# GLIO2 preprint reports real-time robot localization through bridge sensor failures

_Published Thursday, October 8, 2026 at 10:48 PM EDT · Robotics, Science · Latest · Tier 2 — Notable_

Researchers report that GLIO2, a system combining laser scans, inertial measurements and satellite navigation, maintained 1.6 m horizontal accuracy on a 5.66-km bridge traversed at up to 96 km/h. In the preprint's tests, every competing baseline diverged when the laser measurements could no longer adequately constrain localization.

The system jointly optimizes measurements across a sliding window, allowing satellite data to adjust how laser observations contribute to the position estimate. Its full pipeline runs at about 25 Hz (39.60 ms per scan) on an NVIDIA Jetson Orin NX. An offline stage also refines recorded trajectories. The researchers say source code and datasets will be released.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.12411v1)

---
Canonical: https://techandbusiness.org/newswire/2iZW3nZUSx4Zn_SXRNgehO
Published: 2026-10-09T02:48:59.707Z
Story chronology: 2026-10-08T17:49:33.000Z
Retrieved: 2026-10-09T05:19:38.996Z
Publisher: Tech & Business (techandbusiness.org)