Evolving collective behavior in an artificial ecology

Abstract

Collective behavior refers to coordinated group motion, common to many animals. The dynamics of a group can be seen as a distributed model, each “animal” applying the same rule set. This study investigates the use of evolved sensory controllers to produce schooling behavior. A set of artificial creatures “live” in an artificial world with hazards and food. Each creature has a simple artificial neural network brain that controls movement in different situations. A chromosome encodes the network structure and weights, which may be combined using artificial evolution with another chromosome, if a creature should choose to mate. Prey and predators coevolve without an explicit fitness function for schooling to produce sophisticated, nondeterministic, behavior. The work highlights the role of species’ physiology in understanding behavior and the role of the environment in encouraging the development of sensory systems.