Learning Stability Certificates from Data

08/13/2020
by   Nicholas M. Boffi, et al.
2

Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guarantees a desired property. However, algorithms for synthesizing certificate functions typically require a closed-form analytical expression of the underlying dynamics, which rules out their use on many modern robotic platforms. To circumvent this issue, we develop algorithms for learning certificate functions only from trajectory data. We establish bounds on the generalization error - the probability that a certificate will not certify a new, unseen trajectory - when learning from trajectories, and we convert such generalization error bounds into global stability guarantees. We demonstrate empirically that certificates for complex dynamics can be efficiently learned, and that the learned certificates can be used for downstream tasks such as adaptive control.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/30/2020

Learning nonlinear dynamical systems from a single trajectory

We introduce algorithms for learning nonlinear dynamical systems of the ...
09/15/2022

Stability Guarantees for Continuous RL Control

Lack of stability guarantees strongly limits the use of reinforcement le...
10/23/2019

Prioritized Inverse Kinematics: Desired Task Trajectories in Nonsingular Task Spaces

A prioritized inverse kinematics (PIK) solution can be considered as a (...
10/01/2021

Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview

Contraction theory is an analytical tool to study differential dynamics ...
02/16/2022

Single Trajectory Nonparametric Learning of Nonlinear Dynamics

Given a single trajectory of a dynamical system, we analyze the performa...
02/20/2021

Measuring the Stability of Learned Features

Many modern datasets don't fit neatly into n × p matrices, but most tech...
06/21/2022

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

Learned models and policies can generalize effectively when evaluated wi...