Thermodynamics-informed neural networks for physically realistic mixed reality

Hernández, Quercus ; Badías, Alberto ; Chinesta, Francisco ; Cueto, Elías (Universidad de Zaragoza)

Resumen: 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.

Idioma: Inglés

DOI: 10.1016/j.cma.2023.115912

Año: 2023

Publicado en: Computer Methods in Applied Mechanics and Engineering 407 (2023), 115912 [11 pp.]
ISSN: 0045-7825

Factor impacto JCR: 6.9 (2023)

Categ. JCR: MECHANICS rank: 7 / 170 = 0.041 (2023) - Q1 - T1
Categ. JCR: MATHEMATICS, INTERDISCIPLINARY APPLICATIONS rank: 4 / 135 = 0.03 (2023) - Q1 - T1
Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 6 / 181 = 0.033 (2023) - Q1 - T1

Factor impacto CITESCORE: 12.7 - Computer Science Applications (Q1) - Computational Mechanics (Q1) - Mechanics of Materials (Q1) - Mechanical Engineering (Q1) - Physics and Astronomy (all) (Q1)

Factor impacto SCIMAGO: 2.397 - Computational Mechanics (Q1) - Computer Science Applications (Q1) - Physics and Astronomy (miscellaneous) (Q1) - Mechanics of Materials (Q1) - Mechanical Engineering (Q1)

Financiación: info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033

Tipo y forma: Article (Published version)

Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)