Online Learning and Control of Dynamical Systems from Sensory Input - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Online Learning and Control of Dynamical Systems from Sensory Input

Abstract

Identifying an effective model of a dynamical system from sensory data and using it for future state prediction and control is challenging. Recent data-driven algorithms based on Koopman theory are a promising approach to this problem, but they typically never update the model once it has been identified from a relatively small set of observations, thus making long-term prediction and control difficult for realistic systems, in robotics or fluid mechanics for example. This paper introduces a novel method for learning an embedding of the state space with linear dynamics from sensory data. Unlike previous approaches, the dynamics model can be updated online and thus easily applied to systems with non-linear dynamics in the original configuration space. The proposed approach is evaluated empirically on several classical dynamical systems and sensory modalities, with good performance on long-term prediction and control.
Fichier principal
Vignette du fichier
neurips_camera_ready_2.pdf (1.74 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03405911 , version 1 (27-10-2021)
hal-03405911 , version 2 (07-11-2021)

Identifiers

  • HAL Id : hal-03405911 , version 2

Cite

Oumayma Bounou, Jean Ponce, Justin Carpentier. Online Learning and Control of Dynamical Systems from Sensory Input. NeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems Year, Dec 2021, Sydney / Virtual, Australia. ⟨hal-03405911v2⟩
204 View
387 Download

Share

Gmail Facebook X LinkedIn More