Robots on Demand: A Democratized Robotics Research Cloud

Victoria Dean, Yonadav G Shavit, Abhinav Gupta
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1769-1775, 2022.

Abstract

Robotics research is slowed by three challenges: building a robotics lab is expensive (few participants), everyone uses different robots (participants’ findings often don’t generalize outside their lab), and there is no internet-scale robotics dataset (no lab has the resources to make many robots do many different tasks to generate data and there is no data in the wild). The solution is to build a “Robotics Research Cloud” consisting of centers filled with remotely operable robots in standardized environments. This would be a valuable resource in pushing forward robot learning as a field by making cutting-edge robotics research broadly accessible, helping the field identify promising new approaches that succeed on agreed benchmarks, and creating a massive real-world robotics dataset similar to those that have revolutionized machine learning for vision and language.

Cite this Paper


BibTeX
@InProceedings{pmlr-v164-dean22a, title = {Robots on Demand: A Democratized Robotics Research Cloud}, author = {Dean, Victoria and Shavit, Yonadav G and Gupta, Abhinav}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1769--1775}, 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/dean22a/dean22a.pdf}, url = {https://proceedings.mlr.press/v164/dean22a.html}, abstract = {Robotics research is slowed by three challenges: building a robotics lab is expensive (few participants), everyone uses different robots (participants’ findings often don’t generalize outside their lab), and there is no internet-scale robotics dataset (no lab has the resources to make many robots do many different tasks to generate data and there is no data in the wild). The solution is to build a “Robotics Research Cloud” consisting of centers filled with remotely operable robots in standardized environments. This would be a valuable resource in pushing forward robot learning as a field by making cutting-edge robotics research broadly accessible, helping the field identify promising new approaches that succeed on agreed benchmarks, and creating a massive real-world robotics dataset similar to those that have revolutionized machine learning for vision and language.} }
Endnote
%0 Conference Paper %T Robots on Demand: A Democratized Robotics Research Cloud %A Victoria Dean %A Yonadav G Shavit %A Abhinav Gupta %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-dean22a %I PMLR %P 1769--1775 %U https://proceedings.mlr.press/v164/dean22a.html %V 164 %X Robotics research is slowed by three challenges: building a robotics lab is expensive (few participants), everyone uses different robots (participants’ findings often don’t generalize outside their lab), and there is no internet-scale robotics dataset (no lab has the resources to make many robots do many different tasks to generate data and there is no data in the wild). The solution is to build a “Robotics Research Cloud” consisting of centers filled with remotely operable robots in standardized environments. This would be a valuable resource in pushing forward robot learning as a field by making cutting-edge robotics research broadly accessible, helping the field identify promising new approaches that succeed on agreed benchmarks, and creating a massive real-world robotics dataset similar to those that have revolutionized machine learning for vision and language.
APA
Dean, V., Shavit, Y.G. & Gupta, A.. (2022). Robots on Demand: A Democratized Robotics Research Cloud. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1769-1775 Available from https://proceedings.mlr.press/v164/dean22a.html.

Related Material