The method of reflection-based marker detection and identification to ensure accurate AGV docking

Accurate localization is essential for Automated Guided Vehicles (AGVs) to ensure reliable motion planning and precise execution of docking tasks. A key challenge lies in robust environmental perception for industrial applications. This paper introduces a novel reflection-based marker detection and identification method that relies solely on two-dimensional Light Detection and Ranging (2D LiDAR) technology. The proposed docking method and 2D marker design enable the AGV to accurately estimate the marker's distance and orientation, reliably identify it, and determine the docking point. Experimental validation on a heavy industrial AGV demonstrated that the docking method achieves accuracy of up to 1 cm in position and below 0.05 degree in YAW orientation. As a result, the AGV achieved docking precision at an assembly station with a standard deviation below 2 cm in X and Y axes and YAW orientation below 1.8 degree.