Computer science

Readers

  • Analytical Chemistry
  • Artificial Intelligence
  • Computational Modeling and Simulation

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy