Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap

We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation. Through gradient-based optimization, identification of the simulation parameters and network weights is performed efficiently in preliminary experiments on a real-world dataset and in sim2sim transfer applications, while poor local optima are overcome through a random search approach.

[1]  Melissa L. McGuire,et al.  Parallel Monotonic Basin Hopping for Low Thrust Trajectory Optimization , 2018 .

[2]  Pierre-Yves Oudeyer,et al.  Sim-to-Real Transfer with Neural-Augmented Robot Simulation , 2018, CoRL.

[3]  Jure Leskovec,et al.  Learning to Simulate Complex Physics with Graph Networks , 2020, ICML.

[4]  Frédo Durand,et al.  DiffTaichi: Differentiable Programming for Physical Simulation , 2020, ICLR.

[5]  K. H. Hunt,et al.  Coefficient of Restitution Interpreted as Damping in Vibroimpact , 1975 .

[6]  E. Kandel,et al.  Proceedings of the National Academy of Sciences of the United States of America. Annual subject and author indexes. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Joonho Lee,et al.  Learning agile and dynamic motor skills for legged robots , 2019, Science Robotics.

[8]  Siddhartha S. Srinivasa,et al.  DART: Dynamic Animation and Robotics Toolkit , 2018, J. Open Source Softw..

[9]  Leslie Pack Kaelbling,et al.  Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[10]  Nicolas Mansard,et al.  Analytical Derivatives of Rigid Body Dynamics Algorithms , 2018, Robotics: Science and Systems.

[11]  Jonas Buchli,et al.  Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimation , 2017, Adv. Robotics.

[12]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Jiajun Wu,et al.  DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions , 2019, Robotics: Science and Systems.

[14]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

[15]  Tomasz Kornuta,et al.  Learning beyond simulated physics , 2018 .

[16]  Joshua B. Tenenbaum,et al.  End-to-End Differentiable Physics for Learning and Control , 2018, NeurIPS.

[17]  C. Karen Liu,et al.  Data-Augmented Contact Model for Rigid Body Simulation , 2018, L4DC.

[18]  Ming C. Lin,et al.  Differentiable Cloth Simulation for Inverse Problems , 2019, NeurIPS.

[19]  Wei Chen,et al.  Learning to predict the cosmological structure formation , 2018, Proceedings of the National Academy of Sciences.

[20]  Gaurav S. Sukhatme,et al.  Physics-based Simulation of Continuous-Wave LIDAR for Localization, Calibration and Tracking , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Alberto Rodriguez,et al.  TossingBot: Learning to Throw Arbitrary Objects With Residual Physics , 2019, IEEE Transactions on Robotics.

[22]  Twan Koolen,et al.  Julia for robotics: simulation and real-time control in a high-level programming language , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[23]  Jiajun Wu,et al.  Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids , 2018, ICLR.

[24]  Jan Peters,et al.  Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning , 2019, ICLR.

[25]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[26]  Hessam Babaee,et al.  Deep Learning of Turbulent Scalar Mixing , 2018, Physical Review Fluids.

[27]  Daniel L. K. Yamins,et al.  Flexible Neural Representation for Physics Prediction , 2018, NeurIPS.

[28]  M. Anitescu,et al.  Formulating Dynamic Multi-Rigid-Body Contact Problems with Friction as Solvable Linear Complementarity Problems , 1997 .

[29]  Gaurav S. Sukhatme,et al.  Interactive Differentiable Simulation , 2019, ArXiv.