Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics

Abstract

Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for adaptable learning-based methods capable of capturing complex interactions beyond explicit physical models and simulations. While graph neural networks can handle simple scenarios, they struggle with complex scenes and long-term predictions. We introduce a novel framework for modeling rigid body dynamics and learning collision interactions, addressing key limitations of existing graph-based methods. Our approach extends the traditional representation of meshes by incorporating higher-order topology complexes, offering a physically consistent representation. Additionally, we propose a physics-informed message-passing neural architecture, embedding physical laws directly in the model. Our method demonstrates superior accuracy, even during long rollouts, and exhibits strong generalization to unseen scenarios. Importantly, this work addresses the challenge of multi-entity dynamic interactions, with applications spanning diverse scientific and engineering domains.

20 pages, 10 figures. Published in Nature Communications

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The physics of higher-order interactions in complex systems
• Interaction Networks for Learning about Objects, Relations and Physics
• Higher-order interactions shape collective dynamics differently in hypergraphs and simplicial complexes
• SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
• ComPhy: Compositional Physical Reasoning of Objects and Events from Videos
• Learning Physical Dynamics with Subequivariant Graph Neural Networks
• Learning rigid dynamics with face interaction graph networks
• AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers