Vous êtes sur la page 1sur 4

Artif Life Robotics (2009) 14:397400 ISAROB 2009

DOI 10.1007/s10015-009-0694-x

ORIGINAL ARTICLE

Djoko Purwanto Ronny Mardiyanto Kohei Arai

Electric wheelchair control with gaze direction and eye blinking

Received and accepted: May 18, 2009

Abstract We propose an electric wheelchair controlled by


1 Introduction
gaze direction and eye blinking. A camera is set up in front
of a wheelchair user to capture image information. The
sequential captured image is interpreted to obtain the gaze The ability to move freely is highly valued by all people.
direction and eye blinking properties. The gaze direction is However, it is sometimes difficult for a person with a physi-
expressed by the horizontal angle of the gaze, and this is cal disability. Nowadays, an electric wheelchair is commer-
derived from the triangle formed by the centers of the eyes cially available for disabled people. It generally requires
and the nose. The gaze direction and eye blinking are used considerable skill to operate. Moreover, some disabled
to provide direction and timing commands, respectively. people cannot drive an electric wheelchair manually, even
The direction command relates to the direction of move- with a joystick, because they lack the physical ability to
ment of the electric wheelchair, and the timing command control the movement. To enable a disabled person to drive
relates to the time when the wheelchair should move. The a wheelchair safely and easily so that they can enjoy a
timing command with an eye blinking mechanism is designed higher quality of life, researchers have proposed several
to generate ready, backward movement, and stop com- electric wheelchair systems. The use of voice commands to
mands for the electric wheelchair. Furthermore, to move at control an electric wheelchair is one research result. A small
a certain velocity, the electric wheelchair also receives a number of command words and high-performance voice
velocity command as well as the direction and timing com- recognition are employed in this system. An electric wheel-
mands. The disturbance observer-based control system is chair control with electro-oculography (EOG) techniques
used to control the direction and velocity. For safety pur- has also been proposed. In this case, the different com-
poses, an emergency stop is generated when the electric mands for the wheelchair are derived from the electro-ocu-
wheelchair user does not focus their gaze consistently in any lography (EOG) potential signals of eye movements.
direction for a specified time. A number of simulations and A system for electric wheelchair control using the eyes
experiments were conducted with the electric wheelchair in was proposed in 2007. A commercially available web camera
a laboratory environment. on a head-mounted display (HMD) which the user wears is
used to capture moving pictures of the users face. A com-
Key words Electric wheelchair control Gaze estimation puter mounted on the electric chair processes the captured
Blinking measurement image data, detecting and tracking movements of the users
eyes, estimating the line-of-sight vector, and actuating the
electric wheelchair in the desired direction indicated by the
users eyes. One of the key essentials of the proposed system
is detecting and tracking the eye movements. This article
deals with the experimental results of the accuracy of the
D. Purwanto R. Mardiyanto estimation of the rotation angle of the eyeball, and with the
Department of Electrical Engineering, Institute of Technology acquired image of the eyes and their surroundings. Through-
Sepuluh Nopember (ITS), Surabaya, Indonesia
out the experiments, a success rate of almost 99% was con-
K. Arai ( ) firmed in terms of matching the accuracy of the electric
Department of Information Science, Saga University, 1 Honjo, Saga
840-8502, Japan
wheelchairs movement with the direction in which the user
e-mail: arai@is.saga-u.ac.jp intended to move.1
In this research, a method of electric wheelchair control
This work was presented in part at the 14th International Symposium by gaze direction and eye blinking properties is proposed.
on Artificial Life and Robotics, Oita, Japan, February 57, 2009 A camera is set up in front of the wheelchair user to capture
398

image information. The camera direction is focused onto processing and control purposes is placed in the bottom of
the face area of the wheelchair user. The camera is con- the wheelchair. The electric wheelchair uses a differential
nected to a computer with vision processing and electric steering mechanism. The wheelchair design considers the
wheelchair motion control capabilities. With vision process- following four important factors: safety, ease of operation,
ing, the sequential captured image is interpreted to obtain low price, and convenience.
the gaze direction and eye blinking properties. The gaze Four commands are use to control the electric wheel-
direction is expressed as the horizontal angle of the users chair, i.e., the safety, timing, direction, and velocity com-
gaze, and is derived from the triangle formed by the centers mands (Fig. 2). The safety command is for any situation in
of the eyes and the nose. The eye-blinking properties are which the wheelchair must stop immediately. The timing
obtained from the timing of blinks. The gaze direction and command is obtained from the eye-blinking mechanism,
eye blinking are used to provide the direction and timing and is used to move or stop the chair. The direction
commands, respectively, for the electric wheelchair. The command is derived from the properties of the points of the
direction command relates to the direction of movement of triangle made by both eyes and the nose of the user. The
the electric wheelchair, and the timing command relates to velocity command is set independently and does not depend
the time when the electric wheelchair should move. The on the vision system. Both the direction and velocity
eye-blinking mechanism with a blink duration of at least commands refer to the wheelchairs motion in Cartesian
400 ms is designed to generate a timing command for when space.
to move. Furthermore, the electric wheelchair also receives
a velocity command to move at a certain velocity, as well
2.2 Electric wheelchair model
as the direction and timing commands. The disturbance
observer-based control system is used to control the direc-
Figure 3 illustrates the differential steering of the electric
tion and velocity. For safety purposes, an emergency stop
wheelchair model. The desired wheelchair motion is deter-
is generated when the electric wheelchair user does not
mined by the command value of direction and linear
focus their gaze consistently in one direction for a specified
velocity v. The wheelchair motion depends on the electric
time.
signal applied to the motor of each wheel. The angular
velocities l and r represent the direct input signals to
move the wheels of the electric wheelchair to the left or to
2 Proposed system the right, respectively. The relation between direction and
velocity (, v) and the angular velocities of the wheels
2.1 System overview

The hardware of an electric wheelchair equipped with a


camera is shown in Fig. 1. The electronic system for vision

Fig. 2. Commands for the electric wheelchair

Fig. 1. Electric wheelchair hardware Fig. 3. Electric wheelchair model


399

Fig. 4. Electric wheelchair system

(l, r) is given by Eq. 1, where Rw is radius of a wheel,


is the gear ratio, and l is the distance between the wheels.
RW RW
2
v 2 l
 = R
R
(1)
W
l W r
l

2.3 Electric wheelchair system

The overall block diagram of the electric wheelchair system


is shown in Fig. 4. The system consists of a vision interpreta-
tion system and an electric wheelchair control system. All
the visual information processing, which includes gaze
direction estimation, eye blinking interpretation, and safety
detection, is carried out by a vision interpretation system.
The gaze direction estimation generates smooth-running
direction commands. The eye blinking interpretation and
safety detection systems generate command signals which Fig. 5. Relation between the triangular shape and the gaze
are sent directly to the controller. In the wheelchair con-
trol system, a disturbance observer-based control strategy
Fig. 6. Triangular shape from the
is applied to solve the two inputs/two outputs control
eyes and the nose
problem.

2.4 Vision interpretation system

2.4.1 Gaze direction estimation

The gaze direction is interpreted from the positions of both


eyes and the nose of the wheelchair user. As shown in Fig.
5, these three positions form a triangular shape that relates
to the direction of the gaze. With the parameters of the tri-
angle, as shown in Fig. 6, the estimation of the gaze direc- The direction command cmd is derived from the gaze
tion is formulated as Eq. 2. The function of f()is determined direction estimation with a smoothing function formula-
during the calibration procedure. tion to yield natural changes in commands and to suppress
a b measurement noise.
= f1
()
(2)
L cmd = f2 (3)
400

2.4.2 Eye-blinking interpretation Linear velocity response


0.4
An interpretation of eye blinking is useful to generate a
timing command which can be applied directly to the con-

(m/sec)
troller. Eye blinking with a duration of at least 400 ms is 0.2
used as the timing command. The algorithm of the timing command
command is as follows: actual
0
1. If <1 blink>then <disable controller> 0 5 10 15 20
2. If <2 blinks>then <enable controller> time (sec)
3. If <long blinking>then <set to move backward>
Rate of direction response
2.4.3 Safety detection 0.2
command

(rad/sec)
The safety detection control monitors the behavior of the actual
electric wheelchair user and the performance of the vision 0.1
system. Bad behavior is defined as when the user does
not focus during wheelchair control. Failure of the vision
system occurs when the system fails to detect the users face. 0
0 5 10 15 20
The safety command algorithm is defined as
time (sec)

If <bad user behavior>or <face detect failed>then <disable Actual response of wheelchair motors
controller> 30
(rad/sec)
2.5 Electric wheelchair control system 20

2.5.1 Electric wheelchair motors and controller 10 left


right
In both of the wheelchair motors, the disturbance observer 0
technique is applied. The disturbance observer is a tech- 0 5 10 15 20
nique to estimate the disturbance existing in a plant, and to time (sec)
make the motion controller be an acceleration controller
Fig. 7. Simulation results
also.3 With an acceleration controller, the wheelchair motors
can be modeled as an ideal integrator, and the block diagram
of the controller is realized by constant gain K.
v K 0 vcmd v
= (4)

0 K  cmd  4 Conclusion

2.5.2 Angular to linear velocity conversion and accelera- The feature points in the triangle made by the positions of
tion reference generator the eyes and the nose can be formulated to generate a direc-
tion command for the electric wheelchair. Combining the
The conversion from angular to linear velocity is formu- direction, velocity, timing, and safety commands yields an
lated in Eq. 1. Furthermore, the acceleration reference can effective method of controlling an electric wheelchair. With
be derived from Eq. 1 as follows: the disturbance observer technique applied as a control
1 strategy, the design criteria of the wheelchair control system
RW RW
l 2 2 
 can easily be satisfied.
 = R
RW
 (5)
r W
l
l References

3 Results 1. Arai K, Purwanto D (2007) Electric wheelchair control with the


human eye. 7th International Conference on Optimization: Tech-
niques and Applications, December 2007, Kobe, Japan
To verify the effectiveness of the proposed method, several 2. Arai K, Uwataki H (2007) Computer input system based on viewing
simulations were carried out. Figure 7 shows that the actual vector estimation with iris center detection from the image of users
response follows the command in a specified time. Further- acquired with relatively cheap web camera allowing user move-
more, the actual response of the motor shows that there ments. J Inst Elec Eng Jpn C-127(7):11071114
3. Ohnishi K, Shibata M, Murakami T (1996) Motion control for
is a difference in the angular velocity of the left and right advance mechatronics. IEEE/ASME Trans Mechatronics 1(1):
motors when the command is change direction. 5667

Vous aimerez peut-être aussi