Morphology and Behaviour Evolution of Virtual Creatures: A Model Based on Swarm Inteligence

摘要

In this work we evolution the morphology and the behavior of the virtual creatures. The morphology is defined by rigid bodies as capsules, cylinders, cones, spheres, or parallelepipeds, and the mass and size may change. The rigid bodies are joined by spherical joints with customizable restrictions of angular limits within a given range in each degree of freedom, so to model any type of rotational joint. The behavior is modeled by an Artificial Neural Network, which receives data from all sensors and transmits the amount of moment of force that must be exerted by each effector, so to induce motion to the creature. Finally, the evolution of morphology and behavior is carried out using Particle Swarm Optimization (PSO), where each particle encodes the morphology and behavior of one creature. In this way, this paper proposes a co-evolutionary process where the behavior and the morphology of the creatures are defined.