Corpus ID: 220361704

Scalable Differentiable Physics for Learning and Control

@inproceedings{Qiao2020ScalableDP,
  title={Scalable Differentiable Physics for Learning and Control},
  author={Yi-Ling Qiao and Junbang Liang and Vladlen Koltun and Ming C. Lin},
  booktitle={ICML},
  year={2020}
}
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… Expand
Differentiable Fluids with Solid Coupling for Learning and Control
TLDR
An efficient differentiable fluid simulator that can be integrated with deep neural networks as a part of layers for learning dynamics and solving control problems and outperforms the previous gradient computations, state-of-the-art derivative-free optimization, and model-free reinforcement learning techniques by at least one order of magnitude. Expand
Efficient Differentiable Simulation of Articulated Bodies
TLDR
It is shown that reinforcement learning with articulated systems can be accelerated using gradients provided by the method, and gradient-based optimization enabled by the work accelerates convergence by more than an order of magnitude. Expand
NeuralSim: Augmenting Differentiable Simulators with Neural Networks
TLDR
Through extensive experiments, the ability of the hybrid simulator to learn complex dynamics involving frictional contacts from real data, as well as match known models of viscous friction, is demonstrated, and an approach for automatically discovering useful augmentations is presented. Expand
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
TLDR
A new differentiable physics benchmark called PasticineLab is introduced, which includes a diverse collection of soft body manipulation tasks, and experimental results suggest that RL-based approaches struggle to solve most of the tasks efficiently and gradient- based approaches can rapidly find a solution within tens of iterations, but still fall short on multi-stage tasks that require long-term planning. Expand
DiffPD: Differentiable Projective Dynamics with Contact
TLDR
The key idea in DiffPD is to speed up backpropagation by exploiting the prefactorized Cholesky decomposition in PD to achieve a super-linear convergence rate. Expand
gradSim: Differentiable simulation for system identification and visuomotor control
We consider the problem of estimating an object’s physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentallyExpand
Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation
TLDR
This paper demonstrates how the inference technique can identify symmetries between the parameters and provide highly accurate predictions on an underactuated mechanism where a 7-DOF robot arm excites an object with an unknown mass configuration. Expand
A Differentiable Recipe for Learning Visual Dexterous Planar Manipulation
  • 2021
Specifying tasks with videos is a powerful technique towards acquiring novel 1 and general robot skills. However, reasoning over mechanics and dexterous interactions 2 can make it challenging toExpand
∇Sim: DIFFERENTIABLE SIMULATION FOR SYSTEM IDENTIFICATION AND VISUOMOTOR CONTROL https://gradsim.github.io
We consider the problem of estimating an object’s physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentallyExpand
DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting
TLDR
DiSECt: the first differentiable simulator for cutting soft materials is presented, which can be calibrated to match resultant forces and deformation fields from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting velocities and object instances. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 31 REFERENCES
Learning to Control PDEs with Differentiable Physics
TLDR
It is shown that by using a differentiable PDE solver in conjunction with a novel predictor-corrector scheme, this work can train neural networks to understand and control complex nonlinear physical systems over long time frames. Expand
End-to-End Differentiable Physics for Learning and Control
TLDR
This paper demonstrates how to perform backpropagation analytically through a physical simulator defined via a linear complementarity problem, and highlights the system's ability to learn physical parameters from data, efficiently match and simulate observed visual behavior, and readily enable control via gradient-based planning methods. Expand
Flexible Neural Representation for Physics Prediction
TLDR
The Hierarchical Relation Network (HRN) is described, an end-to-end differentiable neural network based on hierarchical graph convolution that learns to predict physical dynamics in this hierarchical particle-based object representation. Expand
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
TLDR
This study helps lay the foundation for robot learning of dynamic scenes with particle-based representations, and demonstrates robots achieving complex manipulation tasks using the learned simulator, such as manipulating fluids and deformable foam. Expand
Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics
TLDR
A closed-loop model-predictive control algorithm that infers the simulation parameters through experience while achieving cost-minimizing performance is introduced in the context of trajectory optimization. Expand
Propagation Networks for Model-Based Control Under Partial Observation
TLDR
Propagation Networks is introduced, a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions and achieves superior performance on various control tasks. Expand
Lagrangian Fluid Simulation with Continuous Convolutions
TLDR
This work presents an approach to Lagrangian fluid simulation with a new type of convolutional network that can simulate different materials, generalizes to arbitrary collision geometries, and can be used for inverse problems. Expand
A Compositional Object-Based Approach to Learning Physical Dynamics
TLDR
The NPE's compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass. Expand
A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS
TLDR
This paper proposes an implementation of a modern physics engine, which can differentiate control parameters, which is implemented for both CPU and GPU, and shows how such an engine speeds up the optimization process, even for small problems. Expand
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
TLDR
A real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM), which can simulate deformable Objects with collisions and can be seamlessly incorporated into soft robotic systems. Expand
...
1
2
3
4
...