This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a generalized AG theory for discrete-time systems under bounded uncertainties, and relax the usual requirement of positive invariance to returnability of a safe set. Based on the theory, we present tailored AG design procedures for linear systems and for discrete systems with finite state and action spaces. We further study safe online learning enabled by the AG and present two safe learning strategies, namely safe Q-learning and safe data-driven Koopman operator-based control, both integrated with the AG to guarantee constraint satisfaction during learning. Numerical results illustrate the proposed methods.
@article{arxiv.2211.12628,
title = {Safe Control and Learning Using Generalized Action Governor},
author = {Peiyuan Fang and Weiqi Zhang and Lu Xiong and Nan Li and Yanjun Huang and Yutong Li and Ilya Kolmanovsky and Anouck Girard and H. Eric Tseng and Dimitar Filev},
journal= {arXiv preprint arXiv:2211.12628},
year = {2026}
}