Rocking Stamper and Jumping Snakes from a Dynamical Systems Approach to Artificial Life

Dynamical systems offer intriguing possibilities as a substrate for the generation of behavior because of their rich behavioral complexity. However this complexity together with the largely covert relation between the parameters and the behavior of the agent is also the main hindrance in the goal oriented design of a behavior system. This paper presents a general approach to the self-regulation of dynamical systems so that the design problem is circumvented. We consider the controller (a neural net work) as the mediator for changes in the sensor values over time and define a dynamics for the parameters of the controller by maximizing the dynamical complexity of the sensorimotor loop under the condition that the consequences of the actions taken are still predictable. This very general principle is given a concrete mathematical formulation and is implemented in an extremely robust and versatile algorithm for the parameter dynamics of the controller. We consider two different applications, a mechanical device called the rocking stamper and the ODE simulations of a “snake” with five degrees of freedom. In these and many other examples studied we observed various behavior modes of high dynamical complexity

[1]  E. Glasersfeld.  Radical Constructivism: A Way of Knowing and Learning. Studies in Mathematics Education Series: 6. , 1995 .

[2]  S. Nelson,et al.  Homeostatic plasticity in the developing nervous system , 2004, Nature Reviews Neuroscience.

[3]  José R. Álvarez,et al.  Computational Methods in Neural Modeling , 2003, Lecture Notes in Computer Science.

[4]  Yasuo Kuniyoshi,et al.  From Humanoid Embodiment to Theory of Mind , 2003, Embodied Artificial Intelligence.

[5]  W. Ashby.  Design for a Brain , 1954 .

[6]  E. D. Paolo,et al.  Organismically-inspired robotics: homeostatic adaptation and teleology beyond the closed sensorimotor loop , 2003 .

[7]  G. Zajicek,et al.  The Wisdom of the Body , 1934, Nature.

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

[9]  H. Maturana,et al.  Autopoiesis and Cognition : The Realization of the Living (Boston Studies in the Philosophy of Scie , 1980 .

[10]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[11]  R. Der,et al.  True autonomy from self-organized adaptivity , 2002 .

[12]  Y. Kuniyoshi,et al.  Embodied Artificial Intelligence , 2004, Lecture Notes in Computer Science.

[13]  Axel Steinhage,et al.  Dynamical Systems for the Generation of Navigation Behavior , 1997 .

[14]  Gregor Schöner,et al.  Dynamics of behavior: Theory and applications for autonomous robot architectures , 1995, Robotics Auton. Syst..

[15]  Robert F. Port,et al.  MIND IN MOTION: , 2019, Dune.

[16]  Ralf Der.  Homeokinesis and the Moderation of Complexity in Neural Systems , 2003 .

[17]  Maciej Komosinski,et al.  The World of Framsticks: Simulation, Evolution, Interaction , 2000, Virtual Worlds.

[18]  Kenneth L. Artis.  Design for a Brain , 1961 .

[19]  Frank Pasemann,et al.  SO(2)-Networks as Neural Oscillators , 2003, IWANN.

[20]  Stanley J. Rosenschein,et al.  A dynamical systems perspective on agent-environment interaction , 1996 .

[21]  Randall D. Beer,et al.  A Dynamical Systems Perspective on Agent-Environment Interaction , 1995, Artif. Intell..

[22]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[23]  Hywel T. P. Williams,et al.  Homeostatic plasticity in recurrent neural networks , 2004 .

[24]  Gregor Schöner,et al.  The dynamical foundations of motion pattern formation: Stability, selective adaptation, and perceptual continuity , 2003, Perception & psychophysics.

[25]  Leslie Pack Kaelbling,et al.  A Dynamical Model of Visually-Guided Steering, Obstacle Avoidance, and Route Selection , 2003, International Journal of Computer Vision.

[26]  O. Gingerich.  A mind in motion , 1994, Nature.

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

[28]  Jochen J. Steil,et al.  Input space bifurcation manifolds of recurrent neural networks , 2005, Neurocomputing.