Prediction of Human Driving Behavior Using Dynamic Bayesian Networks

Toru KUMAGAI  Motoyuki AKAMATSU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.2   pp.857-860
Publication Date: 2006/02/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.2.857
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Biocybernetics, Neurocomputing
Keyword: 
dynamic Bayesian network,  switching linear dynamic system,  collision warning system,  collision avoidance system,  driving behavior prediction,  

Full Text: PDF(369.1KB)>>
Buy this Article




Summary: 
This paper presents a method of predicting future human driving behavior under the condition that its resultant behavior and past observations are given. The proposed method makes use of a dynamic Bayesian network and the junction tree algorithm for probabilistic inference. The method is applied to behavior prediction for a vehicle assumed to stop at an intersection. Such a predictive system would facilitate warning and assistance to prevent dangerous activities, such as red-light violations, by allowing detection of a deviation from normal behavior.