Modeling human control strategy (HCS) is becoming an increasingly
popular paradigm in a number of different research areas, ranging from
robotics and intelligent vehicle highway systems to expert training
and virtual reality computer games. Usually, HCS models are derived
empirically, rather than analytically, from real-time human
input-output data. While these empirical models offer an effective
means of transferring intelligent behaviors from humans to robots and
other machines, there is a great need to develop adequate performance
criteria for these models. It is our goal in this paper to develop
several such criteria for the task of human driving. We first collect
driving data from different individuals through a real-time graphic
driving simulator that we have developed, and identify each
individual's control strategy model through the flexible cascade
neural network learning architecture. We then define performance
measures for evaluating two aspects of the resultant HCS models. The
first is based on event analysis, while the second is based on
inherent analysis. Using the proposed performance criteria, we
demonstrate the procedure for evaluating the relative skill of
different HCS models. Finally, we propose an iterative algorithm for
optimizing an initially stable HCS model with respect to independent,
user-specified performance criteria, by applying the Simultaneously
Perturbed Stochastic Approximation (SPSA) algorithm. The methods
proposed herein offer a means for modeling and transferring human
control strategy in response to real-time inputs, and improving the
intelligent behaviors of artificial machines.
|
