TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
This work addresses a critical bottleneck in autonomous driving systems by improving lane topology reasoning, though it appears to be an incremental advancement over existing methods.
The paper tackles the problem of lane topology reasoning in autonomous driving by proposing TopoLogic, an interpretable method that integrates geometric distance and semantic similarity to address endpoint shifts in lane detection, achieving state-of-the-art results with scores of 23.9 vs. 10.9 in TOP_ll and 44.1 vs. 39.8 in OLS on the OpenLane-V2 benchmark.
As an emerging task that integrates perception and reasoning, topology reasoning in autonomous driving scenes has recently garnered widespread attention. However, existing work often emphasizes "perception over reasoning": they typically boost reasoning performance by enhancing the perception of lanes and directly adopt MLP to learn lane topology from lane query. This paradigm overlooks the geometric features intrinsic to the lanes themselves and are prone to being influenced by inherent endpoint shifts in lane detection. To tackle this issue, we propose an interpretable method for lane topology reasoning based on lane geometric distance and lane query similarity, named TopoLogic. This method mitigates the impact of endpoint shifts in geometric space, and introduces explicit similarity calculation in semantic space as a complement. By integrating results from both spaces, our methods provides more comprehensive information for lane topology. Ultimately, our approach significantly outperforms the existing state-of-the-art methods on the mainstream benchmark OpenLane-V2 (23.9 v.s. 10.9 in TOP$_{ll}$ and 44.1 v.s. 39.8 in OLS on subset_A. Additionally, our proposed geometric distance topology reasoning method can be incorporated into well-trained models without re-training, significantly boost the performance of lane topology reasoning. The code is released at https://github.com/Franpin/TopoLogic.