PapersNo Access

Training a Network of Electronic Neurons for Control of a Mobile Robot

Department of Mechanical Engineering, Eindhoven University of Technology, 5600 MB, Eindhoven, The Netherlands

Institute for Complex Molecular Systems, Department of Mechanical Engineering, Eindhoven University of Technology, 5600 MB, Eindhoven, The Netherlands

E-mail Address: e.steur@tue.nl

Search for more papers by this author

, and

H. Nijmeijer

Department of Mechanical Engineering, Eindhoven University of Technology, 5600 MB, Eindhoven, The Netherlands

E-mail Address: h.nijmeijer@tue.nl

Search for more papers by this author

https://doi.org/10.1142/S0218127416501960Cited by:6 (Source: Crossref)

Abstract

An adaptive training procedure is developed for a network of electronic neurons, which controls a mobile robot driving around in an unknown environment while avoiding obstacles. The neuronal network controls the angular velocity of the wheels of the robot based on the sensor readings. The nodes in the neuronal network controller are clusters of neurons rather than single neurons. The adaptive training procedure ensures that the input–output behavior of the clusters is identical, even though the constituting neurons are nonidentical and have, in isolation, nonidentical responses to the same input. In particular, we let the neurons interact via a diffusive coupling, and the proposed training procedure modifies the diffusion interaction weights such that the neurons behave synchronously with a predefined response. The working principle of the training procedure is experimentally validated and results of an experiment with a mobile robot that is completely autonomously driving in an unknown environment with obstacles are presented.

Keywords:

References

Antonelo, E., Baerveldt, A.-J., Rögnvaldsson, T. & Figueiredo, M. [2006] “ Modular neural network and classical reinforcement learning for autonomous robot navigation: Inhibiting undesirable behaviors,” Proc. Int. Joint Conf. Neural Networks, pp. 498–505. Google Scholar
Antonelo, E., Schrauwen, B. & Stroobandt, D. [2008] “ Event detection and localization for small mobile robots using reservoir computing,” Neural Netw. 21, 862–871. Crossref, Web of Science, Google Scholar
Bloch, A. [2003] Nonholonomic Mechanics and Control (Springer-Verlag, NY). Crossref, Google Scholar
Burton, T. A. [1985] Stability and Periodic Solutions of Ordinary and Functional Differential Equations (Academic Press, New York and London). Google Scholar
Chatterjee, R. & Matsuno, F. [2001] “ Use of single side reflex for autonomous navigation of mobile robots in unknown environments,” Robot. Auton. Syst. 35, 77–96. Crossref, Web of Science, Google Scholar
Floreano, D. & Mondada, F. [1998] “ Evolutionary neurocontrollers for autonomous mobile robots,” Neural Netw. 11, 1461–1478. Crossref, Web of Science, Google Scholar
Floreano, D., Epars, Y., Zuffery, J.-C. & Mattiussi, C. [2006] “ Evolution of spiking neural circuits in autonomous mobile robots,” Int. J. Intell. Syst. 21, 1005–1024. Crossref, Web of Science, Google Scholar
Guivant, J., Nebot, E. & Baiker, S. [2000] “ Autonomous navigation and map building using laser range sensors in outdoor applications,” J. Robot. Syst. 17, 565–583. Crossref, Google Scholar
Hindmarsh, J. L. & Rose, R. M. [1984] “ A model of neuronal bursting using three coupled first order differential equations,” Proc. Roy. Soc. London Ser. B, Biol. Sci. 221, 87–102. Crossref, Web of Science, Google Scholar
Johnston, S. P., Prasad, G., Maguire, L. & McGinnity, T. M. [2010] “ An FPGA hardware/software co-design towards evolvable spiking neural networks for robotics application,” Int. J. Neural Syst. 20, 447–461. Link, Web of Science, Google Scholar
Khalil, H. [2002] Nonlinear Systems, 3rd edition (Prentice-Hall). Google Scholar
Manoonpong, P., Pasemann, F. & Fischer, J. [2005] “ Modular neural control for a reactive behavior of walking machines,” Proc. IEEE Int. Symp. Computational Intelligence in Robotics and Automation, pp. 403–408. Google Scholar
Massa, G. L. O., Vinuesa, H. & Lanzarini, L. [2006] “ Modular creation of neuronal networks for autonomous robot control,” Proc. IEEE Latin American Robotics Symp., pp. 66–73. Google Scholar
Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zuffery, J.-C., Floreano, D. & Martinoli, A. [2009] “ The e-puck, a robot designed for education in engineering,” Proc. Conf. Autonomous Robot Systems and Competitions, pp. 59–65. Google Scholar
Neefs, P. [2009] “Experimental synchronisation of Hindmarsh–Rose neurons in complex networks,” Master’s thesis (DCT 2009.107), Eindhoven University of Technology, the Netherlands. Google Scholar
Neefs, P., Steur, E. & Nijmeijer, H. [2010] “ Network complexitiy and synchronous behavior — An experimental approach,” Int. J. Neural Syst. 3, 233–247. Link, Web of Science, Google Scholar
Pearson, M. J., Pipe, A. G., Mitchinson, B., Gurney, K., Melhuish, C. & Nibouche, M. [2007] “ Implementing spiking neural networks for real-time signal-processing and control applications: A model-validated FPGA approach,” IEEE Trans. Neural Netw. 18, 1472–1487. Crossref, Web of Science, Google Scholar
Steur, E., Kodde, R. & Nijmeijer, H. [2008] “ Synchronization of diffusively coupled electronic Hindmarsh–Rose oscillators,” Proc. Euromech Nonlinear Dynamics Conf. Google Scholar
Steur, E., Tyukin, I. & Nijmeijer, H. [2009] “ Semi-passivity and synchronization of diffusively coupled neuronal oscillators,” Physica D 238, 2119–2128. Crossref, Web of Science, Google Scholar
Tang, Y., Qian, F., Gao, H. & Kurths, J. [2014] “ Synchronization in complex networks and its application — A survey of recent advances and challenges,” Ann. Rev. Contr. 38, 184–198. Crossref, Web of Science, Google Scholar
Wang, X., Hou, Z.-G., Zou, A., Tan, M. & Cheng, L. [2008] “ A behavior controller based on spiking neural networks for mobile robots,” Neurocomputing 71, 655–666. Crossref, Web of Science, Google Scholar
Wilamowski, B. [2003] “ Neural network architectures and learning,” Proc. Int. Conf. Industrial Technology, pp. TU1–TU12. Google Scholar
Zhang, M., Peng, S. & Meng, Q. [1997] “ Neural network and fuzzy logic techniques based collision avoidance for a mobile robot,” Robotica 15, 627–632. Crossref, Web of Science, Google Scholar