Robust Multi-Cellular Developmental Design

TL;DR

This paper presents a continuous, neural network-controlled multi-cellular growth model on a 2D grid, demonstrating effective pattern formation and self-healing through an emergent stabilization process optimized by NEAT.

Contribution

It introduces a novel multi-cellular developmental model with local interactions and emergent growth stabilization, advancing the design of self-organizing biological-inspired systems.

Findings

Achieves near-perfect pattern matching on 'flags' problems.

Demonstrates self-healing properties in evolved organisms.

Uses NEAT for topology and weight optimization of neural controllers.

Abstract

This paper introduces a continuous model for Multi-cellular Developmental Design. The cells are fixed on a 2D grid and exchange "chemicals" with their neighbors during the growth process. The quantity of chemicals that a cell produces, as well as the differentiation value of the cell in the phenotype, are controlled by a Neural Network (the genotype) that takes as inputs the chemicals produced by the neighboring cells at the previous time step. In the proposed model, the number of iterations of the growth process is not pre-determined, but emerges during evolution: only organisms for which the growth process stabilizes give a phenotype (the stable state), others are declared nonviable. The optimization of the controller is done using the NEAT algorithm, that optimizes both the topology and the weights of the Neural Networks. Though each cell only receives local information from its neighbors, the experimental results of the proposed approach on the 'flags' problems (the phenotype must match a given 2D pattern) are almost as good as those of a direct regression approach using the same model with global information. Moreover, the resulting multi-cellular organisms exhibit almost perfect self-healing characteristics.