RATopo: Improving Lane Topology Reasoning via Redundancy Assignment

TL;DR

RATopo introduces a redundancy assignment strategy that enhances lane topology reasoning by enabling diverse supervision and improving the detection of lane and traffic element relationships in autonomous driving.

Contribution

The paper proposes a novel redundancy assignment method that restructures the Transformer decoder to improve lane topology reasoning performance.

Findings

Significant improvement in lane-lane topology accuracy

Enhanced lane-traffic relationship modeling

Model-agnostic and easily integrable approach

Abstract

Lane topology reasoning plays a critical role in autonomous driving by modeling the connections among lanes and the topological relationships between lanes and traffic elements. Most existing methods adopt a first-detect-then-reason paradigm, where topological relationships are supervised based on the one-to-one assignment results obtained during the detection stage. This supervision strategy results in suboptimal topology reasoning performance due to the limited range of valid supervision. In this paper, we propose RATopo, a Redundancy Assignment strategy for lane Topology reasoning that enables quantity-rich and geometry-diverse topology supervision. Specifically, we restructure the Transformer decoder by swapping the cross-attention and self-attention layers. This allows redundant lane predictions to be retained before suppression, enabling effective one-to-many assignment. We also instantiate multiple parallel cross-attention blocks with independent parameters, which further enhances the diversity of detected lanes. Extensive experiments on OpenLane-V2 demonstrate that our RATopo strategy is model-agnostic and can be seamlessly integrated into existing topology reasoning frameworks, consistently improving both lane-lane and lane-traffic topology performance.