Event Abstract

A Robotic Platform for Spiking Neural Control Architectures

  • 1 Bernstein Center for Computational Neuroscience, Germany
  • 2 Freie Universität Berlin, Institute of Biology, Germany
  • 3 Freie Universität, Institute of Computer Science, Germany

Spiking neural networks (SNNs) have proven to be excellent control systems in biological organisms. Hence, they should have the potential of providing good control systems for autonomous robots. However, so far only few technical attempts to control artificial agents with SNNs have been made [2].
Here we present a robotic platform for testing biologically inspired SNNs as control architectures. The platform integrates real-time processing of sensory input and motor commands. The sensory data is fed into iqr [1], a software for the real-time simulation of SNNs. We extended its existing models of neurons and synapses to support adaptation and conditional plasticity. All communication between the robot and iqr is done via WiFi. As our platform we use a Rover based on the Arduino micro-controller [DFRobotShop Rover, RobotShop Distribution Inc.,Quebec, Canada]. A vision processing module [HaViMo2.0, fiveam robotics, Berlin] is mounted on the robot. The preprocessed image stream is transformed into spike trains which are fed into a SNN. The network processes this sensory input and generates output that is translated into motor commands. We test the robot on simple associative learning tasks, where we apply a conditional plasticity rule.

Acknowledgements

This project receives funding from the BMBF through grant 01GQ0941, within the Bernstein Focus Neuronal Basis of Learning (BFNL) - Insect Inspired Robots .

References

[1] Ulysses Bernardet and Paul F.M.J. Verschure. iqr: A tool for the construction of multi-
level simulations of brain and behaviour. Neuroinformatics, 8(2):113–134, 2010.
[2] Jeffery L. Krichmar and Hiroaki Wagatsuma, editors. Neuromorphic and Brain-Based
Robots. Cambridge University Press, 2011.

Keywords: associative learning, Autonomous Robots, plasticity, real-time sensory processing, Robotics, spiking neural networks

Conference: Bernstein Conference 2012, Munich, Germany, 12 Sep - 14 Sep, 2012.

Presentation Type: Poster

Topic: Other

Citation: Helgadottir L, Haenicke J, Landgraf T and Nawrot MP (2012). A Robotic Platform for Spiking Neural Control Architectures. Front. Comput. Neurosci. Conference Abstract: Bernstein Conference 2012. doi: 10.3389/conf.fncom.2012.55.00154

Received: 11 May 2012; Published Online: 12 Sep 2012.

* Correspondence: Ms. Lovisa Irpa Helgadottir, Bernstein Center for Computational Neuroscience, Berlin, Germany, lovisa.helgadottir@bccn-berlin.de

© 2007 - 2019 Frontiers Media S.A. All Rights Reserved