B$^2$F-Map: Crowd-sourced Mapping with Bayesian B-spline Fusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910037833678848 |
|---|---|
| author | Xie, Yiping Xia, Yuxuan Stenborg, Erik Fu, Junsheng Beauvisage, Axel Garcia, Gabriel E. Wu, Tianyu Hendeby, Gustaf |
| author_facet | Xie, Yiping Xia, Yuxuan Stenborg, Erik Fu, Junsheng Beauvisage, Axel Garcia, Gabriel E. Wu, Tianyu Hendeby, Gustaf |
| contents | Crowd-sourced mapping offers a scalable alternative to creating maps using traditional survey vehicles. Yet, existing methods either rely on prior high-definition (HD) maps or neglect uncertainties in the map fusion. In this work, we present a complete pipeline for HD map generation using production vehicles equipped only with a monocular camera, consumer-grade GNSS, and IMU. Our approach includes on-cloud localization using lightweight standard-definition maps, on-vehicle mapping via an extended object trajectory (EOT) Poisson multi-Bernoulli (PMB) filter with Gibbs sampling, and on-cloud multi-drive optimization and Bayesian map fusion. We represent the lane lines using B-splines, where each B-spline is parameterized by a sequence of Gaussian distributed control points, and propose a novel Bayesian fusion framework for B-spline trajectories with differing density representation, enabling principled handling of uncertainties. We evaluate our proposed approach, B$^2$F-Map, on large-scale real-world datasets collected across diverse driving conditions and demonstrate that our method is able to produce geometrically consistent lane-level maps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01673 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | B$^2$F-Map: Crowd-sourced Mapping with Bayesian B-spline Fusion Xie, Yiping Xia, Yuxuan Stenborg, Erik Fu, Junsheng Beauvisage, Axel Garcia, Gabriel E. Wu, Tianyu Hendeby, Gustaf Robotics Crowd-sourced mapping offers a scalable alternative to creating maps using traditional survey vehicles. Yet, existing methods either rely on prior high-definition (HD) maps or neglect uncertainties in the map fusion. In this work, we present a complete pipeline for HD map generation using production vehicles equipped only with a monocular camera, consumer-grade GNSS, and IMU. Our approach includes on-cloud localization using lightweight standard-definition maps, on-vehicle mapping via an extended object trajectory (EOT) Poisson multi-Bernoulli (PMB) filter with Gibbs sampling, and on-cloud multi-drive optimization and Bayesian map fusion. We represent the lane lines using B-splines, where each B-spline is parameterized by a sequence of Gaussian distributed control points, and propose a novel Bayesian fusion framework for B-spline trajectories with differing density representation, enabling principled handling of uncertainties. We evaluate our proposed approach, B$^2$F-Map, on large-scale real-world datasets collected across diverse driving conditions and demonstrate that our method is able to produce geometrically consistent lane-level maps. |
| title | B$^2$F-Map: Crowd-sourced Mapping with Bayesian B-spline Fusion |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.01673 |