Advanced soft robot modeling in ChainQueen

We present extensions to ChainQueen, an open source, fully differentiable material point method simulator for soft robotics. Previous work established ChainQueen as a powerful tool for inference, control, and co-design for soft robotics. We detail enhancements to ChainQueen, allowing for more efficient simulation and optimization and expressive co-optimization over material properties and geometric parameters. We package our simulator extensions in an easy-to-use, modular application programming interface (API) with predefined observation models, controllers, actuators, optimizers, and geometric processing tools, making it simple to prototype complex experiments in 50 lines or fewer. We demonstrate the power of our simulator extensions in over nine simulated experiments.

[1]  Connor Schenck,et al.  SPNets: Differentiable Fluid Dynamics for Deep Neural Networks , 2018, CoRL.

[2]  Christof Büskens,et al.  The ESA NLP Solver WORHP , 2012 .

[3]  R. D. Wood,et al.  Nonlinear Continuum Mechanics for Finite Element Analysis , 1997 .

[4]  Wojciech Matusik,et al.  Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations , 2019, NeurIPS.

[5]  Daniela Rus,et al.  A Recipe for Soft Fluidic Elastomer Robots , 2015, Soft robotics.

[6]  John A. Nairn,et al.  Three-Dimensional Dynamic Fracture Analysis Using the Material Point Method , 2006 .

[7]  Theodore Kim,et al.  Stable Neo-Hookean Flesh Simulation , 2018, ACM Trans. Graph..

[8]  Jernej Barbič,et al.  Real-time control of physically based simulations using gentle forces , 2008, SIGGRAPH 2008.

[9]  Jernej Barbic,et al.  FEM simulation of 3D deformable solids: a practitioner's guide to theory, discretization and model reduction , 2012, SIGGRAPH '12.

[10]  Shi-Min Hu,et al.  A Temporally Adaptive Material Point Method with Regional Time Stepping , 2018, Comput. Graph. Forum.

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

[12]  Chenfanfu Jiang,et al.  Anisotropic elastoplasticity for cloth, knit and hair frictional contact , 2017, ACM Trans. Graph..

[13]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[14]  Jiancheng Liu,et al.  ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[15]  Hod Lipson,et al.  Unshackling evolution , 2014 .

[16]  Jonas Degrave,et al.  A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS , 2016, Front. Neurorobot..

[17]  Eftychios Sifakis,et al.  An adaptive generalized interpolation material point method for simulating elastoplastic materials , 2017, ACM Trans. Graph..

[18]  Chenfanfu Jiang,et al.  Silly rubber , 2019, ACM Trans. Graph..

[19]  Marc Toussaint,et al.  Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning , 2018, Robotics: Science and Systems.

[20]  W. Takashima,et al.  Artificial Muscles Based on Polypyrrole Actuators with Large Strain and Stress Induced Electrically , 2004 .

[21]  Jonas Buchli,et al.  The control toolbox — An open-source C++ library for robotics, optimal and model predictive control , 2018, 2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR).

[22]  Andre Pradhana,et al.  A moving least squares material point method with displacement discontinuity and two-way rigid body coupling , 2018, ACM Trans. Graph..

[23]  Yi Sun,et al.  A Miniature Soft Robotic Manipulator Based on Novel Fabrication Methods , 2016, IEEE Robotics and Automation Letters.

[24]  Christian Duriez,et al.  Soft Robot Modeling, Simulation and Control in Real-Time , 2017 .

[25]  Tiantian Liu,et al.  Quasi-newton methods for real-time simulation of hyperelastic materials , 2017, TOGS.

[26]  Sehoon Ha,et al.  Iterative Training of Dynamic Skills Inspired by Human Coaching Techniques , 2014, ACM Trans. Graph..

[27]  Tae-Yong Kim,et al.  Unified particle physics for real-time applications , 2014, ACM Trans. Graph..

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

[29]  Alexey Stomakhin,et al.  A material point method for snow simulation , 2013, ACM Trans. Graph..

[30]  LipsonHod,et al.  Dynamic Simulation of Soft Multimaterial 3D-Printed Objects , 2014 .

[31]  Chenfanfu Jiang,et al.  The material point method for simulating continuum materials , 2016, SIGGRAPH Courses.

[32]  Jérémie Dequidt,et al.  Software toolkit for modeling, simulation, and control of soft robots , 2017, Adv. Robotics.

[33]  Andre Pradhana,et al.  Drucker-prager elastoplasticity for sand animation , 2016, ACM Trans. Graph..

[34]  D. Sulsky.  Erratum: Application of a particle-in-cell method to solid mechanics , 1995 .

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

[36]  Chenfanfu Jiang,et al.  The affine particle-in-cell method , 2015, ACM Trans. Graph..

[37]  KavanLadislav,et al.  Quasi-Newton Methods for Real-Time Simulation of Hyperelastic Materials , 2017 .

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