English

Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness

Robotics 2021-07-19 v1 Computer Vision and Pattern Recognition

Abstract

Probabilistic state-estimation approaches offer a principled foundation for designing localization systems, because they naturally integrate sequences of imperfect motion and exteroceptive sensor data. Recently, probabilistic localization systems utilizing appearance-invariant visual place recognition (VPR) methods as the primary exteroceptive sensor have demonstrated state-of-the-art performance in the presence of substantial appearance change. However, existing systems 1) do not fully utilize odometry data within the motion models, and 2) are unable to handle route deviations, due to the assumption that query traverses exactly repeat the mapping traverse. To address these shortcomings, we present a new probabilistic topometric localization system which incorporates full 3-dof odometry into the motion model and furthermore, adds an "off-map" state within the state-estimation framework, allowing query traverses which feature significant route detours from the reference map to be successfully localized. We perform extensive evaluation on multiple query traverses from the Oxford RobotCar dataset exhibiting both significant appearance change and deviations from routes previously traversed. In particular, we evaluate performance on two practically relevant localization tasks: loop closure detection and global localization. Our approach achieves major performance improvements over both existing and improved state-of-the-art systems.

Keywords

Cite

@article{arxiv.2107.07707,
  title  = {Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness},
  author = {Ming Xu and Tobias Fischer and Niko Sünderhauf and Michael Milford},
  journal= {arXiv preprint arXiv:2107.07707},
  year   = {2021}
}

Comments

8 pages

R2 v1 2026-06-24T04:15:07.981Z