T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving

Understanding the traffic scenes and then generating highdefinition (HD) maps present significant challenges in autonomous driving. In this paper, we defined a novel Traffic Topology Scene Graph (T 2 SG), a unified scene graph explicitly modeling the lane, controlled and guided by different road signals (e.g., right turn), and topology relationships among them, which is always ignored by previous high-definition (HD) mapping methods. For the generation of T 2 SG, we propose TopoFormer, a novel onestage Topology Scene Graph TransFormer with two newlydesigned layers. Specifically, TopoFormer incorporates a Lane Aggregation Layer (LAL) that leverages the geometric distance among the centerline of lanes to guide the aggregation of global information. Furthermore, we proposed a Counterfactual Intervention Layer (CIL) to model the reasonable road structure (e.g., intersection, straight) among lanes under counterfactual intervention. Then the generated T 2 SG can provide a more accurate and explainable description of the topological structure in traffic scenes. Experimental results demonstrate that Topo-Former outperforms existing methods on the T 2 SG generation task, and the generated T 2 SG significantly enhances traffic topology reasoning in downstream tasks, achieving a state-of-the-art performance of 46.3 OLS on the OpenLane-V2 benchmark. Our source code is available at https://github.com/MICLAB-BUPT/T2SG .