INQUIRE: INteractive Querying for User-aware Informative REasoning

Tesca Fitzgerald, Pallavi Koppol, Patrick Callaghan, Russell Quinlan Jun Hei Wong, Reid Simmons, Oliver Kroemer, Henny Admoni
Proceedings of The 6th Conference on Robot Learning, PMLR 205:2241-2250, 2023.

Abstract

Research on Interactive Robot Learning has yielded several modalities for querying a human for training data, including demonstrations, preferences, and corrections. While prior work in this space has focused on optimizing the robot’s queries within each interaction type, there has been little work on optimizing over the selection of the interaction type itself. We present INQUIRE, the first algorithm to implement and optimize over a generalized representation of information gain across multiple interaction types. Our evaluations show that INQUIRE can dynamically optimize its interaction type (and respective optimal query) based on its current learning status and the robot’s state in the world, resulting in more robust performance across tasks in comparison to state-of-the art baseline methods. Additionally, INQUIRE allows for customizable cost metrics to bias its selection of interaction types, enabling this algorithm to be tailored to a robot’s particular deployment domain and formulate cost-aware, informative queries.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-fitzgerald23a, title = {INQUIRE: INteractive Querying for User-aware Informative REasoning}, author = {Fitzgerald, Tesca and Koppol, Pallavi and Callaghan, Patrick and Wong, Russell Quinlan Jun Hei and Simmons, Reid and Kroemer, Oliver and Admoni, Henny}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {2241--2250}, 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/fitzgerald23a/fitzgerald23a.pdf}, url = {https://proceedings.mlr.press/v205/fitzgerald23a.html}, abstract = {Research on Interactive Robot Learning has yielded several modalities for querying a human for training data, including demonstrations, preferences, and corrections. While prior work in this space has focused on optimizing the robot’s queries within each interaction type, there has been little work on optimizing over the selection of the interaction type itself. We present INQUIRE, the first algorithm to implement and optimize over a generalized representation of information gain across multiple interaction types. Our evaluations show that INQUIRE can dynamically optimize its interaction type (and respective optimal query) based on its current learning status and the robot’s state in the world, resulting in more robust performance across tasks in comparison to state-of-the art baseline methods. Additionally, INQUIRE allows for customizable cost metrics to bias its selection of interaction types, enabling this algorithm to be tailored to a robot’s particular deployment domain and formulate cost-aware, informative queries.} }
Endnote
%0 Conference Paper %T INQUIRE: INteractive Querying for User-aware Informative REasoning %A Tesca Fitzgerald %A Pallavi Koppol %A Patrick Callaghan %A Russell Quinlan Jun Hei Wong %A Reid Simmons %A Oliver Kroemer %A Henny Admoni %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-fitzgerald23a %I PMLR %P 2241--2250 %U https://proceedings.mlr.press/v205/fitzgerald23a.html %V 205 %X Research on Interactive Robot Learning has yielded several modalities for querying a human for training data, including demonstrations, preferences, and corrections. While prior work in this space has focused on optimizing the robot’s queries within each interaction type, there has been little work on optimizing over the selection of the interaction type itself. We present INQUIRE, the first algorithm to implement and optimize over a generalized representation of information gain across multiple interaction types. Our evaluations show that INQUIRE can dynamically optimize its interaction type (and respective optimal query) based on its current learning status and the robot’s state in the world, resulting in more robust performance across tasks in comparison to state-of-the art baseline methods. Additionally, INQUIRE allows for customizable cost metrics to bias its selection of interaction types, enabling this algorithm to be tailored to a robot’s particular deployment domain and formulate cost-aware, informative queries.
APA
Fitzgerald, T., Koppol, P., Callaghan, P., Wong, R.Q.J.H., Simmons, R., Kroemer, O. & Admoni, H.. (2023). INQUIRE: INteractive Querying for User-aware Informative REasoning. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:2241-2250 Available from https://proceedings.mlr.press/v205/fitzgerald23a.html.

Related Material