Learning Controllers for Complex Behavioral Systems.

Abstract

Biological control systems routinely guide complex dynamical systems through complicated tasks such as running or diving. Conventional control techniques, however, stumble with these problems, which have complex dynamics, many degrees of freedom, and a task which is often only partially specified. To address problems like these, we are using a biologically inspired, hierarchical control structure, in which controllers composed of radial basis function networks learn the controls required at each level of the hierarchy. Through learning and proper encoding of behaviors and controls, some of these difficulties in controlling complex systems can be overcome.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 03, 1996
Accession Number
ADA325516

Entities

People

  • Lara S. Crawford
  • S. Shankar Sastry

Organizations

  • University of California, Berkeley

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Angular Momentum
  • Complex Systems
  • Computer Programming
  • Computer Science
  • Control Systems
  • Dynamic Programming
  • Dynamics
  • Engineering
  • Generators
  • Hierarchies
  • Learning
  • Neural Networks
  • Reinforcement Learning
  • Simulations
  • Systems Biology
  • Two Dimensional

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Robotics and Automation.
  • Systems Analysis and Design