Mobile robots control with neuromorphic classifires of environment states

Mobile robots control with neuromorphic classifires of environment states

Lev A. Stankevich
PhD in Technical Sciences, Associate Professor, Peter the Great Saint Petersburg Polytechnical University (SPbPU), Assistant Professor, 29, Politekhnicheskaya ul., Saint Petersburg, 195251, Russia; Russian State Scientific Center for Robotics and Technical Cybernetics (RTC), Leading Research Scientist, 21, Tikhoretsky pr., Saint Petersburg, 194064, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it.

Anzhelika Zhuravskaya
SPbPU, Senior lecturer, 29, Politekhnicheskaya ul., Saint Petersburg, 195251, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it.

Received May 25, 2024

Abstract
The article proposes to implement mobile robots control systems using neuromorphic classifiers, in which biosimilar neurons are built on an original neuro-fuzzy model, trained to display the function of the Izhikevich neuron. Using this approach, neuromorphic classifiers of spatial and spatiotemporal patterns were developed. Such a classifiers were used in non-contact supervisory control system for mobile robot based on static and dynamic states of the environment. The experiments performed demonstrated the effectiveness of using the neuromorphic classifiers, both in a neural interface when recognizing imaginary supervisory commands of the user, and when solving problems of robot navigation in environments with static and dynamic obstacles. At comparative analysis of navigation systems implemented using the neuromorphic classifiers, modular fuzzy logic and the adaptive neuro-fuzzy system ANFIS it was shown that the system with the neuromorphic classifiers give the highest average speed of the robot, as well as the shortest travel time. An experiment with the use of the neuromorphic classifiers in the control system based on dynamic states of the environment showed that robot successfully avoids collisions with person.

Key words
Biosimilar neuron, neuromorphic systems, neuro-fuzzy model, mobile robot, state of the environment, contactless control, neural interface.

Acknowledgements
The research is performed with support of Russian Science Foundation # 23-21-00287, https://rscf.ru/en/project/23-21-00287.

DOI
10.31776/RTCJ.12306

Bibliographic description
Stankevich, L.A. and Zhuravskaya, A. (2024), "Mobile robots control with neuromorphic classifires of environment states", Robotics and Technical Cybernetics, vol. 12, no. 3, pp. 212-221, DOI: 10.31776/RTCJ.12306. (in Russian).

UDC identifier
004.896

References

  1. Yu, Q., Yan, R., Tang, H., Tan, K.C. et al. (2016), “A Spiking Neural Network Sys-tem for Robust Sequence Recognition”, IEEE Trans. Neural Network Learn, Syst. 27, pp. 621–635. DOI: 10.1109/TNNLS.2015.2416771.
  2. Gerstner, W., Kistler, W., Naud, R. and Paninski, L. (2014), Neuronal dynamics: From single neurons to networks and models of cognition, Cambridge University Press, Cambridge, USA.
  3. Izhikevich, E.M. et al. (2003), “Simple model of spiking neurons”, IEEE Transactions on neural networks, 14(6), pp. 1569-1572, DOI: 10.1109/TNN.2003.820440.
  4. Stankevich, L.A. (2019), Cognitive systems and robots. Monograph, Polytechnic university Press, Saint-Petersburg, Russia. (in Russian).
  5. Bakhshiev, A.V. and Stankevich, L.A. (2014), “Neural network control systems and information processing”, Robotics and Technical Cybernetics, 2(3), pp. 40-44. (in Russian).
  6. Smolyakov, I. and Stankevich, L. (2021), “Development of spiking neural networks based on neuron model using neuro-fuzzy basis”, In: Proceeding of conference “Cyber Physical Systems and Control”, St. Petersburg, Russia.
  7. Yakimenko, G. (2023), “Development of navigation system of wheeled mobile robot with differential drives using neuro-fuzzy cluster neuron”, Thesis of Master's degree dissertation, SPbSTU, Petersburg, Russia. (in Russian).
  8. Gundelakh, F.V. and Stankevich, L.A. (2024). “Spatiotemporal pattern classification based on neuromorphic networks”, Informatics and Automation, 23, DOI: 10.15622/ia.2024.23.1.4. (in Russian).
  9. Nilsson, T. (2001), Kiks is a khepera simulator, Umea University, Stockholm, Sweden.
  10. Lambercy, F. and Tharin, J. (2013), “KheperaIII/UserManual”, available at: http://ftp.k-team.com/KheperaIII/UserManual/Kh3.Robot.UserManual.pdf (Accessed May 25, 2023).
  11. Pegat, A. (2009), Nechetkoe modelirovanie i upravlenie [Fuzzy modeling and control], Binom. Laboratory of knowledge Publ., Moscow, Russia. (in Russian).
  12. Jyh-Shing, J. (1993), “ANFIS Adaptive-Network-based Fuzzy Inference System”, IEEE Transactions on Systems Man and Cybernetics, 23(3), DOI: 10.1109/21.256541.