Metraipolis › archive › dc_094bce2afb56

Forward-Invariant Policy Classes for Safe Reinforcement Learning in Multicopter Control — arXiv:2609.38655

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38655
License (as archived)
CC0-1.0
Archived
2026-10-07T16:05:14.631Z
SHA-256 of the archived text
109055462eedae467aa987209c07b83cf712bada2696e9cc844ff7451baacdfa
Stable URL of this page
https://metraipolis.com/documento/dc_094bce2afb56

How to cite

Forward-Invariant Policy Classes for Safe Reinforcement Learning in Multicopter Control — arXiv:2609.38655 — arXiv (en), https://arxiv.org/abs/2609.38655 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_094bce2afb56 (Metraipolis archive dc_094bce2afb56, sha256 109055462eedae467aa987209c07b83cf712bada2696e9cc844ff7451baacdfa)
BibTeX
@misc{dc094bce2afb56,
  title = {Forward-Invariant Policy Classes for Safe Reinforcement Learning in Multicopter Control — arXiv:2609.38655},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38655},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_094bce2afb56; sha256 109055462eedae467aa987209c07b83cf712bada2696e9cc844ff7451baacdfa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38655. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes a reinforcement learning (RL) framework for safe gain scheduling based on forwardinvariance-induced action-space design. Under stated nominalmodel and inversion-domain assumptions, rather than enforcing safety through runtime shielding or penalty-based constraints, safety is embedded directly into the policy class. Specifically, we construct a finite library of feedback controllers sharing a common Lyapunov certificate that establishes forward invariance of a prescribed admissible set under arbitrary switching. Consequently, any policy whose actions are restricted to this library, including policies encountered during RL exploration, inherits the same certificate. Policy optimization can therefore focus on closed-loop performance without runtime safety filtering or action projection. The framework is instantiated for quadcopter hover regulation, where a DQN schedules among certified feedback controllers. Nonlinear MuJoCo simulations demonstrate state-dependent gain scheduling and empirically evaluate robustness to wind, model mismatch, sensor noise, and sensing delay. The results illustrate how safety certification can be separated from policy optimization by learning over a forward-invariant policy class.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-01 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.38655 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:38:32.020Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).