Human-in-the-Loop Task and Motion Planning for Imitation Learning

Ajay Mandlekar, Caelan Reed Garrett, Danfei Xu, Dieter Fox
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3030-3060, 2023.

Abstract

Imitation learning from human demonstrations can teach robots complex manipulation skills, but is time-consuming and labor intensive. In contrast, Task and Motion Planning (TAMP) systems are automated and excel at solving long-horizon tasks, but they are difficult to apply to contact-rich tasks. In this paper, we present Human-in-the-Loop Task and Motion Planning (HITL-TAMP), a novel system that leverages the benefits of both approaches. The system employs a TAMP-gated control mechanism, which selectively gives and takes control to and from a human teleoperator. This enables the human teleoperator to manage a fleet of robots, maximizing data collection efficiency. The collected human data is then combined with an imitation learning framework to train a TAMP-gated policy, leading to superior performance compared to training on full task demonstrations. We compared HITL-TAMP to a conventional teleoperation system — users gathered more than 3x the number of demos given the same time budget. Furthermore, proficient agents ($75%$+ success) could be trained from just 10 minutes of non-expert teleoperation data. Finally, we collected 2.1K demos with HITL-TAMP across 12 contact-rich, long-horizon tasks and show that the system often produces near-perfect agents. Videos and additional results at https://hitltamp.github.io .

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-mandlekar23b, title = {Human-in-the-Loop Task and Motion Planning for Imitation Learning}, author = {Mandlekar, Ajay and Garrett, Caelan Reed and Xu, Danfei and Fox, Dieter}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3030--3060}, 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/mandlekar23b/mandlekar23b.pdf}, url = {https://proceedings.mlr.press/v229/mandlekar23b.html}, abstract = {Imitation learning from human demonstrations can teach robots complex manipulation skills, but is time-consuming and labor intensive. In contrast, Task and Motion Planning (TAMP) systems are automated and excel at solving long-horizon tasks, but they are difficult to apply to contact-rich tasks. In this paper, we present Human-in-the-Loop Task and Motion Planning (HITL-TAMP), a novel system that leverages the benefits of both approaches. The system employs a TAMP-gated control mechanism, which selectively gives and takes control to and from a human teleoperator. This enables the human teleoperator to manage a fleet of robots, maximizing data collection efficiency. The collected human data is then combined with an imitation learning framework to train a TAMP-gated policy, leading to superior performance compared to training on full task demonstrations. We compared HITL-TAMP to a conventional teleoperation system — users gathered more than 3x the number of demos given the same time budget. Furthermore, proficient agents ($75%$+ success) could be trained from just 10 minutes of non-expert teleoperation data. Finally, we collected 2.1K demos with HITL-TAMP across 12 contact-rich, long-horizon tasks and show that the system often produces near-perfect agents. Videos and additional results at https://hitltamp.github.io .} }
Endnote
%0 Conference Paper %T Human-in-the-Loop Task and Motion Planning for Imitation Learning %A Ajay Mandlekar %A Caelan Reed Garrett %A Danfei Xu %A Dieter Fox %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-mandlekar23b %I PMLR %P 3030--3060 %U https://proceedings.mlr.press/v229/mandlekar23b.html %V 229 %X Imitation learning from human demonstrations can teach robots complex manipulation skills, but is time-consuming and labor intensive. In contrast, Task and Motion Planning (TAMP) systems are automated and excel at solving long-horizon tasks, but they are difficult to apply to contact-rich tasks. In this paper, we present Human-in-the-Loop Task and Motion Planning (HITL-TAMP), a novel system that leverages the benefits of both approaches. The system employs a TAMP-gated control mechanism, which selectively gives and takes control to and from a human teleoperator. This enables the human teleoperator to manage a fleet of robots, maximizing data collection efficiency. The collected human data is then combined with an imitation learning framework to train a TAMP-gated policy, leading to superior performance compared to training on full task demonstrations. We compared HITL-TAMP to a conventional teleoperation system — users gathered more than 3x the number of demos given the same time budget. Furthermore, proficient agents ($75%$+ success) could be trained from just 10 minutes of non-expert teleoperation data. Finally, we collected 2.1K demos with HITL-TAMP across 12 contact-rich, long-horizon tasks and show that the system often produces near-perfect agents. Videos and additional results at https://hitltamp.github.io .
APA
Mandlekar, A., Garrett, C.R., Xu, D. & Fox, D.. (2023). Human-in-the-Loop Task and Motion Planning for Imitation Learning. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3030-3060 Available from https://proceedings.mlr.press/v229/mandlekar23b.html.

Related Material