An Application of Adaptive Learning to Malfunction Recovery.

Abstract

A self-organizing controller is developed for a simplified two-dimensional aircraft model. The controller learns how to pilot the aircraft through a navigational mission without exceeding pre-established position and velocity limits. The controller pilots the aircraft by activating one of eight directional actuators at all times. By continually monitoring the aircraft's position and velocity with respect to the mission, the controller progressively modifies its decision rules to improve the aircraft's performance. When the controller has learned how to pilot the aircraft, two actuators fail permanently. Despite this malfunction, the controller regains proficiency at its original task. The experimental results reported show the controller's capabilities foe self-organizing control, learning, and malfunction recovery.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1985
Accession Number
ADA158129

Entities

People

  • R. E. Cruz

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Abstracts
  • Aircraft Models
  • Aircrafts
  • California
  • Classification
  • Computer Programs
  • Computer Science
  • Computers
  • Control Systems
  • Four Dimensional
  • Learning
  • Research Facilities
  • Security
  • Self Organizing Systems
  • Simulations
  • Two Dimensional
  • Universities

Readers

  • Aviation Science / Aeronautics.
  • Neural Network Machine Learning.
  • Robotics and Automation.