Vision-Based Low-Level Navigation using a Feed-Forward Neural Network

Abstract

In this paper we propose a simple method for low-level navigation for autonomous mobile robots, employing an artificial neural network. Both corridor following and obstacle avoidance in indoor environments are managed by the same network. Raw grayscale images of size 32 × 23 pixels are processed one at a time by a feed-forward neural network. The output signals from the network directly control the motor control system of the robot. The feed-forward network is trained using the RPROP algorithm. Experiments in both familiar and unfamiliar environments are reported. 1 Introduction Autonomous mobile robots must have a robust lowlevel navigation system in order to work in changing indoor-environments. In this paper we present a simple navigation method that handles both corridor following and obstacle avoidance in indoor environments. We also present some practical experiments done with the mobile platform shown in Figure 1. The platform, controlled by the proposed navigation method, has...