Cellular Non-linear Networks as a New Paradigm for Evolutionary Robotics

One of the most active fields of research in evolutionary robotics is the development of autonomous robots with the ability to interact with the physical world and to communicate with each other, in “robot societies”. Interactions may involve a range of different motor actions, motivational forces and cognitive processes. Actions, in turn directly affect the agent’s perceptions of the world. In the “Action/Perception-Cycle” (see Figure 1), biological organisms are integrated sensorimotor systems. This means that intelligent processes require a body, and that symbols are grounded in the environment in which animals live (Harnad, 1990). In short, behavior is fundamentally linked to cognition. This is true for humans, animals and artificial agents. Without this grounding, artificial animals and agents cannot live and behave successfully in their artificial environments. One way of achieving it, is to use Genetic Algorithms to evolve agents’ neural architecture (Nolfi & Floreano, 2000). This creates the prospect of robots that can live in complex socially organized communities in which they communicate with humans and with each other (Cangelosi e Parisi, 2002). According to these authors, cognition is an intrinsically embedded phenomenon in which the dynamical relations between the neural system, the body and the environment play a central role. In this view, agents are dynamical systems and cognitive functioning has to be understood using tools from dynamical system theory (van Gelder, 1995, 1998a; 1998b; Bilotta et al., 2007a-2007f). This perspective on cognition has been called the Dynamical and Embodied view of Cognition (DEC) (Keijzer, 2002). In this chapter we describe our own contribution to Evolutionary Robotics, namely a proposal for a new generation of believable agents capable of life-like intelligent communicative and emotional behavior. We focus on CNNs (Cellular Neural Networks) and on the use of these networks as robot controllers. In previous work, we used Genetic Algorithms (GAs) to evolve Artificial Non-linear Networks (ANNs) displaying artificial adaptive behavior, with features similar to those observed in animals and humans. In (Bilotta et al. 2006), we replaced ANNs with a new class of dynamical system called Cellular Non-linear Networks (CNNs) and used CNNs to implement a multilayer locomotion model for six-legged artificial robots in a virtual environment with many of the characteristics of a physical environment. First invented by Chua and co-workers (1988), CNNs have been extended to create a CNN Universal Machine (CNN-UM) (Roska & Chua, 1993), the first algorithmically programmable analog computer chip suitable for the modeling of sensory-

[1]  Valeri Mladenov,et al.  Cellular Neural Networks: Theory And Applications , 2004 .

[2]  Holk Cruse,et al.  Hexapod Walking: an expansion to Walknet dealing with leg amputations and force oscillations , 2007, Biological Cybernetics.

[3]  Fred Keijzer,et al.  Representation in dynamical and embodied cognition , 2002, Cognitive Systems Research.

[4]  T. Gelder,et al.  The dynamical hypothesis in cognitive science , 1998, Behavioral and Brain Sciences.

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

[6]  A. Dawidziuk,et al.  Minimum size 0.5 micron CMOS programmable 48 by 48 CNN test chip , 1997 .

[7]  Botond Roska,et al.  Parallel processing in retinal ganglion cells: how integration of space-time patterns of excitation and inhibition form the spiking output. , 2006, Journal of neurophysiology.

[8]  Kuei-Ann Wen,et al.  VLSI Design of Digital Cellular Neural Networks for Image Processing , 1994, J. Vis. Commun. Image Represent..

[9]  S. Espejo,et al.  Challenges in mixed-signal IC design of CNN chips in submicron CMOS , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[10]  Luigi Fortuna,et al.  A CNN-based experimental frame for patterns and autowaves , 1998 .

[11]  V. Krinsky.  Self-Organization Autowaves and Structures Far from Equilibrium , 1984 .

[12]  Manfred Glesner,et al.  Realisation of a digital cellular neural network for image processing , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[13]  T. Gelder.  The distinction between mind and cognition , 1995 .

[14]  Péter Szolgay,et al.  Image-based visual servo control of a robotic arm by using cellular neural networks , 2006 .

[15]  P. Arena,et al.  Analog cellular locomotion control of hexapod robots , 2002 .

[16]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[17]  R. Calabrese.  Oscillation in motor pattern-generating networks , 1995, Current Opinion in Neurobiology.

[18]  F. Werblin,et al.  Directional Selectivity Is Formed at Multiple Levels by Laterally Offset Inhibition in the Rabbit Retina , 2005, Neuron.

[19]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[20]  A. Zarandy,et al.  An emulated digital architecture implementing the CNN Universal Machine , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[21]  T. Gelder.  Disentangling dynamics, computation, and cognition , 1998, Behavioral and Brain Sciences.

[22]  Eleonora Bilotta,et al.  A Gallery of Chua attractors Part V , 2007, Int. J. Bifurc. Chaos.

[23]  K. Pearson.  Common principles of motor control in vertebrates and invertebrates. , 1993, Annual review of neuroscience.

[24]  L. Chua.  Cnn: A Paradigm for Complexity , 1998 .

[25]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[26]  S. I. Andersson.  Recent progress on logic and algorithms for optical neural networks (ONN) , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[27]  Angelo Cangelosi,et al.  Computersimulation:anewscientific Approachtothestudyoflanguageevolution Anewapproachtothestudyoflanguage Evolution:computersimulation , 2001 .

[28]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.

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

[30]  Eleonora Bilotta,et al.  Evolving Robot's Behavior by Using CNNs , 2006, SAB.