Potential Based Diffusion Motion Planning

Yunhao Luo, Chen Sun, Joshua B. Tenenbaum, Yilun Du
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33486-33510, 2024.

Abstract

Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability – different motion constraints can easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints. Project website at https://energy-based-model.github.io/potential-motion-plan.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-luo24h, title = {Potential Based Diffusion Motion Planning}, author = {Luo, Yunhao and Sun, Chen and Tenenbaum, Joshua B. and Du, Yilun}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {33486--33510}, 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/luo24h/luo24h.pdf}, url = {https://proceedings.mlr.press/v235/luo24h.html}, abstract = {Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability – different motion constraints can easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints. Project website at https://energy-based-model.github.io/potential-motion-plan.} }
Endnote
%0 Conference Paper %T Potential Based Diffusion Motion Planning %A Yunhao Luo %A Chen Sun %A Joshua B. Tenenbaum %A Yilun Du %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-luo24h %I PMLR %P 33486--33510 %U https://proceedings.mlr.press/v235/luo24h.html %V 235 %X Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability – different motion constraints can easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints. Project website at https://energy-based-model.github.io/potential-motion-plan.
APA
Luo, Y., Sun, C., Tenenbaum, J.B. & Du, Y.. (2024). Potential Based Diffusion Motion Planning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:33486-33510 Available from https://proceedings.mlr.press/v235/luo24h.html.

Related Material