Development of an autonomous unmanned surface vehicle with object detection using deep learning

Abstract

© 2018 IEEE. A large number of research has been accomplished in the field of the Unmanned Surface Vehicle (USV) in recent years. As deep learning has the potential to raise the technology to the next level by teaching the algorithm to learn by itself, we aim at developing an autonomous USV which has the capabilities to acquire various types of data and information in offshore areas, process them, and then execute missions based on the situation with the aid of the deep convolutional neural network. This paper describes the implementation of such USV system outfitted with sensors for localization with autonomous navigation technologies and algorithms being adopted for the potential real-life applications such as identifying approaching vehicles to alert the ground station or exploring the surrounding environment of assigned locations. In this manuscript, Global Positioning System (GPS) and compass are equipped to provide the geolocation and the heading for autonomous navigation. Experimental results are provided to validate the proposed implementation. In the end, a summary of current progress is presented as well as the proposed future works.