ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
Julen Urain, Michele Ginesi, Davide Tateo, Jan Peters
Abstract
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations. We prove the Lyapunov stability for a class of Stochastic Differential Equations and we propose a learning algorithm to learn them from a set of demonstrated trajectories. Our model extends the set of stable dynamical systems that can be represented by state-of-the-art approaches, eliminates the Gaussian assumption on the demonstrations, and outperforms the previous algorithms in terms of representation accuracy. We show the effectiveness of our method with both standard datasets and a real robot experiment.
BibTeX
@inproceedings{iros2020_imitationflowlea,
title = {ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows},
author = {Julen Urain and Michele Ginesi and Davide Tateo and Jan Peters},
booktitle = {IROS 2020},
year = {2020}
}