On learning discontinuous human control strategies

Citation
Mc. Nechyba et Ys. Xu, On learning discontinuous human control strategies, INT J INTEL, 16(4), 2001, pp. 547-570
Citations number
22
Language
INGLESE
art.tipo
Article
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
ISSN journal
0884-8173 → ACNP
Volume
16
Issue
4
Year of publication
2001
Pages
547 - 570
Database
ISI
SICI code
0884-8173(200104)16:4<547:OLDHCS>2.0.ZU;2-4
Abstract
Models of human control strategy (HCS), which accurately emulate dynamic hu man behavior. have far reaching potential in areas ranging from robotics to virtual reality to the intelligent vehicle highway project. A number of le arning algorithms, including fuzzy logic, neural networks, and locally weig hted regression exist for modeling continuous human control strategies. The se algorithms, however, may not be well suited for modeling discontinuous h uman control strategies. Therefore, we propose a new stochastic, discontinu ous modeling framework, for abstracting human control strategies, based on hidden Markov models (HMM). In this paper, we first describe the real-time driving simulator which we developed for investigating human control strate gies. Next, we demonstrate the shortcomings of a typical continuous modelin g approach in modeling discontinuous human control strategies. We then prop ose an HMM-based method for modeling discontinuous human control strategies . The proposed controller overcomes these shortcomings and demonstrates gre ater fidelity to the human training data. We conclude the paper with furthe r comparisons between the two competing modeling approaches and we propose avenues for future research. (C) 2001 John Wiley & Sons, Inc.