Scalable Differentiable Physics for Learning and Control
- URL: http://arxiv.org/abs/2007.02168v1
- Date: Sat, 4 Jul 2020 19:07:51 GMT
- Title: Scalable Differentiable Physics for Learning and Control
- Authors: Yi-Ling Qiao, Junbang Liang, Vladlen Koltun, Ming C. Lin
- Abstract summary: 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.
- Score: 99.4302215142673
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Differentiable physics is a powerful approach to learning and control
problems that involve physical objects and environments. While notable progress
has been made, the capabilities of differentiable physics solvers remain
limited. We develop a scalable framework for differentiable physics that can
support a large number of objects and their interactions. To accommodate
objects with arbitrary geometry and topology, we adopt meshes as our
representation and leverage the sparsity of contacts for scalable
differentiable collision handling. Collisions are resolved in localized regions
to minimize the number of optimization variables even when the number of
simulated objects is high. We further accelerate implicit differentiation of
optimization with nonlinear constraints. Experiments demonstrate that the
presented framework requires up to two orders of magnitude less memory and
computation in comparison to recent particle-based methods. We further validate
the approach on inverse problems and control scenarios, where it outperforms
derivative-free and model-free baselines by at least an order of magnitude.
Related papers
- Scaling physics-informed hard constraints with mixture-of-experts [0.0]
We develop a scalable approach to enforce hard physical constraints using Mixture-of-Experts (MoE)
MoE imposes the constraint over smaller domains, each of which is solved by an "expert" through differentiable optimization.
Compared to standard differentiable optimization, our scalable approach achieves greater accuracy in the neural PDE solver setting.
arXiv Detail & Related papers (2024-02-20T22:45:00Z) - DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via
Physics Simulation [81.11585774044848]
We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network.
Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
arXiv Detail & Related papers (2023-10-11T05:34:36Z) - Improving Gradient Computation for Differentiable Physics Simulation
with Contacts [10.450509067356148]
We study differentiable rigid-body simulation with contacts.
We propose to improve gradient computation by continuous collision detection and leverage the time-of-impact (TOI)
We show that with TOI-Ve, we are able to learn an optimal control sequence that matches the analytical solution.
arXiv Detail & Related papers (2023-04-28T21:10:16Z) - DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation
and Rendering of Deformable Objects [18.266002992029716]
Research in manipulation of deformable objects is typically conducted on a limited range of scenarios.
Realistic simulators with support for various types of deformations and interactions have the potential to speed up experimentation.
For highly deformable objects it is challenging to align the output of a simulator with the behavior of real objects.
arXiv Detail & Related papers (2022-04-07T00:45:26Z) - DiffSkill: Skill Abstraction from Differentiable Physics for Deformable
Object Manipulations with Tools [96.38972082580294]
DiffSkill is a novel framework that uses a differentiable physics simulator for skill abstraction to solve deformable object manipulation tasks.
In particular, we first obtain short-horizon skills using individual tools from a gradient-based simulator.
We then learn a neural skill abstractor from the demonstration trajectories which takes RGBD images as input.
arXiv Detail & Related papers (2022-03-31T17:59:38Z) - DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes [9.119424247289857]
Differentiable physics is a powerful tool in computer and robotics for scene understanding and reasoning about interactions.
Existing approaches have frequently been limited to objects with simple shape or shapes that are in advance.
arXiv Detail & Related papers (2021-11-30T11:56:24Z) - DeepPhysics: a physics aware deep learning framework for real-time
simulation [0.0]
We propose a solution to simulate hyper-elastic materials using a data-driven approach.
A neural network is trained to learn the non-linear relationship between boundary conditions and the resulting displacement field.
The results show that our network architecture trained with a limited amount of data can predict the displacement field in less than a millisecond.
arXiv Detail & Related papers (2021-09-17T12:15:47Z) - PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable
Physics [89.81550748680245]
We introduce a new differentiable physics benchmark called PasticineLab.
In each task, the agent uses manipulators to deform the plasticine into the desired configuration.
We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
arXiv Detail & Related papers (2021-04-07T17:59:23Z) - Occlusion resistant learning of intuitive physics from videos [52.25308231683798]
Key ability for artificial systems is to understand physical interactions between objects, and predict future outcomes of a situation.
This ability, often referred to as intuitive physics, has recently received attention and several methods were proposed to learn these physical rules from video sequences.
arXiv Detail & Related papers (2020-04-30T19:35:54Z) - 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)
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.