Reinforcement Learning for Low-Thrust Trajectory Design of Interplanetary Missions

TL;DR

This paper explores using reinforcement learning, specifically Proximal Policy Optimization, to design robust low-thrust interplanetary trajectories that can handle various disturbances and uncertainties, demonstrated through Earth-Mars mission simulations.

Contribution

It introduces a reinforcement learning framework for robust trajectory design, integrating disturbances and uncertainties into the control policy for interplanetary missions.

Findings

The RL-based guidance law closely matches deterministic optimal solutions.

The approach demonstrates robustness against disturbances in Monte Carlo simulations.

Preliminary results suggest RL can effectively handle uncertainties in space trajectory planning.

Abstract

This paper investigates the use of Reinforcement Learning for the robust design of low-thrust interplanetary trajectories in presence of severe disturbances, modeled alternatively as Gaussian additive process noise, observation noise, control actuation errors on thrust magnitude and direction, and possibly multiple missed thrust events. The optimal control problem is recast as a time-discrete Markov Decision Process to comply with the standard formulation of reinforcement learning. An open-source implementation of the state-of-the-art algorithm Proximal Policy Optimization is adopted to carry out the training process of a deep neural network, used to map the spacecraft (observed) states to the optimal control policy. The resulting Guidance and Control Network provides both a robust nominal trajectory and the associated closed-loop guidance law. Numerical results are presented for a typical Earth-Mars mission. First, in order to validate the proposed approach, the solution found in a (deterministic) unperturbed scenario is compared with the optimal one provided by an indirect technique. Then, the robustness and optimality of the obtained closed-loop guidance laws is assessed by means of Monte Carlo campaigns performed in the considered uncertain scenarios. These preliminary results open up new horizons for the use of reinforcement learning in the robust design of interplanetary missions.