Evolution of the Sensorimotor Control in an Autonomous Agent

Visually guided agents are introduced, that evolve their sensor orientations and sensorimotor coupling in a simulated evolution. The work builds on neurobiological results from various aspects of insect navigation and the architecture of the \Vehicles" of Braitenberg (1984). Flies have specialized visuomotor programs for tasks like compensating for deviations from the course, tracking, and landing, which involve the analysis of visual motion information. We use genetic algorithms to evolve the obstacle avoidance behavior. The sensor orientations and the transmission weights between sensor input and motor output evolve with the sensors and motors acting in a closed loop of perception and action. The innuence of the crossover and mutation probabilities on the outcome of the simulations, speciically the maximum tness and the convergence of the population are tested.

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[2]  B. Hassenstein,et al.  Systemtheoretische Analyse der Zeit-, Reihenfolgen- und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus , 1956 .

[3]  W. Reichardt,et al.  Autocorrelation, a principle for the evaluation of sensory information by the central nervous system , 1961 .

[4]  N. Tinbergen,et al.  Instinktlehre : Vergleichende Erforschung angeborenen Verhaltens , 1966 .

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

[6]  We Reichardt,et al.  Functional characterization of neural interactions through an analysis of behavior , 1979 .

[7]  H. C. Longuet-Higgins,et al.  The interpretation of a moving retinal image , 1980, Proceedings of the Royal Society of London. Series B. Biological Sciences.

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

[9]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[10]  H. Wagner.  Flight Performance and Visual Control of Flight of the Free-Flying Housefly (Musca Domestica L.) III. Interactions Between Angular Movement Induced by Wide- and Smallfield Stimuli , 1986 .

[11]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[12]  Rodney A. Brooks,et al.  Battling Reality , 1989 .

[13]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[14]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[15]  Schloss Birlinghoven.  Evolution in Time and Space -the Parallel Genetic Algorithm , 1991 .

[16]  N. Franceschini,et al.  From insect vision to robot vision , 1992 .

[17]  A. Borst,et al.  Motion computation and visual orientation in flies. , 1993, Comparative biochemistry and physiology. Comparative physiology.

[18]  S Forrest,et al.  Genetic algorithms , 1996, CSUR.

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

[20]  Holger G. Krapp,et al.  Visual sensation of self-motion in the blowfly Calliphora. , 1998 .