To tackle the problem of existing underwater vehicle covert path planning methods ignoring ambient noise fields, an automated path planning method based on a statistically characterized environmental noise field is proposed. The method involves constructing a background noise spectrum level model using Automatic Identification System (AIS) data and wind speed data. Then, a Range-Dependent Acoustic Model (RAM) is integrated to generate a statistically significant 10th percentile noise field. The result is subsequently incorporated into the sonar equation to develop a noise-considerate concealment effectiveness model, which serves as input for a noise-considerate A* path planning algorithm. Comparative analyses of path planning results demonstrate that, within the studied maritime domain, the noise-prioritized path exhibits a statistically significant reduction in the median detection range by approximately 17%, a 50% reduction in the minimum detection range, and a 20% reduction in the maximum detection range, relative to alternative paths planned with a fixed noise level assumption.
This paper aims to solve the spatial trajectory tracking control problem of underactuated autonomous underwater vehicles (AUVs) in the presence of system parameter uncertainties and complex external disturbances. To accomplish this goal, a model–data-driven learning adaptive robust control (LARC) strategy is introduced for AUVs. Firstly, a serial iterative learning control (ILC) approach is introduced as feedforward compensation, and then the corresponding trajectory tracking error dynamics model, the Feedforward Compensation–Line of Sight (FFC-LOS) guidance law, and the feedforward compensation-based kinematics controller are designed. Secondly, the dynamics controller is designed for AUVs, which consists of a linear feedback term, a nonlinear robust feedback term, an adjustable model compensation term, and a fast dynamic compensation term. In this control framework, the robust control and fast dynamic compensation parts are utilized to deal with nonlinear uncertainties and disturbances, the projection-type adaptive control part solves the influence caused by the uncertainty of system parameters, and the serial ILC part that is a data-driven learning method can further improve the trajectory tracking accuracy for repetitive tasks. Finally, comparative simulations under different scenarios and different types of disturbances are performed to verify the effectiveness of the proposed control strategy for AUVs.
Accurate biological detection is crucial for autonomous navigation of underwater robots, yet severely challenged by optical degradation and scale variation in marine environments. While image enhancement and domain adaptation methods offer some mitigation, they often operate as disjointed preprocessing steps, potentially introducing artifacts and compromising downstream detection performance. Furthermore, existing architectures struggle to balance accuracy, computational efficiency, and robustness across the extreme scale variability of marine organisms in challenging underwater conditions. To overcome these limitations, we propose UW-YOLO-Bio, a novel framework built upon the YOLOv8 architecture. Our approach integrates three dedicated modules: (1) The Global Context 3D Perception Module (GCPM), which captures long-range dependencies to mitigate occlusion and noise without the quadratic cost of self-attention; (2) The Channel-Aggregation Efficient Downsampling Block (CAEDB), which preserves critical information from low-contrast targets during spatial reduction; (3) The Regional Context Feature Pyramid Network (RCFPN), which optimizes multi-scale fusion with contextual awareness for small marine organisms. Extensive evaluations on DUO, RUOD, and URPC datasets demonstrate state-of-the-art performance, achieving an average improvement in mAP50 of up to 2.0% across benchmarks while simultaneously reducing model parameters by 8.3%. Notably, it maintains a real-time inference speed of 61.8 FPS, rendering it highly suitable for deployment on resource-constrained autonomous underwater vehicles (AUVs).
The mission environment has become more and more complex, and the tempo has obviously accelerated. As a result, the traditional manual decision-making can no longer meet the requirements. There is a strong need for an advanced decision-making system to assist decision makers in carrying out on-the-spot mission command. To better carry out the research on artificial intelligent recommendation methods for mission schemes, this paper collated the research articles in this direction in China and abroad in recent years and divided the intelligent recommendation methods into three categories, namely intelligent analysis, intelligent matching, and intelligent learning. It elaborated on the core principles, technical paths, and typical applications of various methods and simultaneously analyzed the advantages and disadvantages of the three types of methods. It identified the deficiencies of the existing methods in terms of dynamic adaptability, autonomous decision-making ability, data dependence, and credibility. Finally, the future development direction was prospected, providing valuable references for subsequent research in this field.
Marine aquaculture has witnessed remarkable growth in recent decades, contributing significantly to global food security and economic development [...]
Accurate acoustic identification of marine mammals is vital for monitoring ocean health and human impacts. Existing methods often struggle with limited single-feature representations or suboptimal fusion of multiple features. This paper proposes an Evaluation-Adaptive Weighted Multi-Head Fusion Network that integrates CQT and STFT features via a dual-branch ResNet architecture. The model enhances intra-branch features using channel attention and adaptive weighting of each branch based on its validation accuracy during training. Experiments on the Watkins Marine Mammal Sound Database show that the proposed method achieves superior performance, reaching 96.05% accuracy and outperforming baseline and attention-based fusion models. This approach offers an effective solution for multi-feature acoustic recognition in complex underwater environments.
This paper presents an optimal output-feedback tracking control problem for multiple unmanned marine vehicles (UMVs) to track a desired trajectory. To guarantee the control objective in an optimal manner, adaptive dynamic programming (ADP) with optimal compensation terms is adopted. A neural velocity observer is designed based on a neural network (NN) to estimate the unmeasured system states and the unknown system dynamics. Furthermore, a disturbance observer (DO) is proposed to go against the effect of the unknown external disturbance of the sea environment. It is proved that the proposed controller can guarantee that all signals in the closed-loop system are bounded. Simulation results are given to demonstrate the effectiveness of the proposed control algorithm.
The precise wake model is crucial for accurately estimating wind farm loads and power, playing a key role in wake control within wind farms. This study proposes a segmented dual-Gaussian wake model, which is built upon existing dual-Gaussian wake models but places greater emphasis on the influence of initial wake generation and evolution processes on the wind speed profile in the near-wake region. The enhanced model optimizes the wake speed profile in the near-wake region and improves the accuracy of wake diffusion throughout the entire flow field. Furthermore, the optimized dual-Gaussian wake model is utilized to estimate the power output and blade root vibration loads in offshore wind farms. Through comparative analysis of high-fidelity simulation results and actual measurement data, the accuracy of the optimized dual-Gaussian wake model is validated. This approach offers high computational efficiency and provides valuable insights for load fluctuations and power estimation, thereby advancing the development of wake control strategies rapidly.
A shallow water equations-based model with an improved local time-stepping (LTS) scheme is developed for modeling coastal hydrodynamics across multiple scales, from large areas to detailed local regions. To enhance the stability of the shallow water model for long-duration simulations and at larger LTS gradings, a prediction-correction method using a single-layer interface that couples coarse and fine time discretizations is adopted. The proposed scheme improves computational efficiency with an acceptable additional computational burden and ensures accurate conservation of time truncation errors in a discrete sense. The model performance is verified with respect to conservation and computational efficiency through two idealized tests: the spreading of a drop of shallow water and a tidal flat/channel system. The results of both tests demonstrate that the improved LTS scheme maintains precision as the LTS grading increases, preserves conservation properties, and significantly improves computational efficiency with a speedup ratio of up to 2.615. Furthermore, we applied the LTS scheme to simulate tides at grid scales of 40,000 m to 200 m for a portion of the Northwest Pacific. The proposed model shows promise for modeling cross-scale hydrodynamics in complex coastal and ocean engineering problems.