A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data
Abstract
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.
Related
- Event-Triggered Funnel Control for Output Reference Tracking of Unknown Nonlinear Systems
- Algebraic Criterion for Nonlinear Unknown Input Observability in Systems Without Control Inputs
- Reach-Stabilize Control of Control-Affine Systems with Unknown Affine Parameters
- Optimal Control of State Constrained Systems via Measure Relaxations and Polynomial Optimization
- BOP2-ENR: a Bayesian optimal phase II design for adaptive enrichment with family-wise error rate control and a bound on joint-claim power
BibTeX
@misc{lefringhausen2026bayesian,
title = {{A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data}},
author = {Robert Lefringhausen and Annalena Daniels and Michael Fink and Sandra Hirche},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03466},
eprint = {2611.03466},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03466},
}
RIS
TY - UNPB
TI - A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data
AU - Robert Lefringhausen
AU - Annalena Daniels
AU - Michael Fink
AU - Sandra Hirche
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.03466
UR - https://arxiv.org/abs/2611.03466
AB - 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.
ER -