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

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 · N/A · 2026

vision reinforcement-learning planning
PDF arXiv Code (GitHub)

Framework

N/A

License

N/A

Stars

N/A

Summary

Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging.

Abstract Summary

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.

Key Points

  • 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.

Preliminary

We assume that the temporal offsets among the five sensors—LiDAR, IMU, camera, wheel odometer, and 4D mmWave radar—are known (via pre-calibration or synchronization). The IMU frame, denoted by $I$, is used as the body frame, and the global frame, denoted by $G$, is defined at the origin of the total-station coordinate system (Table I ).

All sensors are rigidly mounted, and the LiDAR, camera, and IMU are hardware-synchronized.

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

System Overview

Our objective is to estimate the 6-DoF pose of a coal-mine robot while constructing a global map. The overall system architecture is shown in Fig. 1 . The system comprises three modules: (i) Radar-Enhanced LiDAR Visual Inertial Constraint Module: We extract point clouds from mmWave radar echoes. Using ego-velocity estimation, we reject outliers and construct Doppler-velocity constraints (Chapter V-A ).

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

Methodology

We employ an adaptive, octree-based voxel map (Fig. 1 ) with a root voxel size of 0.5 m. Each leaf voxel stores planar features $\Pi\triangleq(\mathbf{n},\mathbf{q},\boldsymbol{\Sigma}_{\mathbf{n},\mathbf{q}})$ and LiDAR points ${}^{L}\mathbf{p}_{i}$.

A subset of points is augmented with $8\times 8$ image patches to form a set of visual map points, denoted by $\mathcal{P}^{map}$: converged points retain only the reference patch, whereas unconverged points additionally store other visible patches.

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

Experiment

We conducted field experiments in severely degenerate underground coal-mine tunnels. The mobile platform is a Husky A200 equipped with a Livox AVIA LiDAR (with a built-in IMU), a Hikvision camera (MVS-CU013-A0UC), an Oculii Eagle 4D mmWave radar, and the chassis wheel odometer.

The LiDAR–camera and radar–IMU extrinsics were carefully calibrated, and a hardware synchronizer time-synchronized the LiDAR, IMU, camera, and mmWave radar. Ground-truth points were measured using a total station.

Experiment — FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement
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 $\mathcal{O}_{G}^{th}=40$.

Sources and Demonstrations

Figures are reproduced from Hu et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.

Share

Related Papers

AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance
arXiv preprint

AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance

Iana Zhura, Didar Seyidov, Dmitrii Plotnikov et al.

Navigating toward human callers is an important capability for rescue robots operating where visual contact is degraded or occluded. We present AcousticDiffusion, a semantically conditioned, audio-guided diffusion policy for human-directed navigation.

locomotion vision reinforcement-learning planning
PDF Advanced
Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think
arXiv preprint

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

Xvyuan Liu, Jianjie Fang, Chen Gao et al.

Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it.

vision reinforcement-learning planning control human-robot-interaction benchmark
PDF Intermediate
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
arXiv preprint

Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics

Rajneesh Anand, Mayuresh V. Kothare

Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms.

manipulation vision reinforcement-learning planning control
Code PDF Intermediate
GitHub ★ —