Expansion of Neuro-Modules by Structure Evolution

Two methods for the extension of neuro-modules are introduced resulting in a new behavioral functionality. We call them restricted and semi-restricted module expansion. These methods are developed and applied using a modular neuro-dynamics approach to behavior control of autonomous mobile robots. Evolved neuro-controllers which solve an obstacle avoidance task are expanded to show in addition a positive phototropism. All resulting neuro-modules produce a robust light seeking behavior. These neuro-modules use recurrent connectivity structures and non-trivial dynamical features to enable the robot to solve its task. For each neuro-module the structure-function-relation is analyzed. The presented results demonstrate that restricted and semi-restricted expansion are promising methods for generating efficient extensions of recurrent neural networks with additional behavioral functionality.

[1]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[2]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[3]  Inman Harvey,et al.  Analysing recurrent dynamical networks evolved for robot control , 1993 .

[4]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[5]  Randall D. Beer,et al.  Integrating reactive, sequential, and learning behavior using dynamical neural networks , 1994 .

[6]  Inman Harvey,et al.  Seeing the Light: Artiicial Evolution, Real Vision Seeing the Light: Artiicial Evolution, Real Vision , 1994 .

[7]  Inman Harvey,et al.  Circle in the round: State space attractors for evolved sighted robots , 1995, Robotics Auton. Syst..

[8]  G. Miller,et al.  Artificial Evolution: A New Path for Artificial Intelligence? , 1997, Brain and Cognition.

[9]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[10]  Chandana Paul,et al.  Making Evolution an Offer It Can't Refuse: Morphology and the Extradimensional Bypass , 2001, ECAL.

[11]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[12]  Bruno Lara,et al.  Robot control and the evolution of modular neurodynamics , 2001, Theory in Biosciences.

[13]  Rolf Pfeifer,et al.  A method for isolating morphological effects on evolved behaviour , 2002 .

[14]  F. Pasemann.  Complex dynamics and the structure of small neural networks , 2002, Network.

[15]  Frank Pasemann,et al.  Dynamical Neural Schmitt Trigger for Robot Control , 2002, ICANN.

[16]  E. Ruppin.  Evolutionary autonomous agents: A neuroscience perspective , 2002, Nature Reviews Neuroscience.

[17]  Randall D. Beer,et al.  The Dynamics of Active Categorical Perception in an Evolved Model Agent , 2003, Adapt. Behav..

[18]  Frank Pasemann,et al.  Representing Robot-Environment Interactions by Dynamical Features of Neur-controllers , 2003, ABiALS.

[19]  Isaac Meilijson,et al.  Localization of Function via Lesion Analysis , 2003, Neural Computation.

[20]  Frank Pasemann,et al.  From Passive to Active Dynamic 3D Bipedal Walking — An Evolutionary Approach , 2004 .