Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908888728600576 |
|---|---|
| author | Liang, Shiyi Chang, Xinyuan Wu, Changjie Yan, Huiyuan Bai, Yifan Liu, Xinran Zhang, Hang Yuan, Yujian Zeng, Shuang Xu, Mu Wei, Xing |
| author_facet | Liang, Shiyi Chang, Xinyuan Wu, Changjie Yan, Huiyuan Bai, Yifan Liu, Xinran Zhang, Hang Yuan, Yujian Zeng, Shuang Xu, Mu Wei, Xing |
| contents | Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, existing methods either focus solely on geometric elements or treat rules as temporary classifications, failing to capture their persistent effectiveness across extended driving sequences. In this paper, we present PAMR (Persistent Autoregressive Mapping with Traffic Rules), a novel framework that performs autoregressive co-construction of lane vectors and traffic rules from visual observations. Our approach introduces two key mechanisms: Map-Rule Co-Construction for processing driving scenes in temporal segments, and Map-Rule Cache for maintaining rule consistency across these segments. To properly evaluate continuous and consistent map generation, we develop MapDRv2, featuring improved lane geometry annotations. Extensive experiments demonstrate that PAMR achieves superior performance in joint vector-rule mapping tasks, while maintaining persistent rule effectiveness throughout extended driving sequences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22756 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving Liang, Shiyi Chang, Xinyuan Wu, Changjie Yan, Huiyuan Bai, Yifan Liu, Xinran Zhang, Hang Yuan, Yujian Zeng, Shuang Xu, Mu Wei, Xing Robotics Artificial Intelligence Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, existing methods either focus solely on geometric elements or treat rules as temporary classifications, failing to capture their persistent effectiveness across extended driving sequences. In this paper, we present PAMR (Persistent Autoregressive Mapping with Traffic Rules), a novel framework that performs autoregressive co-construction of lane vectors and traffic rules from visual observations. Our approach introduces two key mechanisms: Map-Rule Co-Construction for processing driving scenes in temporal segments, and Map-Rule Cache for maintaining rule consistency across these segments. To properly evaluate continuous and consistent map generation, we develop MapDRv2, featuring improved lane geometry annotations. Extensive experiments demonstrate that PAMR achieves superior performance in joint vector-rule mapping tasks, while maintaining persistent rule effectiveness throughout extended driving sequences. |
| title | Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.22756 |