EUVIMEDEUVIMED entdecken
Crossref

Multistage Learning-Based Fusion Framework for Autonomous Vehicle Localization in GNSS-Denied Environments

Kun Wei, Xu Li, Wenkai Zhu, Weiming Hu, Yue Hu, Haoyang Che

IEEE Sensors Journal · 15.08.2025 · 25 (16) · 31897-31909

DOI: 10.1109/jsen.2025.3586680 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.08.2025. Verfasst von Kun Wei und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Key Research and Development Program of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Learning-based multisensor fusion offers a promising solution for the autonomous vehicle localization in GNSS-denied environments. However, existing methods primarily focus on real-time pose estimation while neglecting the suppression of accumulated errors in historical poses. To address this problem, we propose a multistage learning-based fusion framework that integrates pose transformation estimation, local pose correction, and global pose optimization. In Stage1, we deeply fuse geometric structure data from LiDAR, color texture data from camera, and motion state data from IMU to accurately estimate pose transformation. Continuous transformations are accumulated to generate a preliminary pose sequence. Entering Stage2, we constantly introduce absolute pose data from UWB to rapidly correct Stage1 poses in the local region. Accumulated errors in Stage1 poses are evaluated in this region by comparing poses before and after the UWB correction. Reaching Stage3, we fully leverage the spatio-temporal correlation of accumulated errors to globally optimize Stage1 poses. Measured accumulated errors in the UWB-covered region are employed as the benchmark to recursively predict accumulated errors in the non-covered region, generating a more accurate pose sequence. We conduct qualitative and quantitative experiments on KITTI dataset and our dataset to compare our fusion framework with state-of-the-art methods. Experimental results show the competitiveness of our fusion framework in improving the localization performance in GNSS-denied environments.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Key Research and Development Program of Jiangsu Province

Zitieren

APA

Wei, K., Li, X., Zhu, W., Hu, W., Hu, Y., & Che, H. (2025). Multistage Learning-Based Fusion Framework for Autonomous Vehicle Localization in GNSS-Denied Environments. IEEE Sensors Journal, 25(16), 31897-31909. https://doi.org/10.1109/jsen.2025.3586680

Vancouver

Wei K, Li X, Zhu W, Hu W, Hu Y, Che H. Multistage Learning-Based Fusion Framework for Autonomous Vehicle Localization in GNSS-Denied Environments. IEEE Sensors Journal. 2025;25(16):31897-31909. doi:10.1109/jsen.2025.3586680

BibTeX
@article{Wei2025,
  author = {Wei, Kun and Li, Xu and Zhu, Wenkai and Hu, Weiming and Hu, Yue and Che, Haoyang},
  title = {Multistage Learning-Based Fusion Framework for Autonomous Vehicle Localization in GNSS-Denied Environments},
  journal = {IEEE Sensors Journal},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {31897--31909},
  doi = {10.1109/jsen.2025.3586680}
}
Kostenlos starten →