Genetic Programming and Object Modeling of Manipulation Robots
- 作者: Krakhmalev O.N.1
-
隶属关系:
- Financial University under the Government of the Russian Federation
- 期: 卷 10, 编号 2 (2023)
- 页面: 16-25
- 栏目: AUTOMATION OF MANUFACTURING AND TECHNOLOGICAL PROCESSES
- URL: https://journals.eco-vector.com/2313-223X/article/view/568054
- DOI: https://doi.org/10.33693/2313-223X-2023-10-2-16-25
- EDN: https://elibrary.ru/APHXDT
- ID: 568054
如何引用文章
详细
The application of a genetic algorithm to solve the inverse kinematics problem of manipulative robots is considered. The basic concepts of the method of finding solutions using a genetic algorithm are defined. A block diagram of a simple genetic algorithm is presented. It is justified to use multiprocessor computing systems (transputers) to calculate genetic operators. This will greatly increase the efficiency of genetic algorithms. Manipulation systems with three and four links are selected as examples. The problem statement consisted in determining the hinge coordinates of an industrial robot by the specified Cartesian coordinates of the position of the center of the tool (TCP – Tool Center Point) installed on its final link. The results obtained confirm the effectiveness of genetic algorithms in solving inverse kinematics problems of industrial (manipulation) robots. Based on graph theory, the genetic programming procedure is defined as a way to find optimal kinematic structures of robot manipulation systems. The use of genetic programming for modification of object models of manipulation robots is shown. The object representation of the dynamic model of manipulation robots is considered. It is noted that the recombination of objects corresponding to mathematical expressions having mechanical meaning requires kinematic correspondence of the objects used. It is proposed to draw up object diagrams using computer programs that automate this process based on the principle of visual programming (Low-code).
全文:
作者简介
Oleg Krakhmalev
Financial University under the Government of the Russian Federation
编辑信件的主要联系方式.
Email: onkrakhmalev@fa.ru
ORCID iD: 0000-0002-9388-4137
Candidate of Engineering, Associate Professor; associate professor at the Department of Data Analysis and Machine Learning of the Financial University under the Government of the Russian Federation
俄罗斯联邦, Moscow参考
- Al Tahtawi A., Agni M., Hendrawati T. Small-scale robot arm design with pick and place mission based on inverse kinematics. Journal of Robotics and Control. 2021. No. 2. P. 6. DOI: https://doi.org/10.18196/jrc.26124
- Byun G., Kikuuwe R. Stiff and safe task-space position and attitude controller for robotic manipulators. Robomech J. 2020. No. 7. P. 18. DOI: https://doi.org/10.1186/s40648-020-00166-1
- Ferrentino E., Chiacchio P. On the optimal resolution of inverse kinematics for redundant manipulators using a topological analysis. J. Mechanisms Robotics. 2020. No. 12 (3). P. 031002. DOI: https://doi.org/10.1115/1.4045178
- Kalyayev A.V., Galuyev G.A. Digital neurocomputer VLSI-systems with parallel architecture. In: International Neural Network Conference. Dordrecht: Springer, 1990. DOI: https://doi.org/10.1007/978-94-009-0643-3_17
- Karpińska J., Tchoń K. Performance-oriented design of in- verse kinematics algorithms: Extended Jacobian approxi-mation of the Jacobian pseudo-inverse. J. Mechanisms Robotics. 2012. No. 4 (2). P. 021008. DOI: https://doi.org/10.1115/1.4006192
- Krakhmalev N.O., Korostelyov D.A. Solutions of the inverse kinematic problem for manipulation robots based on the genetic algorithm. IOP Conf. Ser.: Mater. Sci. Eng. 2020. No. 747. P. 012117. DOI: https://doi.org/10.1088/1757-899X/747/1/012117
- Krakhmalev O., Krakhmalev N., Gataullin S. et al. Mathe-matics model for 6-DOF joints manipulation robots. Mathe-matics. 2021. No. 9. P. 2828. DOI: https://doi.org/10.3390/math9212828
- Krakhmalev O. Object-oriented modeling of manipulation systems dynamics based on transformation matrices of homo-geneous coordinates. Robotics and Technical Cybernetics. 2017. No. 2 (15). Pp. 32–36.
- Krakhmalev O. Object-oriented simulation of robots’ mani-pulation systems. Robotics and Technical Cybernetics. 2018. No. 4 (21). Pp. 41–47. DOI: https://doi.org/10.31776/RTCJ.6406
- Krakhmalev O. Designing object diagrams and the method of structural mutations in models of robots’ manipulation systems. Proceedings of 14th International Conference on Electromechanics and Robotics “Zavalishin’s Readings”. Smart Innovation. Systems and Technologies. 2020. No. 154. Pp. 209–221. URL: https://link.springer.com/chapter/10.1007/978-981-13-9267-2_18
- Krakhmalev O.N. Use of structural mutations in object-oriented mathematical models of robot manipulation systems. Mathematical Models and Computer Simulations. 2020. No. 12 (1). Pp. 90–98. DOI: https://doi.org/10.1134/S023408791906008X
- Krakhmalev O., Korchagin S., Pleshakova E. et al. Parallel computational algorithm for object‐oriented modeling of manipulation robots. Mathematics. 2021. No. 9. P. 2886. DOI: https://doi.org/10.3390/math9222886
- Liu Q., Tian W., Li B., Ma Y. Kinematics of a 5-axis hybrid robot near singular configurations. Robotics and Computer-Integrated Manufacturing. 2022. No. 75. P. 102294. DOI: https://doi.org/10.1016/j.rcim.2021.102294
- Malik A., Henderson T., Prazenica R. Multi-objective swarm intelligence trajectory generation for a 7 degree of freedom robotic manipulator. Robotics. 2021. No. 10. P. 127. DOI: https://doi.org/10.3390/robotics10040127
- Malik A., Lischuk Y., Henderson T., Prazenica R. A deep reinforcement-learning approach for inverse kinematics solution of a high degree of freedom robotic manipulator. Robotics. 2022. No. 11. P. 44. DOI: https://doi.org/10.3390/robotics11020044
- Marsono M., Yoto Y., Suyetno A., Nurmalasari R. Design and programming of 5 axis manipulator robot with GrblGru open source software on preparing vocational students’ robotic skills. Journal of Robotics and Control. 2021. No. 2. P. 6. DOI: https://doi.org/10.18196/jrc.26134
- Strey A., Avellana N., Holgado R. et al. A configurable parallel neurocomputer. In: Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, November 20–23, 1995. doi: 10.1109/ANNES.1995.499438
- Tian W., Mou M., Yang J., Yin F. Kinematic calibration of a 5-DOF hybrid kinematic machine tool by considering the ill-posed identification problem using regularisation method. Robotics and Computer-Integrated Manufacturing. 2019. No. 60. Pp. 49–62. DOI: https://doi.org/10.1016/j.rcim.2019.05.016
- Torchigin V.P., Kobyakov A.E. Neurocomputers based on massively parallel architecture using optical means. In: Proceedings of SPIE. The International Society for Optical Engineering, December 1994. DOI: https://doi.org/10.1117/12.195591
- Tringali A., Cocuzza S. Globally optimal inverse kinematics method for a redundant robot manipulator with linear and nonlinear constraints. Robotics. 2020. No. 9. P. 61. DOI: https://doi.org/10.3390/robotics9030061
- Wajiansyah A., Supriadi S., Gaffar A.F., Putra A.B. Modeling of 2-DOF hexapod leg using analytical method. Journal of Robotics and Control. 2021. No. 2. P. 5. DOI: https://doi.org/10.18196/jrc.25119
- Ye H., Wang D., Wu J. et al. Forward and inverse kinematics of a 5-DOF hybrid robot for composite material machining. Robotics and Computer-Integrated Manufacturing. 2020. No. 65. P. 101961. DOI: https://doi.org/10.1016/j.rcim.2020. 101961
- Krakhmalev O.N. Object modeling in the kinematics of manipulative robots. Neurocomputers: Development, Application. 2022. No. 5. Pp. 55–66. (In Rus.) DOI: https://doi.org/10.18127/j19998554-202205-06