EUVIMEDEUVIMED entdecken
Crossref

LiteFT-PR: Lightweight and Fault-Tolerant LiDAR-Camera Fusion Network for Robust Place Recognition via Model Distillation

Zihang Wang, Xu Li, Guanyu Zong, Xieyuanli Chen, Dong Kong, Yiming Peng, Wenkai Zhu, Kaiyi Wang

IEEE Robotics and Automation Letters · 2026-04 · 11 (4) · 4267-4274

DOI: 10.1109/lra.2026.3662634 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2026-04. Verfasst von Zihang Wang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: Jiangsu Provincial Key Research and Development Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Place recognition (PR) is a key component of simultaneous localization and mapping (SLAM) in autonomous vehicles and robotics. By efficiently matching descriptors generated from the current scene with a prebuilt reference database, existing PR methods enable accurate vehicle re-localization. However, achieving robust and efficient PR remains challenging, particularly in scenarios with sensor corruptions, such as camera overexposure and LiDAR beam missing, which degrade the performance of traditional PR systems. To address this issue, we propose LiteFT-PR, a fault-tolerant and lightweight LiDAR-camera fusion PR network. To balance accuracy and efficiency under extreme conditions, we adopt a knowledge distillation framework for PR tasks: the teacher network learns robust representations under corrupted sensing, while the student distills and inherits this knowledge for lightweight deployment. In addition, we design efficient multimodal fusion mechanisms for both networks, enabling robust place recognition under various sensor corruption scenarios while significantly reducing computational overhead. To meet real-world deployment needs, we build a dataset covering multiple types of sensor failures and conduct extensive field experiments. Experimental results demonstrate that LiteFT-PR, with only 7.24 M of parameters, outperforms state-of-the-art PR methods in both accuracy and efficiency.

Förderung

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

Zitieren

APA

Wang, Z., Li, X., Zong, G., Chen, X., Kong, D., Peng, Y., Zhu, W., & Wang, K. (2026). LiteFT-PR: Lightweight and Fault-Tolerant LiDAR-Camera Fusion Network for Robust Place Recognition via Model Distillation. IEEE Robotics and Automation Letters, 11(4), 4267-4274. https://doi.org/10.1109/lra.2026.3662634

Vancouver

Wang Z, Li X, Zong G, Chen X, Kong D, Peng Y, et al. LiteFT-PR: Lightweight and Fault-Tolerant LiDAR-Camera Fusion Network for Robust Place Recognition via Model Distillation. IEEE Robotics and Automation Letters. 2026;11(4):4267-4274. doi:10.1109/lra.2026.3662634

BibTeX
@article{Wang2026,
  author = {Wang, Zihang and Li, Xu and Zong, Guanyu and Chen, Xieyuanli and Kong, Dong and Peng, Yiming and Zhu, Wenkai and Wang, Kaiyi},
  title = {LiteFT-PR: Lightweight and Fault-Tolerant LiDAR-Camera Fusion Network for Robust Place Recognition via Model Distillation},
  journal = {IEEE Robotics and Automation Letters},
  year = {2026},
  volume = {11},
  number = {4},
  pages = {4267--4274},
  doi = {10.1109/lra.2026.3662634}
}
Kostenlos starten →