SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions

TL;DR

SeqGrowGraph introduces a novel method for modeling complex lane topologies by incrementally constructing directed graphs with a transformer, achieving state-of-the-art results on autonomous driving datasets.

Contribution

The paper proposes SeqGrowGraph, a new framework that learns lane topology as a chain of graph expansions using a transformer, effectively modeling complex road structures.

Findings

Achieves state-of-the-art performance on nuScenes and Argoverse 2 datasets.

Effectively models complex lane structures including loops and bidirectional lanes.

Demonstrates the effectiveness of incremental graph construction guided by a transformer.

Abstract

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 B\'ezier 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.