SBIR-STTR Award

We will develop a proof-of-concept system that implements an innovative methodology to diagnose and repair unknown satellite anomalies. Our system is based on a novel approach that integrates Case-Based Reasoning (CBR) with Utility Theory. The resulting system deals with unknown and missing information, and selects from a case base the plans or actions that will either fix the satellite or will generate additional information to assist in the diagnosis. The actions are ranked based on criteria selected by the ground operator such as "minimum use of power" or "minimum risk to the spacecraft." The system provides the operator with alternative actions and their ramifications.The main goal of the Phase I effort is to determine how to represent the cases of satellite anomalies, how to implement utility evaluation rules based on user-defined criteria, and to adapt previous research in integrating CBR and utility theory to the satellite anomaly resolution domain. We will also develop metrics of the quality of our technique and will test and evaluate our finished prototype demonstration.We have ensured the collaboration of Hughes Corporation which will provide us with cases and expertise.

Keywords:
SATELLITES DIAGNOSIS ARTIFICIAL INTELLIGENCE

The Lawrence Applied Research Corporation (LARC) proposeds to apply ICARUS to Task Scheduling for the Air Force's Satellite Control Network (SCN). ICARUS (Integrated Case-Based Reasoning and Utility Theory System) is an innovative technology that was developed under a Phase I SBIR, and which uses case-based reasoning (CBR) to rapidly generate multiple, potentially useful schedules, which are evaluated using utility theory based on domain heuristics and problem-specific constraints. ICARUS was successfully demonstrated on a complex-real-life problem of the Space Shuttle. The proposed work adapts the ICARUS technology to the domain of task and resource scheduling for the SCN. Task scheduling of the SCN is a task of extreme significance to the Air Force since it is absolutely essential for data receipt from and transmission to satellites, vehicle maintenance, and orbit tracking and maintenance. ICARUS automates this complex process and minimizes the amount of manpower required and the level of training of the operators, thus resulting in significant savings to the Air Force.The proposed research and development is also applied to NASA's Shuttle Operations Redundancy scheduling and management. ICARUS identifies the recommended redundancy actions, schedules them, and evaluates them based on mission rules and NASA's flight rules.

Keywords:
NASA REDUNDANCY SCHEDULING SATELLITE COMMAND NETWORK SCHEDULING ARTIFICIAL INTELLIGENCE