0%

Lidar Kidnap Robot Problem

1. Intro

Problem:

  • have the learned 3D lidar point cloud map
  • given a single frame (lidar scan) from lidar
  • calculate current robot position and pose (without knowing initial pose)

2. Review

Ref

Map

  • Keyframe-based submaps
  • Global feature map
  • Global metric map

Single shot localization

  • Place Recognition: match the keyu frame
  • Place Recognition and Local Pose Estimation
  • Pose Estimation coupled Place Recognition
  • One stage global estimation
image-20230528013339621

image-20230528013453090

3. Scan Context

4. SegMatch