Geodesic
An efficient data acquisition methodology for inverse dynamics model learning of manipulator based on analytical method. I
Čelâbinskij fiziko-matematičeskij žurnal, Tome 8 (2023) no. 1, pp. 140-145.

Voir la notice de l'article provenant de la source Math-Net.Ru

In the last few years, learning inverse dynamic models of manipulators from data has shown considerable successes and become a progressively developing topic in dynamic modeling of manipulators. In this paper, we presented an efficient data acquisition methodology for inverse dynamics model learning. Our method is based around the parametric physical model of a manipulator that obtained from the rigid body dynamics using the analytical method. Our framework consists of Denavit — Hartenberg method for the generation of the manipulator workspace. The received datasets are validated by the results of simulation of kinematic and dynamic modeling of the tested manipulator.
Keywords: data acquisition, inverse dynamics, model learning, Denavit — Hartenberg method, manipulator. 
@article{CHFMJ_2023_8_1_a12,
     author = {S. M. Sitnik and R. Tu},
     title = {An efficient data acquisition methodology for inverse dynamics model learning of manipulator based on analytical method. {I}},
     journal = {\v{C}el\^abinskij fiziko-matemati\v{c}eskij \v{z}urnal},
     pages = {140--145},
     publisher = {mathdoc},
     volume = {8},
     number = {1},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/CHFMJ_2023_8_1_a12/}
}
TY  - JOUR
AU  - S. M. Sitnik
AU  - R. Tu
TI  - An efficient data acquisition methodology for inverse dynamics model learning of manipulator based on analytical method. I
JO  - Čelâbinskij fiziko-matematičeskij žurnal
PY  - 2023
SP  - 140
EP  - 145
VL  - 8
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CHFMJ_2023_8_1_a12/
LA  - ru
ID  - CHFMJ_2023_8_1_a12
ER  - 
%0 Journal Article
%A S. M. Sitnik
%A R. Tu
%T An efficient data acquisition methodology for inverse dynamics model learning of manipulator based on analytical method. I
%J Čelâbinskij fiziko-matematičeskij žurnal
%D 2023
%P 140-145
%V 8
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CHFMJ_2023_8_1_a12/
%G ru
%F CHFMJ_2023_8_1_a12
S. M. Sitnik; R. Tu. An efficient data acquisition methodology for inverse dynamics model learning of manipulator based on analytical method. I. Čelâbinskij fiziko-matematičeskij žurnal, Tome 8 (2023) no. 1, pp. 140-145. http://geodesic.mathdoc.fr/item/CHFMJ_2023_8_1_a12/

[1] Nair A., Chen D., Agrawal P., Isola P., Abbeel P., Malik J., Levine S., “Combining selfsupervised learning and imitation for vision-based rope manipulation”, Proceedings of IEEE Internatinal Conference on Robotics and Automation (ICRA), 2017, 2146–2153

[2] Nguyen-Tuong D., Peters J., “Model learning for robot control: A survey”, Cognitive Processing, 12:4 (2011), 319–340

[3] Thu Rain, Yan Naing Soe, “Dynamic modelling of manipulator using adaptive neuro fuzzy inference system”, Modeling, Optimization And Information Technology (MOIT), 7:4 (2019), 362–377 (In Russ.)

[4] Thu Rain, Dovgal V.M., Yan Naing Soe, “Modelling of the adaptive neuro-fuzzy inference system based control of 5-dof robotic manipulator “Intelbot””, Belgorod State University Scientific Bulletin. (Economics. Information Technologies), 45:3 (2018), 497–509 (In Russ.)