Waypoint-Based Imitation Learning for Robotic Manipulation

Lucy Xiaoyang Shi, Archit Sharma, Tony Z. Zhao, Chelsea Finn
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2195-2209, 2023.

Abstract

While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC). Waypoints can help address this problem by reducing the horizon of the learning problem for BC, and thus, the errors compounded over time. However, waypoint labeling is underspecified, and requires additional human supervision. Can we generate waypoints automatically without any additional human supervision? Our key insight is that if a trajectory segment can be approximated by linear motion, the endpoints can be used as waypoints. We propose Automatic Waypoint Extraction (AWE) for imitation learning, a preprocessing module to decompose a demonstration into a minimal set of waypoints which when interpolated linearly can approximate the trajectory up to a specified error threshold. AWE can be combined with any BC algorithm, and we find that AWE can increase the success rate of state-of-the-art algorithms by up to $25%$ in simulation and by $4-28%$ on real-world bimanual manipulation tasks, reducing the decision making horizon by up to a factor of 10. Videos and code are available at https://lucys0.github.io/awe/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-shi23b, title = {Waypoint-Based Imitation Learning for Robotic Manipulation}, author = {Shi, Lucy Xiaoyang and Sharma, Archit and Zhao, Tony Z. and Finn, Chelsea}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2195--2209}, 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/shi23b/shi23b.pdf}, url = {https://proceedings.mlr.press/v229/shi23b.html}, abstract = {While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC). Waypoints can help address this problem by reducing the horizon of the learning problem for BC, and thus, the errors compounded over time. However, waypoint labeling is underspecified, and requires additional human supervision. Can we generate waypoints automatically without any additional human supervision? Our key insight is that if a trajectory segment can be approximated by linear motion, the endpoints can be used as waypoints. We propose Automatic Waypoint Extraction (AWE) for imitation learning, a preprocessing module to decompose a demonstration into a minimal set of waypoints which when interpolated linearly can approximate the trajectory up to a specified error threshold. AWE can be combined with any BC algorithm, and we find that AWE can increase the success rate of state-of-the-art algorithms by up to $25%$ in simulation and by $4-28%$ on real-world bimanual manipulation tasks, reducing the decision making horizon by up to a factor of 10. Videos and code are available at https://lucys0.github.io/awe/.} }
Endnote
%0 Conference Paper %T Waypoint-Based Imitation Learning for Robotic Manipulation %A Lucy Xiaoyang Shi %A Archit Sharma %A Tony Z. Zhao %A Chelsea Finn %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-shi23b %I PMLR %P 2195--2209 %U https://proceedings.mlr.press/v229/shi23b.html %V 229 %X While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC). Waypoints can help address this problem by reducing the horizon of the learning problem for BC, and thus, the errors compounded over time. However, waypoint labeling is underspecified, and requires additional human supervision. Can we generate waypoints automatically without any additional human supervision? Our key insight is that if a trajectory segment can be approximated by linear motion, the endpoints can be used as waypoints. We propose Automatic Waypoint Extraction (AWE) for imitation learning, a preprocessing module to decompose a demonstration into a minimal set of waypoints which when interpolated linearly can approximate the trajectory up to a specified error threshold. AWE can be combined with any BC algorithm, and we find that AWE can increase the success rate of state-of-the-art algorithms by up to $25%$ in simulation and by $4-28%$ on real-world bimanual manipulation tasks, reducing the decision making horizon by up to a factor of 10. Videos and code are available at https://lucys0.github.io/awe/.
APA
Shi, L.X., Sharma, A., Zhao, T.Z. & Finn, C.. (2023). Waypoint-Based Imitation Learning for Robotic Manipulation. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2195-2209 Available from https://proceedings.mlr.press/v229/shi23b.html.

Related Material