To overcome the limitations of the sparrow search algorithm and the challenges of dynamic obstacle avoidance in mobile robots, an integrated method combining the enhanced sparrow search algorithm with the dynamic window approach is introduced. First, logistic–tent chaotic mapping is utilized for the initialization of the sparrow population, thereby achieving a uniform distribution of the sparrow population and simultaneously enhancing the exploratory capability of the algorithm. The implementation of the elite reverse learning strategy aims to diversify the sparrow population, thus improving the quality of initial solutions and the algorithm’s search accuracy. Additionally, the position update dynamic self-adaptive adjustment strategy is adopted to enhance the optimization capability of the algorithm by refining the position update formulas for both producers and scroungers. By combining the Lévy flight strategy and the optimal position perturbation strategy, the algorithm’s efficacy in escaping local optima can be improved. Second, an adaptive velocity adjustment strategy is presented for the dynamic window approach and optimized for its evaluation function to enhance the safety of the path. Third, the enhanced sparrow search algorithm is integrated with the dynamic window approach to tackle the problems of the non-smooth global path and inadequate dynamic obstacle avoidance capability. Both simulation and experimental results show the superiority of the enhanced sparrow search algorithm in comparison to other algorithms in terms of the path length, total rotation angle, and algorithm execution time. Notably, in comparison to the basic sparrow search algorithm, there is a decrease in average path lengths by 15.31% and 11.92% in the improved sparrow search algorithm. The integrated algorithm not only crafts local paths rooted in global paths but also adeptly facilitates real-time dynamic obstacle evasion, ensuring the robot’s safe arrival at its destination.

In this paper, we propose a Circular-ring visual location marker based on a global image-matching model to improve the positioning ability in the fiducial marker system of a single-target mobile robot. The unique coding information is designed according to the cross-ratio invariance of the projective theorem. To verify the accuracy of full 6D pose estimation using the Circular-ring marker, a 6 degree of freedom (DoF) robotic arm platform is used to design a visual location experiment. The experimental result shows in terms of small resolution images, different size markers, and long-distance tests that our proposed robot positioning method significantly outperforms AprilTag, ArUco, and Checkerboard. Furthermore, through a repeatable robot positioning experiment, the results indicated that the proposed Circular-ring marker is twice as accurate as the fiducial marker at 2–4 m. In terms of recognition speed, the Circular-ring marker processes a frame within 0.077 s. When the Circular-ring marker is used for robot positioning at 2–4 m, the maximum average translation error of the Circular-ring marker is 2.19, 3.04, and 9.44 mm. The maximum average rotation error is also 1.703°, 1.468°, and 0.782°.

The 3D scanning of a freeform structure relies on the laser probe and the localization system. The localization system, determining the effect of the point cloud reconstruction, will generate positioning errors when the laser probe works in complex paths with a fast speed. To reduce the errors, in this paper, a linear laser scanning measurement method is proposed based on binocular vision calibration. A simple and effective eight-point positioning marker attached to the scanner is proposed to complete the positioning and tracking procedure. Based on this, the method of marked point detection based on image moment and the principle of global coordinate system calibration are introduced in detail. According to the invariance principle of space distance, the corresponding points matching method between different coordinate systems is designed. The experimental results show that the binocular vision system can complete localization under different light intensities and complex environments, and that the repeated translation error of the binocular vision system is less than 0.22 mm, while the rotation error is less than 0.15°. The repeated error of the measurement system is less than 0.36 mm, which can meet the requirements of the 3D shape measurement of the complex workpiece.

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model.

Current UAV path planning methods exhibit efficient performance in navigating environments with small obstacles, such as indoor areas and outdoor forests. However, they often encounter challenges when dealing with environments characterized by large obstacles, such as expansive walls and towering structures scenario (ET scenario). These challenges often cause problems of path redundancy or even complete failure in path planning. In this letter, a hierarchical frontier-based path planning framework is proposed to enhance the adaptability of planners to diverse environments. The collected frontiers, processed by a point cloud voxel down-sampling method, are transformed into a spatially uniform point set. An analysis is conducted to explore the relationship among the UAV's current position, the target, and the potential guide point. Following this, a decision function is designed to identify the optimal local guide point from the point set to guide the UAV in path planning. The comparison of methods in the simulation environment demonstrates the outstanding performance of the proposed method, and its feasibility is further validated through real-world experiments.