Technology for Creating Digital Twins to Optimize the Design Parameters of Robots and Their Control Systems
https://doi.org/10.35596/1729-7648-2025-31-3-43-53
Abstract
A universal software technology for rapid creation and testing of digital twins of robotic systems with adaptive control capability has been developed. It allows for flexible and relatively rapid creation of digital twins of mobile and anthropomorphic robots. A digital twin consisting of simulation models of the kinematic system, control system, and operating environment is capable of almost completely simulating the robot’s beha vior in various modes in real or pseudo-real time. The technology operation process is described, starting from creating a solid model and ending with selecting the optimal robot motion control method. Particular attention is paid to adaptive control through reinforcement learning, which allows the system to adapt to changing conditions. Depending on the goals of the proposed object and the availability of initial data, the proposed technology makes it possible design and implement a robot control system or test new control methods. A practical example of applying the technology for creating digital twins to control an anthropomorphic robot aimed at simulating human walking has been implemented. The results confirm a reduction in development time and an increase in the reliability of solutions. The technology is integrated into a single software package, which simplifies the creation of new twins and testing of algorithms.
About the Authors
T. Yu. Kim
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Kim T. Yu., Junior Researcher of the Laboratory of Robotic Systems No 116
220072, Minsk, Surganova St., 6
Tel.: +375 17 270-31-75
Kim Tatyana Yuryevna
R. A. Prakapovich
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
220072, Minsk, Surganova St., 6
References
1. Stjepandić J. (2022) Digital Twin: A Conceptual View. An Approach for Production Process Optimization in a Built Environment. Cham, Springer.
2. Kim T. Yu. (2022) Development of a Digital Twin for an Anthropomorphic “Astronaut” Robot Using Real-Time Reinforcement Learning. Youth in Science. Minsk. 419–422 (in Russian).
3. Prokopovich G. A. (2019) Development of a Control System for an Educational Parallel-Structure Manipulator Robot Using Model-Based Design Technology. Informatics. 16 (4), 99–114 (in Russian).
4. Kim T. Y., Pechkovskaya A. V., Pechkovsky E. I. (2024) Mass Optimization Method for Gearbox Parts Manufactured by 3D Printing Based on a Genetic Algorithm. Journal of the Belarusian State University. Mathematics. Informatics. 21 (3), 32–46 (in Russian).
5. Kim T. Y., Prokopovich G. A. (2020) Simulation of Two-Wheeled RoboCake Robot Motion on a Horizontal Plane. Youth in Science – 2020, Proc. XVII Int. Sci. Conf. Minsk, Belaruskaya Navuka. 398–400 (in Russian).
6. Kim T. Y., Prokopovich G. A. (2021) Optimization of PID Controller Coefficients for Mobile Robot Motion Control System Along a Color-Contrast Line Using a Genetic Algorithm. Informatics. 18 (4), 53–68 (in Russian).
7. Kim T. Y., Prokopovich G. A. (2024) . Study of the Influence of Reward Function Formation Method Using the “Twin” Approach for Reinforcement Learning Algorithms. Information and Communication Technologies: Achievements, Problems, Innovations (ICT–2024): Electronic Collection of Articles of the III International Scientific and Practical Conference, Polotsk, March 29. Novopolotsk, Polotsk State University. 93–97 (in Russian).
8. Kim T., Prakapovich R. (2022) Automatic Tuning of the Motion Control System of a Mobile Robot Along a Trajectory Based on the Reinforcement Learning Method. Communications in Computer and Information Science. 1562, 234–244.
9. Kim T. Y., Prokopovich G. A. (2024) Development of Imitation Learning Method for Neural Network Control System of Mobile Robot Using Maze Exit Search Task. Informatics. 21 (3), 32–46 (in Russian).
10. Kim T. Y. (2023) Training a Mobile Robot to Navigate in an Unknown Environment Using Reinforcement Learning. Information Technologies in Industry, Logistics and Social Sphere (ITI'2023): Proceedings of the 12th International Scientific and Technical Conference. Minsk, United Institute of Informatics Problems of the National Academy of Sciences of Belarus. 78–81 (in Russian).
11. Wang Y., Qin Z., Kim T. Y., Wu P., Cheng P., Zhang X., et al. (2024) Research on Autonomous Lift Control Method of Hovercraft Based on DDPG. Artificial Intelligence in Belarus: Proceedings of the III IT-Akademgrad Forum. Minsk, National Academy of Sciences of Belarus. 336–347.
12. Dankwort C. W., Weidlich R., Guenther B., Blaurock J. E. (2004) Engineers' CAx Education – It's Not Only CAD. Computer-Aided Design. 36 (14), 1439–1450. https://doi.org/10.1016/j.cad.2004.02.011.
Review
For citations:
Kim T.Yu., Prakapovich R.A. Technology for Creating Digital Twins to Optimize the Design Parameters of Robots and Their Control Systems. Digital Transformation. 2025;31(3):43-53. (In Russ.) https://doi.org/10.35596/1729-7648-2025-31-3-43-53
Views:
49
Email this article 