用高阶动态图建模交通场景，提升自动驾驶中的时空表征能力
High-Order Evolving Graphs for Enhanced Representation of Traffic Dynamics
- 构建时序双向二分图，融合高阶多聚合策略捕捉复杂交互
- 在ROAD和Waymo数据集上显著提升交通行为建模精度
- 支持新场景快速适应，适合自动驾驶系统研发者参考
我们提出一种基于高阶动态图的交通动态分析框架，旨在提升自动驾驶场景下的时空表征能力。该方法构建时序双向二分图，实时建模交通场景中的复杂交互。通过结合图神经网络（GNN）与高阶多聚合策略，显著增强对交通场景动态的建模能力，实现更精准、细致的交互分析。此外，借鉴GraphSAGE的归纳学习机制，模型可无需重训练即可适应新出现的交通场景，确保强泛化能力。在ROAD和ROAD Waymo数据集上进行了充分实验，建立了全面的基准，验证了该方法在准确捕捉交通行为方面的潜力。结果表明，高阶统计矩与特征门控注意力机制对提升交通行为分析具有重要价值，为自动驾驶技术发展奠定基础。源代码已开源：https://github.com/Addy-1998/High_Order_Graphs
原文摘要 · Abstract (English)
We present an innovative framework for traffic dynamics analysis using High-Order Evolving Graphs, designed to improve spatio-temporal representations in autonomous driving contexts. Our approach constructs temporal bidirectional bipartite graphs that effectively model the complex interactions within traffic scenes in real-time. By integrating Graph Neural Networks (GNNs) with high-order multi-aggregation strategies, we significantly enhance the modeling of traffic scene dynamics, providing a more accurate and detailed analysis of these interactions. Additionally, we incorporate inductive learning techniques inspired by the GraphSAGE framework, enabling our model to adapt to new and unseen traffic scenarios without the need for retraining, thus ensuring robust generalization. Through extensive experiments on the ROAD and ROAD Waymo datasets, we establish a comprehensive baseline for further developments, demonstrating the potential of our method in accurately capturing traffic behavior. Our results emphasize the value of high-order statistical moments and feature-gated attention mechanisms in improving traffic behavior analysis, laying the groundwork for advancing autonomous driving technologies. Our source code is available at: https://github.com/Addy-1998/High_Order_Graphs
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。