Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry

Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry

|Authors: Joaquin Caballero, Emilio Garcia-Fidalgo, Alberto Ortiz, Jarno Ralli

|Venue: arXiv preprint | Year: 2026

|arXiv: 2609.10336v1

Abstract

Despite significant progress in odometry estimation, long-term drift remains a fundamental limitation of incremental pose integration, especially in large-scale or loop-free environments. Existing map-assisted methods can reduce drift, but often depend on dense maps, sensor-specific processing, or complex matching pipelines. We propose a lightweight open-source, odometry-agnostic correction method that aligns short trajectory segments to OpenStreetMap (OSM) lane centerlines. By formulating drift correction as a direct alignment between recent odometry and sparse lane geometry, the method enables efficient online operation without dense priors or expensive preprocessing. Experiments with LiDAR and visual odometry backends demonstrate consistent improvements, with particularly strong gains under severe drift.

Key Contributions

• Despite significant progress in odometry estimation, long-term drift remains a fundamental limita…
• Existing map-assisted methods can reduce drift, but often depend on dense maps, sensor-specific p…
• We propose a lightweight open-source, odometry-agnostic correction method that aligns short traje…
• By formulating drift correction as a direct alignment between recent odometry and sparse lane geo…
• Experiments with LiDAR and visual odometry backends demonstrate consistent improvements, with par…

Topics

• vision
• reinforcement-learning

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Caballero2026_260910336v1,
  title     = {Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry},
  author    = {Joaquin Caballero and Emilio Garcia-Fidalgo and Alberto Ortiz and Jarno Ralli},
  year      = {2026},
  eprint    = {2609.10336v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2609.10336v1}
}