Robust and incremental robot learning by Imitation

In the last years, Learning by Imitation (LbI) has been increasingly explored in order to easily instruct robots to execute complex motion tasks. However, most of the approaches do not consider the case in which multiple and sometimes conflicting demonstrations are given by different teachers. Nevertheless, it seems advisable that the robot does not start as a tabula-rasa, but re-using previous knowledge in imitation learning is still a difficult research problem. In order to be used in real applications, LbI techniques should be robust and incremental. For this reason, the challenge of our research is to find alternative methods for incremental, multi-teacher LbI.