Considerations in the application of evolution to the generation of robot controllers

Abstract This paper is concerned with different aspects of the use of evolution for the successful generation of real robot Artificial Neural Network (ANN) controllers. Several parameters of an evolutionary/genetic algorithm (GA) and the way they influence the evolution of ANN behavioral controllers for real robots have been contemplated. These parameters include the way the initial populations are distributed, how the individuals are evaluated, the implementation of race schemes, etc. A batch of experiments on the evolution of three types of behaviors with different population sizes have been carried out in order to ascertain their effect on the evolution of the controllers and their validity in real implementations. The results provide a guide to the design of evolutionary algorithms for generating ANN based robot controllers, especially when, due to computational constraints, the populations to be used are small with respect to the complexity of the problem to be solved. The problem of transferring the controllers evolved in simulated environments to the real systems operating in real environments are also considered and we present results of this transference to reality with a robot which has few and extremely noisy sensors.

[1]  Randall D. Beer,et al.  Application of evolved locomotion controllers to a hexapod robot , 1996, Robotics Auton. Syst..

[2]  Charles E. Taylor,et al.  Selection for Wandering Behavior in a Small Robot , 1994, Artificial Life.

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

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

[5]  Richard J. Duro,et al.  Progressive Construction of Compound Behavior Controllers for Autonomous Robots Using Temporal Information , 1999, ECAL.

[6]  Stefano Nolfi,et al.  How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics , 1994 .

[7]  David J. Chalmers,et al.  Subsymbolic Computation and the Chinese Room , 1992 .

[8]  Inman Harvey,et al.  Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics , 1995, ECAL.

[9]  Lisa Meeden,et al.  An incremental approach to developing intelligent neural network controllers for robots , 1996, IEEE Trans. Syst. Man Cybern. Part B.

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

[11]  Ralf Salomon,et al.  The evolution of different neuronal control structures for autonomous agents , 1997, Robotics Auton. Syst..

[12]  Stefano Nolfi,et al.  Using Emergent Modularity to Develop Control Systems for Mobile Robots , 1997, Adapt. Behav..

[13]  Aude Billard,et al.  Evolutionary robotics-a children's game , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[14]  Francesco Mondada,et al.  Evolutionary neurocontrollers for autonomous mobile robots , 1998, Neural Networks.

[15]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[16]  Stefano Nolfi,et al.  Evolving Mobile Robots in Simulated and Real Environments , 1995, Artificial Life.