Summary
A modular approach to neural behavior control of autonomous robots is presented. It is based on the assumption that complex internal dynamics of recurrent neural networks can efficiently solve complex behavior tasks. For the development of appropriate neural control structures an evolutionary algorithm is introduced, which is able to generate neuromodules with specific functional properties, as well as the connectivity structure for a modular synthesis of such modules. This so called ENS 3-algorithm does not use genetic coding. It is primarily designed to develop size and connectivity structure of neuro-controllers. But at the same time it optimizes also parameters of individual networks like synaptic weights and bias terms. For demonstration, evolved networks for the control of miniature Khepera robots are presented. The aim is to develop robust controllers in the sense that neuro-controllers evolved in a simulator show comparably good behavior when loaded to a real robot acting in a physical environment. Discussed examples of such controllers generate obstacle avoidance and phototropic behaviors in non-trivial environments.
Similar content being viewed by others
References
Adami, C. (1998) Introduction to Artificial Life, Springer Verlag, New York.
Angeline, P. J.; Saunders, G. B. and Pollack, J. B. (1994) An Evolutionary Algorithm that Evolves Recurrent Neural Networks, IEEE Transactions on Neural Networks, 5, 54–65.
Arbib, M. A.; Érdi, P., and Szentágothai, J (1998) Neural Organization — Structure, Function, and Dynamics, MIT Press, Massachusetts.
Ashby, W. R. (1952) Design for a Brain, Wiley, New York.
Beer, R. D., and Gallagher, J. C. (1992) Evolving dynamical neural networks for adaptive behavior, Adaptive Behavior, 1, 91–122.
Braitenberg, V. (1984) Vehicles: Experiments in Synthetic Psychology, MIT Press, Cambridge, MA.
Brooks, R. A. (1986) A robust layered control system for as mobile robot, IEEE Journal of Robotics and Automation, RA-2, 14–23.
Buzsáki, G.; Llinás, R.; Singer, W.; Berthoz, A., and Christen, Y. (eds.) (1994) Temporal Coding in the Brain, Springer Verlag, Berlin.
Calabretta, R.; Nolfi, S.; Parisi, D., and Wagner, P. (1998) A case study of the evolution of modularity: towards a bridge between evolutionary biology, artificial life, neuro- and cognitive science, in: Adami, C., Belew, R. K., Kitano, H., and Taylor, C. E. (Eds.), Artificial Life VI, Proceedings of The Sixth International Conference on Artificial Life, MIT Press, Cambridge.
Cliff, D.; Harwey, I., and Husbands, P. (1993) Exploration in evolutionary robotics, Adaptive Behavior, 2, 73–110.
Duke, W., and Pritchard, W. S. (Eds.) (1991) Proceedings of the Conference on Measuring Chaos in the Human Brain, World Scientific, Singapore.
Elbert, T.; Ray, W. J.; Kowalik, Z. J.; Skinner, K. E.; Graf, K. E., and Birbaumer, N. (1994) Chaos and physiology: deterministic chaos in excitable cell assemblies, Physiological Review, 74, 1–47.
Floreano, D. (1997) Ago ergo sum, in: Mulhauser, G (ed.), Evolving Consciousness, J. Benjamins, Amsterdam.
Gaussier, P., and Zrehen, S. (1994) A topological neural map for on-line learning: Emergence of obstacle avoidance in a mobile robot, in: Cliff, D., Husbands, P., Meyer, J.-A., and Wilson, S. (eds.), From Animals to Animats III: Proceedings of the Second International Conference on Simulation of Adaptive Behavior, Cambridge, MA: MIT Press-Bradford Books, pp. 282–290.
Husbands, P., and Harwey, I. (1992) Evolution versus design: Controlling autonomous robots, in: Integrating perception, planning and action: Proceedings of the Third Annual Conferences on Artificial Intelligence, IEEE Press, Los Alamitos.
Husbands, P.; Harwey, I., and Cliff, D. (1995) Circle in the Round: State Space Attractors for Evolved Sighted Robots, in: Steels, L. (ed.), The Biology and Technology of Intelligent Autonomous Agents}, NATO ASI Series, Series F: Computer and Systems Sciences, Vol. 144, Springer, pp. 222–257.
Kodjabachian, J., and Meyer, J. A. (1998) Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects, IEEE Transactions on Neural Networks, 9, 796–812.
Langton, C. G. (1989) Artificial Life, in: Langton, C. G. (ed.) Artificial Life, Addison-Wesley, Redwood City CA.
Lara, B.; Hülse, M., and Pasemann, F. (2001) Evolving different neuro-modules and their interfaces to control autonomous robots, MPI-MIS-Preprint 21, accepted paper for “The 5th World Multi-Conference on Systemics, Cybernetics and Informatics” (SCI2001), July 22–25, 2001, Orlando, Florida USA, Proceedings.
Michel, O., (1996) Khepera Simulator Package version 2.0: Freeware mobile robot simulator written at the University of Nice Sophia-Antipolis by Oliver Michel. Downloadable from the World Wide Web at http://www.i3s.unice.fr/~om/khep-sim.html.
Mondada, F.; Franzi, E., and Ienne, P. (1993) Mobile robots miniturization: a tool for investigation in control algorithms, in: Proceedings of ISER’ 93, Kyoto, October 1993.
Mondada, F. and Floreano, D. (1995), Evolution of neural control structures: Some experiments on mobile robots, Robotics and Autonomous Systems, 16, 183–195.
Nolfi, S., and Floreano, D. (2000), Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines, MIT Press, Cambridge.
Nolfi, S. (1998), Evolutionary robotics: Exploiting the full power of self-organization, Connection Science, 10, 167–183.
Pantev, C.; Elbert, T., and Lutkenhöhner, B. (eds.) (1995), Oscillatory Event-related Brain Dynamics, Plenum Press, London.
Pasemann, F. (1993), Dynamics of a single model neuron, International Journal of Bifurcation and Chaos, 2, 271–278.
Pasemann, F. (1998), Evolving neurocontrollers for balancing an inverted pendulum, Network: Computation in Neural Systems, 9, 495–511.
Pasemann, F. (1998), Structure and Dynamics of Recurrent Neuromodules, Theory in Biosciences, 117, 1–17.
Pfeifer, R., and Scheier, C. (2000), Understanding Intelligence, MIT Press, Cambridge.
Pfeifer, R., and Verschure, F. M. J. (1993), Designing efficiently navigating non-goal-directed robots, in: Meyer, J.-A., Roitblat, H., and Wilson, S. (eds.), From Animals to Animats II: Proceedings of the Second International Conference on Simulation of Adaptive Behavior, Cambridge, MA: MIT Press-Bradford Books, pp. 31–38.
Renals, S., and Rohwer, R. (1990), A study of network dynamics, Journal of Statistical Physics, 58, 825–848.
Scutt, T. (1994), The fife neuron trick: Using classical conditioning to learn how to seek light, in: Cliff, D., Husbands, P., Meyer, J.-A., and Wilson, S. (eds.), From Animals to Animats III: Proceedings of the Third International Conference on Simulation of Adaptive Behavior, Cambridge, MA: MIT Press-Bradford Books, pp. 264–370.
Schaffer, J. D.; Whitley, D., and Eshelman, L. J. (1992), Combination of genetic algorithms and neural networks: A survey of the state of the art, in: Whitley, D., and Schaffer, J. D. (eds.) International Workshop on Combinations of Genetic Algorithms and Neural Networks — Proceedings COGANN-92, IEEE Computer Society Press, Los Alamitos, CA.
Turney, P.; Whitley, D., and Anderson, R. (1996), Evolution, learning, and instinct: 100 years of the Baldwin effect, Editorial for the Special Issue: The Baldwin Effect, Evolutionary Computation, 3, 4.
Verschure, F. M. J., and Pfeifer, R. (1993), Categorization, representation, and the dynamics of system-environment interaction: a case study in autonomous systems, in: Meyer, J.-A., Roitblat, H., and Wilson, S. (eds.), From Animals to Animats II: Proceedings of the Second International Conference on Simulation of Adaptive Behavior, Cambridge, MA: MIT Press-Bradford Books, pp. 210–217.
Wang, X., and Blum, E. K. (1995), Dynamics and bifurcation of neural networks, in: Arbib, M. A. (ed.), The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, Massachusetts.
Drawing Graphs with VGJ, http://lsiibm15.epfl.ch/graph_drawing.html, 07. 06. 2001.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pasemann, F., Steinmetz, U., Hülse, M. et al. Robot control and the evolution of modular neurodynamics. Theory Biosci. 120, 311–326 (2001). https://doi.org/10.1007/s12064-001-0025-9
Issue Date:
DOI: https://doi.org/10.1007/s12064-001-0025-9