Vehicle/Driver Monitoring for Enhanced Safety of Transit Buses

This report documents the findings of the study “Vehicle/Driver Monitoring for Enhanced Safety of Transit Buses” conducted as part of the PATH project TO5400. The goal of study TO5400 is todesign and implementation of a reliable vehicle/driver monitoring system with aim to enhance driving safety of transit buses.The main objectives of the project are: (1) to identify a simply model that best describes the driving patterns of human drivers, and (2) to develop an algorithm which can generate warning messages when there is a provision of danger.In this study, it is assumed that the driver sets the angle of the steering wheel in response to the lateral deviation of the vehicle from the center line of the road and/or the road curvature ahead of the vehicle which he/she infers from the visual perception. It is also assumed that the dynamic relationship between the lateral deviation and the road curvature (i.e. the inputs to the driver) and the steering angle (i.e. the output from the driver) may be represented by a linear model with Auto Regressive Moving Average with eXogeneous (ARMAX) structure. The order of the ARMAX model is determined by off-line analysis of experimental data collected from actual driving tests. Once the order of the model is determined, the parameters of the model can be estimated by processing the input and output data in real time during actual driving.The on-line data processing and prediction can also estimate three critical parameters for driving safety: the driver’s response time (tr), the time-to-collision (TTC) and the time-to-lane-crossing (TLC) TLC. A timely warning message scheme, which incorporates all the three parameters, is designed to determine whether an alarm should be issued.