SMART: Advancing Scalable Map Priors for Driving Topology Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929701024432128 |
|---|---|
| author | Ye, Junjie Paz, David Zhang, Hengyuan Guo, Yuliang Huang, Xinyu Christensen, Henrik I. Wang, Yue Ren, Liu |
| author_facet | Ye, Junjie Paz, David Zhang, Hengyuan Guo, Yuliang Huang, Xinyu Christensen, Henrik I. Wang, Yue Ren, Liu |
| contents | Topology reasoning is crucial for autonomous driving as it enables comprehensive understanding of connectivity and relationships between lanes and traffic elements. While recent approaches have shown success in perceiving driving topology using vehicle-mounted sensors, their scalability is hindered by the reliance on training data captured by consistent sensor configurations. We identify that the key factor in scalable lane perception and topology reasoning is the elimination of this sensor-dependent feature. To address this, we propose SMART, a scalable solution that leverages easily available standard-definition (SD) and satellite maps to learn a map prior model, supervised by large-scale geo-referenced high-definition (HD) maps independent of sensor settings. Attributed to scaled training, SMART alone achieves superior offline lane topology understanding using only SD and satellite inputs. Extensive experiments further demonstrate that SMART can be seamlessly integrated into any online topology reasoning methods, yielding significant improvements of up to 28% on the OpenLane-V2 benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SMART: Advancing Scalable Map Priors for Driving Topology Reasoning Ye, Junjie Paz, David Zhang, Hengyuan Guo, Yuliang Huang, Xinyu Christensen, Henrik I. Wang, Yue Ren, Liu Computer Vision and Pattern Recognition Robotics Topology reasoning is crucial for autonomous driving as it enables comprehensive understanding of connectivity and relationships between lanes and traffic elements. While recent approaches have shown success in perceiving driving topology using vehicle-mounted sensors, their scalability is hindered by the reliance on training data captured by consistent sensor configurations. We identify that the key factor in scalable lane perception and topology reasoning is the elimination of this sensor-dependent feature. To address this, we propose SMART, a scalable solution that leverages easily available standard-definition (SD) and satellite maps to learn a map prior model, supervised by large-scale geo-referenced high-definition (HD) maps independent of sensor settings. Attributed to scaled training, SMART alone achieves superior offline lane topology understanding using only SD and satellite inputs. Extensive experiments further demonstrate that SMART can be seamlessly integrated into any online topology reasoning methods, yielding significant improvements of up to 28% on the OpenLane-V2 benchmark. |
| title | SMART: Advancing Scalable Map Priors for Driving Topology Reasoning |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2502.04329 |