robot-mh

especially x、y and yaw？

let me say, visual global localization evey 1 second initiatively through DBOW2 or vocabulary tree，or NetVLAD. And then fusion global localization pose with Vio through EKF or vins-fusion. this can...

compare with FIESTA from HKUST

2

How do you guys think about “[FIESTA: Fast Incremental Euclidean Distance Fields for Online Motion Planning of Aerial Robots](https://github.com/HKUST-Aerial-Robotics/FIESTA)”，Which is published by IROS2019.

This repo can substitute loop_fusion in vins_fusion? Can it substitute global_fusion in vins_fusion? As it also use pose graph fusion. How to fusion different pose with global map, say visual...