| Abstract |
We are investigating an evolutionary robotic system where robot morphologies and controllers can evolve. In such a system newborn robots face the problem of having to learn to control their own body that is a random combination of the bodies of the parents. This paper focuses on learning an elementary skill: walking in a given direction. To this end, we apply the HyperNEAT algorithm guided by a fitness function that balances the distance travelled in a direction and the deviation between the desired and the actually travelled directions. We validate the generality and scalability of this method on a test suite of nine modular robots with evolvable morphologies in different shapes and sizes. The experimental results show that the best controllers obtained this way produce trajectories that accurately follow the correct direction and reach a considerable distance within 60 seconds |