In order to solve the problem of low recognition rate and low real-time performance of vehicle detection in complex road environment, a data-driven forward vehicle detection algorithm based on improved tiny-YOLOv3 is proposed. Based on tiny-YOLOv3, the context feature information is combined to increase the two scale detections of tiny-YOLOv3 to three. The spatial pyramid pooling (SPP) module is added to increase the number of feature channels to improve the network feature extraction ability. According to the dense arrangement of vehicles on the horizontal axis in the road image ahead, we change the grid size of tiny-YOLOv3 and increase the number of candidate boxes on the horizontal axis. In addition, combined with the characteristics of the vehicle size in the road image ahead, K-means clustering method is used to select the appropriate number and size of target candidate boxes. We obtain the optimal detection model by multi-scale training of the improved network. The experimental results show that the average accuracy of the improved algorithm on the KITTI datasets is 91.03%, which is 7.12% higher than that of tiny-YOLOv3. And the detection speed of improved network is 144 frames/s, which meets the real-time requirements.

Considering the low coverage of roadside cooperative devices at the current time, automated driving should detect all road markings relevant to driving safety, such as traffic signs that tend to be of great variety but are fewer in number. In this work, we propose an innovative few-shot object detection framework, namely Meta-YOLO, whose challenge is to generalize to the unseen classes by using only a few seen classes. Simply integrating the YOLO mechanism into a meta-learning pipeline will encounter problems in terms of computational efficiency and mistake detection. Therefore, we construct a two-stage meta-learner $ℱ$ model that can learn the learner initialization, the learner update direction and learning rate, all in a single meta-learning process. To facilitate deep networks with learning, the fidelity features of the targets improve the performance of meta-learner $ℱ$, but we also design a feature decorrelation module (FDM), which firstly transforms non-linear features into computable linear features based on RFF, and secondly perceives and removes global correlations by iteratively saving and reloading the features and sample weights of the model. We introduce a three-head module to learn global, local and patch correlations with the category detection result outputted by the aggregation in meta-learner $ℱ$, which endows a multi-scale ability with detector $\varphi$. In our experiments, the proposed algorithm outperforms the three benchmark algorithms and improves the mAP of few-shot detection by 39.8%.

With the acceleration of urbanization process, the country’s strong support for the healthy development of the logistics industry has made urban logistics become a hot topic in recent years. With the increase in the number of logistics vehicles, traffic accidents have become more frequent. Intelligent vehicle collision avoidance system is an important part of advanced safety technology. To increase veracity and practicability of logistics vehicle safety collision avoidance, this paper presents a safety distance model for longitudinal collision avoidance of logistics vehicles considering road slope and road adhesion coefficient. Based on the vehicle kinetic theory, the information of surrounding environment for the vehicle is obtained using environment sensing system adequately, a method is designed to estimate the road slope and road adhesion coefficient. Combined with vehicle dynamics and tire normal force variation, the road slope was estimated. Based on the relationship between slip rate and adhesion coefficient, the Least Square Method is used for multivariate fitting to obtain the relationship between rolling resistance coefficient and road adhesion coefficient, estimate the road adhesion coefficient, and the maximum deceleration of vehicle braking is modified. Therefore, the safety distance model is established. In order to verify the accuracy and effectiveness of the model, three cases are designed for verification: case I is verification of the safety distance model considering the slope factor; case II is verification of the safety distance model considering the road adhesion factor; case III is the safety distance verification considering both the factors of slope and road adhesion coefficient. The result shows that it is necessary to take the factors of road slope and adhesion coefficient into the safety distance model to improve the accuracy of the model.

Despite the rapid advancement in the field of autonomous driving vehicles, developing a safe and sensible decision-making system remains a challenging problem. The driving decision-making module is one of the most essential sections of the entire autonomous driving system, and the decision generated from it can significantly impinge the lives and property of passengers. Complicated interactions among traffic participants have the most profound impact on the decision-making process, yet the interactions are often simplified or overlooked due to their complexity and implicit nature. To address this issue, this work proposes an Edge-Enhanced Graph Attention Reinforcement Learning (EGARL) framework that aims to make rational driving decisions by comprehensively modeling the interactions among agents. EGARL comprises three core components: a graphical representation of the traffic scenario that covers both topological and interactive information; an Edge-enhanced Graph Attention Network (E-GAT) that utilizes the graphical representation to extract interactive features by comprehensively considering nodes and edges of the graph; and a deep reinforcement learning method that generates driving decisions based on the current state and features extracted from E-GAT. Experimental results demonstrate the satisfying performance of EGARL. Our proposed framework can contribute to the development of intelligent transportation systems, enhancing the safety and efficiency of driving.