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.

Massive-Scale Automation in Cyber-Physical Systems: Vision & Challenges

“…These systems making up the smart city will automatically manage power and communication infrastructure, environment, traffic and other aspects of the city for the benefit and well-being of its inhabitants through ubiquitous sensing and embedded intelligence. This includes robotics for repair and maintenance [31], [32], driverless transportation [33] and power management [30] among others.…”

Service-Oriented Reference Architecture for Smart Cities

“…Though often independent systems, the possibility of interconnecting vehicles together into an Internet of Vehicles or a Vehicular Cloud [47] could allow for the sharing of sensor data and even allow the city systems to perform holistic traffic management. Repair, maintenance and inspection could also be performed using robotic platforms [48], [49]. Figure 1 captures many of the dimensions of the smart city [1] and forms the basis of our reference architecture.…”

An Improved Robot for Bridge Inspection

“…Structure-from-Motion (SfM) was used in this work and in previous work [1] as a method for adding value to visual inspection. SfM uses multiple 2D image views to find the 3D geometry (i.e., the structure) of a scene or an object by taking images from different viewpoints (i.e., the camera has motion).…”

“…Continuing on from work by the same authors [1], more off-the-shelf and low-cost solutions are considered for autonomously navigating a bridge abutment, with the aim of performing a visual inspection on a bridge bearing.…”