Gait Generation of Multilegged Robots by using Hardware Artificial Neural Networks

Living organisms can act autonomously because biological neural networks process the environmental information in continuous time. Therefore, living organisms have inspired many applications of autonomous control to small-sized robots. In this chapter, a small-sized robot is controlled by a hardware artificial neural network (ANN) without software programs. Previously, the authors constructed a multilegged walking robot. The link mechanism of the limbs was designed to reduce the number of actuators. The current paper describes the basic characteristics of hardware ANNs that generate the gait for multilegged robots. The pulses emitted by the hardware ANN generate oscillating patterns of electrical activity. The pulse-type hardware ANN model has the basic features of a class II neuron model, which behaves like a resonator. Thus, gait generation by the hardware ANNs mimics the synchronization phenomena in biological neural networks. Consequently, our constructed hardware ANNs can generate multilegged robot gaits without requiring software programs.

[1]  Yasuhiro Fukuoka,et al.  Adaptive dynamic walking of a quadruped robot using a neural system model , 2001, Adv. Robotics.

[2]  Johan Grasman,et al.  Relaxation Oscillations , 2009, Encyclopedia of Complexity and Systems Science.

[3]  Michael I. Jordan,et al.  The Handbook of Brain Theory and Neural Networks , 2002 .

[4]  K. Aihara,et al.  Bifurcations in a mathematical model for circadian oscillations of clock genes. , 2006, Journal of theoretical biology.

[5]  Auke Jan Ijspeert,et al.  Central pattern generators for locomotion control in animals and robots: A review , 2008, Neural Networks.

[6]  Hiroaki Kitano,et al.  Development of an Autonomous Quadruped Robot for Robot Entertainment , 1998, Auton. Robots.

[7]  Maki K. Habib.  Biomimetics: innovations and robotics , 2011 .

[8]  Thierry Hoinville,et al.  A hexapod walker using a heterarchical architecture for action selection , 2013, Front. Comput. Neurosci..

[9]  Kevin Blankespoor,et al.  BigDog, the Rough-Terrain Quadruped Robot , 2008 .

[10]  Ken Saito,et al.  Synchronization of coupled pulse-type hardware neuron models for CPG model , 2009, 2009 International Joint Conference on Neural Networks.

[11]  Tetsuro Endo,et al.  Mode analysis of a ring of a large number of mutually coupled van der Pol oscillators , 1978 .

[12]  Hiroshi Kawakami,et al.  Bifurcation Analysis of Current Coupled BVP oscillators , 2007, Int. J. Bifurc. Chaos.

[13]  Ken Saito,et al.  Biomimetics Micro Robot with Active Hardware Neural Networks Locomotion Control and Insect-Like Switching Behaviour , 2012 .

[14]  G. Ermentrout,et al.  Analysis of neural excitability and oscillations , 1989 .

[15]  Thierry Hoinville,et al.  Walknet, a bio-inspired controller for hexapod walking , 2013, Biological Cybernetics.

[16]  Yoshifumi Sekine,et al.  Synchronization of Coupled Oscillators Using Pulse-Type Hardware Neuron Models with Mutual Coupling , 2004 .

[17]  Huma Ashraf,et al.  Advanced silicon etching using high-density plasmas , 1995, Photonics West - Micro and Nano Fabricated Electromechanical and Optical Components.

[18]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1952, The Journal of physiology.

[19]  Balth. van der Pol Jun..  LXXXVIII. On “relaxation-oscillations” , 1926 .

[20]  K. Saito,et al.  15 – Locomotion rhythm generation using pulse-type hardware neural networks for quadruped robots , 2015 .

[21]  Hiroshi Kawakami,et al.  Bifurcations in Synaptically Coupled Hodgkin-huxley Neurons with a Periodic Input , 2003, Int. J. Bifurc. Chaos.

[22]  Kazuyuki Aihara,et al.  Analog Hardware Implementation of a Mathematical Model of an Asynchronous Chaotic Neuron , 2002 .

[23]  Akio Ushida,et al.  Analysis of Phase-Inversion Waves in Coupled Oscillators Synchronizing at In-and-Anti-Phase , 2003, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[24]  Dai Homma.  Metal Artificial Muscle ‘BioMetal Fiber’ , 2003 .

[25]  Ken Saito,et al.  MEMS Microrobot with Pulse-Type Hardware Neural Networks Integrated Circuit , 2017 .

[26]  Maki Habib,et al.  Biomimetics Robots From Bio-inspiration to Implementation , 2007, IECON 2007 - 33rd Annual Conference of the IEEE Industrial Electronics Society.

[27]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[28]  Yasuhiro Fukuoka,et al.  Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Based on Biological Concepts , 2003, Int. J. Robotics Res..

[29]  F. Delcomyn.  Neural basis of rhythmic behavior in animals. , 1980, Science.

[30]  Akio Ushida,et al.  Wave Propagation Phenomena of Phase States in Oscillators Coupled by Inductors as a Ladder , 1999 .

[31]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[32]  Hiroyuki Kitajima,et al.  Chaotic Bursts and bifurcation in Chaotic Neural Networks with Ring Structure , 2001, Int. J. Bifurc. Chaos.

[33]  Robert B. McGhee,et al.  Adaptive Locomotion of a Multilegged Robot over Rough Terrain , 1979, IEEE Transactions on Systems, Man, and Cybernetics.