The accurate prediction of the behavior of surrounding agents is crucial for the safe operation of autonomous vehicles. Currently, the dominant approach involves manually defining rules, which often fail to cover all potential scenarios. To address the rigidity and challenges of generalizing these rules to real-world driving contexts, we introduce a novel attention mechanism called “Out Way Attention”. This mechanism improves the model’s capacity to dynamically adapt to various driving situations by incorporating attention exits (out way) into the attention framework. Additionally, we present a new trajectory prediction framework that includes a learnable proposal matrix and permutation-invariant positional encoding. This matrix aids in forecasting future multimodal trajectories for multiple interacting agents in dynamic settings. The permutation-invariant positional encoding ensures that the processing sequence of agents at the same time does not influence the prediction outcomes. By integrating the proposed methods into the Transformer architecture, our approach reduces human intervention and significantly enhances the model’s adaptability, as well as improving training and inference efficiency. We have validated the effectiveness of our model on three public datasets, Argoverse, Trajnet++, and ETH/UCY. The results confirm that our method sustains robust performance in complex, highly dynamic environments with multiple interacting agents.

The optimization of auto parts supply chain logistics plays a decisive role in the development of the automotive industry. To reduce logistics costs and improve transportation efficiency, this paper addresses the joint optimization problem of multi-vehicle pickup and delivery transportation paths under time window constraints, coupled with the three-dimensional loading of goods. The model considers mixed time windows, three-dimensional loading constraints, cyclic pickup and delivery paths, varying vehicle loads and volumes, flow balance, and time window constraints. Evaluation rules for the three-dimensional loading test of goods are also set, resulting in constructing a comprehensive optimization model for the inbound logistics of auto parts and components. In this study, a Greedy-Tabu Dual-Heuristic algorithm is proposed, which integrates an Improved Greedy Algorithm with an Enhanced Tabu Search Algorithm based on the \(\varepsilon\)-sampling strategy. The overall problem-solving process for the Improved Greedy Algorithm and the Tabu Search Algorithm is outlined. The superiority, efficiency, and stability of the improved algorithm are verified by solving cases of various sizes and analyzing the algorithm’s results before and after improvement. A case study involving the third-party logistics company R Enterprise compares the pickup and delivery-separated Milk-Run mode with the simultaneous delivery and pickup Milk-Run mode. The proposed method shows a 26.67% reduction in total distance traveled and a 46.60% decrease in waiting time compared to the traditional Milk-Run approach. Additionally, when evaluated against the standard 3D loading inspection method, the proposed approach improves average vehicle load utilization by 17% and vehicle volume utilization by 15%. These findings verify the applicability and superiority of the proposed algorithms and models in practical scenarios.

While multi-object tracking is critical for autonomous driving systems, traditional algorithms exhibit three fundamental limitations in complex scenarios: (1) blurred feature representation under occlusion and re-identification scenarios causing identity switches, (2) insufficient sensitivity to scale-variant targets due to fixed geometric constraints in conventional IoU-based loss functions, and (3) gradient degradation in deep convolutional layers hindering discriminative feature learning. To address these challenges, we propose AE-StrongSORT (Attention-Enhanced StrongSORT), an attention-enhanced tracking framework featuring three systematic innovations: first, the GAM-YOLO (global attention mechanism-YOLO)hybrid architecture integrates multi-scale feature fusion with a global attention mechanism (GC2f structure). This design enhances cross-dimensional feature interaction through localized channel-spatial attention gates, significantly improving occlusion-resistant feature representation (IDF1 \(\uparrow\) 9.99%, IDsw \(\downarrow\) 9.85%). Second, the F-EIoU loss function introduces dynamic size-dependent penalty terms and difficulty-adaptive weighting factors, effectively balancing learning priorities between small targets and normal instances. Third, the optimized CBH-Conv module employs Hardswish activation and depthwise separable convolution to mitigate gradient vanishing while maintaining real-time efficiency (achieving a 17% MOTA improvement at 213 FPS).Evaluated on the MOT-16 dataset, AE-StrongSORT demonstrates substantial improvements over the baseline StrongSORT, with 17%, 2.78%, and 9.99% gains in MOTA, HOTA, and IDF1 metrics respectively, alongside significant reductions in false/missed detections. These advances establish a novel technical pathway for robust vehicle tracking in real-world traffic scenarios characterized by coexisting challenges of scale variation, motion blur, and dense occlusion.

With the development of e-commerce logistics in China, online shopping has become increasingly popular among consumers, and the fresh e-commerce industry has shifted to a pre-positioning warehouse distribution model closer to consumers. This study starts from consumer demands and considers the spatial distribution characteristics of consumers. Through cluster analysis, demand points with high consumer density are identified, and potential locations are determined through two rounds of clustering. Drawing insights from the warehousing and distribution models of Freshippo and MissFresh in Wuhan and Nanjing, four classification algorithms are compared to determine the optimal pre-positioning warehouse distribution model for the enterprise in this study. A multi-objective optimization model is established, aiming to minimize enterprise costs and maximize customer satisfaction, and the optimal site selection plan is obtained. By determining the number and locations of pre-positioning warehouses through the optimal solution, the enterprise can achieve maximum investment returns in the spatial layout of these warehouses.

To address the inherent limitations of single-modality sensors constrained by physical properties and data modalities, we propose DTC-YOLO (Depth-Texture Coupling Mechanism YOLO), a depth-texture coupled multimodal detection framework. The main contributions are as follows: RGB-LiDAR (RGB-Light Detection and Ranging) Fusion: We propose a depth-color mapping and weighted fusion strategy to effectively integrate depth and texture features. ADF³-Net (Adaptive Dimension-aware Focused Fusion Network): A feature fusion network with hierarchical perception, channel decoupling, and spatial adaptation. A dynamic gated fusion mechanism enables adaptive weighting across multidimensional features, thereby enhancing depth-texture representation. Adown Module: A dual-path adaptive downsampling module that separates high-frequency details from low-frequency semantics, reducing GFLOPs (Giga Floating-point Operations Per Second) by 10.53% while maintaining detection performance. DTC-YOLO achieves substantial improvements over the baseline: +3.50% mAP50, +3.40% mAP50-95, and +3.46% precision. Moreover, it maintains moderate improvements for medium-scale objects while significantly enhancing detection of extremely large and small objects, effectively mitigating the scale-related accuracy discrepancies of vision-only models in complex traffic environments.

Public transportation is the core of easing urban traffic congestion, reducing pollution and advancing smart city transportation intellectualization. Its refined operation relies heavily on accurate, real-time passenger origin–destination (OD) data. However, traditional manual surveys are costly with low sampling rates, while smart card big data lacks alighting information and has deviations, failing to reflect real travel behaviors and becoming a bottleneck for intelligent public transportation development. To address this, this paper proposes a bus passenger boarding/alighting detection and recognition study based on video images and the YOLO algorithm. Aiming at traditional YOLO’s shortcomings in on-vehicle scenarios (insufficient feature extraction, inefficient feature fusion, slow convergence), the baseline YOLOv8n is improved for bus scenarios’ high-density, high-occlusion and variable-target scales: (1) DAC2f structure (deformable attention + C2f) captures occluded passengers’ core features and suppresses background interference; (2) SWD-PAN enables bidirectional cross-scale feature interaction to adapt to scale differences; and (3) WIoUv3 balances sample weights for small targets and non-standard posture passengers. Experiments show that precision, recall and mAP increase by 3.68%, 5.12% and 6.26%, respectively, meeting real-time requirements. The improved YOLOv8 is deeply integrated with DeepSORT to enhance tracking stability. Tests show that MOTA reaches 31.24% (2.6% higher than YOLOv8n, 16.4% higher than YOLO-X) and MOTP reaches 88.06%, solving trajectory breakage and ID switching. This addresses traditional OD data collection pain points, providing technical support for intelligent public transportation refined management and smart city transportation optimization.