Inductive transfer assist-control for human-interface steering device

Abstract

Human Adaptive Mechatronics (HAM) is the research area that covers the design for assisting the human operator in improving its skills. HAM devices are capable to measure/estimate the operator's skill/dexterity, while a realtime embedded assist-controller enhances machine operation, improving the overall human-machine performance. Nowadays, the demand for such devices has particular potential in many activities which involve manual operations. The main contribution of this work is the development of a human adaptive real-time electronic switching controller obtained from a fuzzy clustering inductive learning technique, for improving the operator's proficiency, based on the transfer learning information of an expert driver. Several tests were conducted under a hardware/software driving simulator setup, to prove the effectiveness of the proposed methodology.