Due to the complexity and diversity of underwater environments, traditional object detection algorithms face challenges in maintaining robustness and detection accuracy when applied underwater. This paper proposes an underwater object detection algorithm based on an improved YOLOv8 model. First, the introduction of CIB building blocks into the backbone network, along with the optimization of the C2f structure and the incorporation of large-kernel depthwise convolutions, effectively enhances the model’s receptive field. This improvement increases the capability of detecting multi-scale objects in complex underwater environments without adding a computational burden. Next, the incorporation of a Partial Self-Attention (PSA) module at the end of the backbone network enhances model efficiency and optimizes the utilization of computational resources while maintaining high performance. Finally, the integration of the Neck component from the Gold-YOLO model improves the neck structure of the YOLOv8 model, facilitating the fusion and distribution of information across different levels, thereby achieving more efficient information integration and interaction. Experimental results show that YOLOv8-CPG significantly outperforms the traditional YOLOv8 in underwater environments. Precision and Recall show improvements of 2.76% and 2.06%. Additionally, mAP50 and mAP50-95 metrics have increased by 1.05% and 3.55%, respectively. Our approach provides an efficient solution to the difficulties encountered in underwater object detection.

In order to solve the problem of inconsistent state estimation when multiple autonomous underwater vehicles (AUVs) are co-located, this paper proposes a method of multi-AUV co-location based on the consistent extended Kalman filter (EKF). Firstly, the dynamic model of cooperative positioning system follower AUV under two leaders alternately transmitting navigation information is established. Secondly, the observability of the standard linearization estimator based on the lead-follower multi-AUV cooperative positioning system is analyzed by comparing the subspace of the observable matrix of state estimation with that of an ideal observable matrix, it can be concluded that the estimation of state by standard EKF is inconsistent. Finally, aiming at the problem of inconsistent state estimation, a consistent EKF multi-AUV cooperative localization algorithm is designed. The algorithm corrects the linearized measurement values in the Jacobian matrix for cooperative positioning, ensuring that the linearized estimator can obtain accurate measurement values. The positioning results of the follower AUV under dead reckoning, standard EKF, and consistent EKF algorithms are simulated, analyzed, and compared with the real trajectory of the following AUV. The simulation results show that the follower AUV with a consistent EKF algorithm can keep synchronization with the leader AUV more stably.

As a key method of ocean exploration, the positioning accuracy of autonomous underwater vehicles (AUVs) directly influences the success of subsequent missions. This study aims to develop a novel method to address the low accuracy in visual simultaneous localization and mapping (SLAM) within underwater environments, enhancing its application in the navigation and localization of AUVs. We propose an underwater multisensor fusion SLAM system based on image enhancement. First, we integrate hybrid attention mechanisms with generative adversarial networks to address the blurring and low contrast in underwater images, thereby increasing the number of feature points. Next, we develop an underwater feature-matching algorithm based on a local matcher to solve the feature tracking problem caused by grayscale changes in the enhanced image. Finally, we tightly couple the Doppler velocity log (DVL) with the SLAM algorithm to better adapt to underwater environments. The experiments demonstrate that, compared to other algorithms, our proposed method achieves reductions in both mean absolute error (MAE) and standard deviation (STD) by up to 68.18% and 44.44%, respectively, when all algorithms are operating normally. Additionally, the MAE and STD of our algorithm are 0.84 m and 0.48 m, respectively, when other algorithms fail to operate properly.

The failure of the traditional initial alignment algorithm for the strapdown inertial navigation system (SINS) in high latitude is a significant challenge due to the rapid convergence of polar longitude. This paper presents a novel vision aided initial alignment method for the SINS of autonomous underwater vehicles (AUV) in polar regions. In this paper, we redesign the initial alignment model by combining inertial navigation mechanization equations in a transverse coordinate system (TCS) and visual measurement information obtained from a camera fixed on the vehicle. The observability of the proposed method is analyzed under different swing models, while the extended Kalman filter is chosen as an information fusion algorithm. Simulation results show that: the proposed method can improve the accuracy of the initial alignment for SINS in polar regions, and the deviation angle has a similar estimation accuracy in the case of uniaxial, biaxial, and triaxial swing modes, which is consistent with the results of the observable analysis.