search

KalmanNet / KalmanNet_TSP

code for KalmanNet
287 stars 76 forks source link

The process of NCLT Dataset is important. #24

Closed TayloreZhou closed 1 year ago

TayloreZhou commented 1 year ago

Dear Authors: The NCLT Dataset used in KalmanNet is processed one. The odometry data in the official NCLT is without velocity, while the used data have. So how to generate the velocity value is a critical question for the experiment. Can you provide more information about the process? It will be nice to see the code.

Sincerely, Taylor Zhou

adrialopezescoriza commented 1 year ago

Hi Taylor, In the NCLT experiment we use the longitudinal velocity provided by the odometry readinground truth heading of the robot (provided by the dataset) to decompose the longitudinal velocity provided in the odometry readings into $v_x$ and $v_y$ as a preprocessing step.

TayloreZhou commented 1 year ago

Hi Adrià, Thank you for your answer, it solved my confusion.