Thermodynamics-informed neural networks for physically realistic mixed reality
Article dans une revue avec comité de lecture
Auteur
HERNÁNDEZ, Quercus BADIAS, Alberto CHINESTA SORIA, Francisco CUETO, EliasRésumé
The imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this context, realistic means to be compliant to the laws of physics. In this paper we present a method for computing the dynamic response of (possibly non-linear and dissipative) deformable objects induced by real-time user interactions in mixed reality using deep learning. The graph-based architecture of the method ensures the thermodynamic consistency of the predictions, whereas the visualization pipeline allows a natural and realistic user experience. Two examples of virtual solids interacting with virtual or physical solids in mixed reality scenarios are provided to prove the performance of the method.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Documents liés
Visualiser des documents liés par titre, auteur, créateur et sujet.
-
Article dans une revue avec comité de lectureHERNÁNDEZ, Quercus; BADIAS, Alberto; CHINESTA SORIA, Francisco; CUETO, Elias (2023)
We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of ...
-
Article dans une revue avec comité de lecture; ; ;CHINESTA SORIA, Francisco; CUETO, Elias (Elsevier, 2021)
We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of ...
-
Article dans une revue avec comité de lecture; ; ;CHINESTA SORIA, Francisco; CUETO, Elias (Elsevier, 2021)
We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse ...
-
Article dans une revue avec comité de lecture; ; ;CUETO, Elias; CHINESTA SORIA, Francisco (Elsevier, 2020)
We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of ...
-
Article dans une revue avec comité de lectureMOYA GARCÍA, Beatriz; BADIAS, Alberto; ; CHINESTA SORIA, Francisco; CUETO, Elias (2023)
Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events ...