Our understanding of the oceans remains limited by sparse and infrequent observations, primarily because current methods are constrained by the high cost and logistical effort of underwater monitoring, relying either on sporadic surveys across broad areas or on long-term measurements at fixed locations. To overcome these limitations, monitoring systems must enable persistent and autonomous operations without the need for continuous surface support. Despite recent advances, resident underwater vehicles remain uncommon due to persistent challenges in autonomy, robotic resilience, and mechanical robustness, particularly under long-term deployment in harsh and remote environments. This work addresses these problems by presenting the development, deployment, and operation of a resident infrastructure using a docking station with a mini-class Remotely Operated Vehicle (ROV) at 90 m depth. The ROV is equipped with enhanced onboard processing and perception, allowing it to autonomously navigate using USBL signals, dock via ArUco marker-based visual localisation fused through an Extended Kalman Filter, and carry out local inspection routines. The system demonstrated a 90 % autonomous docking success rate and completed full inspection missions within four minutes, validating the integration of acoustic and visual navigation in real-world conditions. These results show that reliable, untethered operations at depth are feasible, highlighting the potential of resident ROV systems for scalable, cost-effective underwater monitoring.
Figures & tables
Fig. 1: Autonomous homing, docking and inspection workflow of the ROV. 1) The ROV initiates homing using acoustic positioning via USBL. 2) Upon visual contact, it transitions to camera-based navigation using ArUco markers or manual navigation and data exchange through the optical modem. 3) The ROV docks into the station, aligning with an inductive charger to charge and establish communication. 4) After recharging or data transfer, it undocks and proceeds with the inspection mission.
Fig. 2: R/V Gunnerus and the working-class ROV Minerva II during the deployment operation. The inset highlights Minerva II equipped with manipulators used to position and adjust the station underwater.
Fig. 3: Network layout of the sensors connected to the Blueye X3 ROV.
Fig. 4: Docking station aboard R/V Gunnerus prior to deployment. The ROV is secured in the main compartment, with a 20 m tether below and an 80 m reserve tether on the right. The USBL and optical modem are mounted on the right column.
Fig. 5: Software architecture for guidance, navigation, and control of the resident ROV.
Fig. 6: The final docking station design viewed from the front as a Blender rendering, courtesy of [ 17 ] .
Fig. 7: Photogrammetry model of the docking station with coordinate frames of robot and docking station as defined by the center ArUco tag, courtesy of [ 17 ] .
Fig. 9: Comparison of detection performance metrics for tags with different bit patterns, courtesy of [ 17 ] .
Fig. 10: Manually flown robot trajectory colored by the number of detected ArUco tags during field deployment, with example camera frames illustrating detection performance near the docking station under real underwater conditions.
Fig. 11: Docking sequence from the right-side loop at TBS. The vehicle begins at the green triangle and follows a sequence of waypoints (magenta circles) to reach the docking station. The estimated trajectory is shown in green, red and blue arrows denote the estimated vehicle X and Z axes and the green intensity the Y position. The dashed line represents the reference path, and the red square marks the final docking position. Slightly Modified from [ 17 ] .
Fig. 12: Docking sequence from the right-side loop at the 90 msite. The vehicle begins at the green triangle and follows a sequence of waypoints (magenta circles) to reach the docking station. The estimated trajectory is shown in green, red and blue arrows denote the estimated vehicle X and Z axes and the green intensity represents the Y position. The dashed line represents the reference path, and the red square marks the final docking position.
Fig. 13: 3D model created in Agisoft Metashape from inspection routine.
Fig. 14: ROV during manual inspection of the pigloop module on which the docking station is mounted.
Underwater robotics develops autonomous and remotely operated machines for navigation, inspection, manipulation, and exploration in aquatic environments.
A Remotely Operated Vehicle (ROV) is a tethered underwater robot used for tasks like inspection and intervention. While essential tools for underwater science, the high cost of commercial ROVs and a persistent gap between mechanically capable platforms and those with integrated intelligence create a significant barrier to access. HyDRA Scorpion differs from conventional systems by addressing these challenges, integrating an advanced, AI-driven perception stack with in-situ measurement capabilities onto a low-cost, locally manufacturable platform. The system combines 4-DoF maneuverability, dual manipulators, and a custom pressure-tested housing. Experimental results validate the system's robustness and performance. Leak-free operation was confirmed through prolonged pressure testing of the electronics housing to 4 bar, equivalent to the pressure of a 304.8-meter water depth approximately in a simulated environment, with no moisture ingress detected. The vehicle also demonstrated stable station-keeping, maintaining its position within a tight tolerance of $$\pm0.15 meters under external disturbances. The onboard AI module achieved underwater object detection mean Average Precision (mAP) of 0.89 with real-time inference, length and 3D-mapping based distance measurement. Also, 4-DoF manipulator arm can grip and maintain dual-function manipulator feature which support 360 degree tangle-free rotation.
Department of Computer Science and Engineering, United International University, United City, Madani Ave, Dhaka 1212, Bangladesh · Department of Electrical and Electronic Engineering, United International University, United City, Madani Ave, Dhaka 1212, Bangladesh
This paper presents a novel acoustic-visual-inertial odometry solution leveraging a continuous-time trajectory estimation framework for unmanned underwater vehicles. Underwater environments present unique challenges for visual localization and mapping, such as light attenuation, illumination variance, and the presence of particulate matter. This motivates the use of additional sensing modalities and a visual tracking pipeline that is robust to diverse subsea conditions. The proposed system is the first continuous-time trajectory estimation framework based on Gaussian processes to fuse asynchronous measurements from a Doppler velocity log, a stereo camera, and an inertial measurement unit. Additionally, a novel visual frontend is proposed, incorporating learning-based feature extraction and matching that is robust to the specific challenges that subsea environments present. The proposed framework enables seamless integration of additional sensor modalities in continuous-time and is adaptable to different environments without reconfiguration. The proposed system is extensively tested on real-world underwater inspection datasets, where it outperforms state-of-the-art visual-inertial and acoustic-visual-inertial SLAM algorithms in accuracy, robustness, and trajectory coverage. Notably, the proposed system outperforms the state-of-the-art despite only forming short-term visual data associations.
Kyungmin Jung, Angad Bajwa, Junha Yoo +2
Department of Mechanical Engineering, McGill University, Montreal, QC, Canada
Autonomous underwater robots require robust perception, estimation and control to operate in confined environments. This paper presents an open-source BlueROV2 platform combining onboard vision with nonlinear Model Predictive Control (NMPC) for autonomous navigation and docking. The platform integrates an NVIDIA Jetson Orin NX and an Intel RealSense D435i stereo camera in a modular pressure housing. Underwater-calibrated stereo depth and realtime object detection provide relative position measurements of nearby BlueROV2 vehicles in the camera and body frames. A quaternion-based estimator fuses external pose and inertial measurements, while an NMPC controller based on a nonlinear six-degree-of-freedom model tracks planned navigation and docking trajectories. To support reproducible development, we also provide open-source physics-based PX4 SITL and Gazebo environments, multi-robot simulation tools and a lowcost physical docking station. Experiments evaluate underwater perception, onboard computational performance, state estimation, trajectory tracking and autonomous docking.
Victor Nan Fernandez-Ayala, Wiktor Kowalczyk, Cezary Banaszek +1
Department of Decision and Control Systems, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.