LiDAR-based pedestrian detection and tracking (PDT) with high-resolution sensing capability plays an important role in real-world applications such as security monitoring, human behavior analysis, and intelligent transportation. The problem of LiDAR-based PDT suffers from the complex gathering movements and the phenomenon of self- and inter-object occlusions. In this paper, the detection and tracking of dense pedestrians using three-dimensional (3D) real-measured LiDAR point clouds in surveillance applications is studied. To deal with the problem of undersegmentation of dense pedestrian point clouds, the kernel density estimation (KDE) is used for pedestrians center estimation which further leads to a pedestrian segmentation method. Three novel features are defined and used for further PDT performance improvements, which takes advantage of the pedestrians’ posture and body proportion. Finally, a new track management strategy for dense pedestrians is presented to deal with the tracking instability caused by dense pedestrians occlusion. The performance of the proposed method is validated with experiments on the KITTI dataset. The experiment shows that the proposed method can significantly increase F1 score from 0.5122 to 0.7829 compared with the STM-KDE. In addition, compared with AB3DMOT and EagerMOT, the tracking trajectories from the proposed method have the longest average survival time of 36.17 frames.

This paper presents a novel online learning-based fault detection designed for underwater robotic thruster health monitoring. In the fault detection algorithm, we build a mathematical model between the control variable and the propeller speed by fitting collected online work status data to the model. To improve the accuracy of online modeling, a multi-center PSO algorithm with memory ability is utilized to optimize the modeling parameters. Additionally, a model online update mechanism is designed to accommodate the model to the change of thruster work status and sea environment. During the operation, propeller speed of the underwater robot is predicted through the online learning-based model, and the model residuals are used for thruster health monitoring. To avoid false alarm, an adaptive fault detection strategy is established based on model online update mechanism. The proposed method has been extensively evaluated using different underwater robotics, through a sea trial data simulation, a pool test fault detection experiment and a sea trial fault detection experiment. Compared with fixed model-based method, speed prediction MAE of the online learning model is at least 37.9% lower than that of the fixed model. The online learning-based method show no misdiagnosis in experiments, while the fixed model-based method is misdiagnosed. Experimental results show that the proposed method is competitive in terms of accuracy, adaptability, and robustness.

Cultural artifacts found underwater are located in complex environments with poor imaging conditions. In addition, the artifacts themselves present challenges for automated object detection owing to variations in their shape and texture caused by breakage, stacking, and burial. To solve these problems, this paper proposes an underwater cultural object detection algorithm based on the deformable deep aggregation network model for autonomous underwater vehicle (AUV) exploration. To fully extract the object feature information of underwater objects in complex environments, this paper designs a multi-scale deep aggregation network with deformable convolutional layers. In addition, the approach also incorporates a BAM module for feature optimization, which enhances the potential feature information of the object while weakening the background interference. Finally, the object prediction is achieved through feature fusion at different scales. The proposed algorithm has been extensively validated and analyzed on the collected underwater artifact datasets, and the precision, recall, and mAP of the algorithm have reached 93.1%, 91.4%, and 92.8%, respectively. In addition, our method has been practically deployed on an AUV. In the field testing over a shipwreck site, the artifact detection frame rate reached up to 18 fps, which satisfies the real-time object detection requirement.

To achieve precise control of the symmetrical unmanned surface vehicle (USV) under strong external disturbances, we propose a disturbance estimation and conditional disturbance compensation control (CDCC) scheme. First, the differential flatness method is applied to convert the underactuated model into a fully actuated one, simplifying the controller design. Then, a nonlinear disturbance observer (NDOB) is designed to estimate the lumped disturbance. Subsequently, a continuous disturbance characterization index (CDCI) is proposed, which not only indicates whether the disturbance is beneficial to the system stability but also makes the controller switch smoothly and suppresses the chattering phenomenon greatly. Indicated by the CDCI, the proposed CDCC method can not only utilize the beneficial disturbance but also compensate for the detrimental disturbance, which improves the USV’s control performance under strong external disturbances. Moreover, a trajectory-planning method is designed to generate an obstacle avoidance reference trajectory for the controller. Finally, simulations verify the feasibility of applying the proposed control method to USV.

Underwater vehicle is an important tool in the exploration, survey and investigation of the ocean and have many scientific, military, and commercial applications. To develop an underwater vehicle is not an easy task; a reliable underwater vehicle requires a thorough system design and many costly field tests during which system specifications can be validated, and these field tests can be hard and time-consuming. In the development of underwater vehicles, modeling and simulation technology can provides a cost-effective measure to carry out preliminary components, system, and mission testing of the vehicle, thereby reducing the number of potential failures in field tests. This paper first give a review of the simulation technology of underwater vehicles, then a simulation system of an autonomous underwater vehicle and a simulation system of a human occupied vehicle was described respectively; finally, a new type of simulation system of underwater vehicles was introduced.

Facing the challenges of scarce annotations in forward-looking sonar image segmentation, this paper proposes a teacher–student network for unsupervised domain adaptation. The proposed model undergoes supervised learning with optical image data to endow the student model with basic segmentation capabilities, using the segment anything model (SAM) as the teacher to generate pseudo-labels in the sonar image domain, thus achieving knowledge transfer without relying on annotated sonar images. An adaptive weighting approach is proposed, which generates a consistency map using predictive consistency in the source domain and the target domain to assess the quality of pseudo-labels. This method dynamically adjusts supervisory strength, preventing incorrect fitting caused by noisy pseudo-labels. In addition, a multi-scale attention module is designed to refine bottleneck features of the U-Net. The effectiveness of the proposed method is validated on a self-built public forward-looking sonar image dataset, achieving a mean intersection over union (IoU) of 40.8% and a mean average precision (mAP) of 70.3%, demonstrating significant improvements over existing typical UDA methods.