Owing to environmental constraints, it is challenging to stably conduct various missions or surveys of the seabed for a prolonged period in the marine environment. To address this challenge, several devices and technologies are being developed. In this study, we aimed to develop an unmanned underwater vehicle (UUV)—specifically, a towed underwater platform—that can be loaded and unloaded via joint operation with an unmanned surface vehicle, which can be connected to a wired cable to obtain a stable power supply and high-speed communication. In addition, various sensors for detection are employed to investigate the marine environment and conduct missions. Furthermore, we operated the developed UUV in actual waters, reviewed the results, and examined its practical operability.

The construction industry is a challenging field for the application of robots. In particular, bridge construction, which involves many tasks at great heights, makes it difficult to implement robots. To construct a bridge, it is necessary to build numerous piers that can support the bridge deck. Pier construction involves a series of tasks including rebar connection, formwork installation, concrete pouring, formwork dismantling, and formwork reinstallation. These activities require working at heights, presenting a significant risk of falls. If bridge construction could be performed remotely using robots instead of relying on human labor, it would greatly contribute to the safety of bridge construction. This paper proposes a multi-robot system capable of remote operation and automation for rebar structure connection, concrete pouring, and concrete vibrating tasks in pier construction. The proposed multi-robot system for pier construction is composed of three robot systems. Each robot system consists of a robot arm mounted on a mobile robot that can move along rails. And to apply the proposed system to a construction site, it is essential to implement a compliance control algorithm that adapts to external forces. In this paper, we propose an admittance control that takes into account the weight of the tool for the compliance control of the proposed robot, which performs tasks by switching between various construction tools of different weights. Furthermore, we propose a synchronization control method for the multi-robot system to connect reinforcing structures. We validated the proposed algorithm through simulation. Furthermore, we developed a prototype of the proposed system to verify the feasibility of the suggested hardware design and control.

Despite major economic and technological advances, much of the ocean remains unexplored, which has led to the use of remotely operated vehicles (ROVs) and gliders for surveying. ROVs and underwater gliders are essential for ocean data collection. Gliders, which control their own buoyancy, are particularly effective unmanned platforms for long-term observations. The traditional method of recovering the glider on a small boat is a risky operation and depends on the skill of the workers. Therefore, a safer, more efficient, and automated system is needed to recover them. In this study, we propose a lightweight artificial neural network for underwater glider detection that is efficient for learning and inference. In order to have a smaller parameter size and faster inference, a convolutional neural network (CNN) vision encoder in an artificial neural network splits an image of a glider into a number of elongated patches that overlap to better preserve the spatial information of the pixels in the horizontal and vertical directions. Global max-pooling, which computes the maximum over all the spatial locations of an input feature, was used to activate the most salient feature vectors at the end of the encoder. As a result of the inference of the glider detection models on the test dataset, the average precision (AP), which indicates the probability that an object is located within the predicted bounding box, shows that the proposed model achieves AP = 99.7%, while the EfficientDet-D2 model for comparison of detection performance achieves AP = 69.2% at an intersection over union (IOU) threshold of 0.5. Similarly, the proposed model achieves an AP of 78.9% and the EfficientDet-D2 model achieves an AP of 50.5% for an IOU threshold of 0.75. These results show that accurate prediction is possible within a wide range of recall for glider position inference in a real ocean environment.

A variety of mission equipment is mounted and utilized on UUVs (unmanned underwater vehicles) for the development of marine resources and underwater searching for military purposes. For exploration of a wide area, it is advantageous to use a towed underwater platform, and for precision exploration to a specific location, to use an active mobile ROV (remotely operated vehicles). Since the TUV (towed underwater vehicle) moves according to the speed of the towing vessel, it cannot be operated if the vessel is stationary or the speed is low. Therefore, TUVs do not have equipment that is useful at low speeds, such as optical cameras or forward looking sonars. If a TUV capable of active movement such as stationary or low-speed operation is developed, it can search a wide area and then accurately search for a specific location, with one platform mounting various mission equipment. In this paper, we propose a method for estimating the control model for a prototype of this novel TUV, and propose a depth and posture control algorithm to which the model is applied. The proposed TUV and control algorithm were verified by experiments under the flow rate environment in the circulating water channel.

Although underwater gliders are highly energy-efficient platforms capable of long-duration and large-scale ocean observation, their lack of self-propulsion requires external assistance for recovery upon mission completion. In harsh and dynamic marine environments, reliably detecting the glider and accurately estimating its three-dimensional position are critical to ensuring the recovery operations are safe and efficient. This paper proposes a perception framework based on deep learning to detect underwater glider hulls and estimate their three-dimensional relative positions using camera–sonar multi-sensor fusion. This approach integrates a hierarchical convolutional neural network (CNN) vision encoder and a transformer-based architecture to estimate the glider’s spatial location and heading direction simultaneously. The hierarchical CNN encoder extracts multi-level, semantically rich visual features, thereby improving robustness to visual degradation and environmental disturbances common in underwater settings. Additionally, the transformer incorporates a variable mixture-of-experts (vMoE) mechanism that adaptively allocates expert networks across layers, enhancing representational capacity while maintaining computational efficiency. The resulting pose estimates enable precise, collision-free ROV navigation for automated recovery and onboard sensor inspection tasks. Experimental results, including ablation studies, validate the effectiveness of the proposed components and demonstrate their contributions to accurate glider hull detection and three-dimensional localization. Overall, the proposed framework provides a scalable, reliable perception solution that allows for the safe, autonomous recovery of underwater gliders with an ROV in realistic ocean environments.

A post-flight analysis of unmanned aerial vehicle (UAV) imagery has the potential to result in a delay in the inspection of source water. This delay can occur when visible debris or changes in the water surface necessitate a prompt response. The present study does not evaluate in-flight operation; rather, it presents a bench-level feasibility assessment of two deployment tasks—broad two-class screening and close-range debris classification—using lightweight YOLO detectors on an edge-AI camera in a host-fed configuration that approximates the timing constraints of a future UAV workflow. The YOLOv8, YOLO11, and YOLO26 models were lightweighted through structural pruning (YOLOv8) or architecture scaling (YOLO11 and YOLO26). These models were then refined through a process of fine-tuning, exported to the camera, and evaluated in terms of several metrics. The metrics encompassed training-environment accuracy, the accuracy of device-returned outputs, round-trip latency, and snapshot-based operating-load estimates. The dataset under consideration is extensive, comprising 4813 training images and 575 validation images, accompanied by 13,051 and 1615 annotations, respectively. The depth-pruned YOLOv8s variant demonstrated a significant reduction in mean round-trip latency, from 426.87 milliseconds to 231.58 milliseconds (45.75%), while the mAP@0.5 metric exhibited a decrease from 0.7018 to 0.6650, and the mAP@0.5:0.95 metric demonstrated a decline from 0.5433 to 0.5290. A class-level analysis reveals that aggregate accuracy is primarily influenced by the weaker floating-debris class, whose AP@0.5 ranges from 0.29 to 0.46, in contrast to the 0.82 to 0.94 range observed for pond/reservoir. In comparison to a matched baseline that was trained for an equivalent number of epochs with the sampler disabled, debris-biased sampling contributes 1.5 ± 0.6 mAP@0.5 points for YOLO11 and 3.6 ± 0.2 points for YOLO26 across three seed-matched pairs. The primary effect of this method is to increase floating-debris recall by 4.7–5.9 percentage points, with a concomitant small reduction in precision. The latency reduction increased the broad-inspection rate by 1.85×, provided approximately 195 milliseconds of idle margin within a 1-hertz cycle, and increased the paired far/near rate by 1.59× with two models resident on the camera. Three-seed repetitions of compact-model fine-tuning yielded 0.6717 ± 0.0033 and 0.6290 ± 0.0028 mAP@0.5. These results express detector compression in terms of operational monitoring capacity rather than model-size reduction alone, while also showing that compression by itself does not resolve the weak-class limitation that governs source-water inspection accuracy.