DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation
Paper Code Video BibTex DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation Pingchuan Ma1, Tao Du1, John Z. Zhang2, Kui Wu1, Andrew Spielberg1, Robert K. Katzschmann2, and Wojciech Matusik1 1MIT CSAIL 2ETH Zürich The overview of our differentiable pipeline for both forward and backward propagation. Abstract The computational design of soft underwater swimmers is challenging because of the high degrees of freedom in soft-body modeling. In this paper, we present a differentiable pipeline for co-designing a soft swimmer's geometry and controller. Our pipeline unlocks gradient-based algorithms for discovering novel swimmer designs more efficiently than traditional gradient-free solutions. We propose Wasserstein barycenters as a basis for the geometric design of soft underwater swimmers since it is differentiable and can naturally interpolate between bio-inspired base shapes via optimal transport. By combining this design space with
DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation Pingchuan Ma 1 , Tao Du 1 , John Z. Zhang 2 , Kui Wu 1 , Andrew Spielberg 1 , Robert K. Katzschmann 2 , and Wojciech Matusik 1 1 MIT CSAIL 2 ETH Zürich The overview of our differentiable pipeline for both forward and backward propagation. Abstract The computational design of soft underwater swimmers is challenging because of the high degrees of freedom in soft-body model
Explore this link on the map →related reading
- When Models Manipulate Manifolds: The Geometry of a Counting Tasktransformer-circuits.pub
- Optimizing Cubature for Efficient Integration of Subspace Deformationscs.cornell.edu
- A differentiable wave optics model for end-to-end imaging system optimization | SPIE Photonics Westspie.org
- Learning the integral of a diffusion model – Sander Dielemansander.ai
- Biohybrid microswimmer - Wikipediaen.wikipedia.org
- [2607.02954] Microcosmos: Reimagining Artificial Life for the GPU Eraarxiv.org
- Differentiable Programming from Scratchthenumb.at
- Falcon - Design Differentfalcon.so
- [2311.13159] Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flowarxiv.org
- Gray Crawfordgraycrawford.com
- Reproducing DeepTFUS | projectsmasonjwang.com
- TU Berlin | CG | Marc Alexacg.tu-berlin.de