EUVIMEDEUVIMED entdecken
Crossref

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

Chenghao Shi, Xieyuanli Chen, Junhao Xiao, Bin Dai, Huimin Lu

IEEE Transactions on Robotics · 2024 · 40 · 2620-2640

DOI: 10.1109/tro.2024.3386363 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2024. Verfasst von Chenghao Shi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Fund for key Laboratory of Space Flight Dynamics Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Loop closing and relocalization are crucial techniques to establish reliable and robust long-term SLAM by addressing pose estimation drift and degeneration. This article begins by formulating loop closing and relocalization within a unified framework. Then, we propose a novel multihead network, LCR-Net, to tackle both tasks effectively. It exploits novel feature extraction and a pose-aware attention mechanism to precisely estimate similarities and 6-DoF poses between pairs of LiDAR scans. In the end, we integrate our LCR-Net into a SLAM system and achieve robust and accurate online LiDAR SLAM in outdoor driving environments. We thoroughly evaluate our LCR-Net through three setups derived from loop closing and relocalization, including candidate retrieval, closed-loop point cloud registration, and continuous relocalization using multiple datasets. The results demonstrate that LCR-Net excels in all three tasks, surpassing the state-of-the-art methods and exhibiting a remarkable generalization ability. Notably, our LCR-Net outperforms baseline methods without using a time-consuming robust pose estimator, rendering it suitable for online SLAM applications. To the best of the authors' knowledge, the integration of LCR-Net yields the first LiDAR SLAM with the capability of deep loop closing and relocalization.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Fund for key Laboratory of Space Flight Dynamics Technology
  • Young Elite Scientists Sponsorship Program by CAST
  • Major Project of Natural Science Foundation of Hunan Province

Zitieren

APA

Shi, C., Chen, X., Xiao, J., Dai, B., & Lu, H. (2024). Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM. IEEE Transactions on Robotics, 40, 2620-2640. https://doi.org/10.1109/tro.2024.3386363

Vancouver

Shi C, Chen X, Xiao J, Dai B, Lu H. Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM. IEEE Transactions on Robotics. 2024;40:2620-2640. doi:10.1109/tro.2024.3386363

BibTeX
@article{Shi2024,
  author = {Shi, Chenghao and Chen, Xieyuanli and Xiao, Junhao and Dai, Bin and Lu, Huimin},
  title = {Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM},
  journal = {IEEE Transactions on Robotics},
  year = {2024},
  volume = {40},
  pages = {2620--2640},
  doi = {10.1109/tro.2024.3386363}
}
Kostenlos starten →