Metraipolis › archive › dc_47dbbc530b8a

A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data — arXiv:2611.03466

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03466
License (as archived)
CC0-1.0
Archived
2026-11-03T18:41:31.372Z
SHA-256 of the archived text
e96648dc2f80b06f68801b5e6cf5a82a3f54d3168359d113531dbc0f621a7ec6
Stable URL of this page
https://metraipolis.com/documento/dc_47dbbc530b8a

How to cite

A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data — arXiv:2611.03466 — arXiv (en), https://arxiv.org/abs/2611.03466 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47dbbc530b8a (Metraipolis archive dc_47dbbc530b8a, sha256 e96648dc2f80b06f68801b5e6cf5a82a3f54d3168359d113531dbc0f621a7ec6)
BibTeX
@misc{dc47dbbc530b8a,
  title = {A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data — arXiv:2611.03466},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03466},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47dbbc530b8a; sha256 e96648dc2f80b06f68801b5e6cf5a82a3f54d3168359d113531dbc0f621a7ec6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03466. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As control engineering is applied to increasingly complex systems, learning-based control, which uses empirical data to reduce the reliance on first-principles models, has emerged as a promising paradigm. However, such approaches must cope with nonlinear and stochastic dynamics, the absence of state measurements, and scarce data, while ensuring safe operation under constraints, which requires rigorous uncertainty quantification. Whereas existing methods treat these challenges in isolation, this article proposes a Bayesian framework that jointly addresses them. A prior in state-space form is updated from input-output data using particle Markov chain Monte Carlo methods, yielding a representation of joint uncertainty over dynamics and latent states. Building on this representation, a validation procedure is developed that provides probabilistic guarantees for constraint satisfaction under arbitrary causal control laws. For control synthesis, a formulation penalizing the conditional value-at-risk of the constraint function is proposed, together with an adaptive calibration mechanism that adjusts the performance-robustness trade-off to achieve a desired robustness level. The probability of successful certification is characterized theoretically. The framework is extended to a receding-horizon setting, where posterior updates from new measurements allow the controller to progressively reduce uncertainty and improve performance. The approach is demonstrated on the optimal control of a vertical farm.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.03466 — 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 2026-11-03T18:12:54.809Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).