Date of Award
Master of Science in Space Systems
Department of Aeronautics and Astronautics
Joshuah A. Hess, PhD
Recent successes in machine learning research, buoyed by advances in computational power, have revitalized interest in neural networks and demonstrated their potential in solving complex controls problems. In this research, the reinforcement learning framework is combined with traditional direct shooting methods to generate optimal proximal spacecraft maneuvers. Open-loop and closed-loop feedback controllers, parameterized by multi-layer feed-forward artificial neural networks, are developed with evolutionary and gradient-based optimization algorithms. Utilizing Clohessy- Wiltshire relative motion dynamics, terminally constrained fixed-time, fuel-optimal trajectories are solved for intercept, rendezvous, and natural motion circumnavigation transfer maneuvers using three different thrust models: impulsive, finite, and continuous. In addition to optimality, the neurocontroller performance robustness to parametric uncertainty and bounded initial conditions is assessed. By bridging the gap between existing optimal and nonlinear control techniques, this research demonstrates that neurocontrollers offer a flexible and robust alternative approach to the solution of complex controls problems in the space domain and present a promising path forward to more capable, autonomous spacecraft.
DTIC Accession Number
George, B. Cole, "Optimal and Robust Neural Network Controllers for Proximal Spacecraft Maneuvers" (2019). Theses and Dissertations. 2217.