A Soft-Computing basis for robots’ cognitive autonomous learning
Résumé
The present work deals with development of a Soft-Computing-based intelligent system allowing to discover autonomously the surrounding world and to learn new knowledge about it by semantically interacting with human. The learning is accomplished by observation and by interaction with a human. We provide experimental validation of the proposed concept using as well simulated environment as implementing the approach on a humanoid robot in a real-world environment. We show, that our approach allows a humanoid robot to learn without negative input and from small number of samples.