English

Controlled Invariant Sets for Gaussian Process State Space Models

Systems and Control 2026-04-21 v2 Systems and Control

Abstract

We compute probabilistic controlled invariant sets for nonlinear systems using Gaussian process state space models, which are data-driven models that account for unmodeled and unknown nonlinear dynamics. We propose a semidefinite programming scheme for designing state-feedback controllers that maximize the probability of the trajectories staying within a probabilistic controlled invariant set while satisfying input constraints. The results are validated on a quadrotor, both in simulation and on a physical platform.

Keywords

Cite

@article{arxiv.2407.11256,
  title  = {Controlled Invariant Sets for Gaussian Process State Space Models},
  author = {Paul Griffioen and Bingzhuo Zhong and Murat Arcak and Majid Zamani and Marco Caccamo},
  journal= {arXiv preprint arXiv:2407.11256},
  year   = {2026}
}
R2 v1 2026-06-28T17:42:18.827Z