Abstract
Assessment of the accuracy of neural network manipulator control is considered. The accuracy is assessed by comparing the required clamp coordinates with the actual experimental coordinates for a DOBOT Magician robot manipulator. The proposed approach permits the formation of a complete control space with the required accuracy over the entire working region.
Similar content being viewed by others
REFERENCES
Zenkevich, S.L. and Yushchenko, A.S., Osnovy upravleniya manipulyatsionnymi robotami: Uchebnik dlya vuzov (Fundamentals of Manipulation Robot Control: Manual for Higher Education Institutions), Moscow: Mosk. Gos. Tekh. Univ. im. N.E. Baumana, 2004.
Veselovskii, A.B., Rybinskaya, T.A., and Shapova-lov, R.G., Types and applications of industrial robot manipulators, Mezdunarod. Student. Nauchn. Vestn., 2015, no. 3-1. https://eduherald.ru/ru/article/view?id=11996
Metody resheniya zadach kinematiki manipulyatora (Methods for Solving Manipulator Kinematics Problems), Saratov: Saratovsk. Gos. Tekh. Univ., 2005. https://studfile.net/preview/9726683
Bausekov, S.D., Mekhanika robotov i manipulyatorov. Teoriya i praktika: Uchebnik (Mechanics of Robots and Manipulators. Theory and Practice: Manual), Taraz: TISS-Zhanaru, 2014.
Os’kin, D.A. and Dyda, A.A., Inverse kinematics problem for manipulator robot by penalty function method, Fundam. Issled., 2015, no. 11-4, pp. 673–677.
Koltygin, D.S., Sedel’nikov, I.A., and Petukhov, N.V., Analytical and numerical methods of inverse kinematic problem solution for Delta robot, Vestn. Irkutsk. Gos. Tekh. Univ., 2017, vol. 21, no. 5 (124), pp. 87–95.
Kharyunin, A.S., Kil’dishev, M.G., and Borisov, N.A., The solution of the inverse kinematics problem by the fabric method, in Trudy III mezhdunarodnoi nauchnoi konferentsii “Konvergentnye kognitivno-informatsionnye tekhnologii” (Proc. 3rd Int. Conf. “Convergent Cognitive Information Technologies”), Moscow: Mosk. Gos. Univ. im. M.V. Lomonosova, 2019, pp. 212–219.
Lisovskii, A.L., Application of neural network technologies for management development of systems, Strateg. Reshen. Risk-Menedzhment, 2020, vol. 11, no. 4, pp. 378–389. https://doi.org/10.17747/2618-947x-92310.17747/2618-947X-923
Shumikhin, A.G. and Boyarshinova, A.S., Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior, Komp. Issled. Model., 2015, vol. 7, no. 2, pp. 243–251.
Kozhevnikov, V.V., Leont’ev, M.Yu., Prikhod’ko, V.P., Sergeev, V.A., and Fomin, A.N., Principal directions of develo** the design methods for intelligent systems to control robots, Uchen. Zap. Ul’yanovsk. Gos. Univ. Ser. Matem. Inform. Tekhnol., 2019, no. 2, pp. 36–53. https://ulsu.ru/ru/page/page_3821/
Gumennyi, D. and Pirumov, A., Metodicheskie materialy dlya podgotovki inzhenerov. Chastʹ 1: Simulink dlya robototekhnicheskikh sistem (Methodological Materials for the Training of Engineers. Part 1: Simulink for Robotic Systems), Katsypa, E., Ed., Kiev, 2018. www.researchgate.net/publication/327915610_Metodiceskie_materialy_dla_podgotovki_inzenerov_Cast_1_Simulink_dla_robototehniceskih_sistem#pf4
Dobot Magician: Rukovodstvo pol’zovatelya (Dobot Magician: User Manual), Moscow: Inst. New Technol., 2018. www.int-edu.ru
Red’ko, V., Iskusstvennye neironnye seti. Formal’nyi neiron. Osnovnye neirosetevye paradigmy (Artificial Neural Networks. A Formal Neuron. The Main Neural Network Paradigms), Moscow, 1999. https://www.keldysh.ru/pages/BioCyber/Lectures/Lecture11/Lecture11.html
Il’in, I.V. and Gudkov, K.V., Analysis of the shortcomings of artificial neural networks and methods of their minimization, Materialy X mezhdunarodnoi studencheskoi nauchnoi konferentsii “Studencheskii nauchnyi forum” (Proc. 10th Int. Student Sci. Conf. “Student Scientific Forum”), 2018. https://scienceforum.ru/2018/article/2018000271
Kruglov, V.V. and Borisov, V.V., Iskusstvennye neironnye seti. Teoriya i praktika (Artificial Neural Networks. Theory and Practice), Moscow: Goryachaya Liniya–Telekom, 2001.
Saraev, P.V., Numerical methods of interval analysis in learning neural network, Autom. Remote Control, 2012, vol. 73, no. 11, pp. 1865–1876. https://doi.org/10.1134/S0005117912110082
Tsaregorodtsev, V.G., Preprocessing of the training sample, the Lipschitz sampling constant and the properties of trained neural networks, Materialy X Vserossiiskogo seminara “Neiroinformatika i ee prilozheniya” (Proc. 10th All-Russian Seminar “Neuroinformatics and Its Applications”), Krasnoyarsk, 2002, pp. 146–150.
https://ozlib.com/995657/tehnika/neyrosetevoy_podhod_resheniyu_obratnoy_zadachi_kinematiki
https://ozlib.com/995658/tehnika/upravlenie_mnogozvennym_manipulyatorom_osnove_iskusstvennoy_neyronnoy_seti_pryamogo_rasprostraneniya
https://ozlib.com/995656/tehnika/primenenie_metodov_neyronnyh_setey_resheniya_zadach_upravleniya_robotami
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by B. Gilbert
About this article
Cite this article
Girenko, D.S., Zhidkov, V.N. & Kim, N.V. Accuracy of Neural Network Manipulator Control. Russ. Engin. Res. 42, 929–931 (2022). https://doi.org/10.3103/S1068798X2209009X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068798X2209009X