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
This paper presents GLIO2, a GPU-parallelized tightly-coupled LiDAR-Inertial-GNSS system designed for robust and real-time global localization and mapping. It addresses limitations in existing fusion methods by jointly optimizing scan-to-multiscan LiDAR, IMU pre-integration, and raw GNSS measurements in a single sliding-window factor graph. The system achieves high accuracy in challenging environments, including a 5.66-km bridge traversed at up to 96 km/h, and runs at about 25 Hz on an NVIDIA Jetson Orin NX.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
horizontal accuracy
1.6
trajectory length
4.51
processing time
≈24
View original evidence
completing the 30-min, 4.51-km UrbanNav Whampoa sequence in about 24 s
Open source S4processing time
39.6
trajectory length
5.66
processing speed
≈25
- code: not_reported
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
) 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.
Open source S5
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
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org