用逐步扩展图结构建模车道拓扑，更准识别复杂道路
SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions
- 通过逐个添加节点的方式构建车道图，模拟人工制图过程
- 在nuScenes和Argoverse 2上达到当前最优性能
- 适合需要精确道路结构的自动驾驶系统
准确的车道拓扑对自动驾驶至关重要，但传统方法难以建模真实道路中常见的环路、双向车道等复杂非线性结构。本文提出SeqGrowGraph，一种将车道拓扑学习为图逐步扩展链的新框架，灵感来自人类地图绘制过程。将车道图表示为有向图 $G=(V,E)$，其中 $V$ 为交叉口节点，$E$ 为中心线边。该方法按序逐个引入顶点，每步将邻接矩阵 $A$ 从 $n imes n$ 扩展至 $(n+1) imes (n+1)$ 以编码连接关系，同时用几何矩阵 $M$ 以二次贝塞尔曲线捕捉中心线形状。通过深度优先搜索排序将图序列化，使变换器模型可自回归预测扩展序列。在 nuScenes 与 Argoverse 2 数据集上的评估表明，该方法达到当前最优性能。
原文摘要 · Abstract (English)
Accurate lane topology is essential for autonomous driving, yet traditional methods struggle to model the complex, non-linear structures-such as loops and bidirectional lanes-prevalent in real-world road structure. We present SeqGrowGraph, a novel framework that learns lane topology as a chain of graph expansions, inspired by human map-drawing processes. Representing the lane graph as a directed graph $G=(V,E)$, with intersections ($V$) and centerlines ($E$), SeqGrowGraph incrementally constructs this graph by introducing one vertex at a time. At each step, an adjacency matrix ($A$) expands from $n \times n$ to $(n+1) \times (n+1)$ to encode connectivity, while a geometric matrix ($M$) captures centerline shapes as quadratic Bézier curves. The graph is serialized into sequences, enabling a transformer model to autoregressively predict the chain of expansions, guided by a depth-first search ordering. Evaluated on nuScenes and Argoverse 2 datasets, SeqGrowGraph achieves state-of-the-art performance.
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。