Learning and Validation of Human Control Strategies
Michael C. Nechyba| Abstract | |
|
In this thesis, we apply machine learning techniques and statistical
analysis towards the learning and validation of human control strategy
(HCS) models. This work has potential impact in a number of
applications ranging from space telerobotics and real-time training to
the Intelligent Vehicle Highway System (IVHS) and human-machine
interfacing. We specifically focus on the following two important
questions: (1) how to efficiently and effectively model human control
strategies from real-time human control data and (2) how to validate
the performance of the learned HCS models in the feedback control
loop. To these ends, we propose two discrete-time modeling frameworks,
one for continuous and another for discontinuous human control
strategies. For the continuous case, we propose and develop an
efficient neural-network learning architecture that combines flexible
cascade neural networks with extended Kalman filtering. This learning
architecture demonstrates convergence to better local minima in many
fewer epochs than alternative, competing neural network learning
regimes. For the discontinuous case, we propose and develop a
statistical framework that models control actions by individual
statistical models. A stochastic selection criterion, based on the
posterior probabilities for each model, then selects a particular
control action at each time step. Next, we propose and develop a stochastic similarity measure - based on Hidden Markov Model (HMM) analysis - that compares dynamic, stochastic control trajectories. We derive important properties for this similarity measure, and then, by quantifying the similarity between model-generated control trajectories and corresponding human control data, apply this measure towards validating the learned models of human control strategy. The degree of similarity (or dissimilarity) between a model and its training data indicates how appropriate a specific modeling approach is within a specific context. Throughout, the learning and validation methods proposed herein are tested on human control data, collected through a dynamic, graphic driving simulator that we have developed for this purpose. In addition, we analyze actual driving data collected through the Navlab project at Carnegie Mellon University. |
|
 |
M. C. Nechyba, Learning and Validation of Human Control Strategies, Ph.D. Thesis, The Robotics Institute, Carnegie Mellon University, 1998 (4.7 Mb). |