A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space

Leonidas Koutras, Zoe Doulgeri
Proceedings of the Conference on Robot Learning, PMLR 100:293-302, 2020.

Abstract

Dynamic movement primitives (DMP) are an efficient way for learning and reproducing complex robot behaviors. A singularity free DMP formulation for orientation in the Cartesian space is proposed by Ude et al. [1] and has been largely adopted by the research community. In this work, we demonstrate the undesired oscillatory behavior that may arise when controlling the robot’s orientation with this formulation, producing a motion pattern highly deviant from the desired and highlight its source. A correct formulation is then proposed that alleviates such problems while guaranteeing generation of orientation parameters that lie in SO(3). We further show that all aspects and advantages of DMP including ease of learning, temporal and spatial scaling and the ability to include coupling terms are maintained in the proposed formulation. Simulations and experiments with robot control in SO(3) are performed to demonstrate the performance of the proposed formulation and compare it with the previously adopted one.

Cite this Paper

BibTeX
@InProceedings{pmlr-v100-koutras20a, title = {A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space}, author = {Koutras, Leonidas and Doulgeri, Zoe}, booktitle = {Proceedings of the Conference on Robot Learning}, pages = {293--302}, 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/koutras20a/koutras20a.pdf}, url = {https://proceedings.mlr.press/v100/koutras20a.html}, abstract = {Dynamic movement primitives (DMP) are an efficient way for learning and reproducing complex robot behaviors. A singularity free DMP formulation for orientation in the Cartesian space is proposed by Ude et al. [1] and has been largely adopted by the research community. In this work, we demonstrate the undesired oscillatory behavior that may arise when controlling the robot’s orientation with this formulation, producing a motion pattern highly deviant from the desired and highlight its source. A correct formulation is then proposed that alleviates such problems while guaranteeing generation of orientation parameters that lie in SO(3). We further show that all aspects and advantages of DMP including ease of learning, temporal and spatial scaling and the ability to include coupling terms are maintained in the proposed formulation. Simulations and experiments with robot control in SO(3) are performed to demonstrate the performance of the proposed formulation and compare it with the previously adopted one.} }
Endnote
%0 Conference Paper %T A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space %A Leonidas Koutras %A Zoe Doulgeri %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-koutras20a %I PMLR %P 293--302 %U https://proceedings.mlr.press/v100/koutras20a.html %V 100 %X Dynamic movement primitives (DMP) are an efficient way for learning and reproducing complex robot behaviors. A singularity free DMP formulation for orientation in the Cartesian space is proposed by Ude et al. [1] and has been largely adopted by the research community. In this work, we demonstrate the undesired oscillatory behavior that may arise when controlling the robot’s orientation with this formulation, producing a motion pattern highly deviant from the desired and highlight its source. A correct formulation is then proposed that alleviates such problems while guaranteeing generation of orientation parameters that lie in SO(3). We further show that all aspects and advantages of DMP including ease of learning, temporal and spatial scaling and the ability to include coupling terms are maintained in the proposed formulation. Simulations and experiments with robot control in SO(3) are performed to demonstrate the performance of the proposed formulation and compare it with the previously adopted one.
APA
Koutras, L. & Doulgeri, Z.. (2020). A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space. Proceedings of the Conference on Robot Learning, in Proceedings of Machine Learning Research 100:293-302 Available from https://proceedings.mlr.press/v100/koutras20a.html.

Related Material