Neural-based Control for CubeSat Docking Maneuvers

TL;DR

This paper introduces a neural network-based control method using reinforcement learning for autonomous spacecraft docking, demonstrating improved adaptability and robustness through simulations and hardware tests.

Contribution

It presents a novel neural network and reinforcement learning approach for spacecraft docking, enabling onboard implementation and enhanced disturbance handling.

Findings

Effective in simulation environments with 6DoF dynamics.

Demonstrated feasibility through hardware testing.

Improves robustness and adaptability of docking maneuvers.

Abstract

Autonomous Rendezvous and Docking (RVD) have been extensively studied in recent years, addressing the stringent requirements of spacecraft dynamics variations and the limitations of GNC systems. This paper presents an innovative approach employing Artificial Neural Networks (ANN) trained through Reinforcement Learning (RL) for autonomous spacecraft guidance and control during the final phase of the rendezvous maneuver. The proposed strategy is easily implementable onboard and offers fast adaptability and robustness to disturbances by learning control policies from experience rather than relying on predefined models. Extensive Monte Carlo simulations within a relevant environment are conducted in 6DoF settings to validate our approach, along with hardware tests that demonstrate deployment feasibility. Our findings highlight the efficacy of RL in assuring the adaptability and efficiency of spacecraft RVD, offering insights into future mission expectations.