TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

2025-05-23

AI Summary

To address the critical problem of topological structure errors in autonomous driving intersection topology reasoning—caused by inaccuracies in lane endpoint detection—this paper proposes the first end-to-end unified framework jointly modeling lane markings and their endpoints. We introduce an explicit endpoint detection and lane joint reasoning paradigm, incorporating: (i) a geometric distance mask-guided point-lane fusion self-attention mechanism; (ii) a point-lane graph convolutional network; and (iii) an endpoint-lane geometric matching algorithm to refine endpoint localization. Evaluated on the OpenLane-V2 benchmark, our method achieves 48.8 OLS (Ordered Lane Structure) for topology reasoning and 52.6 DET$_p$ for endpoint detection—substantially surpassing state-of-the-art methods. The implementation is publicly available.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Browser and end-point security
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Topology reasoning, which unifies perception and structured reasoning, plays a vital role in understanding intersections for autonomous driving. However, its performance heavily relies on the accuracy of lane detection, particularly at connected lane endpoints. Existing methods often suffer from lane endpoints deviation, leading to incorrect topology construction. To address this issue, we propose TopoPoint, a novel framework that explicitly detects lane endpoints and jointly reasons over endpoints and lanes for robust topology reasoning. During training, we independently initialize point and lane query, and proposed Point-Lane Merge Self-Attention to enhance global context sharing through incorporating geometric distances between points and lanes as an attention mask . We further design Point-Lane Graph Convolutional Network to enable mutual feature aggregation between point and lane query. During inference, we introduce Point-Lane Geometry Matching algorithm that computes distances between detected points and lanes to refine lane endpoints, effectively mitigating endpoint deviation. Extensive experiments on the OpenLane-V2 benchmark demonstrate that TopoPoint achieves state-of-the-art performance in topology reasoning (48.8 on OLS). Additionally, we propose DET$_p$ to evaluate endpoint detection, under which our method significantly outperforms existing approaches (52.6 v.s. 45.2 on DET$_p$). The code is released at https://github.com/Franpin/TopoPoint.

Problem

• Improves topology reasoning by detecting lane endpoints accurately
• Reduces lane endpoint deviation for correct topology construction
• Enhances autonomous driving intersection understanding via robust endpoint-lane reasoning

Innovation

• Explicitly detects lane endpoints for topology
• Uses Point-Lane Merge Self-Attention mechanism
• Employs Point-Lane Graph Convolutional Network