English

PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

Robotics 2021-11-23 v3

Abstract

In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map. Compared to RGB image-based relocalization, LiDAR frames can provide rich and robust geometric information about a scene. However, LiDAR point clouds are unordered and unstructured making it difficult to apply traditional deep learning regression models for this task. We address this issue by proposing a novel PointNet-style architecture with self-attention to efficiently estimate 6-DoF poses from 360{\deg} LiDAR input frames.Extensive experiments on recently released challenging Oxford Radar RobotCar dataset and real-world robot experiments demonstrate that the proposedmethod can achieve accurate relocalization performance.

Keywords

Cite

@article{arxiv.2003.02392,
  title  = {PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization},
  author = {Wei Wang and Bing Wang and Peijun Zhao and Changhao Chen and Ronald Clark and Bo Yang and Andrew Markham and Niki Trigoni},
  journal= {arXiv preprint arXiv:2003.02392},
  year   = {2021}
}

Comments

To appear in IEEE Sensors Journal 2021

R2 v1 2026-06-23T14:04:27.858Z