Effect of Fitness for the Evolution of Autonomous Robots in an Open-Environment

The choice of a fittness function in artificial evolution has strong consequences on the evolvability of robots, dynamics of the evolutionary process, and ultimately on the outcome of the evolutionary process. In this paper, the effect of fitness functions for the evolution of autonomous robots to navigate in an open-environment by avoiding obstacles is studied. It is found that both the number and description of components of a fitness function affect the convergence of the evolutionary process. However, the performance of evolved robots in an unknown environment is greatly dependent on the description of components of a fitness function.

[1]  Jean-Arcady Meyer,et al.  Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects , 1998, IEEE Trans. Neural Networks.

[2]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .

[3]  Inman Harvey,et al.  Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

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

[5]  John J. Grefenstette,et al.  Genetic Algorithms for Tracking Changing Environments , 1993, ICGA.

[6]  A. Hoffman Arguments on evolution : a paleontologist's perspective , 1989 .

[7]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

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

[9]  Takahiro Sasaki,et al.  Evolving Learnable Neural Networks Under Changing Environments with Various Rates of Inheritance of Acquired Characters: Comparison of Darwinian and Lamarckian Evolution , 1999, Artificial Life.

[10]  R. Michod,et al.  The Evolution of sex : an examination of current ideas , 1988 .

[11]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[12]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[13]  Kathleen M. Swigger,et al.  An Analysis of Genetic-Based Pattern Tracking and Cognitive-Based Component Tracking Models of Adaptation , 1983, AAAI.

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

[15]  Xin Yao,et al.  A review of evolutionary artificial neural networks , 1993, Int. J. Intell. Syst..

[16]  Dario Floreano,et al.  Evolutionary robots with on-line self-organization and behavioral fitness , 2000, Neural Networks.