Large-Scale Point Cloud Map Merging Algorithm via Planarity-Adaptive Hybrid Error Fusion

Junhyuk Yang; Jongrok Lee; Mincheol Park; Jung-Hoon Hwang

doi:10.55785/JCAR.4.3.1

All Issue

2025 Vol.4, Issue 3 Next Page

Research Article

Large-Scale Point Cloud Map Merging Algorithm via Planarity-Adaptive Hybrid Error Fusion 평면성 기반 하이브리드 오차 결합을 통한 대규모 점군 맵 병합 알고리즘

30 September 2025. pp. 1-9

PDF XML

Abstract

In high-risk environments such as recent disaster sites and underground structures, it is important to build accurate, large-scale, three-dimensional point cloud maps by integrating areas explored individually by multiple autonomous robots. However, existing point cloud registration algorithms are susceptible to rapid degradation in registration performance, especially in degenerative environments with scarce geometric features such as corridors and tunnels. To solve this problem, we propose a hybrid registration algorithm that utilizes voxel-wise covariance to maintain fast computational performance efficiency while adaptively adjusting the matching error model according to the planarity of the local surface, resulting in robust performance in degenerate environments. Experimental results using the KITTI dataset and the degenerative environment dataset show that the proposed method has significantly improved registration accuracy and stability in the degenerative environment compared to the conventional method. The results of this study are expected to contribute to improving the accuracy and reliability of large-scale point cloud map merging in practical robotic exploration environments such as tunnels and disaster environments.

Keywords

Point cloud map merging

point cloud registration

LiDAR SLAM

multiple robots

최근 재난 현장이나 지하 구조물 등 고위험 환경에서는 다수의 자율 로봇이 개별적으로 탐색한 영역을 통합하여 정확한 대규모 3차원 점군 맵을 구축하는 것이 중요하다. 하지만 기존의 점군 정합 알고리즘은 특히 복도와 터널처럼 기하학적 특징이 부족한(degenerative) 환경에서는 정합 성능이 급격히 저하되는 문제가 있다. 본 연구는 이를 해결하기 위해 복셀 단위 공분산을 활용하여 빠른 계산 성능 효율을 유지하면서도, 국부 표면의 평면성에 따라 정합 오차 모델을 적응적으로 조절함으로써, degenerative 환경에서도 강건한 성능을 보이는 하이브리드 정합 알고리즘을 제안한다. KITTI 데이터셋과 degenerative 환경 데이터셋을 이용한 실험 결과, 본 연구에서 제안한 기법은 기존 알고리즘 대비 degenerative 환경에서 현저히 개선된 정합 정확도와 안정성을 나타냈다. 본 연구의 결과는 터널이나 재난 환경과 같은 실질적인 로봇 탐사 환경에서 대규모 점군 맵 병합의 정확성과 신뢰성을 향상시키는 데 기여할 것으로 기대된다.

키워드

점군 맵 병합

점군 정합

라이다 SLAM

다중 로봇

References

Birk, A., and Carpin, S. (2006). Merging occupancy grid maps from multiple robots. Proceedings of the IEEE, 94(7), pp. 1384-1397. https://doi.org/10.1109/JPROC.2006.876965

10.1109/JPROC.2006.876965

Deutsch, I., Liu, M., and Siegwart, R. (2016). A framework for multi- robot pose graph SLAM. 2016 IEEE International Conference on Real-time Computing and Robotics (RCAR), Angkor Wat, Cambodia. https://doi.org/10.1109/RCAR.2016.7784092

10.1109/RCAR.2016.7784092

Dubé, R., Cramariuc, A., Dugas, D., Nieto, J., Siegwart, R., and Cadena, C. (2018). SegMap: 3D segment mapping using data-driven descriptors. arXiv preprint arXiv:1804.09557. https://doi.org/10.15607/RSS.2018.XIV.003

10.15607/RSS.2018.XIV.003

Huang, S., Gojcic, Z., Usvyatsov, M., Wieser, A., and Schindler, K. (2021). Predator: Registration of 3D point clouds with low overlap. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA. https://doi.org/10.1109/CVPR46437.2021.00425

10.1109/CVPR46437.2021.00425

Koide, K., Yokozuka, M., Oishi, S., and Banno, A. (2021). Voxelized GICP for fast and accurate 3D point cloud registration. 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China. https://doi.org/10.1109/ICRA48506.2021.9560835

10.1109/ICRA48506.2021.9560835

Lee, D., Lim, H., and Han, S. (2024). GenZ-ICP: Generalizable and degeneracy-robust LiDAR odometry using an adaptive weighting. IEEE Robotics and Automation Letters, 10(1), pp. 152-159. https://doi.org/10.1109/LRA.2024.3498779

10.1109/LRA.2024.3498779

Qin, Z., Yu, H., Wang, C., Guo, Y., Peng, Y., and Xu, K. (2022). Geometric transformer for fast and robust point cloud registration. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA. https://doi.org/10.1109/CVPR52688.2022.01086

10.1109/CVPR52688.2022.01086

Stathoulopoulos, N., Lindqvist, B., Koval, A., Agha-Mohammadi, A., and Nikolakopoulos, G. (2024). FRAME: A modular framework for autonomous map-merging: advancements in the field. IEEE Transactions on Field Robotics, 1, pp. 1-26. https://doi.org/10.1109/TFR.2024.3419439

10.1109/TFR.2024.3419439

Wei, H., Li, R., Cai, Y., Yuan, C., Ren, Y., and Zou, Z. (2024). Large-scale multi-session point-cloud map merging. IEEE Robotics and Automation Letters, 10(1), pp. 88-95. https://doi.org/10.1109/LRA.2024.3504317

10.1109/LRA.2024.3504317

Xie, Y., Tang, Y., Zhou, R., Guo, Y., and Shi, H. (2020). Map merging with terrain-adaptive density using mobile 3D laser scanner. Robotics and Autonomous Systems, 134, 103649. https://doi.org/10.1016/j.robot.2020.103649

10.1016/j.robot.2020.103649

Yang, H., Shi, J., and Carlone, L. (2020). Teaser: Fast and certifiable point cloud registration. IEEE Transactions on Robotics, 37(2), pp. 314-333. https://doi.org/10.1109/TRO.2020.3033695

10.1109/TRO.2020.3033695

Yu, H., Li, F., Saleh, M., Busam, B., and Ilic, S. (2021). Cofinet: Reliable coarse-to-fine correspondences for robust point cloud registration. Advances in Neural Information Processing Systems 34, pp. 23872-23884. https://dl.acm.org/doi/10.5555/3540261.3542089

10.5555/3540261.3542089

Yu, Zehuan, Qiao, Z., Liu, W., Yin, H., and Shen, S. (2025). SLIM: Scalable and Lightweight LiDAR Mapping in Urban Environments. IEEE Transactions on Robotics, 41, pp. 2569-2588. https://doi.org/10.1109/TRO.2025.3554400

10.1109/TRO.2025.3554400

Information

Publisher :Korean Society of Automation and Robotics in Construction
Publisher(Ko) :(사)한국건설자동화·로보틱스학회
Journal Title :Journal of Construction Automation and Robotics
Journal Title(Ko) :건설자동화·로보틱스 논문집
Volume : 4
No :3
Pages :1-9
Received Date : 2025-08-06
Revised Date : 2025-09-03
Accepted Date : 2025-09-08
DOI :https://doi.org/10.55785/JCAR.4.3.1

Journal of Construction Automation and Robotics ISSN:2800-0552(Print) 2951-116X(Online) 건설자동화·로보틱스 논문집

All Issue