About this document
Mars Landing Control via Reinforcement Learning by Vahid Ataei is a document available to read on EtoBox.
The document presents a novel integrated guidance and control algorithm for pinpoint Mars landing using reinforcement learning. The algorithm directly maps the estimated lander state to actuator commands using a policy trained with reinforcement learning. Specifically, proximal policy optimization is used to learn a policy that results in accurate and fuel efficient trajectories. Simulation results demonstrate the algorithm
- Author
- Vahid Ataei
- Language
- EN