AUTOMATIC SYNTHESIS OF GAIT SCENARIOS FOR RECONFIGURABLE MECHATRONIC MODULAR ROBOTS IN THE MODIFICATION OF THE WALKING PLATFORM
https://doi.org/10.32362/2500-316X-2018-6-4-26-41
Abstract
Reconfigurable mechatronic modular robots capable of adapting their structure depending on the specifics of the tasks performed and the environmental conditions are of great interest for a wide range of different applications. One of the key issues in controlling the movement of robots of this type is the need to use original algorithms for each of the possible configurations. The variety of configurations is determined by the structure of mechatronic modules, their number and the selected connection option. Some typical configurations of mechatronic modular robots allow the development of motion control algorithms invariant with respect to the number of modules in the kinematic structure. However, a promising approach to solving the problem is generally associated with the development of self-learning methods and tools for the automated synthesis of motion control algorithms of a multi-link mechatronic modular robot in case of chosen configuration. This article discusses the results of research on the use of self-organized finite-state machines for solving the problem of automatic synthesis of scenarios for the gait of reconfigurable mechatronic-modular robots in the modification of the walking platform. The results of model experiments confirming the efficiency and effectiveness of the developed algorithms are presented.
About the Authors
S. V. Manko
MIREA - Russian Technological University
Russian Federation
Russian Federation
E. I. Shestakov
MIREA - Russian Technological University
Russian Federation
Russian Federation
References
1. Jing G., Tosun T., Yim M., Kress-Gazit H. An end-to-end system for accomplishing tasks with modular robots / In: Proceedings of Conference Robotics: Science and Systems, 2016.
2. Makarov I.M., Lokhin V.M., Manko S.V., Pomanov M.P., Kadochnikov M.V. Algoritms of control by motion of multilinkmechatronic-Modular robots with adaptive kinematic structure // Mehatronika, Avtomatizatsiya, Upravlenie (Mechatronics, Automation, Control). 2008. № 3. P. 1–10. (in Russ.).
3. Lokhin V.M., Manko S.V., Alexandrova R.I., Diane S.A.K., Panin A.S. Intelligent feedback, knowledge processing and self learning in control systems of autonomous robots and multi-agent robotic groups // Mehatronika, Avtomatizatsiya, Upravlenie (Mechatronics, Automation, Control). 2015. V. 16. № 8. P. 545–555. (in Russ.).
4. Nikolaenko S.N., Tulupyev A.L. Self-Learning Systems. Moscow: MTSNMO Publ., 2009. 288 р. (in Russ.).
5. Makarov I.M., Lokhin V.M., Manko S.V., Kadochnikov M.V., Sitnikov M.S. Use of genetic algorithms for automatic formation of base of knowledges of intellectual control system by autonomous mobile robot // Mehatronika, Avtomatizatsiya, Upravlenie (Mechatronics, Automation, Control). 2008. № 5. P. 18–23. (in Russ.).
6. Busch J., Ziegler J., Aue C., Ross A., Sawitzki D., Banzhaf W. Automatic generation of control programs for walking robots using genetic programming / In: Foster J.A., Lutton E., Miller J., Ryan C., Tettamanzi A. (eds.) Genetic Programming. European Conference on Genetic Programming EuroGP, 2002. Lecture Notesin Computer Science, book series. Springer, Berlin, Heidelberg. V. 2278. Р. 258–267.
7. Kober J., Peters J. Reinforcement learning in robotics: A survey // In: Reinforcement Learning / Wiering M., van Otterlo M. (eds.). Adaptation, Learning, and Optimization. V. 12. Springer, Berlin, Heidelberg, 2012. Р. 579–610.
8. Lokhin V.M., Manko S.V., Diane S.A.K., Panin A.S., Aleksandrova R.I. Self-learning mechanisms in the multi-robot systems based on the evolution forests and classification trees // Mehatronika, Avtomatizatsiya, Upravlenie (Mechatronics, Automation, Control). 2017. V. 18. № 3. P. 159–165. (in Russ.).
9. Kojcev R., Etxezarreta N., Hernandez A., Mayoral V. Evaluation of deep reinforcement learning methods for modular robots. arXiv preprint arXiv:1802.02395, 2018.
10. D’Angelo M., Weel B., Eiben A.E. online gait learning for modular robots with arbitrary shapes and sizes // In: Dediu A.H., Martín-Vide C., Truthe B., Vega-Rodríguez M.A. (eds) Second International Conference on the Theory and Practice of Natural Computing (TPNC 2013), № 8273 in LNCS. Springer, Berlin, Р. 45–56.
11. Varshavskaya, P., Kaelbling, L.P., Rus, D. Learning distributed control for modular robots // In: Intelligent robots and systems, of the 2004. Proceedings 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 28 Sept.–02 Oct. 2004. Sendai, Japan. V. 3. P. 2648–2653.
12. Zhang J., Springenberg J.T., Boedecker J., Burgard W. Deep reinforcement learning with successor features for navigation across similar environments // Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference. P. 2371–2378.
13. Mnih V., Badia A.P., Mirza M., Graves A., Lillicrap T.P., Harley T., Silver D., Kavukcuoglu K. Asynchronous methods for deep reinforcement learning // Proceedings of the 33rd International Conference on Machine Learning, PMLR. 2016. P. 1928–1937.
14. Yoshida E., Murata S., Kamimura A., Tomita K., Kurokawa H., Kokaji S. Evolutionary synthesis of dynamic motion and reconfiguration process for a modular robot M-TRAN // Proceedings of the 2003 International Symposium on Computational Intelligence in Robotics and Automation. 2003. P. 1004–1010.
15. Demin A.V., Vityaev E.E. Adaptive control of modular robots // In: Samsonovich A., Klimov V. (eds) Biologically Inspired Cognitive Architectures (BICA) for Young Scientists. BICA 2017. Advances in Intelligent Systems and Computing. Springer, Cham., 2018. V. 636. P. 204–212.
16. Tsetlin M.L. Studies on the Theory of Automata and Modeling of Biological Systems. Moscow: Nauka (Science) Publ., 1969. 316 p. (in Russ.).
Review
For citations:
Manko S.V., Shestakov E.I. AUTOMATIC SYNTHESIS OF GAIT SCENARIOS FOR RECONFIGURABLE MECHATRONIC MODULAR ROBOTS IN THE MODIFICATION OF THE WALKING PLATFORM. Russian Technological Journal. 2018;6(4):26-41. (In Russ.) https://doi.org/10.32362/2500-316X-2018-6-4-26-41
Views:
506
Email this article 