One-Shot Imitation Learning: A Pose Estimation Perspective

Pietro Vitiello, Kamil Dreczkowski, Edward Johns
Proceedings of The 7th Conference on Robot Learning, PMLR 229:943-970, 2023.

Abstract

In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning can be formulated as a combination of trajectory transfer and unseen object pose estimation. To explore this idea, we provide an in-depth study on how state-of-the-art unseen object pose estimators perform for one-shot imitation learning on ten real-world tasks, and we take a deep dive into the effects that camera calibration, pose estimation error, and spatial generalisation have on task success rates. For videos, please visit www.robot-learning.uk/pose-estimation-perspective.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-vitiello23a, title = {One-Shot Imitation Learning: A Pose Estimation Perspective}, author = {Vitiello, Pietro and Dreczkowski, Kamil and Johns, Edward}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {943--970}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/vitiello23a/vitiello23a.pdf}, url = {https://proceedings.mlr.press/v229/vitiello23a.html}, abstract = {In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning can be formulated as a combination of trajectory transfer and unseen object pose estimation. To explore this idea, we provide an in-depth study on how state-of-the-art unseen object pose estimators perform for one-shot imitation learning on ten real-world tasks, and we take a deep dive into the effects that camera calibration, pose estimation error, and spatial generalisation have on task success rates. For videos, please visit www.robot-learning.uk/pose-estimation-perspective.} }
Endnote
%0 Conference Paper %T One-Shot Imitation Learning: A Pose Estimation Perspective %A Pietro Vitiello %A Kamil Dreczkowski %A Edward Johns %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-vitiello23a %I PMLR %P 943--970 %U https://proceedings.mlr.press/v229/vitiello23a.html %V 229 %X In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning can be formulated as a combination of trajectory transfer and unseen object pose estimation. To explore this idea, we provide an in-depth study on how state-of-the-art unseen object pose estimators perform for one-shot imitation learning on ten real-world tasks, and we take a deep dive into the effects that camera calibration, pose estimation error, and spatial generalisation have on task success rates. For videos, please visit www.robot-learning.uk/pose-estimation-perspective.
APA
Vitiello, P., Dreczkowski, K. & Johns, E.. (2023). One-Shot Imitation Learning: A Pose Estimation Perspective. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:943-970 Available from https://proceedings.mlr.press/v229/vitiello23a.html.

Related Material