Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations

M. Asif Rana, Anqi Li, Harish Ravichandar, Mustafa Mukadam, Sonia Chernova, Dieter Fox, Byron Boots, Nathan Ratliff
Proceedings of the Conference on Robot Learning, PMLR 100:1457-1468, 2020.

Abstract

Complex manipulation tasks often require non-trivial and coordinated movements of different parts of a robot. In this work, we address the challenges associated with learning and reproducing the skills required to execute such complex tasks. Specifically, we decompose a task into multiple subtasks and learn to reproduce the subtasks by learning stable policies from demonstrations. By leveraging the RMPflow framework for motion generation, our approach finds a stable global policy in the configuration space that enables simultaneous execution of various learned subtasks. The resulting global policy is a weighted combination of the learned policies such that the motions are coordinated and feasible under the robot’s kinematic and environmental constraints. We demonstrate the necessity and efficacy of the proposed approach in the context of multiple constrained manipulation tasks performed by a Franka Emika robot.

Cite this Paper

BibTeX
@InProceedings{pmlr-v100-rana20a, title = {Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations}, author = {Rana, M. Asif and Li, Anqi and Ravichandar, Harish and Mukadam, Mustafa and Chernova, Sonia and Fox, Dieter and Boots, Byron and Ratliff, Nathan}, booktitle = {Proceedings of the Conference on Robot Learning}, pages = {1457--1468}, year = {2020}, editor = {Kaelbling, Leslie Pack and Kragic, Danica and Sugiura, Komei}, volume = {100}, series = {Proceedings of Machine Learning Research}, month = {30 Oct--01 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v100/rana20a/rana20a.pdf}, url = {https://proceedings.mlr.press/v100/rana20a.html}, abstract = {Complex manipulation tasks often require non-trivial and coordinated movements of different parts of a robot. In this work, we address the challenges associated with learning and reproducing the skills required to execute such complex tasks. Specifically, we decompose a task into multiple subtasks and learn to reproduce the subtasks by learning stable policies from demonstrations. By leveraging the RMPflow framework for motion generation, our approach finds a stable global policy in the configuration space that enables simultaneous execution of various learned subtasks. The resulting global policy is a weighted combination of the learned policies such that the motions are coordinated and feasible under the robot’s kinematic and environmental constraints. We demonstrate the necessity and efficacy of the proposed approach in the context of multiple constrained manipulation tasks performed by a Franka Emika robot.} }
Endnote
%0 Conference Paper %T Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations %A M. Asif Rana %A Anqi Li %A Harish Ravichandar %A Mustafa Mukadam %A Sonia Chernova %A Dieter Fox %A Byron Boots %A Nathan Ratliff %B Proceedings of the Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2020 %E Leslie Pack Kaelbling %E Danica Kragic %E Komei Sugiura %F pmlr-v100-rana20a %I PMLR %P 1457--1468 %U https://proceedings.mlr.press/v100/rana20a.html %V 100 %X Complex manipulation tasks often require non-trivial and coordinated movements of different parts of a robot. In this work, we address the challenges associated with learning and reproducing the skills required to execute such complex tasks. Specifically, we decompose a task into multiple subtasks and learn to reproduce the subtasks by learning stable policies from demonstrations. By leveraging the RMPflow framework for motion generation, our approach finds a stable global policy in the configuration space that enables simultaneous execution of various learned subtasks. The resulting global policy is a weighted combination of the learned policies such that the motions are coordinated and feasible under the robot’s kinematic and environmental constraints. We demonstrate the necessity and efficacy of the proposed approach in the context of multiple constrained manipulation tasks performed by a Franka Emika robot.
APA
Rana, M.A., Li, A., Ravichandar, H., Mukadam, M., Chernova, S., Fox, D., Boots, B. & Ratliff, N.. (2020). Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations. Proceedings of the Conference on Robot Learning, in Proceedings of Machine Learning Research 100:1457-1468 Available from https://proceedings.mlr.press/v100/rana20a.html.

Related Material