期刊
AUTOMATICA
卷 129, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.automatica.2021.109597
关键词
Safe learning-based control; Control of constrained systems; Robust control of nonlinear systems; Data-based control
资金
- Swiss National Science Foundation, Switzerland [PP00P2 157601/1]
This paper introduces a predictive safety filter for nonlinear systems with continuous state and input spaces, which can turn a constrained dynamical system into an unconstrained safe system and be applied to any RL algorithm. Safety is ensured by a continuously updated safety policy based on a data-driven system model and considering state and input dependent uncertainties.
The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support explicit consideration of state and input constraints. In this paper, we address this problem for nonlinear systems with continuous state and input spaces by introducing a predictive safety filter, which is able to turn a constrained dynamical system into an unconstrained safe system and to which any RL algorithm can be applied 'out-of-the-box'. The predictive safety filter receives the proposed control input and decides, based on the current system state, if it can be safely applied to the real system, or if it has to be modified otherwise. Safety is thereby established by a continuously updated safety policy, which is based on a model predictive control formulation using a data-driven system model and considering state and input dependent uncertainties. (C) 2021 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据