Population Dynamics in ARIEL Robotics Systems Featuring Embodied Evolution via Spatial Mating Mechanisms

TL;DR

This paper introduces a spatially embedded evolutionary algorithm for robot populations in a simulated environment, revealing how spatial structure influences evolutionary dynamics and stability.

Contribution

It demonstrates the impact of spatial structure on evolutionary processes, including phase transitions and stability issues, in robot populations using embodied evolution.

Findings

Spatial structure causes a phase transition in energy-based selection regimes.

Density-dependent death selection achieves high completion but reduces fitness.

Coupled selection mechanisms can lead to bistability and instability.

Abstract

We present a Spatially Embedded Evolutionary Algorithm where robot individuals exist in a physically simulated 2D environment, must navigate to encounter potential mates, and compete for survival under various spatially-aware selection pressures. Using HyperNEAT evolved neural controllers for ARIEL gecko-inspired quadrupeds in MuJoCo, we investigate how spatial structure fundamentally alters evolutionary dynamics. Our experiments show a modest 4.9% difference in peak fitness between proximity-based and random pairing possibly within stochastic variation while combining spatial parent selection with stochastic death selection produces unstable population dynamics. We discover a continuous phase transition in energy-based selection experiments, with critical zone count separating extinction-dominated and explosion-dominated regimes. Our density-dependent death selection mechanism achieves 97% completion rates but causes fitness decline, revealing a fundamental dilemma where decoupled mechanisms produce bistable dynamics, positively coupled mechanisms create counter-selection pressures, and only deterministic fitness-based selection maintains stability. These findings provide important constraints for future spatial EA design.