Once More Unto the Breach: Towards Artificial Homeostasis?

The field of biologically inspired computing has generated many novel, interesting and useful computational systems. None of these systems alone is capable of approaching the level of behaviour for which the artificial intelligence and robotics communities strive. We suggest that it is now time to move on to integrating a number of these approaches in a biologically justifiable way. To this end we present a conceptual framework which integrates artificial neural networks, artificial immune systems and a novel artificial endocrine system. The natural counterparts of these three components are usually assumed to be the principal actors in maintaining homeostasis within biological systems. This chapter proposes a system, which promises to capitalise on the self-organising properties of these artificial systems to yield artificially homeostatic systems. The components develop in a common environment and interact in ways which draw heavily on their biological counterparts for inspiration. A case study is presented, in which aspects of the nervous and endocrine systems are exploited to create a simple robot controller. Mechanisms for the moderation of system growth using an artificial immune system are also presented.

[1]  B. Bernstein,et al.  Animal Behavior , 1927, Japanese Marine Life.

[2]  Stephanie Forrest,et al.  Infect Recognize Destroy , 1996 .

[3]  F. Azuaje.  Artificial Immune Systems: A New Computational Intelligence Approach , 2003 .

[4]  Manuel Samuelides,et al.  Sparse image coding using an asynchronous spiking neural network , 2002, ESANN.

[5]  Alan S. Perelson,et al.  Self-nonself discrimination in a computer , 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy.

[6]  Nak Young Chong,et al.  Inverse kinematics learning by modular architecture neural networks with performance prediction networks , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[7]  Demetri Terzopoulos,et al.  Artificial fishes: Autonomous locomotion, perception, behavior, and learning in a simulated physical world , 1994 .

[8]  Thomas S. Ray,et al.  An Evolutionary Approach to Synthetic Biology: Zen and the Art of Creating Life , 1993, Artificial Life.

[9]  Marco Tomassini,et al.  A Statistical Study of a Class of Cellular Evolutionary Algorithms , 1999, Evolutionary Computation.

[10]  Mark James Neal,et al.  Meta-stable Memory in an Artificial Immune Network , 2003, ICARIS.

[11]  Peter J. Bentley,et al.  Immune Memory in the Dynamic Clonal Selection Algorithm , 2002 .

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  Ananth Ramaswamy,et al.  Developments in Structural Optimization and Applications to Intelligent Structural Vibration Control , 2007 .

[14]  F. Burnet.  The clonal selection theory of acquired immunity , 1959 .

[15]  Giulio Sandini,et al.  Learning about objects through action - initial steps towards artificial cognition , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[16]  Andy M. Tyrrell,et al.  A hardware immune system for benchmark state machine error detection , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[17]  Alan S. Perelson,et al.  The immune system, adaptation, and machine learning , 1986 .

[18]  D. S. Luciano,et al.  Human Physiology: The Mechanism of Body Function , 1975 .

[19]  Ruth Aylett.  Emotion in Behavioural Architectures , 2007 .

[20]  Myra S. Wilson,et al.  Diminishing returns of engineering effort in telerobotic systems , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[21]  Jerne Nk.  Towards a network theory of the immune system. , 1974 .

[22]  Brian Scassellati,et al.  Humanoid Robots: A New Kind of Tool , 2000, IEEE Intell. Syst..

[23]  Francisco Varela Hugues Bersini.  Self-Assertion versus Self-Recognition : A Tribute to Francisco Varela , 2002 .

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

[25]  A. Perelson.  Immune Network Theory , 1989, Immunological reviews.

[26]  L.N. de Castro,et al.  An artificial immune network for multimodal function optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[27]  Dave Cliff,et al.  Creatures: artificial life autonomous software agents for home entertainment , 1997, AGENTS '97.

[28]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[29]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[30]  Hershel Raff,et al.  Human Physiology: The Mechanisms of Body Function , 2006 .

[31]  M. Klein.  Parallel Distributed Processing , 1992 .

[32]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[33]  Shigeki Sugano,et al.  Emotional Communication Robot: WAMOEBA-2R - Emotion Model and Evaluation Experiments - , 2000 .

[34]  Alex Alves Freitas,et al.  A Danger Theory Inspired Approach to Web Mining , 2003, ICARIS.

[35]  S. Swain,et al.  Culture supernatants of a stimulated T-cell line have helper activity that acts synergistically with interleukin 2 in the response of B cells to antigen. , 1981, Proceedings of the National Academy of Sciences of the United States of America.

[36]  Jon Timmis,et al.  Timidity: A Useful Mechanism for Robot Control? , 2003 .

[37]  H. Besedovsky,et al.  Immune-neuro-endocrine interactions: facts and hypotheses. , 1996, Endocrine reviews.

[38]  P. Matzinger.  The Danger Model: A Renewed Sense of Self , 2002, Science.

[39]  V. Sugumaran.  The Inaugural Issue of the International Journal of Intelligent Information Technologies , 2005 .

[40]  Ankush Mittal,et al.  Bayesian Network Technologies: Applications and Graphical Models , 2007 .

[41]  R. Brooks,et al.  The cog project: building a humanoid robot , 1999 .