One-Shot Generative Design for Disordered Metamaterials via Self-Organizing Neural Cellular Automata

2026-07-15

AI Summary

This work addresses the limitations of conventional parametric approaches in efficiently generating disordered metamaterial microstructures with inherent randomness and irregularity, as well as the reliance of existing data-driven models on large training datasets and their limited generalizability. The authors propose a single-sample generative design framework based on neural cellular automata that learns local interaction rules to emulate self-organizing growth processes. This approach dynamically produces spatially varying, complex disordered microstructures from just one exemplar, without requiring retraining. It enables flexible control over orientation, anisotropy, and thickness, accommodates arbitrary domain geometries and discretizations, and naturally yields spatially graded architectures tailored to position-dependent mechanical properties. The method is successfully demonstrated in multiscale mechanical cloaking applications, significantly streamlining fabrication and offering an efficient design pathway for biomedical implants and soft robotics.

Abstract

Disordered metamaterials feature microstructures with inherent randomness and irregularity, enabling them to achieve broader property coverage and superior performance unavailable in their regular counterparts. Despite their promise, designing disordered microstructures is substantially harder than designing regular ones. Their design remains trapped between manual parameterizations with limited expressiveness, and generative AI that is data-hungry and struggles to generalize. To address these limitations, we propose a generative design framework based on Neural Cellular Automata that dynamically grows complex microstructures through learned local interaction rules, inspired by the self-organizing processes in natural materials. This framework requires only a single training template, yet accommodates diverse disordered microstructures and adapts to irregular domains and arbitrary discretizations. By manipulating the learned local rules, we can steer the growth process to generate microstructures unseen during training, providing control over orientation, anisotropy, and directional thickness without retraining. As a dynamic, local growth process, it naturally produces spatially varying microstructures that transition smoothly to enable location-specific mechanical properties. We demonstrate this in a multiscale mechanical cloaking design, where microstructures vary across the space to meet an optimized heterogeneous property distribution. Our design enables excellent cloaking performance without complicated post-processing and incompatible assembly common in existing methods. This data-efficient, generalizable approach opens access to previously intractable disordered materials for biomedical implants and soft robotics.

Problem

• disordered metamaterials
• generative design
• microstructure generation
• data efficiency
• generalization

Innovation

• Neural Cellular Automata
• One-Shot Generative Design
• Disordered Metamaterials
• Self-Organization
• Spatially Varying Microstructures