Search

As the exploration of marine resources continues to deepen, the utilization of Autonomous Underwater Vehicles (AUVs) for conducting marine resource surveys and underwater environmental mapping has become a common practice. In order to successfully accomplish exploration missions, AUVs require high-precision underwater navigation information as support. A Strapdown Inertial Navigation System (SINS) can provide AUVs with accurate attitude and heading information, while a Doppler Velocity Log (DVL) is capable of measuring the velocity vector of the AUVs. Therefore, the integrated SINS/DVL navigation system can furnish the necessary navigational information required by an AUV. In response to the issue of DVL being susceptible to external environmental interference, leading to reduced measurement accuracy, this paper proposes an end-to-end deep-learning approach to enhance the accuracy of DVL velocity vector measurements. The utilization of the raw measurement data from an Inertial Measurement Unit (IMU), which includes gyroscopes and accelerometers, to assist the DVL in velocity vector estimation and to refine it towards the Global Positioning System (GPS) velocity vector, compensates for the external environmental interference affecting the DVL, therefore enhancing the navigation accuracy. To evaluate the proposed method, we conducted lake experiments using SINS and DVL equipment, from which the collected data were organized into a dataset for training and assessing the model. The research results show that the DVL vector predicted by our model can achieve a maximum improvement of 69.26% in terms of root mean square error and a maximum improvement of 78.62% in terms of relative trajectory error.

Investigating underwater environments using Multi-Beam Echo Sounder (MBES) point cloud registration technology is a critical yet underdeveloped area in oceanographic research. This paper presents a fast, deterministic Branch-and-Bound (BnB) method with four degrees of freedom, which combines Inertial Measurement Unit (IMU) data with MBES point cloud data for precise registration. Given the prevalence of outliers and noise in underwater acoustic measurements, the BnB method is employed to provide globally deterministic solutions. However, due to the exponential convergence speed of the BnB method with respect to the dimensionality of the solution space, searching within a six-degree-of-freedom parameter space (three rotational and three translational degrees of freedom) can be extremely time-consuming. To this end, the Z-axis of the point cloud is aligned with the gravitational direction of the IMU, reducing the rotational degrees of freedom from three to one, specifically concerning yaw. Additionally, an outlier exclusion strategy is introduced to eliminate mismatches, significantly reducing the number of key-point correspondences and thereby improving registration efficiency. Experiments conducted on both public and real-world lake datasets demonstrate that the proposed method achieves a favorable balance between speed and accuracy, outperforming other tested methods and meeting the demands of contemporary research.

The competition mechanism between the slip motions and cleavage fractures is related to the anisotropy of deformation behaviors, which is essential to manufacture complex optical components. To identify competition mechanism between the slip motions and cleavage fractures and reveal the anisotropy of deformation and damage behaviors of MgF2 crystals, the nanoindentation tests were systematically conducted on different crystal planes. In addition, the stress induced by the nanoindentation was developed and decomposed along the slip systems and cleavage planes, and cleavage factors and Schmid factors were calculated. The stress, cleavage factors and Schmid factors indicated that the activation degree of the slip motions and cleavage fractures determined the indentation morphologies. Under the same indentation conditions, the nanoindentation of the (001) crystal plane activated most slip motions, so the plastic deformation is most prone to occur on this crystal plane. The nanoindentation of the (010) crystal plane activated less slip motions and most cleavage fractures, resulting in the severest brittle fractures on the (010) crystal plane. The theoretical results consisted well with the experimental results, which provides the theoretical guidance to the low-damage manufacturing of MgF2 components.

Autonomous Underwater Vehicles (AUVs) are widely used for hydrological monitoring, underwater exploration, and geological surveys. However, AUVs face limitations in underwater navigation due to the high costs associated with Strapdown Inertial Navigation System (SINS) and Doppler Velocity Log (DVL), hindering the development of low-cost vehicles. Micro Electro Mechanical System Inertial Measurement Units (MEMS IMUs) are widely used in industry due to their low cost and can output acceleration and angular velocity, making them suitable as an Attitude Heading Reference System (AHRS) for low-cost vehicles. However, poorly calibrated MEMS IMUs provide an inaccurate angular velocity, leading to rapid drift in orientation. In underwater environments where AUVs cannot use GPS for position correction, this drift can have severe consequences. To address this issue, this paper proposes Underwater Gyros Denoising Net (UGDN), a method based on dilated convolutions and LSTM that learns and extracts the spatiotemporal features of IMU sequences to dynamically compensate for the gyroscope’s angular velocity measurements, reducing attitude and heading errors. In the experimental section of this paper, we deployed this method on a dataset collected from field trials and achieved significant results. The experimental results show that the accuracy of MEMS IMU data denoised by UGDN approaches that of fiber-optic SINS, and when integrated with DVL, it can serve as a low-cost underwater navigation solution.

In ocean observation missions, unmanned autonomous ocean observation platforms play a crucial role, with precise target detection technology serving as a key support for the autonomous operation of unmanned platforms. Among various underwater sensing devices, side-scan sonar (SSS) has become a primary tool for wide-area underwater detection due to its extensive detection range. However, current research on target detection with SSS primarily focuses on large targets such as sunken ships and aircraft, lacking investigations into small targets. In this study, we collected data on underwater small targets using an unmanned boat equipped with SSS and proposed an enhancement method based on the YOLOv7 model for detecting small targets in SSS images. First, to obtain more accurate initial anchor boxes, we replaced the original k-means algorithm with the k-means++ algorithm. Next, we replaced ordinary convolution blocks in the backbone network with Omni-dimensional Dynamic Convolution (ODConv) to enhance the feature extraction capability for small targets. Subsequently, we inserted a Global Attention Mechanism (GAM) into the neck network to focus on global information and extract target features, effectively addressing the issue of sparse target features in SSS images. Finally, we mitigated the harmful gradients produced by low-quality annotated data by adopting Wise-IoU (WIoU) to improve the detection accuracy of small targets in SSS images. Through validation on the test set, the proposed method showed a significant improvement compared to the original YOLOv7, with increases of 5.05% and 2.51% in mAP@0.5 and mAP@0.5: 0.95 indicators, respectively. The proposed method demonstrated excellent performance in detecting small targets in SSS images and can be applied to the detection of underwater mines and small equipment, providing effective support for underwater small target detection tasks.

In the field of underwater perception and detection, side-scan sonar (SSS) plays an indispensable role. However, the imaging mechanism of SSS results in slow information acquisition and high complexity, significantly hindering the advancement of downstream data-driven applications. To address this challenge, we designed an SSS image generator based on diffusion models. We developed a data collection system based on Autonomous Underwater Vehicles (AUVs) to achieve stable and rich data collection. For the process of converting acoustic signals into image signals, we established an image compensation method based on nonlinear gain enhancement to ensure the reliability of remote signals. On this basis, we developed the first controllable category SSS image generation algorithm, which can generate specified data for five categories, demonstrating outstanding performance in terms of the Fréchet Inception Distance (FID) and the Inception Score (IS). We further evaluated our image generator in the task of SSS object detection, and our cross-validation experiments showed that the generated images contributed to an average accuracy improvement of approximately 10% in object detection. The experimental results validate the effectiveness of the proposed SSS image generator in generating highly similar sonar images and enhancing detection accuracy, effectively addressing the issue of data scarcity.

Side-scan sonar plays a crucial role in underwater exploration, and the autonomous detection of side-scan sonar images is vital for detecting unknown underwater environments. However, due to the complexity of the underwater environment, the presence of a few highlighted areas on the targets, blurred feature details, and difficulty in collecting data from side-scan sonar, achieving high-precision autonomous target recognition in side-scan sonar images is challenging. This article addresses this problem by improving the You Only Look Once v7 (YOLOv7) model to achieve high-precision object detection in side-scan sonar images. Firstly, given that side-scan sonar images contain large areas of irrelevant information, this paper introduces the Swin-Transformer for dynamic attention and global modeling, which enhances the model’s focus on the target regions. Secondly, the Convolutional Block Attention Module (CBAM) is utilized to further improve feature representation and enhance the neural network model’s accuracy. Lastly, to address the uncertainty of geometric features in side-scan sonar target features, this paper innovatively incorporates a feature scaling factor into the YOLOv7 model. The experiment initially verified the necessity of attention mechanisms in the public dataset. Subsequently, experiments on our side-scan sonar (SSS) image dataset show that the improved YOLOv7 model has 87.9% and 49.23% in its average accuracy (mAP0.5) and (mAP0.5:0.95), respectively. These results are 9.28% and 8.41% higher than the YOLOv7 model. The improved YOLOv7 algorithm proposed in this paper has great potential for object detection and the recognition of side-scan sonar images.

Underwater vehicles heavily depend on the integration of inertial navigation with Doppler Velocity Log (DVL) for fusion-based localization. Given the constraints imposed by sensor costs, ensuring the optimization ability and robustness of fusion algorithms is of paramount importance. While filtering-based techniques such as Extended Kalman Filter (EKF) offer mature solutions to nonlinear problems, their reliance on linearization approximation may compromise final accuracy. Recently, Invariant EKF (IEKF) methods based on the concept of smooth manifolds have emerged to address this limitation. However, the optimization by matrix Lie groups must satisfy the “group affine” property to ensure state independence, which constrains the applicability of IEKF to high-precision positioning of underwater multi-sensor fusion. In this study, an alternative state-independent underwater fusion invariant filtering approach based on a two-frame group utilizing DVL, Inertial Measurement Unit (IMU), and Earth-Centered Earth-Fixed (ECEF) configuration is proposed. This methodology circumvents the necessity for group affine in the presence of biases. We account for inertial biases and DVL pole-arm effects, achieving convergence in an imperfect IEKF by either fixed observation or body observation information. Through simulations and real datasets that are time-synchronized, we demonstrate the effectiveness and robustness of the proposed algorithm.

Multibeam echo sounders (MBESs) enable extensive underwater environment exploration. However, due to weak correlation between adjacent multibeam sonar data and difficulties in inter-frame feature matching, the resulting underwater mapping accuracy frequently falls short of the desired level. To address this issue, this study presents the development of a multibeam data processing system, which includes functionalities for sonar parameter configuration, data storage, and point cloud conversion. Subsequently, an Iterative Extended Kalman Filter (iEKF) algorithm is employed for odometry estimation, facilitating the initial construction of the point cloud map. To further enhance mapping accuracy, we utilize the Generalized Iterative Closest Point (GICP) algorithm for point cloud registration, effectively merging point cloud data collected at different times from the same location. Finally, real-world lake experiments demonstrate that our method achieves an Absolute Trajectory Error (ATE) of 15.10 m and an average local point cloud registration error of 0.97 m. Furthermore, we conduct measurements on various types of artificial targets. The experimental results indicate that the average location error of the targets calculated by our method is 4.62 m, which meets the accuracy requirements for underwater target exploration.

Accurate underwater target detection is crucial for the operation of autonomous underwater vehicles (AUVs), enhancing their environmental awareness and target search and rescue capabilities. Current deep learning-based detection models are typically large, requiring substantial storage and computational resources. However, the limited space on AUVs poses significant challenges for deploying these models on the embedded processors. Therefore, research on model compression is of great practical importance, aiming to reduce model parameters and computational load without significantly sacrificing accuracy. To address the challenge of deploying large detection models, this paper introduces an automated pruning method based on dependency graphs and successfully implements efficient pruning on the YOLOv7 model. To mitigate the accuracy degradation caused by extensive pruning, we design a hybrid distillation method that combines output-based and feature-based distillation techniques, thereby improving the detection accuracy of the pruned model. Finally, we deploy the compressed model on an embedded processor within an AUV to evaluate its performance. Multiple experiments confirm the effectiveness of our proposed method in practical applications.

Objective: Compare the spine’s stability after laminectomy (LN) and laminoplasty (LP) for two posterior surgeries. Simultaneously, design a new vertebral titanium porous mini plate (TPMP) to achieve firm fixation of the open-door vertebral LP fully. The objective is to enhance the fixation stability, effectively prevent the possibility of “re-closure,” and may facilitate bone healing.Methods: TPMP was designed by incorporating a fusion body and porous structures, and a three-dimensional finite element cervical model of C2-T1 was constructed and validated. Load LN and LP finite element models, respectively, and analyze and simulate the detailed processes of the two surgeries. It was simultaneously implanting the TPMP into LP to evaluate its biomechanical properties.Results: We find that the range of motion (ROM) of C4-C5 after LN surgery was greater than that of LP implanted with different plates alone. Furthermore, flexion-extension, lateral bending, and axial rotation reflect this change. More noteworthy is that LN has a much larger ROM on C2-C3 in axial rotation. The ROM of LP implanted with two different plates is similar. There is almost no difference in facet joint stress in lateral bending. The facet joint stress of LN is smaller on C2-C3 and C4-C5, and larger more prominent on C5-C6 in the flexion-extension. Regarding intervertebral disc pressure (IDP), there is little difference between different surgeries except for the LN on C2-C3 in axial rotation. The plate displacement specificity does not significantly differ from LP with vertebral titanium mini-plate (TMP) and LP with TPMP after surgery. The stress of LP with TPMP is larger in C4-C5, C5-C6. Moreover, LP with TMP shows greater stress in the C3-C4 during flexion-extension and lateral bending.Conclusion: LP may have better postoperative stability when posterior approach surgery is used to treat CSM; at the same time, the new type of vertebral titanium mini-plate can achieve almost the same effect as the traditional titanium mini-plate after surgery for LP. In addition, it has specific potential due to the porous structure promoting bone fusion.

Common RGBD, CMOS, and CCD-based cameras produce motion blur and incorrect exposure under high-speed and improper lighting conditions. According to the bionic principle, the event camera developed has the advantages of low delay, high dynamic range, and no motion blur. However, due to its unique data representation, it encounters significant obstacles in practical applications. The image reconstruction algorithm based on an event camera solves the problem by converting a series of “events” into common frames to apply existing vision algorithms. Due to the rapid development of neural networks, this field has made significant breakthroughs in past few years. Based on the most popular Events-to-Video (E2VID) method, this study designs a new network called E2VIDX. The proposed network includes group convolution and sub-pixel convolution, which not only achieves better feature fusion but also the network model size is reduced by 25%. Futhermore, we propose a new loss function. The loss function is divided into two parts, first part calculates the high level features and the second part calculates the low level features of the reconstructed image. The experimental results clearly outperform against the state-of-the-art method. Compared with the original method, Structural Similarity (SSIM) increases by 1.3%, Learned Perceptual Image Patch Similarity (LPIPS) decreases by 1.7%, Mean Squared Error (MSE) decreases by 2.5%, and it runs faster on GPU and CPU. Additionally, we evaluate the results of E2VIDX with application to image classification, object detection, and instance segmentation. The experiments show that conversions using our method can help event cameras directly apply existing vision algorithms in most scenarios.

In the realm of underwater environment detection, achieving information matching stands as a pivotal step, forming an indispensable component for collaborative detection and research in areas such as distributed mapping. Nevertheless, the progress in studying the matching of underwater side-scan sonar images has been hindered by challenges including low image quality, intricate features, and susceptibility to distortion in commonly used side-scan sonar images. This article presents a comprehensive overview of the advancements in underwater sonar image processing. Building upon the novel SchemaNet image topological structure extraction model, we introduce a feature matching model grounded in side-scan sonar images. The proposed approach employs a semantic segmentation network as a teacher model to distill the DeiT model during training, extracting the attention matrix of intermediate layer outputs. This emulates SchemaNet’s transformation method, enabling the acquisition of high-dimensional topological structure features from the image. Subsequently, utilizing a real side-scan sonar dataset and augmenting data, we formulate a matching dataset and train the model using a graph neural network. The resulting model demonstrates effective performance in side-scan sonar image matching tasks. These research findings bear significance for underwater detection and target recognition and can offer valuable insights and references for image processing in diverse domains.

IntroductionAutonomous underwater vehicles (AUVs) are required to thoroughly scan designated areas during underwater missions. They typically follow a zig-zag trajectory to achieve full coverage. However, effective coverage can be challenging in complex environments due to the accumulation and drift of navigation errors. Possible solutions include surfacing for satellite positioning or underwater acoustic positioning using transponders on other vehicles. Nevertheless, surfacing or active acoustics can compromise stealth during reconnaissance missions in hostile areas by revealing the vehicle’s location.MethodsWe propose calibration and planning strategies based on error models and acoustic positioning to address this challenge. Acoustic markers are deployed via surface ships to minimize navigation errors while maintaining stealth. And a new path planning method using a traceless Kalman filter and acoustic localization is proposed to achieve full-area coverage of AUVs. By analyzing the statistics of accumulated sensor errors, we optimize the positions of acoustic markers to communicate with AUVs and achieve better coverage. AUV trajectory concealment is achieved during detection by randomizing the USV navigation trajectory and irregularizing the locations of acoustic marker.ResultsThe proposed method enables the cumulative determination of the absolute position of a target with low localization error in a side-scan sonar-based search task. Simulations based on large-scale maps demonstrate the effectiveness and robustness of the proposed algorithm.DiscussionSolving the problem of accumulating underwater localization errors based on inertial navigation by error modeling and acoustic calibration is a typical way. In this paper, we have implemented a method to solve the localization error in a search scenario where stealth is considered.

Elucidating the complex interactions between the work material and abrasives during grinding of gallium nitride (GaN) single crystals is an active and challenging research area. In this study, molecular dynamics simulations were performed on double-grits interacted grinding of GaN crystals; and the grinding force, coefficient of friction, stress distribution, plastic damage behaviors, and abrasive damage were systematically investigated. The results demonstrated that the interacted distance in both radial and transverse directions achieved better grinding quality than that in only one direction. The grinding force, grinding induced stress, subsurface damage depth, and abrasive wear increase as the transverse interacted distance increases. However, there was no clear correlation between the interaction distance and the number of atoms in the phase transition and dislocation length. Appropriate interacted distances between abrasives can decrease grinding force, coefficient of friction, grinding induced stress, subsurface damage depth, and abrasive wear during the grinding process. The results of grinding tests combined with cross-sectional transmission electron micrographs validated the simulated damage results, i.e. amorphous atoms, high-pressure phase transition, dislocations, stacking faults, and lattice distortions. The results of this study will deepen our understanding of damage accumulation and material removal resulting from coupling between abrasives during grinding and can be used to develop a feasible approach to the wheel design of ordered abrasives.

Abstract This paper proposes a personalized output‐feedback path‐following control strategy for automated vehicles. A personalized path generation approach is created to obtain the expected paths of drivers with different driving styles. Historical driving data and road features are used to calculate the waypoints that characterize driving styles. Then, a robust H∞ output‐feedback controller is designed to follow the generated paths. A solution based on matrix partition is provided to compute the output‐feedback control gains without using the vehicle lateral velocity signal, which facilitates the practical implementation of the designed controller. The proposed driving strategy is validated in CarSim® simulations and scaled car experiments. The results show the personalized paths can match with drivers’ driving styles and can be tracked by the designed output‐feedback path‐following controller.

Deep learning-based object detection methods have demonstrated remarkable effectiveness across various domains. Recently, there has been growing interest in applying these techniques to underwater environments. Conventional optical imaging methods face severe limitations when operating in underwater conditions, restricting their ability to identify objects with good visibility and at close distances. Consequently, side-scan sonar (SSS) has emerged as a common equipment choice for underwater detection due to its compatibility with the characteristics of sound waves in water. This paper introduces a novel method, termed the Enhanced YOLOv7-Based Approach, for detecting small objects in SSS images. Building upon the widely-adopted YOLOv7 method, the proposed approach incorporates several enhancements aimed at improving detection accuracy. First, a dedicated detection layer tailored for small objects is added to the original network architecture. Additionally, two attention mechanisms are integrated within the backbone and neck components of the network, respectively, to strengthen the network’s focus on object features. Finally, the network features are recombined based on the BiFPN structure. Experimental results demonstrate that the proposed method outperforms mainstream object detection algorithms. In comparison to the original YOLOv7 network, it achieves a Precision of 95.5%, indicating a significant improvement of 4.8%. Moreover, its Recall reaches 87.0%, representing an enhancement of 5.1%, while the mean Average Precision (mAP) at an IoU threshold of 0.5 (mAP@.5) reaches 86.9%, reflecting a 6.7% improvement. Furthermore, the mAP@.5:.95 reaches 55.1%, a 4.8% enhancement. Therefore, the method presented in this paper enhances the performance of YOLOv7 for object detection in SSS images, providing a fresh perspective on small object detection based on SSS images and contributing to the advancement of underwater detection techniques.

Multi-vehicle collaborative mapping proves more efficient in constructing maps in unfamiliar underwater environments in comparison to single-vehicle methods. One of the pivotal hurdles of Simultaneous Localization and Mapping (SLAM) with multiple underwater vehicles is map registration. Due to the inadequate characteristics of the underwater grid maps, matching map features poses a challenge, and outliers between maps add to the complexity. We propose an algorithm to solve this problem. This approach employs the Gaussian Mixture Robust Branch and Bound (GMRBnB) algorithm with an interior point filtering technique. Feature point extraction, registration using the GMRBnB algorithm, inlier extraction based on density, and registration of the inlier are performed to obtain a more precise transformation matrix. The results of the simulation and experiments demonstrate that this technique heightens outlier tolerance and reinforces map registration accuracy. The proposed approach surpasses Iterative Closest Point (ICP) and Normal Distributions Transform (NDT) methods with respect to map registration quality.

For a long time, fish school swimming has attracted a great deal of attention in biological systems, as fish schools can have complex hydrodynamic effects on individuals. This work adopted a non-iterative, immersed boundary–lattice Boltzmann method (IB–LBM). A numerical simulation of two-dimensional three-degree-of-freedom self-propelled fish, in side-by-side, staggered, and triangle formations, was conducted by adjusting spacing and motion parameters. A comprehensive analysis of individual speed gains and energy efficiencies in these formations was carried out. Furthermore, an analysis of the hydrodynamic characteristics of fish schools was performed, using instantaneous vorticity profiles and pressure fields. Certain studies have shown that passive interactions between individuals cannot always bring hydrodynamic benefits. The swimming efficiency of side-by-side formations in the same phase gradually increases as the distance decreases, but it also brings certain burdens to individuals when the phases are different. This paper also shows that the roles of passive interactions, spacing, and deflections affect fish school subsystems differently. When the low-pressure areas created by a wake vortex act on one side of an individual’s body, the tail-end fish are good at gaining hydrodynamic benefits from it. This effect is not universal, and the degree to which individuals benefit from changes in exercise parameters varies. This study provides a theoretical basis for bioinspired robots, as well as providing certain insights into the mechanism of collective biological movement.

In the realm of underwater exploration, particularly within the domain of autonomous detection, sidescan sonar stands as a pivotal sensor apparatus. Autonomous detection models necessitate a substantial volume of scanned sonar image data for optimal training, yet the challenges and costs associated with acquiring such data pose significant limitations on the deployment of autonomous detection models in underwater exploration scenarios. Consequently, there arises a demand for the development of cost-effective data augmentation techniques. In the present investigation, an initial collection of scanned sonar image data was conducted during lake trials, encompassing diverse environmental regions, including rocky terrain, shadowed areas, and aquatic bodies. Subsequently, a proprietary generative adversarial network (GAN) model was devised for the purpose of synthesizing scanned sonar data. The synthesized data underwent denoising and underwent post-processing via algorithmic methods. Subsequently, similarity metrics were computed to gauge the quality of the generated scanned sonar data. Furthermore, a semantic segmentation model was meticulously crafted and trained by employing authentic data. The generated data were subsequently introduced into this semantic segmentation model. The output outcomes demonstrated that the model exhibited preliminary labeling proficiency on the generated image data, requiring only minimal manual intervention to conform to the standards of a conventional dataset. Following the inclusion of the labeled data into the original dataset and the subsequent training of the network model utilizing the expanded dataset, there was an observed discernible enhancement in the segmentation performance of the model.

Underwater target detection technology plays a crucial role in the autonomous exploration of underwater vehicles. In recent years, significant progress has been made in the field of target detection through the application of artificial intelligence technology. Effectively applying AI techniques to underwater target detection is a highly promising area of research. However, the difficulty and high cost of underwater acoustic data collection have led to a severe lack of data, greatly restricting the development of deep-learning-based target detection methods. The present study is the first to utilize diffusion models for generating underwater acoustic data, thereby effectively addressing the issue of poor detection performance arising from the scarcity of underwater acoustic data. Firstly, we place iron cylinders and cones underwater (simulating small preset targets such as mines). Subsequently, we employ an autonomous underwater vehicle (AUV) equipped with side-scan sonar (SSS) to obtain underwater target data. The collected target data are augmented using the denoising diffusion probabilistic model (DDPM). Finally, the augmented data are used to train an improved YOLOv7 model, and its detection performance is evaluated on a test set. The results demonstrate the effectiveness of the proposed method in generating similar data and overcoming the challenge of limited training sample data. Compared to models trained solely on the original data, the model trained with augmented data shows a mean average precision (mAP) improvement of approximately 30% across various mainstream detection networks. Additionally, compared to the original model, the improved YOLOv7 model proposed in this study exhibits a 2% increase in mAP on the underwater dataset.

High-precision positioning capability is a crucial technology for achieving accurate navigation in autonomous underwater vehicles (AUVs). However, due to severe electromagnetic wave attenuation underwater and the unavailability of the global positioning system (GPS), inertial-navigation-based dead reckoning is considered the primary method for underwater positioning. Unfortunately, errors accumulated during the navigation process lead to unbounded drift, and filtering-based methods have been used to mitigate the errors, but with limited success. In this paper, we propose a precise underwater dead-reckoning mathematical model that recursively calculates the ground truth and corresponding errors based on an AUV’s motion model, and we derive empirical formulas. Compared to related methods, this approach not only models the cumulative errors of relative noise measurements, but also provides recursive expressions with corresponding statistical moments. The experimental results demonstrate that this formula significantly reduces positioning errors in underwater navigation tasks.

Abstract Objective Coronavirus disease 2019 (COVID-19) is a major challenge facing the world. Certain guidelines issued by National Health Commission of the People's Repubilic of China recommend intravenous immunoglobulin (IVIG) for adjuvant treatment of COVID-19. However, there is a lack of clinical evidence to support the use of IVIG. Methods This single-center retrospective cohort study included all adult patients with laboratory-confirmed severe COVID-19 in the Respiratory and Critical Care Unit of Dabie Mountain Regional Medical Center, China. Patient information, including demographic data, laboratory indicators, the use of glucocorticoids and IVIG, hospital mortality, the application of mechanical ventilation, and the length of hospital stay was collected. The primary outcome was the composite end point, including death and the use of mechanical ventilation. The secondary outcome was the length of hospital stay. Results Of the 285 patients with confirmed COVID-19, 113 severely ill patients were included in this study. Compared to the non-IVIG group, more patients in the IVIG group reached the composite end point [12 (25.5%) vs 5 (7.6%), P = 0.008] and had longer hospital stay periods [23.0 (19.0–31.0) vs 16.0 (13.8–22.0), P

The AUV (Autonomous Underwater Vehicle) navigation process relies on the interaction of a variety of sensors. The side-scan sonar can collect underwater images and obtain semantic underwater environment information after processing, which will help improve the ability of AUV autonomous navigation. However, there is no practical method to utilize the semantic information of side scan sonar image. A new convolutional neural network model is proposed to solve this problem in this paper. The model is a standard codec structure, which extracts multi-channel features from the input image and then fuses them to reduce parameters and strengthen the weight of feature channels. Then, a larger convolution kernel is used to extract the features of large-scale sonar images more effectively. Finally, a parallel compensation link with a small-scale convolution kernel is added and spliced with features extracted from a large convolution kernel in the decoding part to obtain features of different scales. We use this model to conduct experiments on self-collected sonar data sets, which were uploaded on github. The experimental results show that ACC and MIoU reach 0.87 and 0.71, better than other classical small-order semantic segmentation networks. Furthermore, the 347.52 g FOLP and the number of parameters around 13 m also ensure the computing speed and portability of the network. The result can extract the semantic information of the side-scan sonar image and assist with AUV autonomous navigation and mapping.

Path planning obtains the trajectory from one point to another with the robot's kinematics model and environment understanding. However, as the localization uncertainty through the odometry sensors is inevitably affected, the position of the moving path will deviate further and further compared to the original path, which leads to path drift in GPS denied environments. This article proposes a novel path planning algorithm based on Dijkstra to address such issues. By combining statistical characteristics of localization error caused by dead-reckoning, the replanned path with minimum cumulative error is generated with uniforming distribution in the searching space. The simulation verifies the effectiveness of the proposed algorithm. In a real scenario with measurement noise, the results of the proposed algorithm effectively reduce cumulative error compared to the results of the conventional planning algorithm.

In this paper, a circular objects detection method for Autonomous Underwater Vehicle (AUV) docking is proposed, based on the Dynamic Vision Sensor (DVS) and the Spiking Neural Network (SNN) framework. In contrast to the related work, the proposed method not only avoids motion blur caused by frame-based recognition during docking procedure but also reduces data redundancy with limited on-chip resources. First, four coplanar and rectangular constrained circular light sources are constructed as the docking landmark. By combining asynchronous Hough circle transform with the SNN model, the coordinates of landmarks in the image are detected. Second, a Perspective-4-Point (P4P) algorithm is utilized to calculate the relative pose between AUV and the landmark. In addition, a spatiotemporal filter is also used to eliminate noises generated by the background. Finally, experimental results are demonstrated from both software simulation and experimental pool, respectively, to verify the proposed method. It is concluded that the proposed method achieves better performance in accuracy and efficiency in underwater docking scenarios.

SLAM (Simultaneous Localization And Mapping) plays a vital role in navigation tasks of AUV (Autonomous Underwater Vehicle). However, due to a vast amount of image sonar data and some acoustic equipment's inherent high latency, it is a considerable challenge to implement real-time underwater SLAM on a small AUV. This paper presents a filter based methodology for SLAM algorithms in underwater environments. First, a multi-beam forward looking sonar (MFLS) is utilized to extract environmental features. The acquired sonar image is then converted to sparse point cloud format through threshold segmentation and distance-constrained filtering to solve the calculation explosion issue caused by a large amount of original data. Second, based on the proposed method, the DVL, IMU, and sonar data are fused, the Rao-Blackwellized particle filter (RBPF)-based SLAM method is used to estimate AUV pose and generate an occupancy grid map. To verify the proposed algorithm, the underwater vehicle is equipped as an experimental platform to conduct field tasks in both the experimental pool and wild lake, respectively. Experiments illustrate that the proposed approach achieves better performance in both state estimation and suppressing divergence.

The key challenge for multiple vessel cooperative localization is considered as data association, in which state-of-the-art approaches adopt a divide-and-conquer strategy to acquire measurement-to-target association. However, traditional approaches suffer both the computational time and accuracy issues. Here, an improved algorithm under Random Finite Set statistics (RFSs) is proposed, in which the Probability Hypothesis Density (PHD) filter is utilized to address the aforementioned issues, by jointly estimating both the number of vessels and the corresponding states in complex environments. Furthermore, to avoid the prior requirement constrain with respect to the PHD filter, the pattern recognition method is simultaneously utilized to calculate the birth intensities. Simulation results exhibit the proposed approach performs better than normal PHD for multiple vessel cooperative localization, in scenarios of unknown birth intensity.

AUV docking requires the platform to have both wide range cruising and accurate operating abilities, to against challenges of ocean currents, obstacles, and constraints. This paper proposed an evolutionary-based method, for the purpose of docking path optimization. First, the ocean environment and constraints are analyzed and modeled. Next, the control points are designed to satisfy the model constraints. Then, the adaptive law and quantum behavior are introduced in particle swarm optimization (PSO), to achieve global time-optimization. Finally, the proposed approach is evaluated via Monte-Carlo trials, which demonstrates a significant improvement with respect to the state-of-the-art approaches.

Continuous polishing is the first choice for machining optical elements with a large aperture. The lubrication in the continuous polishing is an important factor affecting the surface quality of the optical elements. In this study, the lubrication system between the optic element and polishing lap was analyzed firstly and then was verified by the measurement experiment of the friction coefficient. In addition, the numerical simulation model of the mixture lubrication was established. The polishing pressure distribution and material removal distribution can be obtained by the model. The influences of the rotating speed, optical element load, and surface roughness of the polishing lap on polishing pressure were also analyzed. Finally, the influence rules of the lubrication on the surface shape of optical elements were revealed by the polishing experiments.

To understand the anisotropy dependence of the damage evolution and material removal during the machining process of MgF _2 single crystals, nanoscratch tests of MgF _2 single crystals with different crystal planes and directions were systematically performed, and surface morphologies of the scratched grooves under different conditions were analyzed. The experimental results indicated that anisotropy considerably affected the damage evolution in the machining process of MgF _2 single crystals. A stress field model induced by the scratch was developed by considering the anisotropy, which indicated that during the loading process, median cracks induced by the tensile stress initiated and propagated at the front of the indenter. Lateral cracks induced by tensile stress initiated and propagated on the subsurface during the unloading process. In addition, surface radial cracks induced by the tensile stress were easily generated during the unloading process. The stress change led to the deflection of the propagation direction of lateral cracks. Therefore, the lateral cracks propagated to the workpiece surface, resulting in brittle removal in the form of chunk chips. The plastic deformation parameter indicated that the more the slip systems were activated, the more easily the plastic deformation occurred. The cleavage fracture parameter indicated that the cracks propagated along the activated cleavage planes, and the brittle chunk removal was owing to the subsurface cleavage cracks propagating to the crystal surface. Under the same processing parameters, the scratch of the (001) crystal plane along the [100] crystal-orientation was found to be the most conducive to achieving plastic machining of MgF _2 single crystals. The theoretical results agreed well with the experimental results, which will not only enhance the understanding of the anisotropy dependence of the damage evolution and removal process during the machining of MgF _2 crystals, but also provide a theoretical foundation for achieving the high-efficiency and low-damage processing of anisotropic single crystals.

Path planning is often considered as an important task in autonomous driving applications. Current planning method only concerns the knowledge of robot kinematics, however, in GPS denied environments, the robot odometry sensor often causes accumulated error. To address this problem, an improved path planning algorithm is proposed based on reinforcement learning method, which also calculates the characteristics of the cumulated error during the planning procedure. The cumulative error path is calculated by the map with convex target processing, while modifying the algorithm reward and punishment parameters based on the error estimation strategy. To verify the proposed approach, simulation experiments exhibited that the algorithm effectively avoid the error drift in path planning.

This paper proposes a framework for uncertainty prediction in complex fusion networks, where signals become available sporadically. Assuming there is no information of the sensor characteristics available, a surrogated model of the sensor uncertainty is yielded directly from data through artificial neural networks. The strategy developed is applied to autonomous vehicle localization through odometry sensors (speed and orientation), so as to determine the location uncertainty in the trajectory. The results obtained allow for fusion of autonomous vehicle location measurements, and effective correction of the accumulated odometry error in most scenarios. The neural networks applicability and generalization capacity are proven, evidencing the suitability of the presented methodology for uncertainty estimation in non-linear and intractable processes.

The fluid–structure interaction (FSI) effect has a significant impact on the static and dynamic performance of aerostatic spindles, which should be fully considered when developing a new product. To enhance the overall performance of aerostatic spindles, a two-round optimization design method for aerostatic spindles considering the FSI effect is proposed in this article. An aerostatic spindle is optimized to elaborate the design procedure of the proposed method. In the first-round design, the geometrical parameters of the aerostatic bearing were optimized to improve its stiffness. Then, the key structural dimension of the aerostatic spindle is optimized in the second-round design to improve the natural frequency of the spindle. Finally, optimal design parameters are acquired and experimentally verified. This research guides the optimal design of aerostatic spindles considering the FSI effect.

This paper presents a multi-objective evolutionary algorithm of bio-inspired geomagnetic navigation for Autonomous Underwater Vehicle (AUV). Inspired by the biological navigation behavior, the solution was proposed without using a priori information, simply by magnetotaxis searching. However, the existence of the geomagnetic anomalies has significant influence on the geomagnetic navigation system, which often disrupts the distribution of the geomagnetic field. An extreme value region may easily appear in abnormal regions, which makes AUV lost in the navigation phase. This paper proposes an improved bio-inspired algorithm with behavior constraints, for sake of making AUV escape from the abnormal region. First, the navigation problem is considered as the optimization problem. Second, the environmental monitoring operator is introduced, to determine whether the algorithm falls into the geomagnetic anomaly region. Then, the behavior constraint operator is employed to get out of the abnormal region. Finally, the termination condition is triggered. Compared to the state-of- the-art, the proposed approach effectively overcomes the disturbance of the geomagnetic abnormal. The simulation result demonstrates the reliability and feasibility of the proposed approach in complex environments.

This paper studies the problem of multiple vehicle cooperative localization with spatial registration in the formulation of the probability hypothesis density (PHD) filter. Assuming vehicles are equipped with proprioceptive and exteroceptive sensors (with biases) to cooperatively localize positions, a simultaneous solution for joint spatial registration and state estimation is proposed. For this, we rely on the sequential Monte Carlo implementation of the PHD filtering. Compared to other methods, the concept of multiple vehicle cooperative localization with spatial registration is first proposed under Random Finite Set Theory. In addition, the proposed solution also addresses the challenges for multiple vehicle cooperative localization, e.g., the communication bandwidth issue and data association uncertainty. The simulation result demonstrates its reliability and feasibility in large-scale environments.

This paper proposes a novel method for identifying carriage errors. A general mathematical model of a guideway system is developed, based on the multi-body system method. Based on the proposed model, most error sources in the guideway system can be measured. The flatness of a workpiece measured by the PGI1240 profilometer is represented by a wavelet. Cross-correlation analysis performed to identify the error source of the carriage. The error model is developed based on experimental results on the low frequency components of the signals. With the use of wavelets, the identification precision of test signals is very high.

The ability to predict the grinding force for hard and brittle materials is important to optimize and control the grinding process. However, it is a difficult task to establish a comprehensive grinding force model that takes into account the brittle fracture, grinding conditions, and random distribution of the grinding wheel topography. Therefore, this study developed a new grinding force model for micro-grinding of reaction-bonded silicon carbide (RB-SiC) ceramics. First, the grinding force components and grinding trajectory were analysed based on the critical depth of rubbing, ploughing, and brittle fracture. Afterwards, the corresponding individual grain force were established and the total grinding force was derived through incorporating the single grain force with dynamic cutting grains. Finally, a series of calibration and validation experiments were conducted to obtain the empirical coefficient and verify the accuracy of the model. It was found that ploughing and fracture were the dominate removal modes, which illustrate that the force components decomposed are correct. Furthermore, the values predicted according to the proposed model are consistent with the experimental data, with the average deviation of 6.793% and 8.926% for the normal and tangential force, respectively. This suggests that the proposed model is acceptable and can be used to simulate the grinding force for RB-SiC ceramics in practice.

By simulating the geomagnetic fields and analyzing thevariation of intensities, this paper presents a model for calculating the objective function ofan Autonomous Underwater Vehicle (AUV)geomagnetic navigation task. By investigating the biologically inspired strategies, the AUV successfullyreachesthe destination duringgeomagnetic navigation without using the priori geomagnetic map. Similar to the pattern of a flatworm, the proposed algorithm relies on a motion pattern to trigger a local searching strategy by detecting the real-time geomagnetic intensity. An adapted strategy is then implemented, which is biased on the specific target. The results show thereliabilityandeffectivenessofthe proposed algorithm.

Cooperative localization (CL) is considered a promising method for underwater localization with respect to multiple autonomous underwater vehicles (multi-AUVs). In this paper, we proposed a CL algorithm based on information entropy theory and the probability hypothesis density (PHD) filter, aiming to enhance the global localization accuracy of the follower. In the proposed framework, the follower carries lower cost navigation systems, whereas the leaders carry better ones. Meanwhile, the leaders acquire the followers’ observations, including both measurements and clutter. Then, the PHD filters are utilized on the leaders and the results are communicated to the followers. The followers then perform weighted summation based on all received messages and obtain a final positioning result. Based on the information entropy theory and the PHD filter, the follower is able to acquire a precise knowledge of its position.

Precise localization is a key requirement for the success of highly assisted or autonomous vehicles. The diminishing cost of hardware has resulted in a proliferation of the number of sensors in the environment. Cooperative localization (CL) presents itself as a feasible and effective solution for localizing the ego-vehicle and its neighboring vehicles. However, one of the major challenges to fully realize the effective use of infrastructure sensors for jointly estimating the state of a vehicle in cooperative vehicle-infrastructure localization is an effective data association. In this paper, we propose a method which implements symmetric measurement equations within factor graphs in order to overcome the data association challenge with a reduced bandwidth overhead. Simulated results demonstrate the benefits of the proposed approach in comparison with our previously proposed approach of topology factors.

While most filtering approaches based on random finite sets have focused on improving performance, in this paper, we argue that computation times are very important in order to enable real-time applications such as pedestrian detection. Towards this goal, this paper investigates the use of OpenCL to accelerate the computation of random finite set-based Bayesian filtering in a heterogeneous system. In detail, we developed an efficient and fully-functional pedestrian-tracking system implementation, which can run under real-time constraints, meanwhile offering decent tracking accuracy. An extensive evaluation analysis was carried out to ensure the fulfillment of sufficient accuracy requirements. This was followed by extensive profiling analysis to spot the potential bottlenecks in terms of execution performance, which were then targeted to come up with an OpenCL accelerated application. Video-throughput improvements from roughly 15 fps to 100 fps (6×) were observed on average while processing typical MOT benchmark videos. Moreover, the worst-case frame processing yielded an 18× advantage from nearly 2 fps to 36 fps, thereby comfortably meeting the real-time constraints. Our implementation is released as open-source code.

Through the polishing experiments of potassium dihydrogen phosphate (KDP) crystals based on deliquescent action, the effect of several major factors, including crystal’s initial surface state, polishing time, and revolution of polishing plate, on material removal was researched. Under certain experimental conditions, the rules of material removal were reached, and experimental results are discussed, which lays the foundation for popularization and application of polishing technology for KDP crystals based on deliquescent action.

This paper analyzes the statistic properties of the systematic error in terms of range and bearing during the transformation process. Furthermore, we rely on a weighted nonlinear least square method to calculate the biases based on the proposed models. The results show the high performance of the proposed approach for error modeling and bias estimation.

In the past decade, the developments of vehicle detection have been significantly improved. By utilizing cameras, vehicles can be detected in the Regions of Interest (ROI) in complex environments. However, vision techniques often suffer from false positives and limited field of view. In this paper, a LiDAR based vehicle detection approach is proposed by using the Probability Hypothesis Density (PHD) filter. The proposed approach consists of two phases: the hypothesis generation phase to detect potential objects and the hypothesis verification phase to classify objects. The performance of the proposed approach is evaluated in complex scenarios, compared with the state-of-the-art.