Safely Learning Dynamical Systems

05/20/2023
by   Amir Ali Ahmadi, et al.
0

A fundamental challenge in learning an unknown dynamical system is to reduce model uncertainty by making measurements while maintaining safety. In this work, we formulate a mathematical definition of what it means to safely learn a dynamical system by sequentially deciding where to initialize the next trajectory. In our framework, the state of the system is required to stay within a safety region for a horizon of T time steps under the action of all dynamical systems that (i) belong to a given initial uncertainty set, and (ii) are consistent with the information gathered so far. For our first set of results, we consider the setting of safely learning a linear dynamical system involving n states. For the case T=1, we present a linear programming-based algorithm that either safely recovers the true dynamics from at most n trajectories, or certifies that safe learning is impossible. For T=2, we give a semidefinite representation of the set of safe initial conditions and show that ⌈ n/2 ⌉ trajectories generically suffice for safe learning. Finally, for T = ∞, we provide semidefinite representable inner approximations of the set of safe initial conditions and show that one trajectory generically suffices for safe learning. Our second set of results concerns the problem of safely learning a general class of nonlinear dynamical systems. For the case T=1, we give a second-order cone programming based representation of the set of safe initial conditions. For T=∞, we provide semidefinite representable inner approximations to the set of safe initial conditions. We show how one can safely collect trajectories and fit a polynomial model of the nonlinear dynamics that is consistent with the initial uncertainty set and best agrees with the observations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2020

Safely Learning Dynamical Systems from Short Trajectories

A fundamental challenge in learning to control an unknown dynamical syst...
research
08/23/2020

Learning Dynamical Systems with Side Information

We present a mathematical and computational framework for the problem of...
research
05/09/2018

Robust-to-Dynamics Optimization

A robust-to-dynamics optimization (RDO) problem is an optimization probl...
research
04/21/2022

Model-free Learning of Regions of Attraction via Recurrent Sets

We consider the problem of learning an inner approximation of the region...
research
01/12/2021

Machine Learning for Initial Value Problems of Parameter-Dependent Dynamical Systems

We consider initial value problems of nonlinear dynamical systems, which...
research
08/23/2020

Learning Dynamical Systems using Local Stability Priors

A coupled computational approach to simultaneously learn a vector field ...
research
08/15/2023

Polynomial Stochastic Dynamical Indicators

This paper introduces three types of dynamical indicators that capture t...

Please sign up or login with your details

Forgot password? Click here to reset