That a mobile welding robot with an adaptive seam tracking ability can greatly improve welding efficiency and quality has been extensively studied. To further improve automation in multiple-station welding, we developed a novel intelligent mobile welding robot consisting of a four-wheeled mobile platform and a collaborative manipulator. With the support of simultaneous localization and mapping (SLAM) technology, the robot is capable of automatically navigating to different stations to perform welding operations. To automatically detect the welding seam, a composite sensor system including an RGB-D camera and a laser vision sensor is creatively applied. Based on the sensor system, a multi-layer sensing strategy is performed to ensure that the welding seam can be detected and tracked with high precision. By applying a hybrid filter to the RGB-D camera measurement, the initial welding seam could be effectively extracted. Next, a novel welding start point detection method is proposed. Meanwhile, to guarantee the tracking quality, a robust welding seam tracking algorithm based on laser vision sensor is presented, to eliminate the tracking discrepancy caused by the platform parking error, through which the tracking trajectory can be corrected in real-time. The experimental results show that the robot can autonomously detect and track the welding seam effectively at different welding stations. Also, multiple-station welding efficiency can be improved and quality can also be guaranteed.

The safe and efficient autonomous navigation of mobile manipulators is still challenging in harsh manufacturing environments with dynamic obstacles and narrow spaces. This paper addresses that challenge by proposing an industrial-grade LIDAR-based navigation system for four-wheel-steering and four-wheel-driving mobile manipulators and focuses on enhancing the system’s safety and efficiency in manufacturing plants. On one hand, using an efficient soft-evidence unscented distance filter, a robust localization method is presented to eliminate dynamic interference. The variation results of scan matching are ingeniously applied to formulate a practical localization-failure-detection strategy, therefore improving localization safety under confusing working conditions. On the other hand, an efficient path-graph-based trajectory-planning method is proposed, which can instantly generate a trajectory in a safe and effective search space. Considering the regional connectivity and movement characteristics of the 4WS4WD mobile manipulator, a novel path graph is designed to construct the search space. Even in a large-scale scenario, a robot can obtain the desired trajectory within 5 ms. Ultimately, some core modules, such as a safety module and a fault-tolerant control module are integrated to form a comprehensive navigation system. The simulated and real experimental results prove the excellent performance of our navigation system, which has been successfully applied in many real-world scenarios.

With excellent mobility and flexibility, mobile manipulators have great potential for loading and unloading tasks of numerical control machine tools (CNC) in manufacturing workshops. However, because of the rough and oily ground, dynamic obstacles and the convex plate of a CNC, harsh manufacturing workshop poses a huge challenge to the localization system of an autonomous mobile manipulator. To address the above problem, this paper presents a hybrid maps enhanced localization system which mainly consists of a global localization method and a pose tracking method. Hybrid maps including hybrid grid map, multi-resolution likelihood fields (MLFs) and hybrid point map are constructed to efficaciously model the harsh environment and to improve localization performance. Our global localization method employs the convex hull sampling to spares dense Lidar data and the MLFs based branch and bound (BnB) search to speed up global search. To achieve real-time localization reliably and accurately, our pose tracking method seamlessly combines the BnB search and the adaptive Monte Carlo localization, and the Iterative Closest Point (ICP) based scan matching using the hybrid point map is adopted for higher accuracy. In addition, a distance filter improved by unscented transform is integrated into the pose tracking process to mitigate the influence of dynamic obstacles. The developed localization system is evaluated through different experiments including two weeks of loading and unloading tasks in a real manufacturing scenario, resulting in superior localization performance.

In order to accurately estimate the distribution of Trachinotus ovatus in marine cages, a novel method was developed using omnidirectional scanning sonar and deep-learning techniques. This method involved differentiating water layers and clustering data layer by layer to achieve precise location estimation. The approach comprised two main components: fish identification and fish clustering. Firstly, omnidirectional scanning sonar was employed to perform spiral detection within marine cages, capturing fish image data. These images were then labeled to construct a training dataset for an enhanced CS-YOLOv8s model. After training, the CS-YOLOv8s model was used to identify and locate fish within the images. Secondly, the cages were divided into water layers with depth intervals of 40 cm. The identification coordinate data for each water layer were clustered using the DBSCAN method to generate location coordinates for the fish in each layer. Finally, the coordinate data from all water layers were consolidated to determine the overall distribution of fish within the cage. This method was shown, through multiple experimental results, to effectively estimate the distribution of Trachinotus ovatus in marine cages, closely matching the distributions detected manually.

Obtaining clear underwater images is crucial for smart aquaculture, so it is necessary to repair degraded underwater images. Although underwater image restoration techniques have achieved remarkable results in recent years, the scarcity of labeled data poses a significant challenge to continued advancement. It is well known that semi-supervised learning can make use of unlabeled data. In this study, we proposed a semi-supervised underwater image enhancement method, MCR-UIE, which utilized multimodal contrastive learning and a dynamic quality reliability repository to leverage the unlabeled data during training. This approach used multimodal feature contrast regularization to prevent the overfitting of incorrect labels, and secondly, introduced a dynamic quality reliability repository to update the output as pseudo ground truth. The robustness and generalization of the model in pseudo-label generation and unlabeled data learning were improved. Extensive experiments conducted on the UIEB and LSUI datasets demonstrated that the proposed method consistently outperformed existing traditional and deep learning-based approaches in both quantitative and qualitative evaluations. Furthermore, its successful application to images captured from deep-sea cage aquaculture environments validated its practical value. These results indicated that MCR-UIE held strong potential for real-world deployment in intelligent monitoring and visual perception tasks in complex underwater scenarios.

Accurate underwater fish perception is a prerequisite for intelligent aquaculture, providing essential support for automated growth monitoring and precision feeding. Nevertheless, underwater imaging is severely affected by light scattering and cluttered backgrounds, making reliable fish perception and image-based non-contact fish size estimation particularly challenging. To overcome these limitations, this paper presents a geometry-aware underwater fish perception framework based on YOLOv5 for simultaneous object detection, pose estimation, and fish body size measurement. The proposed framework incorporates a Fish Geometry Coordinate Attention (FGCA) module into the backbone to enhance geometric feature representation by jointly modeling horizontal and vertical spatial dependencies, thereby improving the discrimination of elongated fish structures. In addition, a Dynamic Edge Relation Modeling (DERM) module is integrated into the neck to explicitly capture edge cues and structural relationships among key body regions, leading to more robust feature aggregation and more accurate key point localization under complex underwater conditions. Based on the predicted key points, the length and width of the fish can be estimated in a non-contact manner. Experimental results on a public underwater fish dataset demonstrate that the proposed framework achieves a Box mAP_0.5 of 93.07% and a Pose mAP_0.5 of 93.10%, consistently outperforming several representative YOLO-based detectors. Moreover, the proposed method maintains low body size estimation errors across different fish size categories. These results indicate that the proposed framework provides an accurate and practical solution for integrated underwater fish perception and image-based non-contact fish size estimation, offering significant potential for intelligent aquaculture and automated fish growth monitoring.