SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving

TL;DR

SEPT introduces a novel framework that enhances autonomous driving scene perception and topology reasoning by integrating standard-definition maps with advanced fusion strategies and auxiliary tasks, significantly improving performance.

Contribution

The paper presents a new hybrid feature fusion method and an intersection-aware keypoint detection task that effectively incorporate SD maps into perception pipelines, advancing online scene understanding.

Findings

Significant performance improvements on OpenLane-V2 dataset.

Enhanced perception and topology reasoning accuracy.

Effective integration of SD maps with BEV features.

Abstract

Online scene perception and topology reasoning are critical for autonomous vehicles to understand their driving environments, particularly for mapless driving systems that endeavor to reduce reliance on costly High-Definition (HD) maps. However, recent advances in online scene understanding still face limitations, especially in long-range or occluded scenarios, due to the inherent constraints of onboard sensors. To address this challenge, we propose a Standard-Definition (SD) Map Enhanced scene Perception and Topology reasoning (SEPT) framework, which explores how to effectively incorporate the SD map as prior knowledge into existing perception and reasoning pipelines. Specifically, we introduce a novel hybrid feature fusion strategy that combines SD maps with Bird's-Eye-View (BEV) features, considering both rasterized and vectorized representations, while mitigating potential misalignment between SD maps and BEV feature spaces. Additionally, we leverage the SD map characteristics to design an auxiliary intersection-aware keypoint detection task, which further enhances the overall scene understanding performance. Experimental results on the large-scale OpenLane-V2 dataset demonstrate that by effectively integrating SD map priors, our framework significantly improves both scene perception and topology reasoning, outperforming existing methods by a substantial margin.