An Experiment in Morphological Development for Learning ANN Based Controllers
This work addresses the problem of optimizing learning in robotics by exploring morphological development, but it is incremental as it builds on existing literature with a specific experimental focus.
The paper investigates morphological development in robotic systems, analyzing its inconsistent benefits through a quadruped walking experiment, and provides initial insights on when and how to apply it effectively.
Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to facilitate learning and make it more robust. However, when this approach is transferred to robotic systems, the results found in the literature are inconsistent: morphological development does not provide a learning advantage in every case. In fact, it can lead to poorer results than when learning with a fixed morphology. In this paper we analyze some of the issues involved by means of a simple, but very informative experiment in quadruped walking. From the results obtained an initial series of insights on when and under what conditions to apply morphological development for learning are presented.