Reinforcement learning in spacecraft control applications: Advances, prospects, and challenges

M Tipaldi, R Iervolino, PR Massenio - Annual Reviews in Control, 2022 - Elsevier
This paper presents and analyzes Reinforcement Learning (RL) based approaches to solve
spacecraft control problems. Different application fields are considered, eg, guidance …

Reinforcement learning for robust trajectory design of interplanetary missions

A Zavoli, L Federici - Journal of Guidance, Control, and Dynamics, 2021 - arc.aiaa.org
This paper investigates the use of reinforcement learning for the robust design of low-thrust
interplanetary trajectories in presence of severe uncertainties and disturbances, alternately …

Deep learning techniques for autonomous spacecraft guidance during proximity operations

L Federici, B Benedikter, A Zavoli - Journal of Spacecraft and Rockets, 2021 - arc.aiaa.org
This paper investigates the use of deep learning techniques for real-time optimal spacecraft
guidance during terminal rendezvous maneuvers, in presence of both operational …

Autonomous closed-loop guidance using reinforcement learning in a low-thrust, multi-body dynamical environment

NB LaFarge, D Miller, KC Howell, R Linares - Acta Astronautica, 2021 - Elsevier
Onboard autonomy is an essential component in enabling increasingly complex missions
into deep space. In nonlinear dynamical environments, computationally efficient guidance …

Meta-reinforcement learning for adaptive spacecraft guidance during finite-thrust rendezvous missions

L Federici, A Scorsoglio, A Zavoli, R Furfaro - Acta Astronautica, 2022 - Elsevier
In this paper, a meta-reinforcement learning approach is investigated to design an adaptive
guidance algorithm capable of carrying out multiple rendezvous space missions …

Image-based meta-reinforcement learning for autonomous guidance of an asteroid impactor

L Federici, A Scorsoglio, L Ghilardi… - Journal of Guidance …, 2022 - arc.aiaa.org
This paper focuses on the use of meta-reinforcement learning for the autonomous guidance
of a spacecraft during the terminal phase of an impact mission toward a binary asteroid …

Optimal Q-laws via reinforcement learning with guaranteed stability

H Holt, R Armellin, N Baresi, Y Hashida, A Turconi… - Acta astronautica, 2021 - Elsevier
Closed-loop feedback-driven control laws can be used to solve low-thrust many-revolution
trajectory design and guidance problems with minimal computational cost. Lyapunov-based …

Orbital guidance using higher-order state transition tensors

S Boone, J McMahon - Journal of Guidance, Control, and Dynamics, 2021 - arc.aiaa.org
This paper derives the equations necessary to use state transition tensors (STTs) in a
spacecraft guidance problem. The derivation includes all necessary equations up to the …

Network architecture and action space analysis for deep reinforcement learning towards spacecraft autonomous guidance

L Capra, A Brandonisio, M Lavagna - Advances in Space Research, 2023 - Elsevier
The growing ferment towards enhanced autonomy on-board spacecrafts is driving the
research of leading space agencies. Concurrently, the rapid developments of Artificial …

Cascaded deep reinforcement learning-based multi-revolution low-thrust spacecraft orbit-transfer

SMT Zaidi, PS Chadalavada, H Ullah, A Munir… - IEEE …, 2023 - ieeexplore.ieee.org
Transferring an all-electric spacecraft from a launch injection orbit to the geosynchronous
equatorial orbit (GEO) using a low thrust propulsion system presents a significant challenge …