Lune

ICML2022Top-tier venue

Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models

Elvis Nava, John Z. Zhang, Mike Yan Michelis, Tao Du, Pingchuan Ma, Benjamin F. Grewe, Wojciech Matusik, Robert Kevin Katzschmann

Abstract

Aquatic locomotion is a classic fluid-structure interaction (FSI) problem of interest to biologists and engineers. Solving the fully coupled FSI equations for incompressible Navier-Stokes and finite elasticity is computationally expensive. Optimizing robotic swimmer design within such a system generally involves cumbersome, gradient-free 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 physics-constrained neural network surrogate to capture hydrodynamic effects of the fluid. For the deformable solid simulation of the swimmer's body, we use state-of-the-art techniques from the field of computer graphics to speed up the finite-element method (FEM). For the fluid simulation, we use a U-Net architecture trained with a physics-based 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 gradient-based optimization.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments cites DiffAqua: a differentiable computational design pipeline for soft underwater swimmers with shape interpolation
  • Differentiable Simulation of Soft Multi-body Systems cites DiffAqua: a differentiable computational design pipeline for soft underwater swimmers with shape interpolation
  • Differentiable Simulation of Soft Multi-body Systems cites Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse EnvironmentsTsun-Hsuan Wang, Pingchuan Ma, Andrew Everett Spielberg, Zhou Xian et al.ICLR 2023 · 4 citations

Builds on5

  1. Learning Mesh-Based Simulation with Graph NetworksTobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. BattagliaICLR 2021 · 1,175 citations
  2. Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that GeneralizeNils Wandel, Michael Weinmann, Reinhard KleinICLR 2021 · 82 citations
  3. DiffAqua: a differentiable computational design pipeline for soft underwater swimmers with shape interpolationPingchuan Ma, Tao Du, John Z. Zhang, Kui Wu et al.SIGGRAPH 2021 · 65 citations
  4. Differentiable Simulation of Soft Multi-body SystemsYi-Ling Qiao, Junbang Liang, Vladlen Koltun, Ming C. LinNeurIPS 2021 · 61 citations
  5. IQ-MPM: an interface quadrature material point method for non-sticky strongly two-way coupled nonlinear solids and fluidsYu Fang, Ziyin Qu, Minchen Li, Xinxin Zhang et al.SIGGRAPH 2020 · 49 citations

Related papers

  1. Differentiable Fluids with Solid Coupling for Learning and ControlTetsuya Takahashi, Junbang Liang, Yi-Ling Qiao, Ming C. LinAAAI 2021 · 33 citations
  2. NeuralFluid: Nueral Fluidic System Design and Control with Differentiable SimulationYifei Li, Yuchen Sun, Pingchuan Ma, Eftychios Sifakis et al.NeurIPS 2024 · 19 citations
  3. Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow PredictionFilipe de Avila Belbute-Peres, Thomas D. Economon, J. Zico KolterICML 2020 · 271 citations
  4. Elastic Locomotion with Mixed Second-order DifferentiationSiyuan Shen, Tianjia Shao, Kun Zhou, Chenfanfu Jiang et al.SIGGRAPH 2025 · 2 citations
  5. Neural-Augmented Kelvinlet for Real-Time Soft Tissue Deformation ModelingAshkan Shahbazi, Kyvia Pereira, Jon S. Heiselman, Elaheh Akbari et al.AAAI 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines