A 3D undulatory locomotion model inspired by C. elegans through DNN approach

In this work, a 3D undulatory locomotion model inspired by Caenorhabditis elegans is constructed. Following the anatomical structure of C. elegans, the body of the model is represented as a multi-joint rigid link system with 12 links. The angle between two consecutive links is determined by the muscle lengths in four quadrants that are controlled by the nervous system. The nervous system of this locomotion model is represented by a dynamic neural network (DNN) that involves three parts: head DNN, central pattern generator (CPG), and body DNN. The head DNN decides turning or not, and CPG produces the sinusoid waves that are transmitted through the body DNN to control the lengths of muscles. The 3D locomotion behavior is achieved by using the DNN to control the muscle lengths, and then using the muscle lengths to control the angles between two consecutive links on both horizontal plane and vertical plane. In this work, the relations between the outputs of DNN and muscle lengths, as well as the muscle lengths and the angles between two consecutive links, are determined. Furthermore, due to the learning capability of DNN, a set of nonlinear functions that are designed to represent the chemotaxis behaviors of C. elegans are learned by the head DNN using Differential Evolution Algorithm. The testing results show good 3D performance of this locomotion model in both forward and backward locomotion, as well as slight turn and @W turn. Furthermore, this locomotion model performs the chemotaxis behaviors of finding food and avoiding toxin successfully. Finally, quantitative analyses by comparing with the experiment results are provided to verify the realness and effectiveness of this locomotion model, which could serve as a prototype for the worm-like robot.

[1]  Robert J. Webster,et al.  Mechanics of Precurved-Tube Continuum Robots , 2009, IEEE Transactions on Robotics.

[2]  Jianxin Xu,et al.  STUDY ON CHEMOTAXIS BEHAVIORS OF C. ELEGANS USING DYNAMIC NEURAL NETWORK MODELS: FROM ARTIFICIAL TO BIOLOGICAL MODEL , 2010 .

[3]  N. Cohen,et al.  Forward locomotion of the nematode C. elegans is achieved through modulation of a single gait , 2009, HFSP journal.

[4]  Jordan H. Boyle,et al.  Gait Modulation in C. elegans: An Integrated Neuromechanical Model , 2012, Front. Comput. Neurosci..

[5]  広瀬 茂男,et al.  Biologically inspired robots : snake-like locomotors and manipulators , 1993 .

[6]  S. Lockery,et al.  Chemotaxis control by linear recurrent networks , 1998 .

[7]  Toshio Tsuji,et al.  A model of motor control of the nematode C. elegans with neuronal circuits , 2005, Artif. Intell. Medicine.

[8]  Fumitoshi Matsuno,et al.  Snake robots to the rescue! , 2002, IEEE Robotics Autom. Mag..

[9]  D. Chklovskii,et al.  Wiring optimization can relate neuronal structure and function. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[10]  John Bryden.  A simulation model of the locomotion controllers for the , 2003 .

[11]  Zhaoyang Feng,et al.  The Neural Circuits and Synaptic Mechanisms Underlying Motor Initiation in C. elegans , 2011, Cell.

[12]  Thomas M. Morse,et al.  The Fundamental Role of Pirouettes in Caenorhabditis elegans Chemotaxis , 1999, The Journal of Neuroscience.

[13]  M. de Bono,et al.  Neuronal substrates of complex behaviors in C. elegans. , 2005, Annual review of neuroscience.

[14]  Ilya A. Rybak,et al.  Modeling the spinal cord neural circuitry controlling cat hindlimb movement during locomotion , 2003, Neurocomputing.

[15]  Jordan H. Boyle,et al.  Gait Modulation in C. Elegans: It's Not a Choice, It's a Reflex! , 2011, Front. Behav. Neurosci..

[16]  Peter Cave,et al.  Biologically Inspired Robots: Serpentile Locomotors and Manipulators , 1993 .

[17]  Marco A. Zenati,et al.  Highly articulated robotic probe for minimally invasive surgery , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[18]  S. Lockery.  The computational worm: spatial orientation and its neuronal basis in C. elegans , 2011, Current Opinion in Neurobiology.

[19]  P. N. Suganthan,et al.  Differential Evolution: A Survey of the State-of-the-Art , 2011, IEEE Transactions on Evolutionary Computation.

[20]  Kazushi Yoshida,et al.  Parallel Use of Two Behavioral Mechanisms for Chemotaxis in Caenorhabditis elegans , 2009, The Journal of Neuroscience.

[21]  Jordan H. Boyle,et al.  A C. elegans-inspired micro-robot with polymeric actuators and online vision , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[22]  Yang Shi,et al.  Modeling and Robust Discrete-Time Sliding-Mode Control Design for a Fluid Power Electrohydraulic Actuator (EHA) System , 2013 .

[23]  Christopher J. Lee.  Open Peer Review by a Selected-Papers Network , 2011, Front. Comput. Neurosci..

[24]  John S. Conery,et al.  A Neural Network Model of Chemotaxis Predicts Functions of Synaptic Connections in the Nematode Caenorhabditis elegans , 2004, Journal of Computational Neuroscience.

[25]  John S. Conery,et al.  A novel neural network analysis method applied to biological neural networks , 2006 .

[26]  Jung Ho Je,et al.  3-D Worm Tracker for Freely Moving C. elegans , 2013, PloS one.

[27]  S. Lockery,et al.  Neuronal microcircuits for decision making in C. elegans , 2012, Current Opinion in Neurobiology.

[28]  Aravinthan D. T. Samuel,et al.  Proprioceptive Coupling within Motor Neurons Drives C. elegans Forward Locomotion , 2012, Neuron.

[29]  Jennifer H. Shin,et al.  Shape memory alloy-based small crawling robots inspired by C. elegans , 2011, Bioinspiration & biomimetics.

[30]  Jason A. Avery,et al.  A Biologically Accurate 3D Model of the Locomotion of Caenorhabditis Elegans , 2010, 2010 International Conference on Biosciences.

[31]  A. A. Dehghani-Sanij,et al.  Adaptive Undulatory Locomotion of a C. elegans Inspired Robot , 2013, IEEE/ASME Transactions on Mechatronics.

[32]  Zhigang Zeng,et al.  Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions , 2012, Neurocomputing.

[33]  Ryuzo Shingai,et al.  Neurons regulating the duration of forward locomotion in Caenorhabditis elegans , 2004, Neuroscience Research.

[34]  S. Lockery,et al.  Evolution and Analysis of Minimal Neural Circuits for Klinotaxis in Caenorhabditis elegans , 2010, The Journal of Neuroscience.

[35]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[36]  J. G. Taylor.  On artificial brains , 2010, Neurocomputing.

[37]  Wei Wang,et al.  A General Internal Model Approach for Motion Learning , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[38]  Deepak E. Solomon,et al.  Locomotion of C. elegans: A Piecewise-Harmonic Curvature Representation of Nematode Behavior , 2012, PloS one.

[39]  Peter A. Robinson,et al.  Stability of random brain networks with excitatory and inhibitory connections , 2009, Neurocomputing.

[40]  Shigeo Hirose,et al.  Snake-like robots [Tutorial] , 2009, IEEE Robotics & Automation Magazine.

[41]  S. Lockery,et al.  Analysis of the effects of turning bias on chemotaxis in C. elegans , 2005, Journal of Experimental Biology.

[42]  Toshio Tsuji,et al.  A dynamic body model of the nematode C. elegans with a touch-response circuit , 2005, 2005 IEEE International Conference on Robotics and Biomimetics - ROBIO.

[43]  N. Logothetis,et al.  Cholinergic Control of Visual Categorization in Macaques , 2011, Front. Behav. Neurosci..

[44]  Jordan H. Boyle,et al.  Caenorhabditis elegans body wall muscles are simple actuators , 2008, Biosyst..

[45]  M. Gupta,et al.  Approximation of discrete-time state-space trajectories using dynamic recurrent neural networks , 1995, IEEE Trans. Autom. Control..

[46]  Shawn R. Lockery,et al.  Computational Rules for Chemotaxis in the Nematode C. elegans , 1999, Journal of Computational Neuroscience.

[47]  Cori Bargmann,et al.  A circuit for navigation in Caenorhabditis elegans , 2005 .

[48]  The neural basis of the locomotion of nematodes , 1990 .

[49]  Sungho Jo,et al.  Design and control of thermal SMA based small crawling robot mimicking C. elegans , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[50]  Johann Borenstein,et al.  The OmniTread OT-4 serpentine robot , 2008, 2008 IEEE International Conference on Robotics and Automation.

[51]  N. Cohen,et al.  Swimming at low Reynolds number: a beginners guide to undulatory locomotion , 2010 .

[52]  Takeshi Goto,et al.  A Motor Control Model of the Nematode C. e1egaans , 2004, 2004 IEEE International Conference on Robotics and Biomimetics.

[53]  Jian-Xin Xu,et al.  Biological modeling of complex chemotaxis behaviors for C. elegans under speed regulation—a dynamic neural networks approach , 2013, Journal of Computational Neuroscience.

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

[55]  Paul W. Sternberg,et al.  Systems level circuit model of C. elegans undulatory locomotion: mathematical modeling and molecular genetics , 2007, Journal of Computational Neuroscience.