NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Machine learning in motion controlThe existing methodologies for robot programming originate primarily from robotic applications to manufacturing, where uncertainties of the robots and their task environment may be minimized by repeated off-line modeling and identification. In space application of robots, however, a higher degree of automation is required for robot programming because of the desire of minimizing the human intervention. We discuss a new paradigm of robotic programming which is based on the concept of machine learning. The goal is to let robots practice tasks by themselves and the operational data are used to automatically improve their motion performance. The underlying mathematical problem is to solve the problem of dynamical inverse by iterative methods. One of the key questions is how to ensure the convergence of the iterative process. There have been a few small steps taken into this important approach to robot programming. We give a representative result on the convergence problem.
Document ID
19940004194
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Su, Renjeng
(Colorado Univ. Boulder, CO, United States)
Kermiche, Noureddine
(Colorado Univ. Boulder, CO, United States)
Date Acquired
August 16, 2013
Publication Date
October 1, 1989
Publication Information
Publication: First Annual Symposium. Volume 1: Plenary Session
Subject Category
Systems Analysis
Accession Number
94N70949
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
Document Inquiry

Available Downloads

There are no available downloads for this record.
No Preview Available