FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement

Kun Hu; Menggang Li; Kaidi Wu; Zhiwen Jin; Yingjie Zhao; Chaoquan Tang; Eryi Hu; Gongbo Zhou

cs.ROSep 4, 2026

FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement

Authors: Kun Hu, Menggang Li, Kaidi Wu, Zhiwen Jin, Yingjie Zhao, Chaoquan Tang, Eryi Hu, Gongbo Zhou

Organizations: School of Mechatronic Engineering, China University of Mining and Technology · Jiangsu Collaborative Innovation Center of Intelligent Mining Equipment, China University of Mining and Technology · National Key Laboratory of Intelligent Mining Equipment Technology, China University of Mining and Technology

Abstract

Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging. Dense smoke and dust cause substantial loss of visual information and degrade LiDAR point-cloud features, while long, self-similar corridors induce geometric degeneration, leading to pronounced odometry drift. To address these issues, we propose FIRE-LIVWO: Failure-Immune mmWave Radar-Enhanced LiDAR-Inertial-Visual-Wheel Odometry, a tightly coupled multi-modal odometry framework based on an iterated error-state Kalman filter (IESKF). The framework fuses 4D mmWave radar, LiDAR, and visual features within a unified VoxelMap and jointly constructs LiDAR-radar point-to-plane residuals and sparse visual photometric residuals. In smoke-filled environments, we exploit the strong penetration of 4D mmWave radar and introduce pointwise Doppler velocity constraints to preserve state observability. In geometrically degenerate corridors, we tightly couple wheel odometry using non-holonomic constraints (NHC) and online lever-arm compensation to reduce drift. Our central contribution is a degeneration detection and adaptive fusion model switching strategy grounded in geometric and visual observability analysis, which quantifies observability online and dynamically adjusts modality weights. Real-world experiments in underground coal mines demonstrate that FIRE-LIVWO accurately identifies failure boundaries, enabling reliable modality switching under extreme conditions. Compared with baselines, it achieves superior accuracy and robustness (average localization error of 5.677m). We open source our code on Github to benefit the robotics community.

Figures & tables

Notation	Meaning
$\mathbf{x},\hat{\mathbf{x}},\overline{\mathbf{x}}$	Ground truth, predicted, and updated estimates of $\mathbf{x}$ .
$\delta\mathbf{x}$	Error-state vector.
${}^{G}(\cdot),\,^{B}(\cdot)$	Vector in global or body frame.
${}^{R}(\cdot),\,^{L}(\cdot),\,^{C}(\cdot)$	Vector in radar, LiDAR, or camera frame.
${}^{W}(\cdot),\,^{I}(\cdot)$	Vector in wheel or IMU frame.

TABLE I: Definitions of Important Variables

Fig. 1: System overview.

Fig. 2: Degradation detection and adaptive fusion based on geometric and visual observability analysis. (a) In feature-rich corridor scenes, the system localizes using the LiDAR+IMU+Visual (LIV) mode, and the ellipsoid defined by the eigenvectors of the geometric Hessian matrix

\mathbf{H}_{pp}

is well conditioned. (b) In smoke-filled, visually degraded scenes, the visual detector identifies a decrease in transmittance; the system introduces radar Doppler-velocity constraints

\mathbf{z}_{R_{V}}

and switches to the LiDAR+IMU+Visual+Radar (LIVR) mode. (c) In feature-sparse, geometrically degenerate corridors, the geometric detector identifies an under-constrained direction in

x

-axis translation (the ellipsoid defined by the eigenvectors of

\mathbf{H}_{pp}

becomes degenerate); the system introduces wheel-odometry velocity constraints

\mathbf{z}_{W}

and switches to the LiDAR+IMU+Visual+Wheel (LIVW) mode.

Fig. 3: Experimental environment in underground coal-mine tunnels. (a) Deployment of the Husky robot and the total station; (b) sensor configuration on the Husky platform, including LiDAR, camera, 4D mmWave radar, IMU, and wheel odometer; (c)–(e) environments, dimensions, and texture details of Tunnel1, Tunnel2, and Tunnel3, respectively; (f) locations exhibiting the most severe visual and geometric degradations (f1, f3).

Fig. 4: Comparison of mapping results of different algorithms in underground coal-mine tunnels. (a) FIRE-Full, (b) FIRE-LIVR, (c) FIRE-LIVW, (d) FIRE-Base, (e) FAST-LIVO2, (f) R3LIVE, (g) GaRLIO, and (h) 4DRadarSLAM. In Tunnel1, FIRE-LIVW and FAST-LIVO2 fail due to smoke-induced visual degradation. In Tunnel3, FIRE-LIVR, FIRE-Base, R3LIVE, and GaRLIO suffer from severe geometric degeneration. 4DRadarSLAM exhibits significant drift along the $y$ - and $z$ -axes. Only FIRE-Full successfully reaches the end of the tunnel.

Fig. 5: Time evolution of the $x$ - and $z$ -axis trajectory components for different methods. (a) and (b) show the $x$ - and $z$ -axis components of FIRE-Full, FIRE-LIVR, FIRE-LIVW, FIRE-Base, FAST-LIVO2, R3LIVE, GaRLIO, and 4DRadarSLAM, respectively. (a1) and (a2) provide zoomed-in views of the $x$ -axis components, and (b1) shows a zoomed-in view of the $z$ -axis components.

	FIRE- Full	FIRE- LIVR	FIRE- LIVW	FIRE- Base	FAST- LIVO2	R3LIVE	GaRLIO	4DRadar- SLAM
$\mathrm{AvgErr}$	5.677	15.420	$\times$	23.962	$\times$	31.596	17.212	45.453

TABLE II: Average localization error analysis (m).

Fig. 6: Geometric observability score $\mathcal{O}_{G}$ and visualization of the eigenvectors of $\mathbf{H}_{pp}$ (red arrows indicate eigen-directions, and their lengths represent eigenvalue magnitudes). (a) $\mathcal{O}_{G}$ versus the robot $x$ -position; (b)–(f) eigenvectors at key locations: inside Tunnel1 ( $x=10,20$ m, $\mathcal{O}_{G}=34.7,36.7$ ), the onset of geometric degradation ( $x=135$ m, $\mathcal{O}_{G}=40$ ), the most severe geometric degradation ( $x=143$ m, $\mathcal{O}_{G}=114.2$ ), and the end of Tunnel3 ( $x=276$ m, $\mathcal{O}_{G}=9.2$ ). The red dashed line denotes the threshold $\mathcal{O}_{G}^{th}=40$ .

Fig. 7: Visual observability score $\mathcal{O}_{V}$ and system behavior in smoke scenarios. (a) $\mathcal{O}_{V}$ versus the robot $x$ -position; (b,b1)–(f,f1) corresponding odometry behavior and in-situ photos: initial clear region ( $x=4$ m, $\mathcal{O}_{V}=0.88$ ), entering the smoke region ( $x=10$ m, $\mathcal{O}_{V}=0.66$ ), densest smoke region ( $x=25$ m, $\mathcal{O}_{V}=0.02$ ), weakening smoke region ( $x=35$ m, $\mathcal{O}_{V}=0.40$ ), and smoke-free region ( $x=53$ m, $\mathcal{O}_{V}=0.66$ ). The red dashed line denotes the threshold $\mathcal{O}_{V}^{th}=0.4$ .

Explore similar work

When LiDAR Fades, Radar Takes Over: LiDAR Reliability-Aware Adaptive Localization Under Airborne Obscurants
Oct 9, 2026Moumita Mukherjee, Avijit Banerjee, Anton Koval +1Robot Localization LiDAR Odometry
Robotics and AI Group, Department of Computer, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden
SA-LIVO: Efficient LiDAR-Inertial-Visual Odometry with Subspace-Aware Degeneracy Handling
Jun 24, 2026Yinong Cao, Xin He, Yuwei Chen +3Inertial Odometry Robot Localization
Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China. · Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China.
FAST-LIVGO: A Degeneracy-Robust LiDAR-Inertial-Visual-GNSS Fusion Odometry
Jun 17, 2026Zhiyu Chen, Chunran Zheng, Jiayu Wen +4Robot Localization Multimodal Sensor Fusion
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, China · Department of Mechanical Engineering, The University of Hong Kong, Hong Kong SAR, China · College of Automation, Harbin Engineering University, Harbin 150001, China

Oct 9, 2026, cs.ROJ/K move · Enter open · S save

When LiDAR Fades, Radar Takes Over: LiDAR Reliability-Aware Adaptive Localization Under Airborne Obscurants

Moumita Mukherjee, Avijit Banerjee, Anton Koval, George Nikolakopoulo

Robotics and AI Group, Department of Computer, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden

Robot Localization LiDAR Odometry Fault Detection Unsupervised Anomaly Detection

Open paper AskPDF arXiv

LiDAR-inertial odometry (LIO) is widely used for real-time localization and mapping, but its reliability can degrade substantially in subterranean environments affected by smoke, dust, and other airborne obscurants, whereas radar remains comparatively robust. This article presents a one-class temporal learning framework for LiDAR degradation detection and reliability-aware localization under such conditions. A broad set of degradation-sensitive cues, including spatial, cross-modal, geometric/motion, intensity, and measurement-recency features, is evaluated to characterize changes in LiDAR sensing quality. Their temporal evolution is modelled over sliding windows using an LSTM autoencoder trained exclusively on nominal operation, enabling deviations from healthy sensor behaviour to be detected without requiring labelled degradation data. The resulting LiDAR reliability estimate governs adaptive selection between LIO and radar inertial odometry (RIO), retaining LIO during reliable sensing and transferring localization authority to RIO when degradation is detected. The framework is evaluated using real-world ground robot data collected in GNSS-denied subterranean tunnels under nominal and dense-smoke conditions. Experimental results demonstrate degradation detection, adaptive modality switching, and continued localization output under severe LiDAR degradation. A feature family ablation study further shows that a reduced feature representation can improve degradation-aware localization performance in the evaluated dense-smoke scenarios, highlighting the importance of feature parsimony in one-class sensor degradation detection. The code will be released as open source to support reproducibility and further research.

Abstract

Explore similar work

When LiDAR Fades, Radar Takes Over: LiDAR Reliability-Aware Adaptive Localization Under Airborne Obscurants

SA-LIVO: Efficient LiDAR-Inertial-Visual Odometry with Subspace-Aware Degeneracy Handling

FAST-LIVGO: A Degeneracy-Robust LiDAR-Inertial-Visual-GNSS Fusion Odometry