Application of Learning from Demonstration to a Mining Tunnel Inspection Robot

Abstract

Current research for Learning From Demonstration (LfD) seems to concentrate on the learning kernel. This paper outlines the need for a more useful variable selection technique using the training dataset. The paper presents a new training dataset selection method, called Information Extraction (IE). The application area is a complex task involving robot mining tunnel inspection, and IE is applied to the robot for this task. The Gaussian Mixture Model (GMM) is adopted to generate a learning curve utilized by a robot. The Gaussian Mixture Regression (GMR) is used to infer actions based on given states. After human demonstration, the robot can finish a pre-defined task independently.