Inspection Robot with Low Cost Perception Sensing

Abstract

This paper presents the use of off-the-shelf products as a low cost solution to bridge bearing inspection. A commercial product, known as a DiddyBorg, is a robot designed for use with a Raspberry Pi as the on-board computer. The DiddyBorg is used as a robotic platform to make a photogrammetric survey of the bearing area of a bridge. The images collected from this survey are then used to make a 3D reconstruction using Structurefrom-Motion (SfM) and software 3DFlow Zephyr Aerial (Zephyr). The quality of the 3D reconstruction had an accuracy of +/-30 mm when compared to the known dimensions of the area. The resulting point cloud was then used as a map that the robot can use for navigation purposes. In particular we present a simple localization algorithm based on distance three readings measured from the robot.