Robotics Research Hub
GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping

GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping

Qi Zhang, Xikun Liu, Qijun Qin, Xiangru Wang, Junzhe Wang, Naigui Xiao, Jianhao Jiao, Weisong Wen · N/A · 2026

benchmark
PDF arXiv

Framework

N/A

License

N/A

Stars

N/A

Summary

Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements.

Abstract Summary

Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements. Existing fusion methods, however, share a scan-to-map front-end with two failure modes. First, each scan is aligned to an incrementally built map that drifts under degeneracy, and once the estimate diverges the error is irrecoverable. Second, even without divergence, a registration biased by dynamic objects or wrong correspondences is propagated as a single pose constraint with an over-confident covariance, leaving its correspondences unavailable for GNSS to re-weight or relinearize. We propose GLIO2, a tightly-coupled LiDAR-Inertial-GNSS system whose GPU-parallel front-end jointly optimizes scan-to-multiscan LiDAR, IMU pre-integration, and raw GNSS measurements in a single sliding-window factor graph, sustaining real-time operation on edge hardware. A complementary offline back-end reuses the same cached factors to refine the entire trajectory in batch, completing the 30-min, 4.51-km UrbanNav Whampoa sequence in about 24 s. Across three public benchmarks (UrbanNav, MARS-LVIG, M3DGR) and self-collected UAV and vehicle data, GLIO2 attains the best overall accuracy among evaluated systems. On a 5.66-km bridge traversed at up to 96 km/h, where every competing baseline diverges under LiDAR degeneracy, it maintains 1.6 m horizontal accuracy. On an NVIDIA Jetson Orin NX, the full pipeline runs at about 25 Hz (39.60 ms per scan). The source code and datasets will be released.

Key Points

  • Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements.
  • Existing fusion methods, however, share a scan-to-map front-end with two failure modes
  • First, each scan is aligned to an incrementally built map that drifts under degeneracy, and once the estimate diverges the error is irrecoverable.
  • Second, even without divergence, a registration biased by dynamic objects or wrong correspondences is propagated as a single pose constraint with an over-confident covariance, leaving its correspondences unavailable for GNSS to re-weight or relinearize.
  • We propose GLIO2, a tightly-coupled LiDAR-Inertial-GNSS system whose GPU-parallel front-end jointly optimizes scan-to-multiscan LiDAR, IMU pre-integration, and raw GNSS measurements in a single sliding-window factor graph, sustaining real-time operation on edge hardware.

System Overview

The overview of GLIO2 is shown in Fig. 2 . GLIO2 fuses three asynchronous streams, LiDAR, IMU, and raw GNSS from the rover and a reference station, in a single tightly-coupled factor graph (Sec. 4 ). The methodology comprises the factor graph formulation (Sec. 4-4.1 ), the four measurement factors (Sec. 4-4.2 – 4-4.5 ), the active keyframe set (Sec. 4-4.6 ), marginalization (Sec. 4-4.7 ), and initialization (Sec.

4-4.8 ) of the online front-end, and the global batch optimization of the back-end (Sec. 4-4.9 ).

System Overview — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 1: GLIO2 in two challenging self-collected scenes, with the point-cloud map (colored by height) projected onto satellite imagery. Top : the $5.66$ km Bridge , crossed at up to $96$ km/h, where the straight bridge and the heavy moving traffic cause LiDAR degeneracy along the driving direction (front views A, B). Bottom : the $1.44$ km dense-canyon Urban route, where high-rise buildings block and reflect the GNSS signals (location C, with fisheye sky view C1 and front view C2). In each scene GLIO2 keeps the global map continuous and aligned with the imagery despite the complementary LiDAR and GNSS degradation.

Methodology

The optimal state estimate is obtained by solving a Maximum A Posteriori (MAP) problem. Assuming that all sensor measurements are independent and their associated measurement noise follows a zero-mean Gaussian distribution, the MAP inference is equivalent to minimizing the sum of squared Mahalanobis distances of the residuals.

Methodology — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 2: System overview of GLIO2. The front-end IMU-deskews each LiDAR scan and bootstraps by LIO initialization, where the IMU pre-integration and scan-to-multiscan (S2MS) voxelized-GICP (VGICP) LiDAR factors supply motion and local geometry; GNSS is then aligned to the LIO trajectory, and its double-differenced (DD) pseudorange and Doppler factors enter the graph. The sliding-window graph is solved on the CPU at the LiDAR rate with the dense per-point linearization on the GPU: at each linearization point $\mathbf{x}_{k}$, the points are re-associated against the hash-indexed keyframe voxel maps and the block Hessians returned, the CPU solves for the next $\mathbf{x}_{k}$ until convergence, and the converged poses update the active keyframe set while out-of-window states are marginalized. The offline back-end reuses the cached relative factors, applies several rounds of GNSS fault detection and de-weighting (FDD), and batch-optimizes the whole trajectory.

Experiments

We evaluate GLIO2 on both public datasets and our self-collected dataset. The public datasets (UrbanNav [ 10 ] , MARS-LVIG [ 11 ] , and M3DGR [ 12 ] ) benchmark GLIO2 against state-of-the-art LiDAR–Inertial–GNSS systems (Sec. 5-5.25.2.1 ).

The self-collected dataset targets the two failure modes this work addresses, raw GNSS denied or NLOS and LiDAR geometric degeneracy, across four sequences ( Urban , Switch , Bridge , and Plain ) (Sec. 5-5.25.2.2 ), and drives the ablation study that isolates the contribution of each module (Sec. 5-5.3 ).

Experiments — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 3: The five coordinate frames of GLIO2: the Earth-centered ECEF frame ($E$), the local-world frame ($w$), and the LiDAR ($l$), IMU ($i$), and GNSS-receiver ($r$) frames on the platform. The LiDAR and IMU share a fixed extrinsic; the local-world frame relates to ECEF through the estimated extrinsic ${}_{w}^{E}\mathbf{T}$.

Applications

To demonstrate the practicality of GLIO2 in real-world tasks, we deploy it as the sole onboard localization and mapping source in two complete autonomous systems: a facade-cleaning UAV and a guide-dog quadruped for the visually impaired.

Together they stress the three properties the estimator is built for: robustness under simultaneous LiDAR and GNSS degradation, global consistency over a long map-referenced route, and real-time operation fully onboard.

Applications — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 4: Double-differenced pseudorange geometry among the rover $r$, base station $b$, master satellite $m$, and secondary satellite $i$. Double differencing cancels the error terms common to both receivers and both satellites, namely the clock offsets and atmospheric delays.

GNSS Factor Jacobians

All Jacobians below use the unit line-of-sight vector $\mathbf{e}_{r}^{s}$ of ( 10 ), pointing from the receiver to satellite $s$ (Table 2 ); the geometric-range derivative is then $\partial\/{}^{E}\mathbf{p}^{s}-{}^{E}\mathbf{p}_{r}\//\partial{}^{E}\mathbf{p}_{r}=-(\mathbf{e}_{r}^{s})^{T}$. The Jacobians of the DD pseudorange residual $r_{\rho}^{mi}$ (Sec.

GNSS Factor Jacobians — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 5: Block structure of the window information matrix (GNSS in red, LiDAR in blue), contrasting the two LiDAR factors; nodes $\mathbf{x}_{i},\mathbf{x}_{j_{1}},\mathbf{x}_{j_{2}},\mathbf{x}_{j_{3}}$ are the current scan and three keyframes, and each cell is a $6\times 6$ pose subblock. (a) Scan-to-map enters LiDAR as a unary absolute constraint on the diagonal blocks (red-boxed), acting on the same global degrees of freedom as GNSS. (b) Scan-to-multiscan enters LiDAR as relative constraints coupling $\mathbf{x}_{i}$ to each keyframe (off-diagonal blocks), so $\mathcal{G}\subseteq\ker(\mathbf{H}^{\mathcal{L}})$.

Single-Receiver Pseudorange Factor

On datasets without a reference station (e.g. M3DGR), the double-differenced pseudorange factor of Sec. 4-4.2 is replaced by an undifferenced single-receiver factor built directly on the raw pseudorange model ( 4 ).

Because differencing no longer cancels the receiver clock offset, the per-constellation offset $\boldsymbol{\delta t}_{r}\in\mathbb{R}^{4}$ is reinstated as a navigation-state variable in this variant (its drift rate $\boldsymbol{\dot{\delta t}}_{r}$ is retained as before).

Single-Receiver Pseudorange Factor — GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Figure 6: Factor graph of the global batch optimization (Sec. 4-4.9 ): the whole trajectory is re-optimized jointly over all states $\mathbf{x}_{0},\dots,\mathbf{x}_{k}$ under IMU pre-integration factors, the scan-to-multiscan LiDAR between-factors, and the raw double-differenced pseudorange and Doppler factors.

Sources and Demonstrations

Figures are reproduced from Zhang 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

4D Radar Perception Algorithms for Autonomous Driving: A Review
arXiv preprint

4D Radar Perception Algorithms for Autonomous Driving: A Review

Xumin Wu, Jun Zhou, Jilin Mei et al.

Research on 4D millimeter-wave radar perception algorithms has flourished in recent years, extending from signal processing and object detection to semantic segmentation, motion estimation, occupancy prediction, and dynamic scene reconstruction.

vision reinforcement-learning benchmark
PDF Beginner