In this paper, aiming at the problem of poor quality and low spraying efficiency of irregular for complex freeform surfaces, a new spray painting robot trajectory planning method based on point cloud slicing technology is proposed. Firstly, the point cloud data of the workpiece to be sprayed is obtained by laser scanning. The point cloud data is processed to obtain the point cloud model of the sprayed workpiece. Then the section polysemy line is obtained after slice acquisition and section data processing of the point cloud model. The section polysemy line is sampled on average, and the normal vector of all sampling points is estimated. Finally, interpolation algorithm is used to connect the data points to obtain the space trajectory of spraying robot. In addition, the droplet trajectory model for electrostatic spray painting is established. The experimental results show that the method fully meets the requirements of coating thickness and improves the spraying efficiency and uniformity of coating.

Real-time detection of apples in natural environment is a necessary condition for robots to pick apples automatically, and it is also a key technique for orchard yield prediction and fine management. To make the harvesting robots detect apples quickly and accurately in complex environment, a Des-YOLO v4 algorithm and a detection method of apples are proposed. Compared with the current mainstream detection algorithms, YOLO v4 has better detection performance. However, the complex network structure of YOLO v4 will reduce the picking efficiency of the robot. Therefore, a Des-YOLO structure is proposed, which reduces network parameters and improves the detection speed of the algorithm. In the training phase, the imbalance of positive and negative samples will cause false detection of apples. To solve the above problem, a class loss function based on AP-Loss (Average Precision Loss) is proposed to improve the accuracy of apple recognition. Traditional YOLO algorithm uses NMS (Nonmaximum Suppression) method to filter the prediction boxes, but NMS cannot detect the adjacent apples when they overlap each other. Therefore, Soft-NMS is used instead of NMS to solve the problem of missing detection, so as to improve the generalization of the algorithm. The proposed algorithm is tested on the self-made apple image data set. The results show that Des-YOLO v4 network has ideal features with a mAP (mean Average Precision) of apple detection of 97.13%, a recall rate of 90%, and a detection speed of 51 f/s. Compared with traditional network models such as YOLO v4 and Faster R-CNN, the Des-YOLO v4 can meet the accuracy and speed requirements of apple detection at the same time. Finally, the self-designed apple-harvesting robot is used to carry out the harvesting experiment. The experiment shows that the harvesting time is 8.7 seconds and the successful harvesting rate of the robot is 92.9%. Therefore, the proposed apple detection method has the advantages of higher recognition accuracy and faster recognition speed. It can provide new solutions for apple-harvesting robots and new ideas for smart agriculture.

Although the ocean is rich in energy and covers a vast portion of the planet, the present results of underwater target identification are not sufficient because of the complexity of the underwater environment. An enhanced technique based on YOLOv8 is proposed to solve the problems of low identification accuracy and low picture quality in the target detection of current underwater robots. Firstly, considering the issue of model parameters, only the convolution of the ninth layer is modified, and the deformable convolution is designed to be adaptive. Certain parts of the original convolution are replaced with DCN v3, in order to address the issue of the deformation of underwater photos with fewer parameters and more effectively capture the deformation and fine details of underwater objects. Second, the ability to recognize multi-scale targets is improved by employing SPPFCSPC, and the ability to express features is improved by combining high-level semantic features with low-level shallow features. Lastly, using WIoU loss v3 instead of the CIoU loss function improves the overall performance of the model. The enhanced algorithm mAP achieves 86.5%, an increase of 2.1% over the YOLOv8s model, according to the results of the testing of the underwater robot grasping. This meets the real-time detection needs of underwater robots and significantly enhances the performance of the object detection model.

Automated tool trajectory planning for spray painting robots is still a challenging problem, especially for a large complex curved surface. This paper presents a new method of trajectory optimization for spray painting robot based on exponential mean Bézier method. The definition and the three theorems of exponential mean Bézier curves are discussed. Then a spatial painting path generation method based on exponential mean Bézier curves is developed. A new simple algorithm for trajectory optimization on complex curved surfaces is introduced. A golden section method is adopted to calculate the values. The experimental results illustrate that the exponential mean Bézier curves enhanced flexibility of the path planning, and the trajectory optimization algorithm achieved satisfactory performance. This method can also be extended to other applications.

With the advancement of agricultural automation technologies, apple-harvesting robots have gradually become a focus of research. As their “perceptual core,” machine vision systems directly determine picking success rates and operational efficiency. However, existing vision systems still exhibit significant shortcomings in target detection and positioning accuracy in complex orchard environments (e.g., uneven illumination, foliage occlusion, and fruit overlap), which hinders practical applications. This study proposes a visual system for apple-harvesting robots based on improved Mask R-CNN and binocular vision to achieve more precise fruit positioning. The binocular camera (ZED2i) carried by the robot acquires dual-channel apple images. An improved Mask R-CNN is employed to implement instance segmentation of apple targets in binocular images, followed by a template-matching algorithm with parallel epipolar constraints for stereo matching. Four pairs of feature points from corresponding apples in binocular images are selected to calculate disparity and depth. Experimental results demonstrate average coefficients of variation and positioning accuracy of 5.09% and 99.61%, respectively, in binocular positioning. During harvesting operations with a self-designed apple-picking robot, the single-image processing time was 0.36 s, the average single harvesting cycle duration reached 7.7 s, and the comprehensive harvesting success rate achieved 94.3%. This work presents a novel high-precision visual positioning method for apple-harvesting robots.

The underwater vehicle manipulator system is a powerful tool for the exploration and development of marine resources. Due to the complexity of the marine environment, there are many disturbance factors and difficult to control. Taking the fixed depth control in hovering mode as an example, the vertical plane decoupling control model is established, and the adaptive sliding mode control method based on the disturbance observation is studied. The nonlinear disturbance observation is used to estimate the external unknown disturbance in real time, and the adaptive sliding mode method is used for compensation control. Simulation results show that the control method can effectively compensate for the sudden disturbance term, does not produce obvious trim motion, has strong robustness, and provides a reliable and stable base for the operation of the underwater manipulators. Finally, the operation experiments in the pool and real sea area under the disturbance condition are carried out, respectively. The experimental results show that the control effect is good and the stability is greatly improved compared with the traditional control method.