Identification of human skill and its application to an automatic driving system - an approach from hybrid dynamical system

In this paper, we propose an approach to model human skill, which can be useful in systems of machine intelligence and human operator assistance. The approach is to consider the model of human manipulation skill as a hybrid dynamical system (HDS), where, each continuous submodel deals with its related manipulation mode, while a discrete event model represents the switches between all the submodels. In particular, we express the HDS model as a hinging hyperplane autoregressive exogenous (HHARX) model as it is able to deal with manipulation modes and their switches simultaneously. Based on experimental data manipulated by an expert human operator, HHARX parameters are identified via mixed-integer linear programming (MILP). As a typical example, we apply our approach to an automatic driving system of a small radio-controlled vehicle. Both simulation and experimental results illustrate the effectiveness of the proposed method