Deep Reinforcement Learning for the Automatic Six-Degree-of-Freedom Docking Maneuver of Space Vehicles

Deep Reinforcement Learning for the Automatic Six-Degree-of-Freedom Docking Maneuver of Space Vehicles

Casals Sadlier, Juliette (TU Delft Aerospace Engineering)

van Kampen, E. (mentor)

Delft University of Technology

Aerospace Engineering

2022-10-31

The implementation of a model-free, off-policy, actor-critic deep reinforcement learning algorithm consistent of two separate agents to a six-degree-of freedom spacecraft docking maneuver to develop a control policy is carried out in the research presented in this article. Reinforcement learning has the ability to learn without instruction, this aspect provides a potential framework for autonomous docking maneuvers in uncertain environments with low on-board computational cost. A Twin-Delayed Deep Deterministic Policy Gradient algorithm consistent of two agents is used to synthesise the docking control policy valid for the six degree-of-freedom continuous state-space. Testing of the resultant policy exhibits its behaviour and capability to achieve successful docking within the established position and attitude ranges.

Deep Reinforcement Learning
Reinforcement Learning (RL)
Spacecraft
Control system
docking

http://resolver.tudelft.nl/uuid:87a148b9-163b-41d7-aea8-479299be113c

Student theses

master thesis

© 2022 Juliette Casals Sadlier