A Cognitive Approach for Robots’ Autonomous Learning
Résumé
In this work we contribute to development of a real-time intelligent system allowing to discover and to learn autonomously new knowledge about the surrounding world by semantically interacting with human. The learning is accomplished by observation and by interaction with a human tutor. 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.