DYNAMO-GRASP: DYNAMics-aware Optimization for GRASP Point Detection in Suction Grippers

Boling Yang, Soofiyan Atar, Markus Grotz, Byron Boots, Joshua Smith
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2096-2112, 2023.

Abstract

In this research, we introduce a novel approach to the challenge of suction grasp point detection. Our method, exploiting the strengths of physics-based simulation and data-driven modeling, accounts for object dynamics during the grasping process, markedly enhancing the robot’s capability to handle previously unseen objects and scenarios in real-world settings. We benchmark DYNAMO-GRASP against established approaches via comprehensive evaluations in both simulated and real-world environments. DYNAMO-GRASP delivers improved grasping performance with greater consistency in both simulated and real-world settings. Remarkably, in real-world tests with challenging scenarios, our method demonstrates a success rate improvement of up to $48%$ over SOTA methods. Demonstrating a strong ability to adapt to complex and unexpected object dynamics, our method offers robust generalization to real-world challenges. The results of this research set the stage for more reliable and resilient robotic manipulation in intricate real-world situations. Experiment videos, dataset, model, and code are available at: https://sites.google.com/view/dynamo-grasp.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-yang23a, title = {DYNAMO-GRASP: DYNAMics-aware Optimization for GRASP Point Detection in Suction Grippers}, author = {Yang, Boling and Atar, Soofiyan and Grotz, Markus and Boots, Byron and Smith, Joshua}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2096--2112}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/yang23a/yang23a.pdf}, url = {https://proceedings.mlr.press/v229/yang23a.html}, abstract = {In this research, we introduce a novel approach to the challenge of suction grasp point detection. Our method, exploiting the strengths of physics-based simulation and data-driven modeling, accounts for object dynamics during the grasping process, markedly enhancing the robot’s capability to handle previously unseen objects and scenarios in real-world settings. We benchmark DYNAMO-GRASP against established approaches via comprehensive evaluations in both simulated and real-world environments. DYNAMO-GRASP delivers improved grasping performance with greater consistency in both simulated and real-world settings. Remarkably, in real-world tests with challenging scenarios, our method demonstrates a success rate improvement of up to $48%$ over SOTA methods. Demonstrating a strong ability to adapt to complex and unexpected object dynamics, our method offers robust generalization to real-world challenges. The results of this research set the stage for more reliable and resilient robotic manipulation in intricate real-world situations. Experiment videos, dataset, model, and code are available at: https://sites.google.com/view/dynamo-grasp.} }
Endnote
%0 Conference Paper %T DYNAMO-GRASP: DYNAMics-aware Optimization for GRASP Point Detection in Suction Grippers %A Boling Yang %A Soofiyan Atar %A Markus Grotz %A Byron Boots %A Joshua Smith %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-yang23a %I PMLR %P 2096--2112 %U https://proceedings.mlr.press/v229/yang23a.html %V 229 %X In this research, we introduce a novel approach to the challenge of suction grasp point detection. Our method, exploiting the strengths of physics-based simulation and data-driven modeling, accounts for object dynamics during the grasping process, markedly enhancing the robot’s capability to handle previously unseen objects and scenarios in real-world settings. We benchmark DYNAMO-GRASP against established approaches via comprehensive evaluations in both simulated and real-world environments. DYNAMO-GRASP delivers improved grasping performance with greater consistency in both simulated and real-world settings. Remarkably, in real-world tests with challenging scenarios, our method demonstrates a success rate improvement of up to $48%$ over SOTA methods. Demonstrating a strong ability to adapt to complex and unexpected object dynamics, our method offers robust generalization to real-world challenges. The results of this research set the stage for more reliable and resilient robotic manipulation in intricate real-world situations. Experiment videos, dataset, model, and code are available at: https://sites.google.com/view/dynamo-grasp.
APA
Yang, B., Atar, S., Grotz, M., Boots, B. & Smith, J.. (2023). DYNAMO-GRASP: DYNAMics-aware Optimization for GRASP Point Detection in Suction Grippers. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2096-2112 Available from https://proceedings.mlr.press/v229/yang23a.html.

Related Material