Differentiable Simulation of Soft Multi-body Systems

Abstract

We present a method for differentiable simulation of soft articulated bodies. Our work enables the integration of differentiable physical dynamics into gradient-based pipelines. We develop a top-down matrix assembly algorithm within Projective Dynamics and derive a generalized dry friction model for soft continuum using a new matrix splitting strategy. We derive a differentiable control framework for soft articulated bodies driven by muscles, joint torques, or pneumatic tubes. The experiments demonstrate that our designs make soft body simulation more stable and realistic compared to other frameworks. Our method accelerates the solution of system identification problems by more than an order of magnitude, and enables efficient gradient-based learning of motion control with soft robots.

arXiv commentNeurIPS 2021

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Training Deep Nets with Sublinear Memory Cost
• Codimensional Incremental Potential Contact
• Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation
• DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation
• Scalable Differentiable Physics for Learning and Control
• Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
• Soft Hybrid Aerial Vehicle via Bistable Mechanism