Communication Dans Un Congrès Année : 2023

Real-Time Elastic Partial Shape Matching Using a Neural Network-Based Adjoint Method

Résumé

Surface matching usually provides significant deformations that can lead to structural failure due to the lack of physical policy. In this context, partial surface matching of non-linear deformable bodies is crucial in engineering to govern structure deformations. In this article, we propose to formulate the registration problem as an optimal control problem using an artificial neural network where the unknown is the surface force distribution that applies to the object and the resulting deformation computed using a hyper-elastic model. The optimization problem is solved using an adjoint method where the hyper-elastic problem is solved using the feed-forward neural network and the adjoint problem is obtained through the backpropagation of the network. Our process improves the computation speed by multiple orders of magnitude while providing acceptable registration errors.

Fichier principal
Vignette du fichier
Real_time_registration_using_neural_network_control.pdf (1.93 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
HAL

relationship_conformsTo hal-04019777 Preprint Alban Odot, Guillaume Mestdagh, Yannick Privat, Stéphane Cotin. Real-time elastic partial shape matching using a neural network-based adjoint method. 2022. ⟨hal-04019777⟩

Dates et versions

hal-04176808 , version 1 (03-08-2023)

Licence

Identifiants

Citer

Alban Odot, Guillaume Mestdagh, Yannick Privat, Stéphane Cotin. Real-Time Elastic Partial Shape Matching Using a Neural Network-Based Adjoint Method. OLA 2023 - 6th International Conference on Optimization and Learning, May 2023, Malaga, Spain. pp.137-147, ⟨10.1007/978-3-031-34020-8_10⟩. ⟨hal-04176808⟩
124 Consultations
224 Téléchargements

Altmetric

Partager

  • More