Vision-based positioning system for auto-docking of unmanned surface vehicles (USVs)

Abstract

This paper presents an independent stereo-vision based positioning system for docking operations. The low-cost system consists of an object detector and different 3D reconstruction techniques. To address the challenge of robust detections in an unstructured and complex outdoor environment, a learning-based object detection model is proposed. The system employs a complementary modular approach that uses data-driven methods, utilizing data wherever required and traditional computer vision methods when the scope and complexity of the environment are reduced. Both, monocular and stereo-vision based methods are investigated for comparison. Furthermore, easily identifiable markers are utilized to obtain reference points, thus simplifying the localization task. A small unmanned surface vehicle (USV) with a LiDAR-based positioning system was exploited to verify that the proposed vision-based positioning system produces accurate measurements under various docking scenarios. Field experiments have proven that the developed system performs well and can supplement the traditional navigation system for safety-critical docking operations.

milliAmpere: An Autonomous Ferry Prototype

“…Again, the ISAM2 framework was used as a back-end, while the segmentation-based AprilTag detector of [36] was used in the front-end. A similar investigation, utilizing stereo vision and machine learning (Yolo v3), was reported in [34].…”

Adaptive Control Algorithm for Trajectory Tracking of Underactuated Unmanned Surface Vehicle (UUSV)

“…Tis section defnes the current trends in this feld. In [14], the article presents the positioning system based on stereo vision. Tis study also proposed an object detection model based on learning to solve the robust detection challenge in a complex environment.…”

GNSS-Independent Maritime Navigation Using Monocular Camera Images with Digital Elevation Map

“…Extensive literature already exists studying Alternative Positioning Navigation and Timing (APNT) systems, utilizing everything from radio beacons to visual markers [3], [4] to infer the state of maritime vessels. However, where the necessary infrastructure for such solutions are not available, the use of standalone sensors is considered a viable alternative.…”

“…[12] propose using cameras and automatic identification systems in junction to improve the situational awareness of Autonomous Surface Vehicles (ASVs), whilst [13] fuse visual, acoustic and inertial data using an error-state Kalman filter for navigation of maritime vessels in narrow waterways. [3], [4] are further examples of how multi-sensor fusion is being investigated in improving Simultaneous Localization And Mapping (SLAM) solutions, allowing for even greater autonomy of unmanned vehicles.…”