DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 oralEveryoneRevisionsBibTeX
Keywords: soft robot, diffusion model, co-design
TL;DR: Use diffusion models augmented by physics-based simulation to breed soft robots
Abstract: Nature evolves creatures with a high complexity of morphological and behavioral intelligence, meanwhile computational methods lag in approaching that diversity and efficacy. Co-optimization of artificial creatures' morphology and control in silico shows promise for applications in physical soft robotics and virtual character creation; such approaches, however, require developing new learning algorithms that can reason about function atop pure structure. In this paper, we present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks. \name bridges the gap between virtually generated content and physical utility by (i) augmenting the diffusion process with a physical dynamical simulation which provides a certificate of performance, and (ii) introducing a co-design procedure that jointly optimizes physical design and control by leveraging information about physical sensitivities from differentiable simulation. We showcase a range of simulated and fabricated robots along with their capabilities. Check our website: https://diffusebot.github.io/
Supplementary Material: pdf
Submission Number: 10463