Proactive Robot Assistance via Spatio-Temporal Object Modeling

Maithili Patel, Sonia Chernova
Proceedings of The 6th Conference on Robot Learning, PMLR 205:881-891, 2023.

Abstract

Proactive robot assistance enables a robot to anticipate and provide for a user’s needs without being explicitly asked. We formulate proactive assistance as the problem of the robot anticipating temporal patterns of object movements associated with everyday user routines, and proactively assisting the user by placing objects to adapt the environment to their needs. We introduce a generative graph neural network to learn a unified spatio-temporal predictive model of object dynamics from temporal sequences of object arrangements. We additionally contribute the Household Object Movements from Everyday Routines (HOMER) dataset, which tracks household objects associated with human activities of daily living across 50+ days for five simulated households. Our model outperforms the leading baseline in predicting object movement, correctly predicting locations for 11.1% more objects and wrongly predicting locations for 11.5% fewer objects used by the human user.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-patel23a, title = {Proactive Robot Assistance via Spatio-Temporal Object Modeling}, author = {Patel, Maithili and Chernova, Sonia}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {881--891}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/patel23a/patel23a.pdf}, url = {https://proceedings.mlr.press/v205/patel23a.html}, abstract = {Proactive robot assistance enables a robot to anticipate and provide for a user’s needs without being explicitly asked. We formulate proactive assistance as the problem of the robot anticipating temporal patterns of object movements associated with everyday user routines, and proactively assisting the user by placing objects to adapt the environment to their needs. We introduce a generative graph neural network to learn a unified spatio-temporal predictive model of object dynamics from temporal sequences of object arrangements. We additionally contribute the Household Object Movements from Everyday Routines (HOMER) dataset, which tracks household objects associated with human activities of daily living across 50+ days for five simulated households. Our model outperforms the leading baseline in predicting object movement, correctly predicting locations for 11.1% more objects and wrongly predicting locations for 11.5% fewer objects used by the human user.} }
Endnote
%0 Conference Paper %T Proactive Robot Assistance via Spatio-Temporal Object Modeling %A Maithili Patel %A Sonia Chernova %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-patel23a %I PMLR %P 881--891 %U https://proceedings.mlr.press/v205/patel23a.html %V 205 %X Proactive robot assistance enables a robot to anticipate and provide for a user’s needs without being explicitly asked. We formulate proactive assistance as the problem of the robot anticipating temporal patterns of object movements associated with everyday user routines, and proactively assisting the user by placing objects to adapt the environment to their needs. We introduce a generative graph neural network to learn a unified spatio-temporal predictive model of object dynamics from temporal sequences of object arrangements. We additionally contribute the Household Object Movements from Everyday Routines (HOMER) dataset, which tracks household objects associated with human activities of daily living across 50+ days for five simulated households. Our model outperforms the leading baseline in predicting object movement, correctly predicting locations for 11.1% more objects and wrongly predicting locations for 11.5% fewer objects used by the human user.
APA
Patel, M. & Chernova, S.. (2023). Proactive Robot Assistance via Spatio-Temporal Object Modeling. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:881-891 Available from https://proceedings.mlr.press/v205/patel23a.html.

Related Material