Intelligent computing for demonstration-based robot learning

Robot learning is an efficient strategy to achieve control task without explicit programming. In this work, we present a learning framework in which the robot is taught how to perform desired behaviors through a demonstration procedure. During the demonstration, the behavior sequences are recorded and transferred to time series data, and intelligent computing methods are proposed to learn the behaviors from the data. To assess the performance of the proposed framework, different sets of experiments have been conducted and the results show that our framework can be used to learn robot behaviors efficiently and successfully.