Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills

Eric Rosen, Steven James, Sergio Orozco, Vedant Gupta, Max Merlin, Stefanie Tellex, George Konidaris
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2278-2287, 2023.

Abstract

We address the problem of efficiently learning high-level abstractions for task-level robot planning. Existing approaches require large amounts of data and fail to generalize learned abstractions to new environments. To address this, we propose to exploit the independence between spatial and non-spatial state variables in the preconditions of manipulation and navigation skills, mirroring the manipulation-navigation split in robotics research. Given a collection of portable manipulation abstractions (i.e., object-centric manipulation skills paired with matching symbolic representations), we derive an algorithm to automatically generate navigation abstractions that support mobile manipulation planning in a novel environment. We apply our approach to simulated data in AI2Thor and on real robot hardware with a coffee preparation task, efficiently generating plannable representations for mobile manipulators in just a few minutes of robot time, significantly outperforming state-of-the-art baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-rosen23a, title = {Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills}, author = {Rosen, Eric and James, Steven and Orozco, Sergio and Gupta, Vedant and Merlin, Max and Tellex, Stefanie and Konidaris, George}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2278--2287}, 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/rosen23a/rosen23a.pdf}, url = {https://proceedings.mlr.press/v229/rosen23a.html}, abstract = {We address the problem of efficiently learning high-level abstractions for task-level robot planning. Existing approaches require large amounts of data and fail to generalize learned abstractions to new environments. To address this, we propose to exploit the independence between spatial and non-spatial state variables in the preconditions of manipulation and navigation skills, mirroring the manipulation-navigation split in robotics research. Given a collection of portable manipulation abstractions (i.e., object-centric manipulation skills paired with matching symbolic representations), we derive an algorithm to automatically generate navigation abstractions that support mobile manipulation planning in a novel environment. We apply our approach to simulated data in AI2Thor and on real robot hardware with a coffee preparation task, efficiently generating plannable representations for mobile manipulators in just a few minutes of robot time, significantly outperforming state-of-the-art baselines.} }
Endnote
%0 Conference Paper %T Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills %A Eric Rosen %A Steven James %A Sergio Orozco %A Vedant Gupta %A Max Merlin %A Stefanie Tellex %A George Konidaris %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-rosen23a %I PMLR %P 2278--2287 %U https://proceedings.mlr.press/v229/rosen23a.html %V 229 %X We address the problem of efficiently learning high-level abstractions for task-level robot planning. Existing approaches require large amounts of data and fail to generalize learned abstractions to new environments. To address this, we propose to exploit the independence between spatial and non-spatial state variables in the preconditions of manipulation and navigation skills, mirroring the manipulation-navigation split in robotics research. Given a collection of portable manipulation abstractions (i.e., object-centric manipulation skills paired with matching symbolic representations), we derive an algorithm to automatically generate navigation abstractions that support mobile manipulation planning in a novel environment. We apply our approach to simulated data in AI2Thor and on real robot hardware with a coffee preparation task, efficiently generating plannable representations for mobile manipulators in just a few minutes of robot time, significantly outperforming state-of-the-art baselines.
APA
Rosen, E., James, S., Orozco, S., Gupta, V., Merlin, M., Tellex, S. & Konidaris, G.. (2023). Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2278-2287 Available from https://proceedings.mlr.press/v229/rosen23a.html.

Related Material