The swift and accurate detection of traffic signs in traffic scenes is a pivotal aspect of environmental perception technology in autonomous driving systems. Traffic signs provide essential road information and regulatory instructions, which are critical to ensuring road safety. This paper presents the HCLT-YOLO model to address the challenges of false alarms and missed detections in complex traffic environments. Specifically, we propose a novel hybrid CNN-transformer network architecture that efficiently integrates both local and global features, thereby improving traffic sign feature representation. To further enhance the model's sensitivity to small traffic signs, we optimize the structure by introducing a dedicated small-object detection layer through upsampling and by leveraging SIoU to improve detection accuracy and computational efficiency. However, the addition of the small object detection layer and the Transformer module increases the overall computational complexity and parameter count, potentially affecting real-time performance. To address this issue, we introduce the DG-C2f module, which employs linear transformations for feature mapping, streamlining the convolution process and enhancing real-time feasibility. Experimental evaluations on the GTSDB and TT100K datasets demonstrate that the proposed model improves detection accuracy by 2.5% and 6.8%, respectively, compared to YOLOv8s models. Notably, the detection accuracy for small traffic signs improved significantly, by 6.9% and 11.7%, respectively. Additionally, processor-in-the-loop experiments on the NVIDIA Jetson AGX Orin show that the model achieves an inference speed of 46 FPS, meeting the real-time requirements for in-vehicle applications.

Ensuring safety in autonomous driving remains a significant challenge. The safety of autonomous vehicles (AVs) is profoundly influenced by the driving behavior of different drivers, especially in complex and dynamic scenarios. To address these safety risks arising from various driving behavior, this study introduces a low-risk, high-efficiency motion planning approach based on a trajectory prediction model. Firstly, an unsupervised driving style recognition framework using real-world data information is developed to categorize vehicles into three distinct driving style: cautions, normal, and aggressive. Next, a trajectory prediction model incorporating different driving styles is established using the Transformer prediction network to predict the future trajectories of surrounding vehicles (SVs). Subsequently, a motion planning framework that incorporates driving intentions is constructed to generate candidate planning trajectory cluster. Moreover, based on trajectory prediction and driving style information of SVs, a personalized risk assessment model is established, while also comprehensively considering the impact of safety, efficiency and comfort. Finally, the proposed approach is verified through real datasets and comparative experiments. The results show that the proposed framework achieves high-precision trajectory prediction and attains a 99% success rate in closed-loop testing with real datasets, thereby providing safe motion planning for AVs in dynamic environments.

Interacting with diverse and stochastic traffic participants is a critical challenge for autonomous vehicles (AVs), as it necessitates advanced decision-making systems to replicate the natural adaptability of human drivers. In particular, navigating safely and efficiently in dense traffic scenarios poses a significant challenge for decision-making, which is inherently an interactive task, i.e., nearby traffic participants will influence AVs’ action, and vice versa. Decision-making solutions that rely solely on unidirectional interaction schemes, neglecting the mutual influence between AVs and other traffic participants, may lead to overly defensive behaviors or the “freezing robot problem”. In recent years, researchers have been increasingly focused on incorporating bidirectional interactions into the decision-making process to make safe, intelligent, and socially compatible decisions. Currently, a comprehensive review of interaction-aware decision-making techniques remains lacking. To this end, this paper aims to provide a systematic review of interaction-aware decision-making methodologies for autonomous driving. Specifically, this paper analyzes the challenges in considering bidirectional interactions between AVs and other traffic participants. In addition, the state-of-the-art techniques for interaction-aware decision-making solutions are reviewed. More importantly, simulation and benchmarks for interaction-aware decision-making validation are also presented. Finally, research perspectives are highlighted to facilitate future studies for interaction-aware decision-making policy design.

To determine the factors affecting the dynamic transmitted torque response characteristics of the wet clutch, the oil film pressure, the asperity contact pressure, the applied pressure, and the dynamic transmitted torque model were established, using the fourth‐order Runge–Kutta numerical method to couple the oil film thickness and the speed difference to obtain the change curve of the joint pressure and the transmitted torque. The established model was used to study the influence of the pressure hysteresis time, lubricant viscosity, friction lining permeability, friction pair equivalent elastic modulus, and surface combined roughness RMS on the dynamic transmitted torque response during the wet clutch engagement. The results indicate that the longer the pressure hysteresis time, the smaller the permeability of the friction lining, the smaller the equivalent elastic modulus, the greater surface combined roughness RMS, the more delayed the response of the transmitted torque, and the smaller the level of jerk of the wet clutch engagement. Also, the lower the lubricant viscosity, the greater the permeability of the friction lining, and the smaller the equivalent elastic modulus is and the greater surface combined roughness RMS is, the more sensitive the transmitted torque response is to pressure response changes.

Intelligent following control for electric-drive unmanned ground vehicles (UGVs) is important for human–robot collaboration and autonomous mobility. However, target occlusion, detection noise, and short-term detection failures can reduce following stability and reliability. To address these challenges, this paper proposes a vision-based following method that integrates adaptive Kalman filtering with target-state-aware control. The proposed method updates the observation noise covariance online using an innovation-sequence sliding window and evaluates the validity of visual measurements based on the intersection over union between adjacent frames, thereby enabling target position prediction and compensation under unstable observation conditions. Meanwhile, the longitudinal velocity and lateral angular velocity are dynamically adjusted according to the target detection state, image-center offset, and distance variation to achieve continuous and stable following control. Experimental results show that the proposed method reduces the target position prediction error by approximately 10% compared with conventional Kalman filtering and maintains the longitudinal following distance at about 3 m, improving the robustness, continuity, and motion smoothness of electric-drive UGV target following in complex environments.