Development of a lane mark drawing robot

Abstract

In this paper, the authors propose a method for detecting and following a half-faded lane on an asphalt road using image processing. It ensures reliable detection and high speed following in ordinary outdoor scenes. The method of the image processing is based on a template matching with the "lane mark model". They also propose a method for the motion control of the robot which is based on the "look-ahead model". The feedback law adopted is PID (proportional-integral-derivative) control. The authors built a testbed robot, which aims to paint a half-faded lane mark semi-automatically. The details of this testbed robot and experimental results of a half-faded lane mark detection and following are described. Experimental results (trajectories of this robot) for an actual half-faded lane mark show the applicability of this method.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>