Cascaded Deep Reinforcement Learning-Based Multi-Revolution Low-Thrust Spacecraft Orbit-Transfer

Syed Muhammad Talha Zaidi, Pardha Sai Chadalavada, Hayat Ullah, Arslan Munir, Atri Dutta

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)82894-82911
Number of pages18
JournalIEEE Access
StatePublished - 2023


  • cascaded reinforcement learning
  • Deep reinforcement learning
  • low-thrust orbit-raising
  • optimization
  • soft actor-critic algorithm
  • solar-electric propulsion
  • spacecraft orbit-transfer

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering


Dive into the research topics of 'Cascaded Deep Reinforcement Learning-Based Multi-Revolution Low-Thrust Spacecraft Orbit-Transfer'. Together they form a unique fingerprint.

Cite this