Fusing Sonars and LRF Data to Glass Detection for Robotics Navigation

Abstract

Identifying and detecting glass is an important part of robotic safety at office conditions. Existing glass detection algorithms rely on high-cost lidars or ultrasonic rings. We propose an efficient and simple algorithm to detect glass based on sensor fusion of ultrasound sensors and laser scanners data that can adapts to all kinds of lidars. Combine the glass detection results with gmapping algorithm to generate a more accurate map, the maximum connected domain algorithm used to remove noise from the map. We tested the glass detection algorithm on the robot platform. Experiments showed that about 93 % of the glass can be detected correctly.