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

Loading...
Thumbnail Image
Authors
Zaidi, Syed Muhammad Talha
Chadalavada, Pardhasai
Ullah, Hayat
Munir, Arslan
Dutta, Atri
Advisors
Issue Date
2023-08-10
Type
Article
Keywords
Artificial neural networks , Cascaded reinforcement learning , Deep learning , Deep reinforcement learning , Low-thrust orbit-raising , Optimization , Orbits , Planetary orbits , Propulsion , Reinforcement learning , Soft actor-critic algorithm , Solar power generation , Solar-electric propulsion , Space vehicles , Spacecraft orbit-transfer
Research Projects
Organizational Units
Journal Issue
Citation
S. M. T. Zaidi, P. S. Chadalavada, H. Ullah, A. Munir and A. Dutta, "Cascaded Deep Reinforcement Learning-Based Multi-Revolution Low-Thrust Spacecraft Orbit-Transfer," in IEEE Access, vol. 11, pp. 82894-82911, 2023, doi: 10.1109/ACCESS.2023.3301726
Abstract

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 due to the long transfer time typically spanning several months. To address the challenge of determining such long time-scale orbit-raising maneuvers to GEO, this paper presents a novel technique to compute transfers starting from geostationary transfer orbit (GTO) and super-GTO. The transfer is complex, involving multiple eclipses and revolutions. To tackle this challenge, we introduce a cascaded deep reinforcement learning (DRL) model to guide a low-thrust spacecraft towards the desired orbit by determining an appropriate thrust direction at each state. To ensure mission requirements, a gradient-aided reward function incorporating the orbital elements, guides the DRL agent to obtain the optimal flight time. The obtained results demonstrate that our proposed approach yields optimal or near-optimal time-efficient spacecraft orbit-raising. DRL implementation is important for spacecraft autonomy; in this context, we demonstrate that our DRL-based trajectory planning provides significantly better transfer time as compared to state-of-the-art approaches that allow for automated trajectory computation. Author

Table of Contents
Description
Open Access article licensed under a Creative Commons License (CC BY-NC-ND 4.0)
Publisher
Institute of Electrical and Electronics Engineers Inc.
Journal
Book Title
Series
IEEE Access
PubMed ID
DOI
ISSN
2169-3536
EISSN