Simulation of animal behavior using neural networks

Abstract

In this paper, we simulated some basic animal behavior by letting it “evolve” through generations. The animals, which are able to survive, will be given the privilege to breed the new generation and pass the good genes to the next generation. Our simulation environment consisted of a Prey-Predator-Food model. The prey and predators created in our simulation are objects that have sensors to make them aware of their environment, and they are able to move freely around the world. The food sources are stationary objects placed randomly throughout the world, which serve as targets for prey to search for and eat.