28-06-2014, 11:16 AM
A Novel Vehicle Safety Model : Vehicle speed Controller under Driver Fatigue
A Novel Vehicle Safety Model.pdf (Size: 362.2 KB / Downloads: 38)
Introduction
Driver fatigue is one of the important factors that cause
traffic accidents, and the ever-increasing number due to a
diminished driver’s vigilance level has become a problem
of serious concern to society. Drivers with a diminished
vigilance level suffer from a marked decline in their
abilities of perception, recognition, and vehicle control,
and therefore pose serious danger to their own life and the
lives of other people [1-2]. The National Police
Administration in France concludes that 14.9 percents of
accident causing human hurt and 20.6 percents of accident
Vehicle Speed Controller under Driver Fatigue
The flowchart of fatigue detection in Fig.1 gives an outline.
Firstly, we use Haar algorithm to locate the face and
projection technique for eye location. And Haar algorithm
has good robustness in terms of head motions, variable
lighting conditions, the change of hair and having glasses,
etc. Secondly, we propose a new real time eye tracking
method based on Unscented Kalman Filter. Thirdly, driver
fatigue can be detected using PERCLO. For detailed eye
tracking method based on Unscented Kalman Filter, refer
to [5,6].
After driver is drowsy, some proposed systems which
turn off the engine for avoiding traffic accidents
[6,9,10,11]. But few authors are concerned the safety
ramifications of their proposed systems. The driving
system of front wheel drive consists of an engine, a clutch
system, a manual transmission, drive shafts, final drive,
front wheels and back wheels. The torque route-line of
driving vehicle is engine——clutch system——gear
shaft——manual transmission——middle drive
Electronic Throttle Control under Driver Fatigue
As the application of driver fatigue detection, we design an
electronic throttle control system model to avoid fatigue
driving as proposed above. The architecture of electronic
throttle based on driver fatigue detection is shown in Fig.6
Experimental Results and Discussion
This part of the research is to experimentally and
scientifically demonstrate the validity of propose safety
model. In order to obtain valuable data, the proposed
system was tested adequately in a realistic driving
environment. As shown in Table. 1, twenty (20) properly
qualified drivers between the ages of 25 and 50 served as
subjects in this study. Drivers had to have at least one year
of experience driving, and they had to be medically
qualified and free from controlled substances and alcohol
Conclusions
Through research presented in this paper, we propose a
new advanced safety model that controls the vehicle speed
under driver fatigue. Firstly? we propose a novel real-time
robust method for fatigue detection based on the
Unscented Kalman Filter[5,6]. Secondly, if driver fatigue
is confirmed, an adaptive speed controller is proposed
using the theory of sliding mode servo control for
providing precise positioning of the throttle valve to
control speed of vehicle to prevent accident. This model
was tested adequately in a realistic driving environment
with subjects of different genders, with/without glasses,
day/night driving, commercial/non-commercial drivers,
continuous driving time, and under different road
conditions. The experimental results show the validity of
the proposed model for vehicle speed controller under
driver fatigue