MulRan
MulRan (https://sites.google.com/view/mulran-pr/dataset): a car carrying an Ouster OS1-64 around Daejeon and Sejong.
Read by mola_input_mulran_dataset from MULRAN_BASE_DIR: a sequence name, no topics or bags. That module also writes the “<seq>_gt.tum” files the batch evaluation in eval/ scores against.
Running it
Online replay with the 3D GUI:
mola-lo-gui-mulran <MULRAN_SEQ> [additional flags]
Offline batch run, writing a trajectory file:
mola-lo-cli-mulran <MULRAN_SEQ> [additional flags]
Where the data is read from
The dataset location is taken from $MULRAN_BASE_DIR.
What this profile sets, and why
These are defaults, not overrides: exporting any of these variables before running the wrapper takes precedence.
MOLA_DESKEW_METHOD
Default: MotionCompensationMethod::IMU
The OS1-64 spins while the car drives at road speed, and this dataset’s IMU is good enough to deskew from:
Under the hood
Online launch file |
|
Offline CLI input |
|
Profile source |