Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems

Aidan Barbieux, Rodrigo Canaan
6/14/2024
cs.NEcs.LGcs.MA

Official code: aidanbx/coralai (18 stars, PyTorch, last commit 2026-03-02).

Abstract

This paper presents Coralai, a framework for exploring diverse ecosystems of Neural Cellular Automata (NCA). Organisms in Coralai utilize modular, GPU-accelerated Taichi kernels to interact, enact environmental changes, and evolve through local survival, merging, and mutation operations implemented with HyperNEAT and PyTorch. We provide an exploratory experiment implementing physics inspired by slime mold behavior showcasing the emergence of competition between sessile and mobile organisms, cycles of resource depletion and recovery, and symbiosis between diverse organisms. We conclude by outlining future work to discover simulation parameters through measures of multi-scale complexity and diversity. Code for Coralai is available at https://github.com/aidanbx/coralai , video demos are available at https://www.youtube.com/watch?v=NL8IZQY02-8 .

View on arXivView PDF

Code Implementations(1)

aidanbx/coralaiOfficial100%
PyTorch

Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems. Parallelized with Taichi and PyTorch

183Shell, PythonJul 23, 20237 months ago
artificial-lemergent-behaviorevolutionary-algorithmsneural-celpytorch+1 more

Cite this paper

@article{barbieux2024coralai,
  title  = {Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems},
  author = {Aidan Barbieux and Rodrigo Canaan},
  year   = {2024},
  eprint = {2406.09654},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.09654v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.09654.svg)](https://codeofpaper.com/paper/2406.09654)

Discussion