19 August 2022 in Current Robotics Reports
Purpose of Review: The goal of this paper is to review current developments in the area of underwater robotics regarding the use of AI, especially in model learning, robot control, perception and navigation as well as manipulation.Recent Findings: AI technologies and advanced control techniques are finding their way into robotics systems to deal with complex and challenging conditions and to equip them with higher levels of autonomy.Summary: Although AI techniques and concepts are already a focus area in research on autonomous underwater systems, broad adoption to commercial systems is still in its infancy. Nonetheless, major advances have been done in recent years, especially on integrating different capabilities (perception, navigation, advanced control) in a single system and with first approaches on interaction and autonomous manipulation.
10 July 2025 in IEEE Robotics and Automation Letters
This work proposes a method for learning features from a batch of 2D sonar images to predict a multi-view point-cloud for achieving a dense 3D-reconstruction. In comparison to vision-based sensors, acoustics are considered a reliable sensing modality in underwater environments. The output of sonars is a 2D image which is unable to represent the scanned scene in all three dimensions. Estimation of this missing information, known as the elevation angle, is the key to performing 3d-reconstruction from acoustic images. One of the approaches is to predict a depth-map from the 2D sonar image, and transforming it into a point-cloud. In this letter, this idea is further improved into learning features from a batch of 2D acoustic images and predicting multiple depthmaps of the scanned object which covers it from different viewpoints. For training the deep learning model, and due to the lack of datasets from real environments, data was generated synthetically. For reducing the simulation-to-real gap, a Cycle-GAN was trained on real images for transferring the realistic style into the synthetically generated images. The conducted experiments in simulation showed that the proposed method is able to perform dense 3D reconstruction. The approach was then further tested in a real environment using an underwater vehicle, which accurately 3D-reconstructed the scanned objects achieving an average chamfer distance error of 0.06 meters when compared to a laser-scanned ground-truth.
25 April 2025 in Ocean Engineering
3 December 2025 in Scientific Data
In this paper, we present a dataset related to the behaviour of underwater umbilicals of a Remotely Operated Vehicle (ROV), specifically the BlueROV2. The data were collected from three different sources: a Motion Capture System (mo-cap system), the onboard sensors of the BlueROV2, and a tension sensor. The mo-cap system tracks the motion of the ROV and its tether, while the tension sensor measures the force exerted by the cable tension on the surface side, near the tether drum. The dataset were acquired for research purposes, specifically for studying underwater cables in the context of modeling, estimation, and control using machine learning and data-driven control methods. They can serve as a benchmark for developing and validating underwater tether models, enabling researchers to develop control methods that consider tether drag or entanglement, improving navigation accuracy of ROVs, or developing automated tether management systems. This paper describes the experimental setup, data acquisition, and post-processing procedures. Furthermore, it provides illustrative plots to highlight key features of the dataset.
1 September 2026 in IEEE Robotics and Automation Letters