Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands

Avishai Sintov, Andrew Kimmel, Bowen Wen, Abdeslam Boularias, Kostas Bekris
Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR 120:771-780, 2020.

Abstract

Precise in-hand manipulation is an important skill for a robot to perform tasks in human environments. Practical robotic hands must be low-cost, easy to control and capable. 3D-printed underactuated adaptive hands provide such properties as they are cheap to fabricate and adapt to objects of uncertain geometry with stable grasps. Challenges still remain, however, before such hands can attain human-like performance due to complex dynamics and contacts. In particular, useful models for planning, control or model-based reinforcement learning are still lacking. Recently, data-driven approaches for such models have shown promise. This work provides the first large public dataset of real within-hand manipulation that facilitates building such models, along with baseline data-driven modeling results. Furthermore, it contributes ROS-based physics-engine model of such hands for independent data collection, experimentation and sim-to-reality transfer work.

Cite this Paper

BibTeX
@InProceedings{pmlr-v120-sintov20a, title = {Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands}, author = {Sintov, Avishai and Kimmel, Andrew and Wen, Bowen and Boularias, Abdeslam and Bekris, Kostas}, booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control}, pages = {771--780}, year = {2020}, editor = {Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie}, volume = {120}, series = {Proceedings of Machine Learning Research}, month = {10--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v120/sintov20a/sintov20a.pdf}, url = {https://proceedings.mlr.press/v120/sintov20a.html}, abstract = {Precise in-hand manipulation is an important skill for a robot to perform tasks in human environments. Practical robotic hands must be low-cost, easy to control and capable. 3D-printed underactuated adaptive hands provide such properties as they are cheap to fabricate and adapt to objects of uncertain geometry with stable grasps. Challenges still remain, however, before such hands can attain human-like performance due to complex dynamics and contacts. In particular, useful models for planning, control or model-based reinforcement learning are still lacking. Recently, data-driven approaches for such models have shown promise. This work provides the first large public dataset of real within-hand manipulation that facilitates building such models, along with baseline data-driven modeling results. Furthermore, it contributes ROS-based physics-engine model of such hands for independent data collection, experimentation and sim-to-reality transfer work. } }
Endnote
%0 Conference Paper %T Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands %A Avishai Sintov %A Andrew Kimmel %A Bowen Wen %A Abdeslam Boularias %A Kostas Bekris %B Proceedings of the 2nd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2020 %E Alexandre M. Bayen %E Ali Jadbabaie %E George Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire Tomlin %E Melanie Zeilinger %F pmlr-v120-sintov20a %I PMLR %P 771--780 %U https://proceedings.mlr.press/v120/sintov20a.html %V 120 %X Precise in-hand manipulation is an important skill for a robot to perform tasks in human environments. Practical robotic hands must be low-cost, easy to control and capable. 3D-printed underactuated adaptive hands provide such properties as they are cheap to fabricate and adapt to objects of uncertain geometry with stable grasps. Challenges still remain, however, before such hands can attain human-like performance due to complex dynamics and contacts. In particular, useful models for planning, control or model-based reinforcement learning are still lacking. Recently, data-driven approaches for such models have shown promise. This work provides the first large public dataset of real within-hand manipulation that facilitates building such models, along with baseline data-driven modeling results. Furthermore, it contributes ROS-based physics-engine model of such hands for independent data collection, experimentation and sim-to-reality transfer work.
APA
Sintov, A., Kimmel, A., Wen, B., Boularias, A. & Bekris, K.. (2020). Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands. Proceedings of the 2nd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 120:771-780 Available from https://proceedings.mlr.press/v120/sintov20a.html.

Related Material