Navigating with an animal brain: a neural network for landmark identification and navigation

Abstract

Navigating in an unknown environment is a task commonly accomplished by most animals. Nevertheless, it is not justified to infer that this capacity needs complex reasoning involving abstract geometrical computations. In this paper, the authors' aim is to show that such behavior, including switching between goals, can be simulated by simple artificial neural networks (NN) where no complex computation is performed. The authors present a real development and simulations about a Khepera robot and a simulated system named Prometheus. The authors use a novel neural architecture named PerAc (Perception-Action) which is a systematic way to decompose the control of an autonomous robot in perception and action flows. The authors show that action simplifies the interpretation of perception: each action is a choice and conditions entirely the future of the robot.