Reduction of the gap between simulated and real environments in evolutionary robotics: a dynamically-rearranging neural network approach

Abstract

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 following 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. 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.