Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems

TL;DR

Coralai is a framework that models diverse ecosystems of Neural Cellular Automata, demonstrating emergent behaviors like competition, resource cycles, and symbiosis through GPU-accelerated simulations inspired by biological systems.

Contribution

This work introduces Coralai, a novel GPU-accelerated platform for evolving complex NCA ecosystems with modular interactions and biologically inspired dynamics.

Findings

Emergence of competition between sessile and mobile organisms

Cycles of resource depletion and recovery observed

Symbiosis between diverse organisms demonstrated

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 .