Evolutionary Robotics | A Children ' s Game

| We explore the concept of development without programming by children. Especially, we look at the case of developing robot control systems. The evolutionary robotics approach has shown that in some cases, given a mathematically described tness function, it is possible to achieve an automatic development of robot controllers. However, it is questionable how one is to construct the mathematical tness function. So we applied an interactive genetic algorithm to the problem of developing robot controllers and achieved an evolutionary robotics approach that allows children without any programming knowledge to develop controllers for LEGO robots. We used neural networks as robot controllers, and found that combining the interactive genetic algorithm with a kind of reinforcement learning { development at the evolutionary time scale combined with life-time development { reduces the development time drastically. Hence, we overcome one of the major drawbacks of the interactive genetic algorithm, namely the development