A fuzzy approach towards inductive transfer and human–machine interface control design

Traditional machines do not adapt to their operators, instead they implicitly demand human adaptation. Human adaptive mechatronics (HAM) is the research topic that covers the design of devices and controllers for assisting the human. HAM devices are capable to measure and estimate the operator’s skill/dexterity, while a real-time assist-controller enhances machine adaptation, improving the overall human–machine performance. Nowadays, the demand for such devices has particular potential in many activities, which involve manual operations, such as in assistive technology. The main contribution of this work is the proposal of a fuzzy clustering methodology to the development of a real-time inductive transfer embedded controller, used for improving the operator’s proficiency, under a human-in-the-loop environment relying on visual feedback information. Other contribution is the proposal of a condition for inductive transfer between human operators, based on correlation analysis. The operator behaviour is modelled and enhanced from a human–machine interface fuzzy classifier and assisting scheme, which uses real-time data and additional information collected from an expert user. Experimental tests were performed by different participants under a driving simulator, for evaluation of the proposed methodology. The fuzzy clustering approach confirmed to significantly improve the transfer learning and the driving skills of the human operators.