To address the challenge of simultaneously ensuring tracking accuracy, safe bottom clearance, and compliance with actuator constraints for an autonomous undersea vehicle(AUV) operating near complex seabed terrain, this paper proposes a terrain-following method based on sliding-window B-spline planning and a meta-learning-based, weight-adaptive linear time-varying model predictive control(LTV-MPC) strategy. The planning layer employs cubic B-splines subject to slope constraints to generate a reference path that maintains a prescribed altitude margin, while a sliding-window mechanism balances local optimization with global continuity. The control layer implements an LTV-MPC controller equipped with a meta-learning network that adaptively adjusts the cost-function weights online based on features such as terrain curvature, depth error, and attitude error, thus accommodating variations in tracking difficulty across different terrain conditions. The meta-network parameters are trained offline through Bayesian optimization using closed-loop simulation data from multiple synthetic terrains, enabling the network to learn the mapping between terrain features and optimal weights. In the online stage, only forward inference is required, resulting in high computational efficiency. In the specified simulation scenarios, validation using synthetic and measured terrain data demonstrates that the proposed method reduces the root-mean-square(RMS) tracking error by 42.5% and 31.3%, respectively, compared with line-of-sight guidance combined with proportional-integral-derivative control(LOS-PID). Compared with standard LTV-MPC, the RMS tracking error is reduced by 4.5% and 6.1%, respectively. Meanwhile, the pitch-angle and rudder-angle constraints are satisfied, effectively resolving the trade-off between tracking accuracy and safety under complex terrain conditions.
The low-speed control performance constitutes a fundamental prerequisite for the propulsion system of unmanned undersea vehicle to execute critical missions such as deep-sea exploration and military reconnaissance effectively. In response to the need for enhanced control capabilities during low-speed operations, limitations in permanent magnet synchronous motor drive systems employing both schemes with and without position sensor were systematically examined. Resolvers tend to introduce position detection errors under harsh environmental conditions. However, among dominant sensorless solutions, due to inherent observation dead zones near zero speed in back-electromotive-force observers, high-frequency signal injection methods improve low-speed observation performance, but their accuracy remains susceptible to motor parameter variations. Moreover, the accuracy of all sensorless control schemes exhibits high dependence on current sampling precision, making such schemes vulnerable to severe engineering challenges in complex disturbance-intensive operating conditions. To resolve these issues, a hybrid observation-based low-speed disturbance rejection control strategy integrating resolver with high-frequency square wave injection was proposed. By applying hardware redundancy and information fusion techniques, the deep integration was achieved between the absolute position reference provided by resolvers and dynamic observations generated through high-frequency square wave injection. An advantage-complementary observation architecture was established to significantly enhance system robustness in difficult scenarios including low-speed operations, variable loading conditions, and signal interference contexts. Simulation results verify the capability of the proposed method to effectively suppress detection error disturbance from position sensors and current sensors, enabling stable and precise rotor position observation and delivering a high-reliability control solution for underwater equipment power systems.
With the continuous development of marine conservation and exploration, traditional underwater actuation devices have inherent drawbacks such as complicated structures and low motion efficiency. Flexible materials have gradually become a research focus in the field of underwater biomimetic actuation due to their advantages of strong adaptability, high safety, and sufficient flexibility. Relying on the material advantages of high energy density and high electromechanical coupling efficiency of electroactive polymer(EAP), and combining the flexural deformation and elastic recovery effects of a spring, this paper designed a cylindrical biomimetic caudal fin actuator by simulating the periodic deformation process of contraction and relaxation of the body-caudal fin(BCF) propulsion mode, which could achieve the continuous compliant changes of the caudal fin muscle. Based on hydrodynamic theory, this study systematically analyzed the coupling mechanism between the movement law of the caudal fin and the propulsion force, constructed an instantaneous mechanical model of fin ray oscillation, and integrated experimental data for solution. Furthermore, this study established a three-dimensional numerical simulation model using Fluent software and verified the effectiveness of the model through the comparative analysis between the dynamic mesh calculation results and the mechanical model prediction results. This study provides theoretical support and experimental basis for the design and development of new biomimetic fish.
In the complex underwater acoustic countermeasures where underwater high-speed maneuvering platforms face the coexistence of true and false targets, incorrect target selection may lead to the escape of true high-value targets. Traditional non-targeted research strategies are inefficient, necessitating an in-depth analysis of high-value target countermeasure strategies, comprehensive consideration of their maneuverability and tactical choices, and the formulation of targeted counter-countermeasure and research strategies. Based on the analysis of high-value target countermeasure strategies, a target escape area model was constructed, and a probability estimation method was proposed for lost target escape areas to predict the escape probability of targets within the countermeasure area. The simulation results indicate that this method helps improve the success rate of target re-search and reduce the search time of underwater high-speed maneuvering platforms, thus enhancing overall search efficiency.
To counter the threat posed by undersea vehicle stealth and meet the demand for the development of non-acoustic detection technology, this study focused on the action mechanism of electromagnetic effects induced by vehicle wakes in density-stratified ocean environments. Existing studies on wake electromagnetic fields are mostly based on the uniform fluid assumption, neglecting the effects of internal waves induced by stratification. To this end, this paper innovatively built a mathematical model for the velocity field of undersea vehicle wakes in stratified fluid, decomposing the wake into a linear superposition of surface wave and internal wave components, with the expression for wake-induced electromagnetic fields derived. By conducting numerical simulations, the spatial distribution, attenuation patterns, and component contributions of the induced magnetic field were analyzed for undersea vehicles at depths ranging from 10 m to 50 m. The results indicate that under stratified environments, the surface wave-induced magnetic field reaches the peak value of 0.15 nT in the near field but decays rapidly with distance. In contrast, the internal wave-induced magnetic field only has a peak value of 0.006 nT in the near field, and it features stable waveform coherence and slow decay, becoming dominant in the far field. Furthermore, as the submergence depth of the vehicle increases, the contribution of the internal wave grows significantly, reaching 84.9% in the near field at a depth of 50 m. This study reveals that as the key physical quantity for far-field detection, internal waves provide a theoretical basis for the development of long-range non-acoustic detection technologies for undersea vehicles.
To address delayed observations caused by acoustic communication in cooperative operations of multiple unmanned undersea vehicles(UUVs), a cooperative encirclement method based on delay-robust multi-agent reinforcement learning was proposed. First, the mechanism of delayed observations was analyzed under common communication scenarios. Second, a turbulent flow field was modeled using the two-dimensional Navier-Stokes equations to construct a simulation environment that reflects realistic task settings. Then, a delay-robust multi-agent reinforcement learning method was proposed, and its constituent modules were described in detail. On this basis, the reward functions for the encirclement task, the network architectures, and the training procedures were designed, and ablation studies were conducted under different tasks and delay conditions. Experimental results demonstrate that the proposed method effectively handles delayed observations and maintains strong performance under varying delay levels, approaching the theoretical upper bound of the no-delay case in some tasks. Furthermore, the ablation results verify the effectiveness of each module in mitigating delayed observations, providing new theoretical support and a practical methodology for multi-UUV cooperative strategies under delayed observations.
The demand for high-fidelity seafloor scene reconstruction is growing in fields such as marine scientific surveying and underwater environmental exploration. As an advanced explicit scene representation method, three-dimensional(3D) Gaussian Splatting holds significant application potential for seafloor reconstruction and novel view synthesis. However, influenced by factors such as blurring effects caused by underwater imaging media, the results often exhibit defects including medium-induced artifacts and structural distortions, severely limiting the applicability of this technique in real-world complex underwater environments. To address these challenges, the paper proposed a high-fidelity 3D seafloor scene reconstruction method based on a cross-dimensional Gaussian normal transition field. In this method, a cross-dimensional mapping and normal transition system for Gaussian primitives was constructed, enabling fine-grained geometric modeling of complex structures. A Gaussian opacity-weighted filtering model was then presented to suppress reconstruction artifacts caused by medium-induced blurring effects. Experimental results on various underwater scenes demonstrate the proposed method’s capability to efficiently reconstruct complex underwater scenes and synthesize novel views.
High-precision trajectory backtracking technology for drifting buoys is urgently needed for maritime search and rescue and pollution source tracing, yet traditional Lagrangian models exhibit significant errors in complex marine environments. A physics-driven trajectory backtracking model was proposed for marine drifting buoys. A dynamic diffusion coefficient based on autocorrelation analysis of wind flow field time series was innovatively introduced to optimize the subgrid velocity compensation mechanism in random walk models. The model integrates a drift kinetics framework incorporating wind driving force, ocean current drag force, and Coriolis force, and combines Monte Carlo simulation with kernel density estimation to quantify the spatio-temporal uncertainties in trajectory backtracking. Based on buoy data from the North Atlantic Ocean Internet of Things, four typical marine environments were selected, namely, tropical open ocean, current convergence zones, temperate westerlies, and nearshore complex terrains, to complete 72-hour trajectory backtracking validation. According to the result, the proposed model achieves 72-hour trajectory backtracking errors of only 3.9~5.8 km. Compared with the traditional Lagrangian models, accuracy improvements of 74%, 55%, 59%, and 22% are achieved in the four sea areas, respectively. The trajectory backtracking accuracy in complex marine environments is significantly improved, providing reliable technical support for maritime emergency rescue and pollution source localization.
Passive acoustic monitoring-based call recognition and classification are essential means for marine animal conservation and population surveys. To address the issues of data scarcity and inter-class imbalance in call recognition and classification, data augmentation methods hold significant practical value and research importance. However, marine animal calls contain rich acoustic information, and relying solely on frequency-domain feature extraction lacks the capability to model audio structure and semantics, making it difficult to effectively capture the deep features of calls. To this end, a data augmentation network based on a multi-modal masked autoencoder with multi-modal fusion(MAE-MF) is proposed in this paper, which breaks through the limitations of single-modal information. The network employed Mel-spectrograms as the primary modality, integrated temporal features and frame-level statistical metrics to form multimodal inputs, and incorporated semantic labels as conditional guidance for reconstruction. Meanwhile, gated fusion and cross-attention mechanisms were combined to enhance multimodal information interaction and feature representation capability. Experiments conducted on the Watkins dataset show that compared with mainstream algorithms, the proposed method achieves better spectrogram reconstruction performance. The average recognition accuracy for six cetacean species reaches 97.6%, which is 6.72% higher than that of the baseline MAE method. This scheme can effectively alleviate the class imbalance problem, enhance the recognition capability for complex acoustic features and weak calls, and provide reliable technical support for cetacean conservation efforts.
Most existing studies on vehicles with water-exit ice-breaking capabilities primarily focus on vertical ice-breaking, lacking investigations into the influence of oblique angles on ice-breaking performance. Therefore, a numerical model for the oblique water-exit and ice-breaking process of a vehicle was built based on the arbitrary Lagrangian-Eulerian(ALE) fluid-solid coupling algorithm. The effects of the oblique angle, initial velocity, and ice thickness on the load and motion characteristics of the vehicle were systematically analyzed. The results indicate that during the initial ice-breaking stage, the impact of the vehicle’s conical head induces intense local stress concentration in the ice. This leads to the early initiation of radial cracks at the top surface, followed by failure originating from the center. The center of the resultant force on the vehicle deviates from its axis, causing an exacerbated deflection along the initial oblique direction. Additionally, this trend becomes more pronounced as the initial velocity and ice thickness increase. During the subsequent ice-breaking process, in low velocity and thick ice conditions for the θ=10° case, the vehicle’s attitude follows a “deflection-recovery” pattern. In high velocity and thin ice conditions, it transitions to a “deflection-steady flight” pattern. The research findings provide reference for the design and development of polar cross-media vehicles.
The unmanned lifeboat is prone to yawing due to external water flow interference because of its light weight. To address the issue, this paper designed a cross-coupling speed cooperative control method for dual propulsion motors based on a sliding mode speed distributor. First, a motor control model was built for the turning radius and rotational speed difference of the unmanned lifeboat. Then, a dual-propulsion motor speed cooperative control system was designed based on cross-coupling control. Finally, a speed distributor based on sliding mode control was developed to adjust the given speeds of the two propulsion motors, enabling the hull to resist external water flow interference and achieve smooth navigation. The simulation results prove that the proposed control method can allocate different set speeds for the dual-propulsion motor based on the actual situation, thereby enabling more accurate course control of the unmanned lifeboat.
To address the problem of optimizing multi-agent collaborative search path planning to maximize cumulative detection probability, a multi-agent reinforcement learning model was developed. A multi-agent collaborative search algorithm based on Deep Q-Network(DQN), Joint-DQN, was proposed. It enhanced the collaboration efficiency and stability among multiple platforms by designing an experience knowledge sharing mechanism. It introduced a conflict detection mechanism and imposed penalties, effectively addressing the frequent path conflicts in multi-agent collaboration research. In addition, it designed a composite reward function to improve search coverage and reduce the rate of duplicate searches. Simulation experimental results demonstrate that this algorithm can effectively guide search platforms to avoid obstacles while efficiently moving in the direction where the target is most likely to be found, both in static and dynamic target scenarios. It rapidly enhances the cumulative detection probability while conducting efficient search, providing theoretical support and valuable guidance for multi-agent collaborative search path planning.
With the development of unmanned undersea vehicle(UUV) swarm operations, the detection and recognition of multiple complex underwater targets have attracted significant attention. Therefore, a fast computational model based on the planar element method was built to improve computational accuracy and efficiency. Initially, an improved planar element method was employed to calculate the target characteristics of a dual-target model. The method was validated by comparing the calculated results with physical field simulation results and experimental measurements obtained in an anechoic water tank. To enhance computational efficiency, the OpenMP parallel algorithm was introduced. To accommodate the varying computational loads involved in calculating the scattered acoustic field characteristics of multiple complex targets at different incident angles and frequencies, the loop-iteration scheduling mechanism was optimized, achieving effective load balancing across threads and a 5.3-fold speedup. This fast algorithm was then applied to investigate more complex multi-target models. Analysis of the angle-frequency maps of target characteristics revealed regular variations in the high-frequency scattered acoustic field characteristics of multiple targets with increasing frequency, with target strength exhibiting extrema at certain angles. Meanwhile, high-frequency interference fringes were observed. The correlation between scattering characteristics and geometric positions was analyzed. The research results provide a theoretical reference for the acoustic detection and characterization of underwater targets.
To improve the traversal path planning capability of autonomous undersea vehicle(AUV), this paper proposed an AUV traversal path planning algorithm based on an advanced Munchausen deep Q-network(AMDQN). First, the paper established a traversal planning environment suitable for practical scenarios. On the one hand, the ray coverage method was used instead of the traditional rectangular grid modeling method to improve modeling accuracy; on the other hand, the optional action set of the AUV was constrained to limit its maneuverability. Second, each component of the algorithm was carefully designed under the above environment. Specifically, in the state space design, the paper fused vague global environmental information, accurate local environmental information centered on the AUV, and the AUV’s own position information to systematically represent the environment. In the reward function design, rule penalty and edge guidance were introduced, enabling the AUV to stably improve coverage along environmental edges. For the parameter update method, an adaptive temperature parameter update strategy was designed based on DQN, while the multi-step reward and a dueling network architecture were introduced to alleviate training variance. During the training process, a soft reset of fully connected layer parameters was adopted to mitigate the local optimum problem. The simulation results show that the proposed algorithm has stronger environmental adaptability and higher traversal coverage than traditional methods and unimproved reinforcement learning algorithms.
In response to the excessive tracking error caused by tangential jumps at switching points during the piecewise linear path tracking of autonomous undersea vehicle(AUV), an online path optimization method was proposed based on overlapping sliding windows. This method overlaps the windows to enable the new window to inherit the latter part of the optimization results from the previous window, thereby mitigating the end effect and decision myopia. The parameterized cubic Bezier curve(PCBC) algorithm is preferably selected to optimize the path in the window. When this algorithm is not applicable, an improved particle swarm optimization(PSO) is used to optimize the control points of cubic Bezier curve, so as to obtain optimized path segments that meet the performance requirements. To achieve high-precision tracking of the optimized path segments by the AUV, an improved line-of-sight(LOS) guidance was designed based on an adaptive look-ahead distance. The look-ahead distance was dynamically adjusted by fusing tracking error, path curvature, and speed to improve guidance accuracy. Simulation analysis and sea trials verify the superiority of the improved LOS and the engineering practicability of its integration with the path optimization method.
Autonomous undersea vehicles(AUVs) play an important role in ocean engineering, marine scientific exploration, and military operations. The energy and power system is one of the core subsystems of AUVs, and its performance directly influences the vehicle’s endurance, operational range, and operational efficiency. AUVs were classified from the perspectives of overall dimension, diving depth and operation scenarios, and the technical characteristics and engineering application status of energy and power systems for various AUVs were systematically analyzed. The emphasis was placed on key energy and power technologies, including high-energy-density battery technology, underwater wireless charging methods, high-density hydrogen/oxygen storage technology, and battery management technology. Finally, the development directions of AUV energy and power technologies were prospected to provide valuable insights for the development of AUV energy and power systems.
Structural shock vibration signals induced by underwater explosions exhibit strong non-stationarity and broadband superposition. Conventional modal decomposition methods are prone to mode mixing and energy leakage, making it difficult to achieve stable frequency-band separation. To address these issues, an adaptive modal decomposition(AMD) method for underwater-explosion-induced shock vibration was proposed. The method was based on frequency-domain parametric modeling, in which the response spectrum was represented by basis functions with local support and adjustable scale. The dominant frequency components were adaptively extracted and reconstructed via the joint optimization of center frequency, bandwidth, and amplitude parameters together with pruning constraints. A numerical simulation of an underwater-explosion stiffened-plate structure was used as an example, and AMD was systematically compared with empirical mode decomposition, variational mode decomposition, and empirical wavelet transform. The results indicate that AMD achieves near-lossless reconstruction, with a maximum inter-modal cross-correlation coefficient of approximately 17.7% and an average spectral overlap ratio of 2.7%, both significantly lower than those of the compared methods, demonstrating its effectiveness for shock-vibration signal analysis under underwater explosion.
An integrated cable-free monitoring architecture comprising an unmanned surface vehicle(USV), a tether management system(TMS), and an autonomous/remotely operated vehicle(ARV) was developed to break through the bottlenecks of traditional wired monitoring for touchdown points(TDPs) during deepwater subsea pipeline laying, including high operation cost, complicated multi-vessel coordination and poor real-time performance. Meanwhile, an underwater wireless optical communication(UWOC) scheme applicable to deepwater vertical links was proposed. Considering the stratified variation of optical parameters with water depth in heterogeneous deepwater channels, a vertical channel model coupling wavelength and depth was built. The Monte Carlo photon tracing method with the Henyey-Greenstein(HG) phase function was adopted to replace the traditional constant transmittance approximation and thus realize accurate mapping from physical characteristics to engineering parameters. In terms of system implementation, the hardware integrates blue-green LED array with secondary light distribution and large-aperture photomultiplier tubes(PMTs), forming a highly redundant architecture of wide-angle transmission and wide field-of-view reception. At the software level, sliding window statistics-based adaptive threshold and automatic gain control were introduced to achieve dynamic coordination between transmit power and reception sensitivity, thus greatly reducing the system’s reliance on high-precision alignment. Tank tests verify the alignment tolerance and stability of the system at rates ranging from 6 Mbit/s to 20 Mbit/s. Offshore sea trials achieved stable communication over a link distance of up to approximately 17 m and error-free video backhaul at the rate of 6.25 Mbit/s, which validates the engineering robustness of the system under dynamic platform disturbance and ambient light fluctuations. It is confirmed that the proposed scheme possesses favorable field transferability. It can support continuous TDP monitoring without additional multi-purpose support vessels(MSVs), providing a reliable technical route for intelligent and lightweight operations of deepwater oil and gas equipment.
The precise detection and identification of small underwater targets, such as micro underwater vehicles and small underwater detectors, constitute important technical support for fields including marine resource development, underwater security early warning, and underwater engineering inspection. Constrained by the combined effects of water body attenuation, optical scattering, acoustic multipath effect, and complex background noise, traditional detection technologies exhibit notable limitations in terms of effective detection range, spatial resolution, and real-time responsiveness. With the advancement of marine development toward refinement and intelligence, coupled with the increasingly prominent strategic value of underwater unmanned equipment countermeasures, optical detection technology for underwater small targets has emerged as a research hotspot in the domain of marine information technology. This paper systematically sorted out the research background and strategic significance of optical detection technology for underwater small targets and presented a comprehensive review focusing on two major technical approaches: image-based and LiDAR-based methods. For the image-based technical system, the paper centered on two core modules, namely image enhancement and target detection and conducted an in-depth analysis of the principle mechanism, improvement strategies, and performance characteristics of various technologies. For the LiDAR-based technical system, aiming at detection modes including area-scan imaging, point-scan imaging, and line-scan imaging, the paper systematically elaborated on their technical features and typical application scenarios. Furthermore, this paper analyzed the bottleneck problems faced by existing technologies and prospected future research directions in combination with the development trend of marine technology, so as to provide theoretical support for the engineering implementation of optical detection technology for underwater small targets.
To address the challenges of magnetic signal acquisition in complex shallow-sea environments, this study designed and constructed a split towed system equipped with a fluxgate array. This system efficiently collected magnetic environmental noise and magnetic anomaly signals from four typical small ferromagnetic targets under dynamic conditions, successfully establishing a corresponding real-world measurement dataset. To compensate for the limitations of measured data and enhance data diversity, based on the characteristics of measured data, a simulation dataset containing the passage characteristic curves of four types of target magnetic sources was constructed using COMSOL multiphysics simulation software, providing data support for model training. To meet the requirements of real-time detection and localization of magnetic sources, this study proposed a magnetic source localization method, named 1D ViT-ResNet, based on the collaboration of a one-dimensional vision transformer(1D-ViT) detection model and a one-dimensional residual network(1D-ResNet) localization model. Validation results using measured target signals show that the algorithm achieves a mean localization estimation error of approximately 7%. Compared with single-model approaches, the dual-model method reduces the false detection rate by an average of 11 percentage points, significantly improving the accuracy and reliability of underwater magnetic detection.
