EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Non-Line-of-Sight Perception Method for Autonomous Haul Trucks in Open-Pit Mines Based on 4D mmWave Radar and LiDAR Fusion

Jianjian Yang iD, Yuyu Zhang iD, Zhiyao Zheng iD, Yuyuan Zhang iD

Sensors · 21.07.2026 · 26 (14) · 4615

DOI: 10.3390/s26144615 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.07.2026. Verfasst von Jianjian Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Inner Mongolia Research Institute, China University of Mining and Technology-Beijing, Ordos 017004, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Researchand Application of Intelligent Robotic Mining and Transportation Equipment for Mines, National Natural Science Foundation of China, Inner Mongolia Research Institute, China University of Mining and Technology-Beijing.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In open-pit mining environments, large equipment frequently causes severe occlusion, creating critical perception blind spots for LiDAR. Meanwhile, 4D millimeter-wave (mmWave) radar provides penetration capability but is highly susceptible to multipath interference generated by metallic structures and uneven terrain. To address these challenges, this paper proposes a Blind-Spot Complementary Fusion (BSCF) framework that integrates 3D LiDAR and 4D mmWave radar through explicit geometric constraints. The proposed framework first suppresses multipath artifacts and performs calibrated spatiotemporal alignment between heterogeneous sensors. It then introduces high-confidence radar observations into LiDAR blind spots through spatial consistency verification, providing existence-level hidden-target risk cues under extreme occlusion. In addition, a Volume Recovery Rate (VRR) proxy metric is proposed to quantitatively describe envelope-level spatial evidence in occluded regions. Experiments conducted on real-world mining datasets demonstrate that the proposed method effectively suppresses severe multipath interference and improves scene-level cross-modal proximity by approximately 16.5%, while the overlap-region RMSE remains approximately 0.18 m. Under complete occlusion where LiDAR observations are unavailable, the framework provides target-existence risk cues with a VRR of up to 15.6%, providing a useful preliminary indication of hidden target existence. Ultimately, the proposed approach enhances perception robustness and safety for autonomous transportation systems in open-pit mines.

Schlagwörter

Stichwörter der Autor:innen

4D millimeter-wave radarLiDARautonomous mining truckmultimodal fusionnon-line-of-sight perceptionopen-pit minepoint cloud processingvolume recovery rate

Autor:innen und Institutionen

  • Inner Mongolia Research Institute, China University of Mining and Technology-Beijing, Ordos 017004, China.
  • School of Mechanical and Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China.
  • Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing 100083, China.

ORCID-Profile: Jianjian Yang, Yuyu Zhang, Zhiyao Zheng, Yuyuan Zhang

Förderung

  • Researchand Application of Intelligent Robotic Mining and Transportation Equipment for Mines
  • National Natural Science Foundation of China
  • Inner Mongolia Research Institute, China University of Mining and Technology-Beijing

Zitieren

APA

Yang, J., Zhang, Y., Zheng, Z., & Zhang, Y. (2026). Non-Line-of-Sight Perception Method for Autonomous Haul Trucks in Open-Pit Mines Based on 4D mmWave Radar and LiDAR Fusion. Sensors, 26(14), 4615. https://doi.org/10.3390/s26144615

Vancouver

Yang J, Zhang Y, Zheng Z, Zhang Y. Non-Line-of-Sight Perception Method for Autonomous Haul Trucks in Open-Pit Mines Based on 4D mmWave Radar and LiDAR Fusion. Sensors. 2026;26(14):4615. doi:10.3390/s26144615

BibTeX
@article{Yang2026,
  author = {Yang, Jianjian and Zhang, Yuyu and Zheng, Zhiyao and Zhang, Yuyuan},
  title = {Non-Line-of-Sight Perception Method for Autonomous Haul Trucks in Open-Pit Mines Based on 4D mmWave Radar and LiDAR Fusion},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4615},
  doi = {10.3390/s26144615}
}
Kostenlos starten →