II-NVM — more accurate, more consistent maps (IEEE RA-L 2025)
Overview
II-NVM (Zhao et al., 2025) improves SLAM map accuracy and consistency by incorporating surface normal vector information into the mapping process, addressing the double-sided mapping problem that arises when both sides of a thin surface (walls, doors) are observed.
II-NVM pipeline: adaptive-radius normal calculation, normal-aware data association, and voxel map management.
My contribution
This is a collaboration led by Chengwei Zhao; I am a co-author (5th of 7) and contributed to the mapping methodology and evaluation. The work was published in IEEE Robotics and Automation Letters (2025).
SLAM technology plays a crucial role in indoor mapping and localization. A common challenge in indoor environments is the "double-sided mapping issue", where closely positioned walls, doors, and other surfaces are mistakenly identified as a single plane, significantly hindering map accuracy and consistency. To address this issue, this letter introduces a novel approach that leverages normal vector consistency to enhance map accuracy and consistency, integrating normal vector information into the mapping and localization process.
@article{zhao2025ii,title={II-NVM: Enhancing Map Accuracy and Consistency with Normal Vector-Assisted Mapping},author={Zhao, Chengwei and Li, Yixuan and Jian, Yina and Xu, Jie and Wang, Linji and Ma, Yongxin and Jin, Xinglai},journal={IEEE Robotics and Automation Letters},year={2025},doi={10.1109/LRA.2025.3561568},}
