PillarSLAM: A Pillar-Based Structural Semantic SLAM With Novel Relocalization for Autonomous Driving in Underground Parking Lot
IEEE Transactions on Intelligent Transportation Systems · 2026-02 · 27 (2) · 2027-2039
DOI: 10.1109/tits.2025.3634152 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-02. Verfasst von Yanchao Dong und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Municipal Science and Technology Major Project, Aeronautical Science Foundation of China.
Abstract (Originalsprache)
Simultaneous localization and mapping (SLAM) is a fundamental technology of autonomous vehicle, yet its deployment in large-scale, low-texture indoor environments remains highly challenging. The paper introduces PillarSLAM, a multimodal, pillar-based semantic SLAM framework designed to address the limitations of conventional feature-driven approaches. First, a dynamic pillar modeling strategy is proposed to continuously refine pillar dimensions without singularity. Second, a geometry-driven data association method is developed, utilizing distance and pose constraints to uniquely identify individual pillar faces. Third, an object-centric multi-view loop closure is introduced, leveraging pillar positions instead of viewpoint-dependent keypoints to achieve robust long-range corrections. Finally, a topology-based relocalization method is designed, where subgraph of observed pillars are matched to the global map via graph isomorphism, enabling reliable place recognition independent of visual appearance. Experiments in both simulated and real-world environments demonstrate that PillarSLAM significantly outperforms state-of-the-art SLAM systems in mapping accuracy and relocalization robustness under challenging conditions.
Förderung
- National Natural Science Foundation of China
- Shanghai Municipal Science and Technology Major Project
- Aeronautical Science Foundation of China
- Fundamental Research Funds for the Central Universities
- 19th Experimental Teaching Reform Fund of Tongji University
Zitieren
APA
Dong, Y., Ye, J., Xu, S., Tang, J., & He, B. (2026). PillarSLAM: A Pillar-Based Structural Semantic SLAM With Novel Relocalization for Autonomous Driving in Underground Parking Lot. IEEE Transactions on Intelligent Transportation Systems, 27(2), 2027-2039. https://doi.org/10.1109/tits.2025.3634152
Vancouver
Dong Y, Ye J, Xu S, Tang J, He B. PillarSLAM: A Pillar-Based Structural Semantic SLAM With Novel Relocalization for Autonomous Driving in Underground Parking Lot. IEEE Transactions on Intelligent Transportation Systems. 2026;27(2):2027-2039. doi:10.1109/tits.2025.3634152
BibTeX
@article{Dong2026,
author = {Dong, Yanchao and Ye, Jinfei and Xu, Sixiong and Tang, Jie and He, Bin},
title = {PillarSLAM: A Pillar-Based Structural Semantic SLAM With Novel Relocalization for Autonomous Driving in Underground Parking Lot},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {2},
pages = {2027--2039},
doi = {10.1109/tits.2025.3634152}
}
EUVIMED