Learning-Based Optimal Control with Performance Guarantees for Unknown Systems with Latent States

arXiv:2303.17963v3 Announce Type: replace-cross
Abstract: As control engineering methods are applied to increasingly complex systems, data-driven approaches for system identification appear as a promising alternative to physics-based modeling. While the Bayesian approaches prevalent for safety-critical applications usually rely on the availability of state measurements, the states of a complex system are often not directly measurable. It may then be necessary to jointly estimate the dynamics and the latent state, making the quantification of uncertainties and the design of controllers with …

abstract applications arxiv availability bayesian complex systems control cs.lg cs.sy data data-driven eess.sy engineering identification math.oc modeling performance physics safety safety-critical state stat.ml systems type