pith. sign in

arxiv: 2606.25796 · v1 · pith:6AALF5PZnew · submitted 2026-06-24 · 💻 cs.RO

MIL-LC: A Robust Magnetometer-Inertial-LiDAR Fusion Multimodal Localization Framework

Qiyang Lyu , Zhenyu Wu , Wei Wang , Hongming Shen , Danwei Wang This is my paper

Pith reviewed 2026-06-25 20:50 UTC · model grok-4.3

classification 💻 cs.RO
keywords magnetometerLiDARmultimodal fusionlocalizationautonomous mobile robotsambient magnetic fieldGNSS-denied
0
0 comments X

The pith

Fusing magnetometer, inertial and LiDAR data enables reliable localization for robots in challenging indoor environments.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper introduces the MIL-LC framework to fuse magnetometer, inertial, and LiDAR sensors for localizing autonomous mobile robots. It targets environments like offices and underground parking where GNSS is unavailable and geometric features are repetitive or absent. The approach uses ambient magnetic field variations as a key signal that requires no extra infrastructure or feature extraction. If successful, it would allow more flexible and cost-effective robot deployment compared to methods relying on beacons or heavy geometric processing.

Core claim

The MIL-LC framework provides reliable localization by fusing data from a custom magnetometer-inertial-LiDAR sensor suite, maintaining performance when LiDAR experiences geometric degeneration or when the magnetic map changes over long-term deployment, as validated in simulation and real-world tests.

What carries the argument

The MIL-LC multimodal fusion framework that integrates ambient magnetic field measurements to complement inertial and LiDAR data for localization.

If this is right

  • Robots can localize accurately without depending on geometric or texture features.
  • Deployment becomes possible without installing additional infrastructure like beacons.
  • Localization remains stable during extended operations despite shifts in the magnetic environment.
  • Both simulated and physical experiments confirm the framework's robustness in GNSS-denied settings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The method could be adapted to other robotic platforms beyond AMRs.
  • Combining this with other modalities might further improve performance in extreme cases.
  • Long-term studies on magnetic field stability in different building types would help assess scalability.

Load-bearing premise

The ambient magnetic field supplies distinctive and repeatable signatures usable for localization in typical AMR environments.

What would settle it

Demonstrating failure of localization in a space where the magnetic field lacks variation or changes unpredictably without corresponding updates to the map.

Figures

Figures reproduced from arXiv: 2606.25796 by Danwei Wang, Hongming Shen, Qiyang Lyu, Wei Wang, Zhenyu Wu.

Figure 1
Figure 1. Figure 1: The high-fidelity simulated seaport environments and the localization [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Data synchronization and motion undistortion of magnetic and LiDAR [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Left side: Visualization of different experimental environments, including simulated (a) industrial warehouse, (b) vehicle tunnel, (c) logistics seaport, [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The Scout Mini AMR is employed in both real-world and simulated [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Comparison of ATE (m) of Seq 1 in simulated warehouse environment [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Cumulative probability of the Absolute Trajectory Error (ATE, m) of [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: An illustration of the change of vehicles in the carpark environments. [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: An illustration of the capability to highlight magnetically disturbed [PITH_FULL_IMAGE:figures/full_fig_p009_10.png] view at source ↗
read the original abstract

Localization in challenging environments, such as GNSS-denied, geometrically repetitive, or textureless scenes commonly found in offices, hotels, and underground parking facilities, remains an open problem for reliable autonomous mobile robot (AMR) deployment. Single-modality localization methods are inherently limited by the constraints of individual sensors. Although multimodal fusion frameworks have shown improved robustness, most existing approaches still rely heavily on geometric or texture features, or on infrastructure-based beacons, which increase installation and maintenance costs while reducing deployment flexibility. Recently, ambient magnetic field (AMF)-based localization has attracted growing attention because it does not depend on geometric or texture features, nor does it require additional infrastructure, making it a promising complementary modality for AMR localization. However, existing studies have only explored such fusion in pedestrian scenarios using smartphone-mounted sensor suites, and practical solutions for AMR systems remain largely unexplored. To address this gap, this article proposes a magnetometer-inertial-LiDAR fused multimodal localization framework with a custom-designed sensor suite, termed MIL-LC, which provides reliable localization even when LiDAR suffers from geometric degeneration or when the magnetic map changes during long-term deployment. Extensive experiments in both simulation and real-world environments demonstrate that the proposed MIL-LC framework achieves robust and accurate localization performance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript proposes MIL-LC, a magnetometer-inertial-LiDAR fusion framework for AMR localization in GNSS-denied, geometrically repetitive or textureless environments. It claims that ambient magnetic field signatures enable reliable localization when LiDAR degenerates geometrically or when the magnetic map changes over long-term deployment, without requiring additional infrastructure, and supports this with a custom sensor suite plus extensive simulation and real-world experiments.

Significance. If the quantitative claims hold, the work would address a genuine gap between pedestrian-focused magnetic fusion studies and practical AMR deployment by demonstrating infrastructure-free complementarity to LiDAR-inertial pipelines under map drift and degeneration; the absence of fitted parameters or circular derivations in the presented text is a positive feature.

major comments (1)
  1. [Abstract] Abstract: the central claim that MIL-LC 'provides reliable localization even when LiDAR suffers from geometric degeneration or when the magnetic map changes' is asserted but unsupported by any error metrics, repeatability statistics, distinctiveness measures, or explicit handling of map change; without these the experimental validation cannot be evaluated.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the major comment below and will incorporate revisions to strengthen the abstract's presentation of results.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that MIL-LC 'provides reliable localization even when LiDAR suffers from geometric degeneration or when the magnetic map changes' is asserted but unsupported by any error metrics, repeatability statistics, distinctiveness measures, or explicit handling of map change; without these the experimental validation cannot be evaluated.

    Authors: We agree that the abstract would benefit from explicit quantitative support to make the central claims immediately evaluable. The full manuscript details extensive simulation and real-world experiments with error metrics (e.g., RMSE under degeneration), repeatability across trials, and long-term tests demonstrating robustness to magnetic map changes via the fusion pipeline. However, we acknowledge the abstract itself lacks these specifics. In the revised version, we will update the abstract to include representative error metrics, repeatability statistics, and a brief note on map-change handling. This addresses the presentation concern while the experimental sections already provide the supporting analysis and distinctiveness through magnetic signature complementarity. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The abstract and available text contain no equations, parameter fittings, self-citations, or derivation steps that reduce to inputs by construction. The central claims concern empirical robustness of a proposed sensor-fusion framework in specific environments, presented as outcomes of experiments rather than any self-referential mathematical reduction. No load-bearing steps match the enumerated circularity patterns, and the work is self-contained as a framework proposal without visible internal circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are described in the abstract; the framework is presented at a high level without mathematical or modeling details.

pith-pipeline@v0.9.1-grok · 5765 in / 984 out tokens · 22103 ms · 2026-06-25T20:50:49.000523+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

36 extracted references · 1 linked inside Pith

  1. [1]

    Mc-mapping: Magnetic-aware collaborative mapping in perceptually degraded environments,

    Z. Wu, W. Wang, H. Shen, Q. Lyu, T. Deng, G. Peng, H. Zhou, and D. Wang, “Mc-mapping: Magnetic-aware collaborative mapping in perceptually degraded environments,”IEEE Transactions on Industrial Electronics, 2026

    2026

  2. [2]

    Simsl: A semantic instance-based multisensor fusion localization system for challenging dynamic and degraded environments,

    Y . Li, L. Jiang, B. Lei, B. Tang, J. Zhu, and H. Liu, “Simsl: A semantic instance-based multisensor fusion localization system for challenging dynamic and degraded environments,”IEEE Transactions on Industrial Electronics, 2025

    2025

  3. [3]

    Vins-mono: A robust and versatile monocular visual-inertial state estimator,

    T. Qin, P. Li, and S. Shen, “Vins-mono: A robust and versatile monocular visual-inertial state estimator,”IEEE Transactions on Robotics, vol. 34, no. 4, pp. 1004–1020, 2018

    2018

  4. [4]

    Fast-lio: A fast, robust lidar-inertial odometry package by tightly-coupled iterated kalman filter,

    W. Xu and F. Zhang, “Fast-lio: A fast, robust lidar-inertial odometry package by tightly-coupled iterated kalman filter,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 3317–3324, 2021

    2021

  5. [5]

    Mglt: Magnetic-lead global localization and tracking in degenerated repetitive environments,

    Z. Wu, W. Wang, J. Zhang, Y . Wang, G. Peng, and D. Wang, “Mglt: Magnetic-lead global localization and tracking in degenerated repetitive environments,”IEEE/ASME Transactions on Mechatronics, vol. 29, no. 6, pp. 4687–4698, 2024

    2024

  6. [6]

    An integrated gnss/lidar- slam pose estimation framework for large-scale map building in partially gnss-denied environments,

    G. He, X. Yuan, Y . Zhuang, and H. Hu, “An integrated gnss/lidar- slam pose estimation framework for large-scale map building in partially gnss-denied environments,”IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–9, 2020

    2020

  7. [7]

    Lcdl: toward dynamic localization for autonomous landing of unmanned aerial vehicle based on lidar–camera fusion,

    Y . Xu, Z. Chen, C. Deng, S. Wang, and J. Wang, “Lcdl: toward dynamic localization for autonomous landing of unmanned aerial vehicle based on lidar–camera fusion,”IEEE Sensors Journal, vol. 24, no. 16, pp. 26407– 26415, 2024

    2024

  8. [8]

    A review of visual-lidar fusion based simultaneous localization and mapping,

    C. Debeunne and D. Vivet, “A review of visual-lidar fusion based simultaneous localization and mapping,”sensors, vol. 20, no. 7, p. 2068, 2020

    2068

  9. [9]

    Range-focused fusion of camera-imu-uwb for accurate and drift-reduced localization,

    T. H. Nguyen, T.-M. Nguyen, and L. Xie, “Range-focused fusion of camera-imu-uwb for accurate and drift-reduced localization,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1678–1685, 2021

    2021

  10. [10]

    Rf-slam: Uhf- rfid based simultaneous tags mapping and robot localization algorithm for smart warehouse position service,

    C. Wu, Z. Gong, B. Tao, K. Tan, Z. Gu, and Z.-P. Yin, “Rf-slam: Uhf- rfid based simultaneous tags mapping and robot localization algorithm for smart warehouse position service,”IEEE Transactions on Industrial Informatics, vol. 19, no. 12, pp. 11765–11775, 2023

    2023

  11. [11]

    Long-distance navigation and magnetoreception in mi- gratory animals,

    H. Mouritsen, “Long-distance navigation and magnetoreception in mi- gratory animals,”Nature, vol. 558, no. 7708, pp. 50–59, 2018. MANUSCRIPT PREPARED FOR IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 10

    2018

  12. [12]

    How he use of magnetic field alone for indoor positioning?,

    B. Li, T. Gallagher, A. G. Dempster, and C. Rizos, “How he use of magnetic field alone for indoor positioning?,” in2012 Internatfeasible is tional Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1–9, 2012

    2012

  13. [13]

    Idf-mfl: Infrastructure-free and drift-free magnetic field localization for mobile robot,

    H. Shen, Z. Wu, W. Wang, Q. Lyu, H. Zhou, and D. Wang, “Idf-mfl: Infrastructure-free and drift-free magnetic field localization for mobile robot,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2278–2285, 2024

    2024

  14. [14]

    Locateme: Magnetic-fields-based indoor localization using smartphones,

    K. P. Subbu, B. Gozick, and R. Dantu, “Locateme: Magnetic-fields-based indoor localization using smartphones,”ACM Transactions on Intelligent Systems and Technology (TIST), vol. 4, no. 4, pp. 1–27, 2013

    2013

  15. [15]

    Indoor mobile robot localization and mapping based on ambient magnetic fields and aiding radio sources,

    J. Jung, S.-M. Lee, and H. Myung, “Indoor mobile robot localization and mapping based on ambient magnetic fields and aiding radio sources,” IEEE Transactions on Instrumentation and Measurement, vol. 64, no. 7, pp. 1922–1934, 2015

    1922

  16. [16]

    Magicol: Indoor localization using pervasive magnetic field and opportunistic wifi sensing,

    Y . Shu, C. Bo, G. Shen, C. Zhao, L. Li, and F. Zhao, “Magicol: Indoor localization using pervasive magnetic field and opportunistic wifi sensing,”IEEE Journal on Selected Areas in Communications, vol. 33, no. 7, pp. 1443–1457, 2015

    2015

  17. [17]

    Magnetic-based indoor localiza- tion using smartphone via a fusion algorithm,

    G. Wang, X. Wang, J. Nie, and L. Lin, “Magnetic-based indoor localiza- tion using smartphone via a fusion algorithm,”IEEE Sensors Journal, vol. 19, no. 15, pp. 6477–6485, 2019

    2019

  18. [18]

    Fusion of magnetic and visual sensors for indoor localization: Infrastructure-free and more effective,

    Z. Liu, L. Zhang, Q. Liu, Y . Yin, L. Cheng, and R. Zimmer- mann, “Fusion of magnetic and visual sensors for indoor localization: Infrastructure-free and more effective,”IEEE Transactions on Multime- dia, vol. 19, no. 4, pp. 874–888, 2017

    2017

  19. [19]

    Multi-sensor fusion and semantic map-based particle filtering for robust indoor localization,

    X. Yang, X. Huang, Y . Zhang, Z. Liu, and Y . Pang, “Multi-sensor fusion and semantic map-based particle filtering for robust indoor localization,” Measurement, vol. 242, p. 115874, 2025

    2025

  20. [20]

    Information fusion for positioning system with location constraint of camera and uwb,

    X. Hao, H. Yang, and Y . Xu, “Information fusion for positioning system with location constraint of camera and uwb,”IEEE Transactions on Automation Science and Engineering, 2025

    2025

  21. [21]

    Gnss/imu/lidar fusion for vehicle localization in urban driving environments within a consensus frame- work,

    L. Gao, X. Xia, Z. Zheng, and J. Ma, “Gnss/imu/lidar fusion for vehicle localization in urban driving environments within a consensus frame- work,”Mechanical Systems and Signal Processing, vol. 205, p. 110862, 2023

    2023

  22. [22]

    A lidar-imu- gnss fused mapping method for large-scale and high-speed scenarios,

    Z. Shen, J. Wang, C. Pang, Z. Lan, and Z. Fang, “A lidar-imu- gnss fused mapping method for large-scale and high-speed scenarios,” Measurement, vol. 225, p. 113961, 2024

    2024

  23. [23]

    Lidar/uwb fusion based slam with anti- degeneration capability,

    H. Zhou, Z. Yao, and M. Lu, “Lidar/uwb fusion based slam with anti- degeneration capability,”IEEE Transactions on Vehicular Technology, vol. 70, no. 1, pp. 820–830, 2020

    2020

  24. [24]

    Tightly coupled lidar/imu/uwb fusion via resilient factor graph for quadruped robot positioning,

    Y . Kuang, T. Hu, M. Ouyang, Y . Yang, and X. Zhang, “Tightly coupled lidar/imu/uwb fusion via resilient factor graph for quadruped robot positioning,”Remote Sensing, vol. 16, no. 22, p. 4171, 2024

    2024

  25. [25]

    Lidar, imu, and camera fusion for simultaneous localization and mapping: A systematic review,

    Z. Fan, L. Zhang, X. Wang, Y . Shen, and F. Deng, “Lidar, imu, and camera fusion for simultaneous localization and mapping: A systematic review,”Artificial Intelligence Review, vol. 58, no. 6, p. 174, 2025

    2025

  26. [26]

    Magloc-ar: Magnetic-based localization for visual-free augmented reality in large- scale indoor environments,

    H. Liu, H. Xue, L. Zhao, D. Chen, Z. Peng, and G. Zhang, “Magloc-ar: Magnetic-based localization for visual-free augmented reality in large- scale indoor environments,”IEEE Transactions on Visualization and Computer Graphics, vol. 29, no. 11, pp. 4383–4393, 2023

    2023

  27. [27]

    Magnetic field aided vehicle localization with acceleration correction,

    M. Deshpande, M. Majji, and J. H. Ramos, “Magnetic field aided vehicle localization with acceleration correction,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3234–3239, IEEE, 2024

    2024

  28. [28]

    Fast-lio2: Fast direct lidar-inertial odometry,

    W. Xu, Y . Cai, D. He, J. Lin, and F. Zhang, “Fast-lio2: Fast direct lidar-inertial odometry,”IEEE Transactions on Robotics, vol. 38, no. 4, pp. 2053–2073, 2022

    2053

  29. [29]

    S- gpr: Sliding gaussian process regression-based magnetic mapping and evaluation of different magnetic mapping methods,

    Q. Lyu, Z. Wu, H. Shen, W. Wang, J. Zhang, H. Zhou, and D. Wang, “S- gpr: Sliding gaussian process regression-based magnetic mapping and evaluation of different magnetic mapping methods,” inIECON 2024- 50th Annual Conference of the IEEE Industrial Electronics Society, pp. 1–7, IEEE, 2024

    2024

  30. [30]

    On degeneracy of optimization-based state estimation problems,

    J. Zhang, M. Kaess, and S. Singh, “On degeneracy of optimization-based state estimation problems,” in2016 IEEE international conference on robotics and automation (ICRA), pp. 809–816, IEEE, 2016

    2016

  31. [31]

    Informed, constrained, aligned: A field analysis on degeneracy- aware point cloud registration in the wild,

    T. Tuna, J. Nubert, P. Pfreundschuh, C. Cadena, S. Khattak, and M. Hut- ter, “Informed, constrained, aligned: A field analysis on degeneracy- aware point cloud registration in the wild,”IEEE Transactions on Field Robotics, 2025

    2025

  32. [32]

    Roslac: Robust simultaneous localization and calibration of multiple magnetometers,

    Q. Lyu, Z. Wu, W. Wang, H. Shen, and D. Wang, “Roslac: Robust simultaneous localization and calibration of multiple magnetometers,” arXiv preprint arXiv:2604.14353, 2026

    Pith/arXiv arXiv 2026

  33. [33]

    Cte-mlo: Continuous-time and efficient multi-lidar odometry with localizability-aware point cloud sampling,

    H. Shen, Z. Wu, Y . Hui, W. Wang, Q. Lyu, T. Deng, Y . Zhu, B. Tian, and D. Wang, “Cte-mlo: Continuous-time and efficient multi-lidar odometry with localizability-aware point cloud sampling,”IEEE Transactions on Field Robotics, vol. 2, pp. 165–187, 2025

    2025

  34. [34]

    A portable three-dimensional lidar-based system for long-term and wide-area people behavior mea- surement,

    K. Koide, J. Miura, and E. Menegatti, “A portable three-dimensional lidar-based system for long-term and wide-area people behavior mea- surement,”International Journal of Advanced Robotic Systems, vol. 16, no. 2, p. 1729881419841532, 2019

    2019

  35. [35]

    Pdr/geomagnetic fusion localization method based on aofa-improved particle filter,

    L.-F. Shi, M.-X. Yu, and W. Yin, “Pdr/geomagnetic fusion localization method based on aofa-improved particle filter,”IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–9, 2022. Qiyang Lyureceived his B.Eng degree of Electronic Information Engineering from University of Elec- tronic Science and Technology of China, China, in 2020, and the...

    2022

  36. [36]

    Currently, he is Emeritus Professor and was the Director of the ST Engineering-NTU Robotics Corporate Lab

    Since 1989, he has been with the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. Currently, he is Emeritus Professor and was the Director of the ST Engineering-NTU Robotics Corporate Lab. He is the Chair of IEEE Singapore Robotics and Automation Chapter and a senator in NTU Academics Council. He has served as ...

    1989