Simultaneous Localization and Mapping with Application to Monitoring of Underground Transportation Infrastructure

This paper presents the results of development, design and implementation of a Simultaneous Localization And Mapping (SLAM) system for autonomous real-time localization with application to Underground Transportation Infrastructure (UTI) such as tunnels. Localization is achieved in absence of any GPS or auxiliary system. The system is a necessary element of a fully autonomous platform for detection of cracks and other anomalies on the interior surfaces of tunnels and other UTI. It can be used for tagging of high-resolution sensor data obtained with low-cost prototype data acquisition platforms previously developed [1], [2]. Visual based SLAM has been used as the core element in an architecture also employing a Commercial Off The Shelf (COTS) ZED stereocamera from Stereolabs. To achieve real-time operation, an NVIDIA Jetson Tx2 massively parallel Graphic Processing Unit (GPU) has been used as the core computational engine employing two different software libraries. We achieved localization at 5 frames per second (fps) using ORBSLAM2 open source software library, while the much lighter but proprietary ZED SDK was able to deliver performance at nearly 60 fps.