Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation

Homanga Bharadhwaj
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3751-3762, 2024.

Abstract

In this paper, we develop a structured critique of robotic simulations for real-world manipulation, by arguing that scaling simulators is neither necessary nor sufficient for making progress in general-purpose real-world robotic manipulation agents that are compliant with human preferences. With the ubiquity of robotic simulators, and recent efforts to scale them for diverse tasks, and at the same time the interest in generally capable real-world manipulation systems, we believe it is important to address the limitations of using simulation for real-world manipulation, so that as a community, we can focus our collective resources, energy, and time on approaches that have more principled odds of success. We further demonstrate the unique challenges that real-world manipulation presents, and show through examples and arguments why scaling simulation doesn’t get us closer to solving these challenges required for diverse real-world deployment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-bharadhwaj24a, title = {Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation}, author = {Bharadhwaj, Homanga}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {3751--3762}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/bharadhwaj24a/bharadhwaj24a.pdf}, url = {https://proceedings.mlr.press/v235/bharadhwaj24a.html}, abstract = {In this paper, we develop a structured critique of robotic simulations for real-world manipulation, by arguing that scaling simulators is neither necessary nor sufficient for making progress in general-purpose real-world robotic manipulation agents that are compliant with human preferences. With the ubiquity of robotic simulators, and recent efforts to scale them for diverse tasks, and at the same time the interest in generally capable real-world manipulation systems, we believe it is important to address the limitations of using simulation for real-world manipulation, so that as a community, we can focus our collective resources, energy, and time on approaches that have more principled odds of success. We further demonstrate the unique challenges that real-world manipulation presents, and show through examples and arguments why scaling simulation doesn’t get us closer to solving these challenges required for diverse real-world deployment.} }
Endnote
%0 Conference Paper %T Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation %A Homanga Bharadhwaj %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-bharadhwaj24a %I PMLR %P 3751--3762 %U https://proceedings.mlr.press/v235/bharadhwaj24a.html %V 235 %X In this paper, we develop a structured critique of robotic simulations for real-world manipulation, by arguing that scaling simulators is neither necessary nor sufficient for making progress in general-purpose real-world robotic manipulation agents that are compliant with human preferences. With the ubiquity of robotic simulators, and recent efforts to scale them for diverse tasks, and at the same time the interest in generally capable real-world manipulation systems, we believe it is important to address the limitations of using simulation for real-world manipulation, so that as a community, we can focus our collective resources, energy, and time on approaches that have more principled odds of success. We further demonstrate the unique challenges that real-world manipulation presents, and show through examples and arguments why scaling simulation doesn’t get us closer to solving these challenges required for diverse real-world deployment.
APA
Bharadhwaj, H.. (2024). Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:3751-3762 Available from https://proceedings.mlr.press/v235/bharadhwaj24a.html.

Related Material