Topo2Seq: Enhanced Topology Reasoning via Topology Sequence Learning

TL;DR

Topo2Seq introduces a novel training method for lane topology reasoning in autonomous driving, using topology sequences to improve long-range perception and topological accuracy without impacting inference speed.

Contribution

It proposes a dual-decoder framework with randomized sequence learning to enhance lane topology extraction from perspective views.

Findings

Achieves state-of-the-art topology reasoning on OpenLane-V2 dataset.

Improves long-range perception and topological accuracy.

Topology sequence decoder is only used during training, ensuring efficient inference.

Abstract

Extracting lane topology from perspective views (PV) is crucial for planning and control in autonomous driving. This approach extracts potential drivable trajectories for self-driving vehicles without relying on high-definition (HD) maps. However, the unordered nature and weak long-range perception of the DETR-like framework can result in misaligned segment endpoints and limited topological prediction capabilities. Inspired by the learning of contextual relationships in language models, the connectivity relations in roads can be characterized as explicit topology sequences. In this paper, we introduce Topo2Seq, a novel approach for enhancing topology reasoning via topology sequences learning. The core concept of Topo2Seq is a randomized order prompt-to-sequence learning between lane segment decoder and topology sequence decoder. The dual-decoder branches simultaneously learn the lane topology sequences extracted from the Directed Acyclic Graph (DAG) and the lane graph containing geometric information. Randomized order prompt-to-sequence learning extracts unordered key points from the lane graph predicted by the lane segment decoder, which are then fed into the prompt design of the topology sequence decoder to reconstruct an ordered and complete lane graph. In this way, the lane segment decoder learns powerful long-range perception and accurate topological reasoning from the topology sequence decoder. Notably, topology sequence decoder is only introduced during training and does not affect the inference efficiency. Experimental evaluations on the OpenLane-V2 dataset demonstrate the state-of-the-art performance of Topo2Seq in topology reasoning.