Reconfigurable Hardware Evolution Platform for a Spiking Neural Network Robotics Controller

This paper describes a platform for the hardware evolution of Spiking Neural Network (SNN) based robotics controllers on multiple Field Programmable Analogue Arrays (FPAAs). The SNN robotics controller, evolved using a GA, performs obstacle avoidance and navigation. A robotics simulator is used to evaluate the performance of the evolved hardware SNN. Simulated sonar data is input to FPAA neurons and the SNN returns motor control data to the simulator. Initial results indicate the emergence of effective navigation behavior.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  Dmitry Berenson,et al.  Hardware evolution of analog circuits for in-situ robotic fault-recovery , 2005, 2005 NASA/DoD Conference on Evolvable Hardware (EH'05).

[3]  Una-May O'Reilly,et al.  GRACE: Generative Robust Analog Circuit Exploration , 2006, EvoWorkshops.

[4]  Wulfram Gerstner,et al.  Spiking Neuron Models , 2002 .

[5]  Stefano Nolfi,et al.  How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics , 1994 .

[6]  Wulfram Gerstner,et al.  Spiking Neuron Models: An Introduction , 2002 .

[7]  Dario Floreano,et al.  Evolutionary bits'n'spikes , 2002 .

[8]  Fearghal Morgan,et al.  Platform for intrinsic evolution of analogue neural networks , 2005, 2005 International Conference on Reconfigurable Computing and FPGAs (ReConFig'05).

[9]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[12]  Hani Hagras,et al.  FPGA implementation of spiking neural networks - an initial step towards building tangible collaborative autonomous agents , 2004, Proceedings. 2004 IEEE International Conference on Field- Programmable Technology (IEEE Cat. No.04EX921).

[13]  Rolf Drechsler,et al.  Applications of Evolutionary Computing, EvoWorkshops 2008: EvoCOMNET, EvoFIN, EvoHOT, EvoIASP, EvoMUSART, EvoNUM, EvoSTOC, and EvoTransLog, Naples, Italy, March 26-28, 2008. Proceedings , 2008, EvoWorkshops.

[14]  Andres Upegui,et al.  A methodology for evolving spiking neural-network topologies on line using partial dynamic reconfiguration , 2003 .

[15]  Fearghal Morgan,et al.  Intrinsic Hardware Evolution of Neural Networks in Reconfigurable Analogue and Digital Devices , 2006, 2006 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines.