Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models
Abstract
Aquatic locomotion is a classic fluidstructure interaction (FSI) problem of interest to biologists and engineers. Solving the fully coupled FSI equations for incompressible NavierStokes and finite elasticity is computationally expensive. Optimizing robotic swimmer design within such a system generally involves cumbersome, gradientfree procedures on top of the already costly simulation. To address this challenge we present a novel, fully differentiable hybrid approach to FSI that combines a 2D direct numerical simulation for the deformable solid structure of the swimmer and a physicsconstrained neural network surrogate to capture hydrodynamic effects of the fluid. For the deformable solid simulation of the swimmer's body, we use stateoftheart techniques from the field of computer graphics to speed up the finiteelement method (FEM). For the fluid simulation, we use a UNet architecture trained with a physicsbased loss function to predict the flow field at each time step. The pressure and velocity field outputs from the neural network are sampled around the boundary of our swimmer using an immersed boundary method (IBM) to compute its swimming motion accurately and efficiently. We demonstrate the computational efficiency and differentiability of our hybrid simulator on a 2D carangiform swimmer. Due to differentiability, the simulator can be used for computational design of controls for soft bodies immersed in fluids via direct gradientbased optimization.
 Publication:

arXiv eprints
 Pub Date:
 March 2022
 DOI:
 10.48550/arXiv.2204.12584
 arXiv:
 arXiv:2204.12584
 Bibcode:
 2022arXiv220412584N
 Keywords:

 Computer Science  Robotics;
 Computer Science  Machine Learning;
 Physics  Fluid Dynamics
 EPrint:
 ICML 2022