Investigating Genetic Network Programming for Multiple Nest Foraging

Abstract

Genetic Network Programming is a relatively unexplored evolutionary algorithm, particularly for more advanced tasks. Foraging is a challenging domain within swarm robotics, since it requires an aptitude for multiple rudimentary behaviours. The work herein thus investigates the application of Genetic Network Programming for multiple nest foraging. Further, a variant of Genetic Network Programming, which incorporates neural network benefits is proposed and evaluated. The results are compared to state-of-the-art foraging algorithms including the generic Neuro-evolution of Augmented Technologies and Novelty Search algorithms and the more application specific Multiple-Place Foraging Algorithm. Results indicate that Genetic Network Programming shows promise.