Method for Detecting Glass Wall with Lidar and Ultrasonic Sensor

Abstract

In modern architecture, the glass wall has become a widely used element. Two-dimensional lidar is one of many sensors used in robots, but it cannot directly identify the glass wall due to the light transmission characteristics of the laser- facing glass. The ultrasonic sensor can detect the presence of glass due to its working principle, but the general single-line ultrasonic sensor can only detect one point when detecting the glass wall. The detection method mentioned in this article combines two sensors by using image processing-related methods. After the experimental verification of various glass wall occasions, the combination of the two sensors can not only judge whether there is glass in the front, but also identify the position and size of the glass wall, and filter out the point cloud behind the glass in the lidar detection results. The data is thus formed into a whole point cloud data that does not contain the item information behind the glass wall. This paper explores the identification method of the glass wall, which has a lower cost and wider application range.