Title :
Realization of robust controllers in evolutionary robotics: a dynamically-rearranging neural network approach
Author :
Kondo, T. ; Ishiguro, A. ; Tokura, S. ; Uchikawa, Y. ; Eggenberger, P.
Author_Institution :
Dept. of Comput. Sci. & Eng., Nagoya Univ., Japan
Abstract :
The evolutionary robotics approach has been attracting a lot of attention in the field of robotics and artificial life. In this approach, neural networks are widely used to construct controllers for autonomous mobile agents, since they intrinsically have generalization, noise-tolerant abilities and so on. However, there are still open questions: (1) the gap between simulated and real environments, (2) the evolutionary and learning phase are completely separated, and (3) the conflict between stability and evolvability/adaptability. In this paper, we try to overcome these problems by incorporating the concept of dynamic rearrangement function of biological neural networks with the use of neuromodulators. Simulation results show that the proposed approach is highly promising
Keywords :
adaptive control; artificial life; evolutionary computation; generalisation (artificial intelligence); learning (artificial intelligence); mobile robots; neurocontrollers; robust control; simulation; software agents; stability; adaptability; artificial life; autonomous mobile agents; biological neural networks; dynamically-rearranging neural network approach; evolutionary robotics; evolvability; generalization; learning phase; neuromodulators; noise-tolerant abilities; real environments; robust controllers; simulated environments; simulation; stability; Artificial neural networks; Automatic control; Biological neural networks; Erbium; Intelligent networks; Neural networks; Neurons; Robot control; Robotics and automation; Robust control;
Conference_Titel :
Evolutionary Computation, 1999. CEC 99. Proceedings of the 1999 Congress on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5536-9
DOI :
10.1109/CEC.1999.781948
