Artificial curiosity driven autonomous knowledge discovery based on learning by interaction

In this work we investigate the development of a real-time intelligent system allowing a humanoid robot to discover its surrounding world and to learn autonomously new knowledge about it by semantically interacting with human. The learning is performed by observation and by interaction with a human tutor. We describe the system in a general manner, and then we apply it to autonomous learning of objects and their colors. We provide experimental results as well using simulated environment as implementing the approach on a humanoid robot in a real-world environment including every-day objects. We show, that our approach allows a humanoid robot to learn without negative input and from small number of samples.