Thermodynamics-informed neural networks for physically realistic mixed reality

• Published in: Computer methods in applied mechanics and engineering Vol. 407; p. 115912
• Main Authors: Hernández, Quercus, Badías, Alberto, Chinesta, Francisco, Cueto, Elías
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.03.2023; Elsevier
• Subjects: Augmented reality; Computer Science; Deep learning; Engineering Sciences; Graphics; Machine Learning; Mechanics; Real-time simulation; Solid mechanics; Structure preserving; Thermodynamics; Deep learning; Thermodynamics; Structure preserving; Real-time simulation; Augmented reality
• ISSN: 0045-7825; 1879-2138
• DOI: 10.1016/j.cma.2023.115912

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.