Using Learning in a Control Agent

James J. Pomykalski, James Madison University, USA

The NASA Goddard Space Flight Center has undertaken an R&D project whose near-term objective is to achieve a higher level of autonomy in ground-based system operations. The multi-agent system, named LOGOS, is designed to replace human operators in the satellite ground control centers. This paper focuses on the on-going development of the control agent for LOGOS and the use of learning technologies to ensure the long-term success of LOGOS.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.