Augmenting differentiable physics with randomized smoothing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Augmenting differentiable physics with randomized smoothing

Résumé

In the past few years, following the differentiable programming paradigm, there has been a growing interest in computing the gradient information of physical processes (e.g., physical simulation, image rendering). However, such processes may be non-differentiable or yield uninformative gradients (i.d., null almost everywhere). When faced with the former pitfalls, gradients estimated via analytical expression or numerical techniques such as automatic differentiation and finite differences, make classical optimization schemes converge towards poor quality solutions. Thus, relying only on the local information provided by these gradients is often not sufficient to solve advanced optimization problems involving such physical processes, notably when they are subject to non-smoothness and non-convexity issues. In this work, inspired by the field of zero-th order optimization, we leverage randomized smoothing to augment differentiable physics by estimating gradients in a neighborhood. Our experiments suggest that integrating this approach inside optimization algorithms may be fruitful for tasks as varied as mesh reconstruction from images or optimal control of robotic systems subject to contact and friction issues.
Fichier principal
Vignette du fichier
lelidec2022diffphys.pdf (2.56 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03703324 , version 1 (23-06-2022)

Identifiants

  • HAL Id : hal-03703324 , version 1

Citer

Quentin Le Lidec, Louis Montaut, Cordelia Schmid, Ivan Laptev, Justin Carpentier. Augmenting differentiable physics with randomized smoothing. RSS 2022 - Robotics Science and Systems, Workshop on Differentiable Simulation For Robotics, Jun 2022, New York, United States. ⟨hal-03703324⟩
50 Consultations
74 Téléchargements

Partager

Gmail Facebook X LinkedIn More