Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions
Journal of Aerospace Information Systems · 2024-12 · 21 (12) · 996-1013
DOI: 10.2514/1.i011391 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Aerospace Information Systems, 2024-12. Verfasst von David van Wijk und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 19 Literaturangaben. Gefördert von: Air Force Research Laboratory under the Safe Trusted Autonomy for Responsible Spacecraft (STARS) Seedlings for Disruptive Capabilities Program.
Abstract (Originalsprache)
While reinforcement learning (RL) offers high-performance solutions to complex tasks, its trial-and-error paradigm presents safety concerns when exploring unsafe states may be unacceptable. Safety filtering or run-time assurance (RTA) approaches can be used to monitor the RL agent’s desired control and prevent the agent from taking unsafe actions by satisfying safety constraints during and after training. This study investigates the problem of on-orbit inspection of a chief spacecraft using a deputy spacecraft controlled by an RL agent with safety constraints. Several constraints on the state space are enforced using discrete control barrier functions and an optimization-based RTA system. This assures the safety of the deputy spacecraft and its sensors even with a neural-network-based primary controller. A detailed analysis of RL agent performance for eight separate experiments is presented, including each safety constraint individually, all constraints simultaneously, and no constraints. Results demonstrate that the RL agent can complete the inspection task while adhering to safety constraints in a simulated RL environment. These results also show that the RTA system can aid the RL agent in learning a successful policy over fewer time steps but may lead to higher fuel usage, depending on the constraint(s) enforced.
Förderung
- Air Force Research Laboratory under the Safe Trusted Autonomy for Responsible Spacecraft (STARS) Seedlings for Disruptive Capabilities Program
Zitieren
APA
Wijk, D. V., Dunlap, K., Majji, M., & Hobbs, K. (2024). Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions. Journal of Aerospace Information Systems, 21(12), 996-1013. https://doi.org/10.2514/1.i011391
Vancouver
Wijk DV, Dunlap K, Majji M, Hobbs K. Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions. Journal of Aerospace Information Systems. 2024;21(12):996-1013. doi:10.2514/1.i011391
BibTeX
@article{Wijk2024,
author = {Wijk, David van and Dunlap, Kyle and Majji, Manoranjan and Hobbs, Kerianne},
title = {Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions},
journal = {Journal of Aerospace Information Systems},
year = {2024},
volume = {21},
number = {12},
pages = {996--1013},
doi = {10.2514/1.i011391}
}
EUVIMED