ntnu-arl / colpred_nmpc

This repository contains the software and data for the ICRA2023 submitted article "NMPC for Deep Neural Network-Based Collision Avoidance exploiting Depth Images"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Missing folder and file for training

CheeGY opened this issue · comments

Hi!

Thanks for sharing your code! I'm trying to train a model using the script "depth_state_check_train.py", but ran into an missing-file error, which requires a folder "collision_dat" and a file "half_clutter.yaml".

Would you be able to provide the data required for training, or the trained model so that the results in your paper can be replicated?

Thanks!

I was supposed to upload those on a drive but kept postponing it, my apologies.
I will do it as soon as possible and update this issue and the readme accordingly.

The training/testing data (in a tar.gz) are accessible through this link: https://ntnu.box.com/v/colpred-nmpc-dataset
One need to modify the path to the folder where the data in unzipped in this line

COLPREDMPC_DATA_DIR = os.path.join(COLPREDMPC_ROOT_DIR, '../collision_data')
; then the rest should work seamlessly.

sorry again for this long overdue upload!