Evolving neural network controllers

An emerging design paradigm uses evolutionary processes to search for optima in design space. The evolutionary technique has the advantage of being a declarative paradigm; the user specifies the task, and a genetic algorithm searches for an optimum solution. Normal techniques require the definition of the controller, and this is computationally expensive. We use a genetic algorithm to design a neural network-based controller for a hexapod robot. The robot must perform the task of moving from a start position to a goal position, under varying degrees of simulated instrument and sensor noise. The findings show that it is possible to embed a degree of noise tolerance into the solution. This is useful in situations where the environment of the robot may change over time.

[1]  Inman Harvey,et al.  Evolving visually guided robots , 1993 .

[2]  Andrew H. Fagg,et al.  Genetic programming approach to the construction of a neural network for control of a walking robot , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[3]  Inman Harvey,et al.  Analysing recurrent dynamical networks evolved for robot control , 1993 .

[4]  Craig W. Reynolds.  Evolution of corridor following behavior in a noisy world , 1994 .

[5]  Inman Harvey,et al.  Genetic Convergence in a Species of Evolved Robot Control Architectures , 1993, ICGA.

[6]  Inman Harvey,et al.  Issues in evolutionary robotics , 1993 .

[7]  A. P. Wieland,et al.  Evolving neural network controllers for unstable systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[8]  Rodney A. Brooks,et al.  A robot that walks; emergent behaviors from a carefully evolved network , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[9]  Inman Harvey,et al.  Incremental evolution of neural network architectures for adaptive behavior , 1993, ESANN.

[10]  P. Husbands,et al.  Analysis of Evolved Sensory-motor Controllers Analysis of Evolved Sensory-motor Controllers , 1992 .

[11]  Michiel van de Panne,et al.  Sensor-actuator networks , 1993, SIGGRAPH.

[12]  Joe Marks,et al.  Spacetime constraints revisited , 1993, SIGGRAPH.

[13]  David B. Fogel,et al.  Evolving neurocontrollers using evolutionary programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.