Traffic sign detection is an essential component of an intelligent transportation system, since it provides critical road traffic data for vehicle decision-making and control. To solve the challenges of small traffic signs, inconspicuous characteristics, and low detection accuracy, a traffic sign recognition method based on improved (You Only Look Once v3) YOLOv3 is proposed. The spatial pyramid pooling structure is fused into the YOLOv3 network structure to achieve the fusion of local features and global features, and the fourth feature prediction scale of 152 × 152 size is introduced to make full use of the shallow features in the network to predict small targets. Furthermore, the bounding box regression is more stable when the distance-IoU (DIoU) loss is used, which takes into account the distance between the target and anchor, the overlap rate, and the scale. The Tsinghua–Tencent 100K (TT100K) traffic sign dataset’s 12 anchors are recalculated using the K-means clustering algorithm, while the dataset is balanced and expanded to address the problem of an uneven number of target classes in the TT100K dataset. The algorithm is compared to YOLOv3 and other commonly used target detection algorithms, and the results show that the improved YOLOv3 algorithm achieves a mean average precision (mAP) of 77.3%, which is 8.4% higher than YOLOv3, especially in small target detection, where the mAP is improved by 10.5%, greatly improving the accuracy of the detection network while keeping the real-time performance as high as possible. The detection network’s accuracy is substantially enhanced while keeping the network’s real-time performance as high as possible.

Designed to meet the demands of AGV global optimal path planning and dynamic obstacle avoidance, this paper proposes a combination of an improved A* algorithm and dynamic window method fusion algorithm. Firstly, the heuristic function is dynamically weighted to reduce the search scope and improve the planning efficiency; secondly, a path-optimization method is introduced to eliminate redundant nodes and redundant turning points in the path; thirdly, combined with the improved A* algorithm and dynamic window method, the local dynamic obstacle avoidance in the global optimal path is realized. Finally, the effectiveness of the proposed method is verified by simulation experiments. According to the results of simulation analysis, the path-planning time of the improved A* algorithm is 26.3% shorter than the traditional A* algorithm, the search scope is 57.9% less, the path length is 7.2% shorter, the number of path nodes is 85.7% less, and the number of turning points is 71.4% less. The fusion algorithm can evade moving obstacles and unknown static obstacles in different map environments in real time along the global optimal path.

Inspired by backstepping method, this paper proposes a novel adaptive stabilizing control method for a class of uncertain underactuated nonlinear systems, which is named as underactuated adaptive backstepping. Firstly, based on a virtual controller and a partial differential equation (PDE), a residual system is constructed. Then, a novel coordinate transformation is introduced to analyse the adaptive stabilizing control problem of the residual system, which breaks through the restriction of strict feedback form and achieves the estimation of unknown parameters. The proposed method first applies backstepping to form a residual system, and then uses backstepping again to design an adaptive controller for the residual system. The stability of the proposed method is proven based on Lyapunov’s theorems. Finally, two actual underactuated examples with physical damping are provided to demonstrate the effectiveness of the proposed underactuated adaptive backstepping. Note to Practitioners —This paper aims to develop a novel underactuated adaptive scheme called underactuated adaptive backstepping for underactuated mechanical systems. This scheme can effectively address the parameter uncertainty problem and achieve good control effect, even if there is uncertain physical damping which may change the equilibrium point in the system. Compared with existing methods, this scheme provides a novel design approach without linearization and approximation, which fully promotes the development of backstepping in the underactuated field. Moreover, the simulation experiments are carried out on the inertia wheel pendulum and ball and beam system with physical damping, thus effectively proving the feasibility of this scheme. In the future, the scheme will be applied to practical mechanical systems.

The performance of the tire has a very important impact on the safe driving of the car, and in the actual use of the tire, due to complex road conditions or use conditions, it will inevitably cause immeasurable wear, scratches and other damage. In order to effectively detect the damage existing in the key parts of the tire, a tire surface damage detection method based on image processing was proposed. In this method, the image of tire side is captured by camera first. Then, the collected images are preprocessed by optimizing the multi-scale bilateral filtering algorithm to enhance the detailed information of the damaged area, and the optimization effect is obvious. Thirdly, the image segmentation based on clustering algorithm is carried out. Finally, the Harris corner detection method is used to capture the “salt and pepper” corner of the target region, and the segmsegmed binary image is screened and matched based on histogram correlation, and the target region is finally obtained. The experimental results show that the similarity detection is accurate, and the damage area can meet the requirements of accurate identification.

Model compression is a technique for transforming large neural network models into smaller ones. Knowledge distillation (KD) is a crucial model compression technique that involves transferring knowledge from a large teacher model to a lightweight student model. Existing knowledge distillation methods typically facilitate the knowledge transfer from teacher to student models in one or two stages. This paper introduces a novel approach called counterclockwise block-wise knowledge distillation (CBKD) to optimize the knowledge distillation process. The core idea of CBKD aims to mitigate the generation gap between teacher and student models, facilitating the transmission of intermediate-layer knowledge from the teacher model. It divides both teacher and student models into multiple sub-network blocks, and in each stage of knowledge distillation, only the knowledge from one teacher sub-block is transferred to the corresponding position of a student sub-block. Additionally, in the CBKD process, deeper teacher sub-network blocks are assigned higher compression rates. Extensive experiments on tiny-imagenet-200 and CIFAR-10 demonstrate that the proposed CBKD method can enhance the distillation performance of various mainstream knowledge distillation approaches.

This paper is concerned with the adaptive tracking control problem for nonlinear systems with virtual control coefficients including known and unknown items. The known items are employed for controller design directly, such that more information is utilized to achieve better performance. To deal with the unknown items, a novel real control law is firstly constructed by introducing an auxiliary system. The proposed controller is designed and applied to an uncertain TCP/AQM network system, which guarantees the practical boundedness of all the signals in the closed-loop system. Finally, the effectiveness and practicability of the developed control strategy are validated by simulation results.