Learning Physical Constraints with Neural Projections
- URL: http://arxiv.org/abs/2006.12745v2
- Date: Sat, 12 Dec 2020 23:08:33 GMT
- Title: Learning Physical Constraints with Neural Projections
- Authors: Shuqi Yang, Xingzhe He, Bo Zhu
- Abstract summary: We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints.
A neural projection operator lies at the heart of our approach, composed of a lightweight network with an embedded recursion architecture.
We demonstrated the efficacy of our approach by learning a set of challenging physical systems all in a unified and simple fashion.
- Score: 16.09436906471513
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a new family of neural networks to predict the behaviors of
physical systems by learning their underpinning constraints. A neural
projection operator lies at the heart of our approach, composed of a
lightweight network with an embedded recursive architecture that interactively
enforces learned underpinning constraints and predicts the various governed
behaviors of different physical systems. Our neural projection operator is
motivated by the position-based dynamics model that has been used widely in
game and visual effects industries to unify the various fast physics
simulators. Our method can automatically and effectively uncover a broad range
of constraints from observation point data, such as length, angle, bending,
collision, boundary effects, and their arbitrary combinations, without any
connectivity priors. We provide a multi-group point representation in
conjunction with a configurable network connection mechanism to incorporate
prior inputs for processing complex physical systems. We demonstrated the
efficacy of our approach by learning a set of challenging physical systems all
in a unified and simple fashion including: rigid bodies with complex
geometries, ropes with varying length and bending, articulated soft and rigid
bodies, and multi-object collisions with complex boundaries.
Related papers
- Physics meets Topology: Physics-informed topological neural networks for learning rigid body dynamics [6.675805308519987]
We introduce a novel framework for modeling rigid body dynamics and learning collision interactions.
We propose a physics-informed message-passing neural architecture, embedding physical laws directly in the model.
This work addresses the challenge of multi-entity dynamic interactions, with applications spanning diverse scientific and engineering domains.
arXiv Detail & Related papers (2024-11-18T11:03:15Z) - Spatial embedding promotes a specific form of modularity with low entropy and heterogeneous spectral dynamics [0.0]
Spatially embedded recurrent neural networks provide a promising avenue to study how modelled constraints shape the combined structural and functional organisation of networks over learning.
We show that it is possible to study these restrictions through entropic measures of the neural weights and eigenspectrum, across both rate and spiking neural networks.
This work deepens our understanding of constrained learning in neural networks, across coding schemes and tasks, where solutions to simultaneous structural and functional objectives must be accomplished in tandem.
arXiv Detail & Related papers (2024-09-26T10:00:05Z) - Physics-Encoded Graph Neural Networks for Deformation Prediction under
Contact [87.69278096528156]
In robotics, it's crucial to understand object deformation during tactile interactions.
We introduce a method using Physics-Encoded Graph Neural Networks (GNNs) for such predictions.
We've made our code and dataset public to advance research in robotic simulation and grasping.
arXiv Detail & Related papers (2024-02-05T19:21:52Z) - Neuromechanical Autoencoders: Learning to Couple Elastic and Neural
Network Nonlinearity [15.47367187516723]
We seek to develop machine learning analogs of.
mechanical intelligence.
We jointly learn the morphology of complex nonlinear elastic solids along with a.
deep neural network to control it.
arXiv Detail & Related papers (2023-01-31T19:04:28Z) - NN-EUCLID: deep-learning hyperelasticity without stress data [0.0]
We propose a new approach for unsupervised learning of hyperelastic laws with physics-consistent deep neural networks.
In contrast to supervised learning, which assumes the stress-strain, the approach only uses realistically measurable full-elastic field displacement and global force availability data.
arXiv Detail & Related papers (2022-05-04T13:54:54Z) - Constructing Neural Network-Based Models for Simulating Dynamical
Systems [59.0861954179401]
Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system.
This paper provides a survey of the different ways to construct models of dynamical systems using neural networks.
In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
arXiv Detail & Related papers (2021-11-02T10:51:42Z) - Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects.
We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations.
Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
arXiv Detail & Related papers (2021-02-22T17:33:51Z) - Scalable Differentiable Physics for Learning and Control [99.4302215142673]
Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments.
We develop a scalable framework for differentiable physics that can support a large number of objects and their interactions.
arXiv Detail & Related papers (2020-07-04T19:07:51Z) - Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains.
Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing.
Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
arXiv Detail & Related papers (2020-02-21T16:44:28Z) - Learning to Control PDEs with Differentiable Physics [102.36050646250871]
We present a novel hierarchical predictor-corrector scheme which enables neural networks to learn to understand and control complex nonlinear physical systems over long time frames.
We demonstrate that our method successfully develops an understanding of complex physical systems and learns to control them for tasks involving PDEs.
arXiv Detail & Related papers (2020-01-21T11:58:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.