End to End (Lidar) Odometry using CNN and LSTM Inspired by the DeepVO and ESP-VO architecture, used CNN-LSTM to learn Lidar Odometry. This also included the attempt to add an EKF to fuse IMU data as part of the network for improving Odometry estimates. The EKF portion is not working, and it is difficult to debug in Tensorflow. The project is abandoned and https://github.com/lichunshang/deep_ekf_vio contains the follow up work on this idea.
-
Notifications
You must be signed in to change notification settings - Fork 2
lichunshang/end_to_end_odometry
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
End to End Odometry using CNN and LSTM
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published