This paper addresses the development of an underwater visual navigation system for a Remotely Operated Vehicle (ROV) based on Real-Time Simultaneous Localization and Mapping method using natural landmarks. Our proposed approach was tested in an indoor tank, where field experiments were performed to obtain 3D vehicle (VIDEORAY Pro3 ROV) trajectory, and results validated using an external stereo vision "ground-truth" system.

Achieving persistent and reliable autonomy for mobile robots in challenging field mission scenarios is a long-time quest for the Robotics research community. Deep learning-based LIDAR odometry is attracting increasing research interest as a technological solution for the robot navigation problem and showing great potential for the task.In this work, an examination of the benefits of leveraging learning-based encoding representations of real-world data is provided. In addition, a broad perspective of emergent Deep Learning robust techniques to track motion and estimate scene structure for real-world applications is the focus of a deeper analysis and comprehensive comparison.Furthermore, existing Deep Learning approaches and techniques for point cloud odometry tasks are explored, and the main technological solutions are compared and discussed.Open challenges are also laid out for the reader, hopefully offering guidance to future researchers in their quest to apply deep learning to complex 3D non-matrix data to tackle localization and robot navigation problems.

No abstract