Development of modular robot control systems poses serious challenges associated with the robot’s construction subject to changes and the presence of a large number of degrees of freedom. The goal of this work was developing a versatile control system for modular hyper-redundant systems, able of independently finding ways to control robots with an arbitrary design from a certain given class. For solving the problem, a model of a control system was proposed, using logical-probabilistic knowledge discovery methods, adapted for control tasks. In accordance with the proposed approach, the task of control system training was reduced to finding patterns in an array of system’s environment interaction statistical data. For making the system independent on the chosen robot design, including modules’ spatial connection data specified in a data tree was proposed. Using this information during the training process allows the control system to independently tune in to control the robot, regardless of its design. For testing the proposed model’s performance and effectiveness, experiments in training a class of robots with different designs to move forward, which have confirmed both the learning rate and control quality being high.

Alexander Demin, PhD, Sobolev Institute of Mathematics, Ershov Institute of Informatics Systems 6, Lavrentyev pr., Novosibirsk, 630090, Russian Federation, tel.: +7 (383) 3306660, e-mail: alexandredemin@yandex.ru

Demin A.V. Adaptive Control of Modular Robots with Arbitrarily Specified Design. The Bulletin of Irkutsk State University. Series Mathematics, 2019, vol. 29, pp. 10-21. (in Russian) https://doi.org/10.26516/1997-7670.2019.29.10

1. Vityaev E.E. Extracting Knowledge from Data. Computer Cognition. Models of Cognitive Processes. Novosibirsk, Novosibirsk State University Publ., 2006, 293 p. (in Russian)
2. Demin A.V. Adaptive Control of Robotw with Modular Design. Systemy Upravlenia, svyazi i bezopasnosti, 2015, no. 4, pp. 180-197 (in Russian).
3. Demin A.V., Vityaev E.E. A Logical Model of an Adaptive Control System. Neiroinformatika, 2008, vol. 3, no. 1, pp. 79-107. (in Russian).
4. Demin A.V. Logical-Probabilistic Method for Modular Robots Control. Sistemnaya informatika, 2017, no. 11, pp. 61-79. (in Russian). https://doi.org/10.31144/si.2307-6410.2017.n11.p61-80
5. Brunete A., Ranganath A., Segovia S., de Frutos J.P., Hernando M., Gambao E. Current trends in reconfigurable modular robots design. International Journal of Advanced Robotic Systems, 2017, vol. 14 (3), pp. 1-21. https://doi.org/10.1177/1729881417710457
6. Christensen D.J., Bordignon M., Schultz U.P., Shaikh D., Stoy K. Morphology independent learning in modular robots. Proceedings of International Symposium on Distributed Autonomous Robotic Systems 8 (DARS 2008), 2008, pp. 379–391. https://doi.org/10.1007/978-3-642-00644-9_34
7. Demin A.V., Vityaev E.E. Adaptive Control of Modular Robots. In: A.V. Samsonovich and V.V. Klimov (eds.), Biologically Inspired Cognitive Architectures (BICA) for Young Scientists, Advances in Intelligent Systems and Computing 636, Springer, 2018, pp. 204-212. https://doi.org/10.1007/978-3-319-63940-6_29
8. Demin A.V., Vityaev E.E. Learning in a virtual model of the C. Elegans nematode for locomotion and chemotaxis. In: Biologically Inspired Cognitive Architectures (2014), Elsevier, 2014, vol. 7, pp. 9-14. https://doi.org/10.1016/j.bica.2013.11.005
9. Ito K., Matsuno F. Control of hyper-redundant robot using QDSEGA. Proceedings of the 41st SICE Annual Conference (2002), 2002, vol. 3, pp. 1499-1504.
10. Kamimura A., Kurokawa H., Yoshida E., Tomita K., Murata S., Kokaji S. Automatic locomotion pattern generation for modular robots. Proceedings of 2003 IEEE International Conference on Robotics and Automation, 2003, pp. 714-720.
11. Marbach D., Ijspeert A.J. Co-evolution of configuration and control for homogenous modular robots. Proceedings of the eighth conference on Intelligent Autonomous Systems (IAS8), IOS Press, 2004, pp. 712-719.
12. Stoy K., Brandt D., Christensen D.J. Self-Reconfigurable Robots: an Introduction. Intellegent robotics and autonomous agents series, MIT Press, 2010, 216 p.
13. Valsalam V.K. Miikkulainen R. Modular neuroevolution for multilegged locomotion. In Proceedings of GECCO, 2008, pp. 265–272. https://doi.org/10.1145/1389095.1389136
14. Yim M.H., Duff D.G., Roufas K.D. Modular reconfigurable robots, an approach to urban search and rescue. 1st International Workshop on Human Welfare Robotics Systems (HWRS-2000), 2000, pp. 19-20.