Saved in:
Bibliographic Details
Main Authors: Woiwode, Dominik, Marten, Jakob, Rosenhahn, Bodo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.07440
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909832221556736
author Woiwode, Dominik
Marten, Jakob
Rosenhahn, Bodo
author_facet Woiwode, Dominik
Marten, Jakob
Rosenhahn, Bodo
contents This paper presents a rotation-invariant embedded platform for simulating (neural) cellular automata (NCA) in modular robotic systems. Inspired by previous work on physical NCA, we introduce key innovations that overcome limitations in prior hardware designs. Our platform features a symmetric, modular structure, enabling seamless connections between cells regardless of orientation. Additionally, each cell is battery-powered, allowing it to operate independently and retain its state even when disconnected from the collective. To demonstrate the platform's applicability, we present a novel rotation-invariant NCA model for isotropic shape classification. The proposed system provides a robust foundation for exploring the physical realization of NCA, with potential applications in distributed robotic systems and self-organizing structures. Our implementation, including hardware, software code, a simulator, and a video, is openly shared at: https://github.com/dwoiwode/embedded_nca
format Preprint
id arxiv_https___arxiv_org_abs_2510_07440
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata
Woiwode, Dominik
Marten, Jakob
Rosenhahn, Bodo
Neural and Evolutionary Computing
Robotics
This paper presents a rotation-invariant embedded platform for simulating (neural) cellular automata (NCA) in modular robotic systems. Inspired by previous work on physical NCA, we introduce key innovations that overcome limitations in prior hardware designs. Our platform features a symmetric, modular structure, enabling seamless connections between cells regardless of orientation. Additionally, each cell is battery-powered, allowing it to operate independently and retain its state even when disconnected from the collective. To demonstrate the platform's applicability, we present a novel rotation-invariant NCA model for isotropic shape classification. The proposed system provides a robust foundation for exploring the physical realization of NCA, with potential applications in distributed robotic systems and self-organizing structures. Our implementation, including hardware, software code, a simulator, and a video, is openly shared at: https://github.com/dwoiwode/embedded_nca
title A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata
topic Neural and Evolutionary Computing
Robotics
url https://arxiv.org/abs/2510.07440