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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pei, Muleilan, Shan, Jiayao, Li, Peiliang, Shi, Jieqi, Huo, Jing, Gao, Yang, Shen, Shaojie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913913408323584
author Pei, Muleilan
Shan, Jiayao
Li, Peiliang
Shi, Jieqi
Huo, Jing
Gao, Yang
Shen, Shaojie
author_facet Pei, Muleilan
Shan, Jiayao
Li, Peiliang
Shi, Jieqi
Huo, Jing
Gao, Yang
Shen, Shaojie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12246
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving
Pei, Muleilan
Shan, Jiayao
Li, Peiliang
Shi, Jieqi
Huo, Jing
Gao, Yang
Shen, Shaojie
Robotics
Computer Vision and Pattern Recognition
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.
title SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12246