IEEE Journal of Oceanic Engineering最新文献

{"title":"Sonar-Based Deep Learning in Underwater Robotics: Overview, Robustness, and Challenges","authors":"Martin Aubard;Ana Madureira;Luís Teixeira;José Pinto","doi":"10.1109/JOE.2025.3531933","DOIUrl":"https://doi.org/10.1109/JOE.2025.3531933","url":null,"abstract":"With the growing interest in underwater exploration and monitoring, autonomous underwater vehicles have become essential. The recent interest in onboard deep learning (DL) has advanced real-time environmental interaction capabilities relying on efficient and accurate vision-based DL models. However, the predominant use of sonar in underwater environments, characterized by limited training data and inherent noise, poses challenges to model robustness. This autonomy improvement raises safety concerns for deploying such models during underwater operations, potentially leading to hazardous situations. This article aims to provide the first comprehensive overview of sonar-based DL under the scope of robustness. It studies sonar-based DL perception task models, such as classification, object detection, segmentation, and simultaneous localization and mapping. Furthermore, this article systematizes sonar-based state-of-the-art data sets, simulators, and robustness methods, such as neural network verification, out-of-distribution, and adversarial attacks. This article highlights the lack of robustness in sonar-based DL research and suggests future research pathways, notably establishing a baseline sonar-based data set and bridging the simulation-to-reality gap.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1866-1884"},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physics-Informed Neural Networks for Modeling Ocean Dynamics and Parameter Estimation: Leveraging Ocean Reanalysis Data","authors":"Shuang Hu;Meiqin Liu;Senlin Zhang;Shanling Dong;Ronghao Zheng","doi":"10.1109/JOE.2025.3538927","DOIUrl":"https://doi.org/10.1109/JOE.2025.3538927","url":null,"abstract":"Advancements in ocean reanalysis and satellite remote sensing products have opened unprecedented opportunities for using large-scale data sets to analyze and model ocean dynamics. This article utilizes the China Ocean Reanalysis Second Edition (CORA2) data set to model and estimate parameters for the ocean dynamics off the East Coast of China. A novel approach combining physics-informed neural networks with characteristic-based split is innovatively proposed to effectively analyze dynamics issues, such as surface waves and tides under open boundary conditions. This method estimates the boundary amplitude of incoming waves using multiple time-series flow field data from coastal areas in China, and uses these estimates to predict future flow field changes. By comparing with the CORA2 data set, the method not only confirms its high accuracy and reliability but also significantly improves the alignment between model predictions and actual observational data by incorporating estimates of seabed friction coefficients. This reveals the effectiveness of using large-scale data sets in conjunction with physical equations to enhance the accuracy and computational precision of ocean dynamics modeling.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2248-2260"},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Gradient-Based Path Following Control Method for Underactuated Autonomous Marine Vehicle","authors":"Zishi Xu;Shiming He;Weijun Zhou;Yanjun Li;Ji Xiang","doi":"10.1109/JOE.2025.3529126","DOIUrl":"https://doi.org/10.1109/JOE.2025.3529126","url":null,"abstract":"Due to their underactuation, motion control for autonomous marine vehicles (AMVs) has always been a tricky problem. Most current path following control methods for underactuated autonomous marine vehicles apply geometric projection to map position error to yaw angle in order to decouple the yaw thrust moment in the controller design. However, there will be deviations in the geometric projection because of sideslip, especially when external disturbances exist. Moreover, the performance of the geometric projection method is greatly affected by the look-ahead distance. In this article, a novel path following control method for underactuated AMVs is proposed. This method directly takes the position of a point as the control object, with the process of geometric projection eliminated, thereby getting rid of the negative impact of sideslip. The desired path is modeled as a scalar field, and the commanded position is taken to lie along the direction of the gradient of this scalar field at the kinematics level. At the kinetics level, disturbance rejection capability is constructed by applying disturbance observers and compensating for the estimated disturbances in the control effort. It is proved that all signals in the closed-loop system are uniformly ultimately bounded. Simulation and experimental results demonstrate that the proposed method is effective.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1855-1865"},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Underwater Image Enhancement via Piecewise Colour Balancing and Multiscale Enhancement Fusion","authors":"Zheng Liang;Haohui Huang;Weidong Zhang;Hang Song;Xinwen Wan;Chuanjian Wang;Linsheng Huang;Peixian Zhuang","doi":"10.1109/JOE.2025.3555684","DOIUrl":"https://doi.org/10.1109/JOE.2025.3555684","url":null,"abstract":"Underwater images often suffer from multiple degradation issues, such as color casting, low contrast levels, and blurry details, which limits the applicability of underwater images in ocean exploration tasks. An underwater image enhancement method implemented via piecewise color balancing and pyramid-based contrast enhancement (PBPE) is proposed in this article. Concretely, PBPE first uses a reference channel with the maximum mean and two gain factors to balance the differences among the r, g, and b channels. PBPE presents a pixelwise transmission estimation method that is based on the mapping between the transmission and the backscattered light. Specifically, an adaptive compensation strategy is proposed to adaptively refine the transmission. Finally, PBPE captures a detail pyramid via multiscale Gaussian decomposition and uses the estimated transmission to remove haze and increase the degree of detail, thereby enhancing the overall contrast level of the underwater image. Comprehensive experiments conducted on two underwater image enhancement data sets indicate that our PBPE approach achieves better results and outperforms the state-of-the-art methods; i.e., compared with those of the second-best method, the average blur and density of the fog assessment-based defogger values of our method decrease by at least 2.67% and 4.55%, respectively, which shows that our method achieves enhancement results with high contrast levels and natural appearances.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1960-1977"},"PeriodicalIF":3.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Analysis of the Cable-Releasing Phase for the Underwater Glider on Mooring Mission","authors":"Xiaoxu Du;Xin Liu;Miao Li;Dong Song","doi":"10.1109/JOE.2025.3550996","DOIUrl":"https://doi.org/10.1109/JOE.2025.3550996","url":null,"abstract":"The blended-wing-body underwater glider (BWB-UG) represents a novel mobile ocean exploration platform. In order to enable the device to perform long-term monitoring at fixed locations, a mooring mission with a cable is proposed. The cable-releasing phase represents a pivotal moment in the mooring mission, as it determines the success of the mission and the stability of the multibody system in motion. Consequently, this article examines the dynamics of the BWB-UG during the cable-releasing phase. A mathematical model of the cable release strategy has been established. A solution algorithm for the cable length increase is established based on the concentrated mass method and the multibody dynamics method. The analysis of the factors influencing the multibody system during the cable release phase has been completed. The effects of three movement patterns, namely downward gliding, upward gliding and straight navigation, are analyzed. The impact of ocean current magnitude and direction on the system is analyzed. The impact of the cable laying position and quantity on the system is analysed. The mechanism of the factors influencing the dynamics of the multibody system during the cable-releasing phase is elucidated.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2030-2049"},"PeriodicalIF":3.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatial Domain Dedispersion Transform and Its Application to Source Localization","authors":"Hongchen Zhang;Shihong Zhou;Yubo Qi;Changpeng Liu","doi":"10.1109/JOE.2025.3558827","DOIUrl":"https://doi.org/10.1109/JOE.2025.3558827","url":null,"abstract":"Due to the multipath and dispersion effects inherent in low-frequency sound propagation within the shallow-water waveguide, localization algorithms that do not account for these underwater acoustic propagation phenomena exhibit significant estimation biases and gain degradation. Furthermore, the increasing complexity of the ocean environment due to human activities necessitates enhanced performance of localization algorithms, particularly under the condition of multiple target interference and low signal-to-noise ratio. To address these challenges and mitigate estimation biases, this article proposes a localization algorithm for a horizontal array that employs the spatial dedispersion transform combined with the frequency domain accumulation (SDDT-FDA) algorithm. The SDDT-FDA is applied to signals received by horizontal arrays under different assumed source locations. It is demonstrated that a distinct multipeak structure in the results emerges only when the assumed source location matches the actual source location, thereby enabling the inference of the source location. This article presents the theoretical proof, discusses the impact of various parameters on performance, and provides simulation analyses and validation results based on experiment data.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1822-1835"},"PeriodicalIF":3.8,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Method for the Simulation and Removal of Multibeam Echosounder Water Column Data Artifacts","authors":"Amy W. Nau;Vanessa Lucieer;Yoann Ladroit;Haris Kunnath;Tara Martin","doi":"10.1109/JOE.2024.3525157","DOIUrl":"https://doi.org/10.1109/JOE.2024.3525157","url":null,"abstract":"Modern multibeam echosounders collect bathymetric soundings, seafloor backscatter intensities, and water column backscatter values. The water column data can be used to identify features or biology above the seafloor with a broad range of applications. A key limitation for the analysis of this data is the presence of intrinsic system artifact patterns due to transducer design and receiver-array sidelobe-induced signal interferences. In this article, a method is described for simulating and removing these artifacts based on a “reference ping,” created using a subset of clear water data, which captures intrinsic artifacts present in the original data set. This reference ping, after adjusting for the range and seafloor amplitude values of each ping, is used to simulate ping-specific artifact patterns (“simulated ping”), which can be removed from the original data for improving target identification within the water column. This method was applied to five different Kongsberg Discovery multibeam echosounder systems covering a range of operational characteristics. Comparison of simulated pings with clear water data acquired by all systems shows greater than 0.9 <italic>R</i>² correlation, highlighting the efficacy of the method to reproduce intrinsic system artifacts prevalent in commonly used multibeam echosounders. The root-mean-squared error between simulated pings and original data was used to demonstrate the method's effectiveness in removing artifacts, with values of <0.04 for all systems. Large values were also used to identify potential features of interest within the water column. This method provides a promising foundation for improved water column analysis, either as a stand-alone method or combined with other current processing methods.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2296-2310"},"PeriodicalIF":3.8,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10944661","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiometric Beam Pattern Extraction and Relative Calibration Method for Backscatter Strength Data from Motion-Stabilized Multibeam Systems","authors":"Anand Hiroji;John Hughes Clarke","doi":"10.1109/JOE.2025.3553936","DOIUrl":"https://doi.org/10.1109/JOE.2025.3553936","url":null,"abstract":"Multibeam sonar backscatter strength (BS) data are increasingly being utilized for seafloor substrate classification, which is a vital component of fisheries, habitat mapping, and many offshore engineering applications. The artifacts in the BS data must be minimized before classification is attempted. This paper looks at the artifacts in BS data due to the radiometric effects of the transmit and receive array. This is particularly confounded for the multisector geometry, where the across-track transmit lobes of individual sectors are much narrower compared to a single sector system. These multisector systems have significant variations in the source level within a sector (up to 8 dB) and between sectors (up to 5 dB). This article also addresses the additional factors affecting the measured intensities due to the roll, pitch, and yaw motion stabilization. To address these complications, a new method is developed to unambiguously compute individual sector-specific radiometric beam pattern (RBP) residuals for the combined effect of the transmit and receiver arrays. For a given frequency and azimuth, the BS of a particular seabed type depends only on the grazing angle, any apparent change in the BS at a given grazing angle due to ship's motion is caused by radiometric properties of the sonar. This is the basic principle used in the development of the new method. The developed method separates the received intensities first based on grazing angles and then further by various sonar-relative angles in along- and across-track. The intensity variations within a given grazing angle for different sonar relative angles are used to estimate variations in the combined transmitter and receiver radiometric effects. This article describes the developed RBP extraction method using real data collected with Kongsberg EM 710 multisector multibeam system. It also demonstrates corrected BS data with minimized transmit and receive radiometric effects. It is estimated that the presented method reduced backscatter uncertainty due to motion artifacts by up to 2 dB, enabling improved seafloor characterization based on quantitative analysis of BS data.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2261-2279"},"PeriodicalIF":3.8,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11015331","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Direct-Adaptive Turbo Equalization Based on Interference Reconstruction for OTFS Underwater Acoustic Communication System","authors":"Lianyou Jing;Zhekai Xue;Chengbing He;Tonghui Zheng;Xingyu Cao","doi":"10.1109/JOE.2025.3531992","DOIUrl":"https://doi.org/10.1109/JOE.2025.3531992","url":null,"abstract":"Orthogonal time frequency space (OTFS) modulation has recently gained recognition as a promising modulation scheme for high-mobility communication systems. It offers significant advantages in terms of error performance compared to orthogonal frequency division multiplexing in time-varying channels. In this article, we apply OTFS modulation to mobile underwater acoustic (UWA) communication. We propose an adaptive turbo equalization technique with a 2-D decision feedback equalizer to address the issue of 2-D interference. To mitigate the performance degradation caused by phase flipping and circular convolution in the delay-Doppler domain, we further propose a 2-D DA-TEQ based on interference reconstruction. An adaptive channel estimation based on the improved proportionate normalized least mean squares algorithm is proposed to reconstruct the interference. To validate the proposed OTFS UWA communication schemes, a lake experiment was conducted in Danjiangkou Lake, Henan, China, in July 2022. The experimental results demonstrate that the proposed scheme achieves satisfactory performance at a speed of 4.5 knots, with a data rate of 5.79 kbps. This experiment confirms the effectiveness of OTFS modulation for mobile UWA communication.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1469-1482"},"PeriodicalIF":3.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Path Following With Finite-Time Convergence for Unmanned Surface Vehicle","authors":"Yanwei Huang;Guozhen Lai;Feng Lin;Xiaocheng Shi;Dongfang Li","doi":"10.1109/JOE.2024.3483328","DOIUrl":"https://doi.org/10.1109/JOE.2024.3483328","url":null,"abstract":"A path-following control scheme is proposed using finite-time convergence line-of-sight (FCL) to achieve rapid convergence of position errors for an unmanned surface vehicle (USV). FCL combines classical line-of-sight (LOS) guidance with finite-time stability theory to ensure that the position of the USV converges to the reference path within a predetermined finite time. Specifically, a USV model is developed to analyze target tracking. Moreover, a novel cross-tracking error function is designed with hyperbolic characteristics for FCL through an analysis of the relationship between convergence speed and cross-tracking error function. Further, the path-following system stability with FCL and finite-time controllers is analyzed to indicate the smaller value of the upper bound of the system convergence time by comparisons. Finally, simulations and experiments are performed to verify that FCL has a faster convergence speed than the LOS with error sign function (LS) and the linear cross-tracking error function (LLCF), and a wider algorithm parameter tuning range compared to LS.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1153-1164"},"PeriodicalIF":3.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}