Automatic Policy Synthesis to Improve the Safety of Nonlinear Dynamical Systems

06/06/2020
by   Arash Mehrjou, et al.
19

Learning controllers merely based on a performance metric has been proven effective in many physical and non-physical tasks in both control theory and reinforcement learning. However, in practice, the controller must guarantee some notion of safety to ensure that it does not harm either the agent or the environment. Stability is a crucial notion of safety, whose violation can certainly cause unsafe behaviors. Lyapunov functions are effective tools to assess stability in nonlinear dynamical systems. In this paper, we combine an improving Lyapunov function with automatic controller synthesis to obtain control policies with large safe regions. We propose a two-player collaborative algorithm that alternates between estimating a Lyapunov function and deriving a controller that gradually enlarges the stability region of the closed-loop system. We provide theoretical results on the class of systems that can be treated with the proposed algorithm and empirically evaluate the effectiveness of our method using an exemplary dynamical system.

READ FULL TEXT

page 23

page 24

research
10/24/2019

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

This paper proposes a framework for safe reinforcement learning that can...
research
11/23/2019

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

The correspondence between residual networks and dynamical systems motiv...
research
11/10/2019

Synthesis of Feedback Controller for Nonlinear Control Systems with Optimal Region of Attraction

The problem of computing and characterizing Region of Attraction (ROA) w...
research
02/06/2023

Learning Control-Oriented Dynamical Structure from Data

Even for known nonlinear dynamical systems, feedback controller synthesi...
research
10/26/2018

Stability-certified reinforcement learning: A control-theoretic perspective

We investigate the important problem of certifying stability of reinforc...
research
06/15/2023

Optimal Exploration for Model-Based RL in Nonlinear Systems

Learning to control unknown nonlinear dynamical systems is a fundamental...
research
07/19/2023

A Shared Control Approach Based on First-Order Dynamical Systems and Closed-Loop Variable Stiffness Control

In this paper, we present a novel learning-based shared control framewor...

Please sign up or login with your details

Forgot password? Click here to reset