Abstract
A system for contact-free control of a robot system is based on a three-dimensional biomechanical model of the human skeleton for gesture recognition, by means of deep learning. Preliminary data analysis by calculating saliency maps permits more efficient classification of gestural commands and thus improves the performance of all control systems in the collaborative robot system.
Similar content being viewed by others
REFERENCES
Khar’kov, M.A., Ivanovskii, S.P., Zelenskii, A.A., and Abdullin, T.Kh., Distributed control system for the electroautomatics of machine tools, industrial robots and automated complexes based on a high-performance communication interface, Vestn. Mosk. Gos. Tekhnol. Univ., Stankin, 2018, no. 1 (44), pp. 91–95.
Dorozhkin, I.N., Dorozhkina, O.K., and Shinkevich, I.A., Digital production introduction at the expense of industrial and operational management automation at the industrial enterprise, Vestn. Mosk. Gos. Tekhnol. Univ., Stankin, 2018, no. 2 (45), pp. 112–116.
Zelenskii, A.A. and Khar’kov, M.A., Safety system for machining equipment and operator protection based on distributed control system, Vestn. Mosk. Gos. Tekhnol. Univ., Stankin, 2018, no. 3 (46), pp. 25–29.
Zelensky, A., Voronin, V., Svirin, I., et al., Video content verification using blockchain technology, Proc. 3rd IEEE Int. Conf. on Smart Cloud, SmartCloud 2018, Piscataway, NJ: Inst. Electr. Electron. Eng., 2018, pp. 208–212.
Zelenskii, A.A. and Pis’menskova, M.M., The human action recognition method on complex-structured images and stochastic texture background, Vestn. Mosk. Gos. Tekhnol. Univ., Stankin, 2018, no. 3 (46), pp. 116–120.
Belagiannis, V. and Zisserman, A., Recurrent human pose estimation, Proc. 12th IEEE Int. Conf. on Automatic Face & Gesture Recognition (FG 2017), Piscataway, NJ: Inst. Electr. Electron. Eng., 2017, pp. 468–475.
Niebur, E., Saliency map, Scholarpedia, 2007, vol. 2, no. 8, p. 2675.
Pismenskova, M., Balabaeva, O., Voronin, V., et al., Classification of a two-dimensional pose using a human skeleton, MATEC Web Conf., 2017, vol. 132, no. 05016.
Zelenskii, A.A. and Frants, V.A., Generative adversarial neural networks for video feature extraction in task of visual quality assessment, Vestn. Mosk. Gos. Tekhnol. Univ., Stankin, 2018, no. 3 (46), pp. 86–90.
Voronin, V., Pismenskova, M., Zelensky, A., et al., Action recognition using the 3D dense microblock difference, Proc. SPIE, 2018, vol. 10802, no. 108020O.
Funding
This work is supported by the Russian Science Foundation under grant no. 18-71-00137.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by B. Gilbert
About this article
Cite this article
Zelenskii, A.A., Pismenskova, M.M. & Voronin, V.V. Control of Collaborative Robot Systems and Flexible Production Cells on the Basis of Deep Learning. Russ. Engin. Res. 39, 1065–1068 (2019). https://doi.org/10.3103/S1068798X19120256
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068798X19120256