Recently, the Evolutionary Robotics approach has been attracting a lot of concern in robotics and artificial life communities. In this approach, neural networks are widely used to construct controllers for autonomous mobile agents, since they intrinsically have nonlinear mapping, generalization, noise-tolerant abilities and so on. However, the followings 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 particularly focus on the gap problem, and try to alleviate this by incorporating the concept of dynamic rearrangement function of biological neural networks with the use of neuromodulators. Simulation and real experimental results show that the proposed approach is highly promising.
|Pages (from-to)||III-239 - III-244|
|Journal||Proceedings of the IEEE International Conference on Systems, Man and Cybernetics|
|Publication status||Published - 1999|
|Event||1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn|
Duration: 1999 Oct 12 → 1999 Oct 15