| ← Back to list of papers of the 2026 EuroGNC conference |
CEAS EuroGNC 2026 |
||||
Deep Reinforcement Learning and Optimal Control for Designing Safe Orbits around Asteroids |
||||
|
||||
| Abstract: The inhomogeneous gravity field of an asteroid strongly perturbs nearby spacecraft trajectories. Orbits that would be bounded under Keplerian assumptions may instead evolve into collision or escape paths. This work addresses the challenge of designing safe and optimal control strategies for low-altitude orbits around asteroids. Two solution approaches are compared: direct transcription of the optimal control problem, and the soft actor-critic algorithm, a deep reinforcement learning method. Direct transcription boils down to a non-linear program which proves to be efficient in terms of delta-v consumption but becomes infeasible for certain test cases. In contrast, the soft actor-critic method produces a global policy that succeeds across the entire test set and offers faster evaluation. In both approaches, an additional penalty term is introduced to keep the spacecraft trajectory within a safe orbital shell. | ||||
| Keywords: Asteroids; Astrodynamics; Reinforcement Learning; Trajectory Optimization | ||||
 View PDF CEAS-GNC-2026-007 doi: 10.82124/CEAS-GNC-2026-007 |
| Julio C. Sanchez, Pablo Redondo-Amaro: Deep Reinforcement Learning and Optimal Control for Designing Safe Orbits around Asteroids. Proceedings of the 2026 CEAS EuroGNC conference. Madrid, Spain. May 2026. doi: 10.82124/CEAS-GNC-2026-007. |
| BibTeX entry (UTF-8): @Incollection{CEAS-GNC-2026-007, author = {Sanchez, Julio C. and Redondo-Amaro, Pablo}, title = {Deep Reinforcement Learning and Optimal Control for Designing Safe Orbits around Asteroids}, booktitle = {Proceedings of the 2026 {CEAS EuroGNC} conference}, address = {Madrid, Spain}, month = may, year = {2026}, doi = {10.82124/CEAS-GNC-2026-007} } |