Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems - Sorbonne Université Access content directly
Journal Articles Systems and Control Letters Year : 2016

Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems

Abstract

We propose a new diffeomorphic matching algorithm and use it to learn nonlinear dynamical systems with the guarantee that the learned systems have global asymptotic stability. For a given set of demonstration trajectories, we compute a diffeomorphism that maps forward orbits of a reference stable time-invariant system onto the demonstrations, thereby deforming the whole reference system into one that reproduces the demonstrations, and is still stable.
Fichier principal
Vignette du fichier
Perrin_2016_Fast_diffeomorphic.pdf (8.95 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01394886 , version 1 (10-11-2016)

Identifiers

Cite

Nicolas Perrin, Philipp Schlehuber-Caissier. Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems. Systems and Control Letters, 2016, 96, pp.51 - 59. ⟨10.1016/j.sysconle.2016.06.018⟩. ⟨hal-01394886⟩
186 View
549 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More