Planning in Interplanetary Space: Theory and Practice

On May 17th 1999, NASA activated for the first time an AI-based planner/scheduler running on the flight processor of a spacecraft. This was part of the Remote Agent Experiment (RAX), a demonstration of closedloop planning and execution, and model-based state inference and failure recovery. This paper describes the RAX Planner/Scheduler (RAX-PS), both in terms of the underlying planning framework and in terms of the fielded planner.

• Type: Conference
• Year: 2000
• Where: AIPS
• Authors: Ari K. Jónsson, Paul H. Morris, Nicola Muscettola, Kanna Rajan, Benjamin D. Smith
• Keywords: AIPS 2000, Artificial Intelligence, Flight Processor, Model-based State Inference, RAX Planner/Scheduler