Differentiable Implicit Soft-Body Physics

• URL: http://arxiv.org/abs/2102.05791v1
• Date: Thu, 11 Feb 2021 01:06:54 GMT
• Title: Differentiable Implicit Soft-Body Physics
• Authors: Junior Rojas, Eftychios Sifakis, Ladislav Kavan
• Abstract summary: We present a differentiable soft-body physics simulator composed with neural networks as a differentiable layer. In contrast to other differentiable physics approaches that use explicit forward models to define state transitions, we focus on implicit state transitions defined via function minimization.
• Score: 12.19631263169426
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a differentiable soft-body physics simulator that can be composed with neural networks as a differentiable layer. In contrast to other differentiable physics approaches that use explicit forward models to define state transitions, we focus on implicit state transitions defined via function minimization. Implicit state transitions appear in implicit numerical integration methods, which offer the benefits of large time steps and excellent numerical stability, but require a special treatment to achieve differentiability due to the absence of an explicit differentiable forward pass. In contrast to other implicit differentiation approaches that require explicit formulas for the force function and the force Jacobian matrix, we present an energy-based approach that allows us to compute these derivatives automatically and in a matrix-free fashion via reverse-mode automatic differentiation. This allows for more flexibility and productivity when defining physical models and is particularly important in the context of neural network training, which often relies on reverse-mode automatic differentiation (backpropagation). We demonstrate the effectiveness of our differentiable simulator in policy optimization for locomotion tasks and show that it achieves better sample efficiency than model-free reinforcement learning.

Related papers

• Unsupervised Discovery of Inertial-Fusion Plasma Physics using Differentiable Kinetic Simulations and a Maximum Entropy Loss Function [77.34726150561087]
  We create a differentiable solver for the plasma kinetics 3D partial-differential-equation and introduce a domain-specific objective function. We apply this framework to an inertial-fusion relevant configuration and find that the optimization process exploits a novel physical effect.
  arXiv  Detail & Related papers  (2022-06-03T15:27:33Z)
• Differentiable Simulation of Soft Multi-body Systems [99.4302215142673]
  We develop a top-down matrix assembly algorithm within Projective Dynamics. We derive a differentiable control framework for soft articulated bodies driven by muscles, joint torques, or pneumatic tubes.
  arXiv  Detail & Related papers  (2022-05-03T20:03:22Z)
• Approximate Latent Force Model Inference [1.3927943269211591]
  latent force models offer an interpretable alternative to purely data driven tools for inference in dynamical systems. We show that a neural operator approach can scale our model to thousands of instances, enabling fast, distributed computation.
  arXiv  Detail & Related papers  (2021-09-24T09:55:00Z)
• Efficient Differentiable Simulation of Articulated Bodies [89.64118042429287]
  We present a method for efficient differentiable simulation of articulated bodies. This enables integration of articulated body dynamics into deep learning frameworks. We show that reinforcement learning with articulated systems can be accelerated using gradients provided by our method.
  arXiv  Detail & Related papers  (2021-09-16T04:48:13Z)
• Nonsmooth Implicit Differentiation for Machine Learning and Optimization [0.0]
  In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a nonsmooth form of the classical invertibility condition is fulfilled. This approach allows for formal subdifferentiation: for instance, replacing derivatives by Clarke Jacobians in the usual differentiation formulas is fully justified.
  arXiv  Detail & Related papers  (2021-06-08T13:59:47Z)
• Efficient and Modular Implicit Differentiation [68.74748174316989]
  We propose a unified, efficient and modular approach for implicit differentiation of optimization problems. We show that seemingly simple principles allow to recover many recently proposed implicit differentiation methods and create new ones easily.
  arXiv  Detail & Related papers  (2021-05-31T17:45:58Z)
• 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)
• ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact [26.408218913234872]
  We present a differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects. Through a principled mollification of normal and tangential contact forces, our method circumvents the main difficulties inherent to the non-smooth nature of frictional contact.
  arXiv  Detail & Related papers  (2020-07-02T09:51:36Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)

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.