This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a principled approach to safety that aims to maximize the worst-case performance of a system. However, the resulting optimization problem is generally intractable for non-linear systems with continuous states. To overcome this issue, we introduce two tractable methods that are based either on sampling or on a conservative approximation of the robust objective. The proposed approaches are applied to the problem of autonomous driving.
@article{arxiv.1903.00220,
title = {Approximate Robust Control of Uncertain Dynamical Systems},
author = {Edouard Leurent and Yann Blanco and Denis Efimov and Odalric-Ambrym Maillard},
journal= {arXiv preprint arXiv:1903.00220},
year = {2019}
}