DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation

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 differentiable simulation and control, we can efficiently optimize a soft underwater swimmer's performance with fewer simulations than baseline methods. We demonstrate the efficacy of our method on various design problems such as fast, stable, and energy-efficient swimming and demonstrate applicability to multi-objective design.

arXiv commentACM SIGGRAPH 2021. Homepage: http://diffaqua.csail.mit.edu/

References in corpus (11)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Neural Ordinary Differential Equations
• Learning to Simulate Complex Physics with Graph Networks
• Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
• Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
• Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimation
• Learning to Control PDEs with Differentiable Physics
• SPNets: Differentiable Fluid Dynamics for Deep Neural Networks
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Scalable Differentiable Physics for Learning and Control
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Cited by in corpus (7)

• Model Based Control of Soft Robots: A Survey of the State of the Art and Open Challenges
• Efficient automatic design of robots
• Sim2Real for Soft Robotic Fish via Differentiable Simulation
• Computational Design of Passive Grippers
• An Open Source Design Optimization Toolbox Evaluated on a Soft Finger
• Differentiable Simulation of Soft Multi-body Systems
• What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks