A Learning-Based Personalized Driver Model Using Bounded Generalized Gaussian Mixture Models
| Autor: | Junqiang Xi, J. Karl Hedrick, Wenshuo Wang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer Networks and Communications
Computer science business.industry Aerospace Engineering 020302 automobile design & engineering Advanced driver assistance systems 02 engineering and technology Mixture model Machine learning computer.software_genre Data modeling Distribution (mathematics) 0203 mechanical engineering Bounded function Automotive Engineering Learning based Artificial intelligence Electrical and Electronic Engineering Hidden Markov model business computer |
| Zdroj: | IEEE Transactions on Vehicular Technology. 68:11679-11690 |
| ISSN: | 1939-9359 0018-9545 |
| Popis: | Individual driver's driving behavior plays a pivotal role in personalized driver assistance systems. Gaussian mixture models (GMM) have been widely used to fit driving data, but unsuitable for capturing the data with a long-tailed distribution. Though the generalized GMM (GGMM) could overcome this fitting issue to some extent, it still cannot handle naturalistic data which is generally bounded. This paper presents a learning-based personalized driver model that can handle non-Gaussian and bounded naturalistic driving data. To this end, we develop a BGGMM-HMM framework to model driver behavior by integrating a hidden Markov model (HMM) in a bounded GGMM (BGGMM), which synthetically includes GMM and GGMM as special cases. Further, we design an associated iterative learning algorithm to estimate the model parameters. Naturalistic car-following driving data from eight drivers are used to demonstrate the effectiveness of BGGMM-HMM. Experimental results show that the personalized driver model of BGGMM-HMM that leverages the non-Gaussian and bounded support of driving data can improve model accuracy from 23 $ \sim$ 30% over traditional GMM-based models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|