You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
cd examples/reorientation/
./download_piles.py
# # train from scratch# for seed in $(seq 0 4999); do# ./pickable_create_dataset.py --seed $seed# done# ./pickable_view_dataset.py# ./pickable_train.py --name franka_panda-panda_suction# NOTE: replace model path to use your own model
./pickable_eval.py --seed 0
Figure 1. Reorient pose selection's dataset (left) and inference (right)
Reorient motion selection
# # train from scratch# for seed in $(seq 0 4999); do# ./reorientable_create_dataset.py --seed $seed# done# ./reorientable_view_dataset.py# ./reorientable_train.py --name franka_panda-panda_suction# NOTE: replace model path to use your own model
./reorient_dynamic.py --seed 0 --face front
Figure 2. Reorient motion selection's dataset (left) and inference (right)
Figure 3. Robotic rearrangement while picking, reorienting and placing objects.
Citation
@inproceedings{Wada:etal:ICRA2022b,
title={{ReorientBot}: Learning Object Reorientation for Specific-Posed Placement},
author={Kentaro Wada and Stephen James and Andrew J. Davison},
booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
year={2022},
}
About
ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022