Toward robots that learn to summarize their actions in natural language: a set of tasks

Chad DeChant, Daniel Bauer
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1807-1813, 2022.

Abstract

Robots should be able to report in natural language what they have done. They should provide concise summaries, respond to questions about them, and be able to learn from the natural language responses they receive to their summaries. We propose that developing the capabilities for robots to summarize their actions is a new and necessary challenge which should be taken up by the robotic learning community. We propose an initial framework for robot action summarization, presented as a set of tasks which can serve as a target for research and a measure of progress.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-dechant22a, title = {Toward robots that learn to summarize their actions in natural language: a set of tasks}, author = {DeChant, Chad and Bauer, Daniel}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1807--1813}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/dechant22a/dechant22a.pdf}, url = {https://proceedings.mlr.press/v164/dechant22a.html}, abstract = {Robots should be able to report in natural language what they have done. They should provide concise summaries, respond to questions about them, and be able to learn from the natural language responses they receive to their summaries. We propose that developing the capabilities for robots to summarize their actions is a new and necessary challenge which should be taken up by the robotic learning community. We propose an initial framework for robot action summarization, presented as a set of tasks which can serve as a target for research and a measure of progress.} }
Endnote
%0 Conference Paper %T Toward robots that learn to summarize their actions in natural language: a set of tasks %A Chad DeChant %A Daniel Bauer %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-dechant22a %I PMLR %P 1807--1813 %U https://proceedings.mlr.press/v164/dechant22a.html %V 164 %X Robots should be able to report in natural language what they have done. They should provide concise summaries, respond to questions about them, and be able to learn from the natural language responses they receive to their summaries. We propose that developing the capabilities for robots to summarize their actions is a new and necessary challenge which should be taken up by the robotic learning community. We propose an initial framework for robot action summarization, presented as a set of tasks which can serve as a target for research and a measure of progress.
APA
DeChant, C. & Bauer, D.. (2022). Toward robots that learn to summarize their actions in natural language: a set of tasks. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1807-1813 Available from https://proceedings.mlr.press/v164/dechant22a.html.

Related Material