A FRAMEWORK FOR DEVELOPING ARTIFICIAL INTELLIGENCE FOR AUTONOMOUS SATELLITE OPERATIONS

In the world of educational satellites, student teams manually conduct operations daily. Educational satellites typically travel in a Low Earth Orbit allowing communication for approximately thirty minutes each day. Manual operations during these times is manageable for student teams as the required manpower is minimal. The international Global Educational Network for Satellite Operations (GENSO), however, promises satellite contact upwards of sixteen hours per day by connecting earth stations globally through the Internet. This large increase in satellite communication time makes manual student operations unreasonable and alternatives must be explored. This paper introduces a framework to conduct autonomous satellite operations using different AI methodologies. This paper additionally demonstrates the framework’s usability by introducing a sample rule-based implementation for Cal Poly’s CubeSat, CP3.