In challenging tasks such as large-scale resource detection, deep-sea exploration, prolonged cruising, extensive topographical mapping, and operations within intricate current regions, AUV swarm technologies play a pivotal role. A core technical challenge within this realm is the precise determination of relative positions among AUVs within the cluster. Given the complexity of underwater environments, this study introduces an integrated and high-precision underwater cluster positioning method, incorporating advanced image restoration algorithms and enhanced underwater visual markers. Utilizing the Hydro-Optical Image Restoration Model (HOIRM) developed in this research, image clarity in underwater settings is significantly improved, thereby expanding the attenuation coefficient range for marker identification and enhancing it by at least 20%. Compared to other markers, the novel underwater visual marker designed in this research elevates positioning accuracy by 1.5 times under optimal water conditions and twice as much under adverse conditions. By synthesizing the aforementioned techniques, this study has successfully developed a comprehensive underwater visual positioning algorithm, amalgamating image restoration, feature detection, geometric code value analysis, and pose resolution. The efficacy of the method has been validated through real-world underwater swarm experiments, providing crucial navigational and operational assurance for AUV clusters.

Due to the limited and fixed field of view of the onboard camera, the guiding beacons gradually drift out of sight as the AUV approaches the docking station, resulting in unreliable positioning and intermittent data. This paper proposes an underwater autonomous docking visual localization method based on a cage-type dual-layer guiding light array. To address the gradual loss of beacon visibility during AUV approach, a rationally designed localization scheme employing a cage-type, dual-layer guiding light array is presented. A dual-layer light array localization algorithm is introduced to accommodate varying beacon appearances at different docking stages by dynamically distinguishing between front and rear guiding light arrays. Following layer-wise separation of guiding lights, a robust tag-matching framework is constructed for each layer. Particle swarm optimization (PSO) is employed for high-precision initial tag matching, and a filtering strategy based on distance and angular ratio consistency eliminates unreliable matches. Under extreme conditions with three missing lights or two spurious beacons, the method achieves 90.3% and 99.6% matching success rates, respectively. After applying filtering strategy, error correction using backtracking extended Kalman filter (BTEKF) brings matching success rate to 99.9%. Simulations and underwater experiments demonstrate stable and robust tag matching across all docking phases, with average detection time of 0.112 s, even when handling dual-layer arrays. The proposed method achieves continuous visual guidance-based docking for autonomous AUV recovery.

The capabilities of AUV mutual perception and localization are crucial for the development of AUV swarm systems. We propose the AUV6D model, a synthetic image-based approach to enhance inter-AUV perception through 6D pose estimation. Due to the challenge of acquiring accurate 6D pose data, a dataset of simulated underwater images with precise pose labels was generated using Unity3D. Mask-CycleGAN technology was introduced to transform these simulated images into realistic synthetic images, addressing the scarcity of available underwater data. Furthermore, the Color Intermediate Domain Mapping strategy is proposed to ensure alignment across different image styles at pixel and feature levels, enhancing the adaptability of the pose estimation model. Additionally, the Salient Keypoint Vector Voting Mechanism was developed to improve the accuracy and robustness of underwater pose estimation, enabling precise localization even in the presence of occlusions. The experimental results demonstrated that our AUV6D model achieved millimeter-level localization precision and pose estimation errors within five degrees, showing exceptional performance in complex underwater environments. Navigation experiments with two AUVs further verified the model’s reliability for mutual 6D pose estimation. This research provides substantial technical support for more complex and precise collaborative operations for AUV swarms in the future.

Accurate perception of a diver’s position and orientation by Autonomous Underwater Vehicles (AUVs) is essential for effective human–robot collaboration in underwater environments. However, conventional position and orientation estimation methods that combine deep learning with Perspective-n-Point (PnP) algorithms are primarily designed for rigid objects. In contrast, divers exhibit highly variable postures underwater, with no fixed configuration. To address this limitation, this paper proposes a framework for estimating the six-degree-of-freedom (6-DoF) position and the orientation of a diver. In addition, a novel network architecture, termed “VideoPose5CH,” is proposed. In the proposed framework, temporal sequences of 2D joint coordinates are provided to VideoPose5CH, which then outputs the 3D joint coordinates of the current frame as well as the corresponding refined 2D joint locations. Subsequently, the diver’s 6-DoF position and orientation relative to the camera are further recovered via a PnP algorithm. To mitigate the scarcity of underwater 3D human pose datasets, a land-based 3D human pose dataset augmentation strategy tailored to underwater conditions is further proposed. With this strategy, diver pose estimation accuracy is improved and the robustness of the proposed method across diverse scenarios is enhanced. Experimental results demonstrate that the proposed method can stably estimate the 6-DoF position and orientation of the diver within a distance range of 2.643 m to 11.477 m. The average position errors along the three axes are 7.33 cm, 4.04 cm, and 27.15 cm, respectively, while the average orientation errors are 6.96°, 8.47°, and 2.62°.

Accurate 6-DoF relative pose estimation is essential for multi-AUV cooperative tasks. However, pose-annotated underwater data are difficult to obtain, limiting learning-based methods. We present ZUPose, a monocular pose estimator trained entirely on synthetic data and deployed directly in real underwater scenes. A key challenge is prediction noise introduced by the sim-to-real gap and underwater optical degradation. To address it, we adopt an algorithm-data co-design strategy. At the algorithm level, we develop an uncertainty-guided densecorrespondence framework in which the network jointly predicts dense correspondences and per-pixel uncertainty under a Laplace-based probabilistic formulation. The predicted uncertainty acts as a learned scale parameter to model correspondence noise and guide pose optimization. At the data level, we construct a physics-guided simulation pipeline to model underwater optical degradation and generate diverse synthetic images. In real turbid water, ZUPose achieves translation and rotation errors of 6.7 cm and 7.7$^\circ$, with both reduced by about half compared with the best-performing baseline. The method remains stable under overexposure and long-range observation, and dual-AUV navigation experiments further validate its practical viability.

Underwater image degradation and occlusion make diver keypoints less visually discernible, leading to substantial localization errors in the keypoint pseudo-labels generated by existing semi-supervised methods. These errors can then accumulate and propagate during consistency learning. Moreover, these methods do not fully exploit the human structural information available in unlabeled images. To address these limitations, a limb-heatmap-guided bidirectional cross-representation consistency method is proposed for semi-supervised learning. A keypoint network and a limb network are employed to learn point-level keypoint responses and region-level limb-structure responses, respectively. For labeled data, limb labels are generated automatically from keypoint annotations and a predefined skeletal topology, without additional annotations. For unlabeled data, intra-representation consistency learning is performed for both networks between the easy-augmentation and hard-augmentation views, and bidirectional cross-representation supervision is applied between the two networks. In the keypoint-to-limb path, keypoint predictions are converted into limb pseudo-labels to supervise the limb network; in the limb-to-keypoint path, limb heatmaps reconstructed from keypoint predictions are compared with the predictions of the limb network to constrain the keypoint configuration. During model inference, only the keypoint network is retained, with no additional inference cost. On the independent test set of a single underwater diver dataset constructed for this study, the proposed method achieves a mean PCKh@0.5 of 80.07% using all labeled training data and outperforms the comparison methods at labeled-data proportions of 25%, 50%, 75%, and 100%. These results demonstrate that region-level limb structure provides effective complementary supervision for point-level keypoint localization within the evaluated setting. Broader applicability requires further validation.