A diffusion model-based intelligent optimization method of rural road environments

作者：Bo Yu, Zehong Zhu, Yuren Chen, Junhua Wang, Kun Gao, Xinming Qian · 发表于：International Journal of Transportation Science and Technology · 年份：2025 · DOI：10.1016/j.ijtst.2025.01.014 · 被引用次数：5 · 研究领域：Traffic Prediction and Management Techniques、Traffic control and management、Simulation and Modeling Applications

• An intelligent optimization method for rural road environments is proposed by image generation technology. • The impacts of environmental semantic components on driving speed are analyzed by explainable machine learning. • These impacts are utilized as the guidance for intelligent optimization. • Diffusion model is employed to directly generate optimized images of rural road environments. • A CycleGAN-based optimization method is also established for comparison. Well-designed rural road environments can guide drivers to adopt reasonable driving behaviors, thereby significantly improving the driving experience and ensuring road safety. Existing methods for optimizing rural road environments mainly rely on expert knowledge, have low automation degrees, and are limited in efficiency and accuracy. Therefore, this study aims to propose an intelligent optimization method for rural road environments by using image generation technology. Using environment images from a naturalistic driving dataset, the area and location information of semantic components (e.g., lane markings, vegetation, guardrails, traffic signs, etc.) in rural road environments are extracted, and their impacts on driving speed is analyzed based on explainable machine learning (XGBoost and SHAP). These impacts are then utilized to determine how to adjust and optimize the road environment components at appropriate locations (i.e., obtain the optimization scheme). Then, a novel image generation technique, Diffusion ...