2021

Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact

Werling, Keenon, Omens, Dalton, Lee, Jeongseok et al.

Understand

We present a fast and feature-complete differentiable physics engine, Nimble (nimblephysics.org), that supports Lagrangian dynamics and hard contact constraints for articulated rigid body simulation.

Our differentiable physics engine offers a complete set of features that are typically only available in non-differentiable physics simulators commonly used by robotics applications.
We solve contact constraints precisely using linear complementarity problems (LCPs).
We present efficient and novel analytical gradients through the LCP formulation of inelastic contact that exploit the sparsity of the LCP solution.

Built on

Difftaichi: Differentiable programming for physical simulation
Original
Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, and Frédo Durand · 1910
Earlier work this paper cites.
Differential dynamic programming
David H Jacobson and David Q Mayne · 1970
Earlier work this paper cites.
Accurate computation of f’(x) and f’(x) f”(x)
C.J.F. Ridders · 1982
Earlier work this paper cites.
A general optimization method using adjoint equation for solving multidimensional inverse heat conduction
Y. Jarny, M.N. Ozisik, and J.P. Bardon · 1991
Earlier work this paper cites.
Fast contact force computation for nonpenetrating rigid bodies
David Baraff · 1994
Earlier work this paper cites.
A gauss-seidel like algorithm to solve frictional contact problems
Franck Jourdan, Pierre Alart, and Michel Jean · 1998
Earlier work this paper cites.
Interactive manipulation of rigid body simulations
Jovan Popović, Steven M. Seitz, Michael Erdmann, Zoran Popović, and Andrew Witkin · 2000
Earlier work this paper cites.
An aerodynamic optimization method based on the inverse problem adjoint equations
A. Iollo, M. Ferlauto, and L. Zannetti · 2001
Earlier work this paper cites.
Subgradient methods
Stephen Boyd, Lin Xiao, and Almir Mutapcic · 2003
Earlier work this paper cites.
Fluid control using the adjoint method
Antoine McNamara, Adrien Treuille, Zoran Popović, and Jos Stam · 2004
Earlier work this paper cites.
A generalized iterative lqg method for locally-optimal feedback control of constrained nonlinear stochastic systems
Emanuel Todorov and Weiwei Li · 2005
Earlier work this paper cites.
Numerical Recipes 3rd Edition: The Art of Scientific Computing
William H. Press, Saul A. Teukolsky, William T. Vetterling, and Brian P. Flannery · 2007
Earlier work this paper cites.
Bullet physics engine
Erwin Coumans · 2010
Earlier work this paper cites.
Lie group formulation of articulated rigid body dynamics
Junggon Kim · 2012
Earlier work this paper cites.

Similar

Synthesis and stabilization of complex behaviors through online trajectory optimization
Yuval Tassa, Tom Erez, and Emanuel Todorov · 2012
Cited alongside, same era.
Mujoco: A physics engine for model-based control
Emanuel Todorov, Tom Erez, and Yuval Tassa · 2012
Cited alongside, same era.
Automated design of complex dynamic systems
Michiel Hermans, Benjamin Schrauwen, Peter Bienstman, and Joni Dambre · 2014
Cited alongside, same era.
Theano: A python framework for fast computation of mathematical expressions
Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, et al · 2016
Cited alongside, same era.
Interaction networks for learning about objects, relations and physics
Peter Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, et al · 2016
Cited alongside, same era.
A compositional object-based approach to learning physical dynamics
Original
Michael B Chang, Tomer Ullman, Antonio Torralba, and Joshua B Tenenbaum · 2016
Cited alongside, same era.
Optnet: Differentiable optimization as a layer in neural networks
Brandon Amos and J Zico Kolter · 2017
Cited alongside, same era.
Automatic differentiation in pytorch
Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer · 2017
Cited alongside, same era.
Analytical derivatives of rigid body dynamics algorithms
Justin Carpentier and Nicolas Mansard · 2018
Cited alongside, same era.
End-to-end differentiable physics for learning and control
Filipe de Avila Belbute-Peres, Kevin Smith, Kelsey Allen, Josh Tenenbaum, and J Zico Kolter · 2018
Cited alongside, same era.
Dart: Dynamic animation and robotics toolkit
Jeongseok Lee, Michael X Grey, Sehoon Ha, Tobias Kunz, Sumit Jain, Yuting Ye, Siddhartha S Srinivasa, Mike Stilman, and C Karen Liu · 2018
Cited alongside, same era.
Flexible neural representation for physics prediction
Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F Fei-Fei, Josh Tenenbaum, and Daniel L Yamins · 2018
Cited alongside, same era.

Then

Spnets: Differentiable fluid dynamics for deep neural networks
Connor Schenck and Dieter Fox · 2018
Later among the works it cites.
Differentiable physics and stable modes for tool-use and manipulation planning
Marc Toussaint, Kelsey R. Allen, K. Smith, and J. Tenenbaum · 2018
Later among the works it cites.
A differentiable physics engine for deep learning in robotics
Jonas Degrave, Michiel Hermans, Joni Dambre, and Francis Wyffels · 2019
Later among the works it cites.
Real2sim: Visco-elastic parameter estimation from dynamic motion
David Hahn, Pol Banzet, James M. Bern, and Stelian Coros · 2019
Later among the works it cites.
Interactive differentiable simulation
Original
Eric Heiden, David Millard, Hejia Zhang, and Gaurav S Sukhatme · 2019
Later among the works it cites.
Differentiable cloth simulation for inverse problems
Junbang Liang, Ming Lin, and Vladlen Koltun · 2019
Later among the works it cites.
Constrained sampling-based trajectory optimization using stochastic approximation
George I Boutselis, Ziyi Wang, and Evangelos A Theodorou · 2020
Later among the works it cites.
Add: analytically differentiable dynamics for multi-body systems with frictional contact
Moritz Geilinger, David Hahn, Jonas Zehnder, Moritz Bächer, Bernhard Thomaszewski, and Stelian Coros · 2020
Later among the works it cites.
Augmenting differentiable simulators with neural networks
Original
Eric Heiden, David Millard, Erwin Coumans, and Gaurav S Sukhatme · 2020
Later among the works it cites.
Learning to control pdes with differentiable physics
Philipp Holl, Nils Thuerey, and Vladlen Koltun · 2020
Later among the works it cites.
Automatic differentiation and continuous sensitivity analysis of rigid body dynamics, 2020
David Millard, Eric Heiden, Shubham Agrawal, and Gaurav S. Sukhatme · 2020
Later among the works it cites.
Scalable differentiable physics for learning and control
Yi-Ling Qiao, Junbang Liang, Vladlen Koltun, and Ming C. Lin · 2020
Later among the works it cites.
Learning to slide unknown objects with differentiable physics simulations
Changkyu Song and Abdeslam Boularias · 2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…