Accession Number : ADA329721

Title :   Nonparametric Modeling and Control of High Performance Maneuvers

Descriptive Note : Final technical rept.

Corporate Author : GEORGIA INST OF TECH ATLANTA COLL OF COMPUTING

Personal Author(s) : Atkeson, Christopher G.

PDF Url : ADA329721

Report Date : 20 JAN 1997

Pagination or Media Count : 6

Abstract : We developed several nonparametric modeling techniques as well as nonlinear controller design techniques. We successfully implementing these techniques on a robot arm. We used a locally weighted modeling approach as the basis of our nonparametric modeling technique. Locally weighted modeling avoids negative interference by retaining the original training data, so the approach is adaptive to changing data distributions. We used sophisticated representations of high dimensional sub-manifolds to enable dynamic programming in higher dimensional spaces than are currently possible.

Descriptors :   *MATHEMATICAL MODELS, *ROBOTICS, *NONLINEAR PROGRAMMING, NEURAL NETS, AUTOMATION, COMPUTER AIDED DESIGN, ROBOTS, NONPARAMETRIC STATISTICS, NONLINEAR SYSTEMS, CONTROL THEORY, DYNAMIC PROGRAMMING.

Subject Categories : Operations Research
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE