11-04-2013, 02:18 PM
Developing Intelligent Wheelchairs for the Handicapped
Developing Intelligent.pdf (Size: 2.12 MB / Downloads: 197)
Abstract
A brief survey of research in the development of autonomy in wheelchairs is presented and
AAI’s R&D to build a series of intelligent autonomous wheelchairs is discussed. A standardized
autonomy management system that can be installed on readily available power chairs which have
beenwell-engineered over the years has been developed and tested. A behavior-based approach was
used to establish sufficient on-board autonomy at minimal cost and material usage, while achieving
high efficiency, sufficient safety, transparency in appearance, and extendability. So far, the add-on
system has been installed and tried on two common power wheelchair models. Initial results are
highly encouraging.
Introduction
In recent years, the concept of applying behavior-based intelligent robots to service tasks [Gomi,
92} has been discussed. With the accelerated rate of aging of the population being reported in many
post-industrial countries, demand for more robotic assistive systems for people with physical
ailments or loss of mental control is expected to increase. This is a seemingly major application area
of service robots in the near future. For the past six years, we have been developing a range of
autonomousmobile robots and their software using the behavior-based approach [Brooks,86] [Maes,
92]. In our experience the behavior-based approach [Brooks, 86] [Brooks, 91a][Steels, 93] [Pfeifer
& Scheier, 96] [Maes, 92] allows developers to generate robot motions which are more appropriate
for use in assistive technology than traditional Cartesian intelligent robotic approaches [Gomi, 96a].
In Cartesian robotics, on which most conventional approaches to intelligent robotics are based,
"recognition" of the environment, followed by planning for the generation of motion sequence and
calculation of kinematics and dynamics for each planned motion, occupy the center of both
theoretical interest and practice. By adopting a behavior-based approach wheelchairs can be built
which can operate daily in complex real-world environments with increased performance in
efficiency, safety, and flexibility, and greatly reduced computational requirements. In addition,
improvements in the robustness and graceful degradation characteristics are expected from this
approach.
Brief survey of the field
Below is a description of research on intelligent wheelchairs that has been conducted and still
ongoing at some institutions. The survey is not intended to be complete but to provide an idea of
the different approaches used.
IBM T.J. Watson Research Center
Some of the earliest work in the development of intelligent wheelchairs was a system
implemented by Connell and Viola, [Connell & Viola, 90] in which a chair is mounted on top of
a robot to make it mobile. Mr. Ed, as the chair was called, could be controlled by the user using a
joystick mounted on the arm of the chair and connected to the robot. The user could also delegate
control to the system itself to perform certain functions such as avoid obstacles or follow other
moving objects. In addition to the joystick, input to the robot comes from bumper switches at the
front and rear of the robot, eight infrared proximity sensors for local navigation and two sonar
sensors at the front of the robot for following objects. Control is passed from the user to the robot
through a series of toggle switches.
KISS Institute for Practical Robotics
The KISS Institute for Practical
Robotics (KIPR), located in
Virginia is a non-profit educational
corporation performing R&D on the
integration of robotics in assistive
technology, space robotics and
autonomous underwater vehicles as
well as education in robotics and
related fields.
David Miller and Marc Slack at
KISS Institute have developed
TinMan I and II. In TinMan II
shown in Figure 1, a supplementary
wheelchair controller is installed
between the joystick and the
standard wheelchair motor
controller.
CALL Centre, University of Edinburgh
CALL Centre at the University of Edinburgh has developed the CALL Centre Smart
Wheelchair. It was originally developed as a motivating educational and therapeutic resource for
severely disabled children. The chairs were designed to assist in the assessment and development
of physical, cognitive, social and communicative skills. Thirteen chairs have been built and
evaluated in three local school, one in a residential hospital and three others in pre-vocational
establishments.
The chairs are adapted, computer-controlled power wheelchairs which can be driven by a
number of methods such as switches, joysticks, laptop computers, and voice-output. The
mechanical, electronic and software design are modular to simplify the addition of new functions,
reduce the cost of individualized systems and create a modeless system. Since there are no modes
and behaviors are combined transparent to the user, an explicit subsystem called the Observer was
set up to report to the user what the system is doing. The Observer responds and reports its
perceptions to the user via a speech synthesizer or input device.
The software runs on multiple 80C552 processors communicating via an I2C serial link
monitoring the sensors and user commands. Objects or groups of objects form modules which
encapsulate specific functional tasks. It is multitasking with each object defined as a separate task.
The architecture of behaviors each performing a specific functional task is similar to Brooks’
Subsumption Architecture.
TIDE Programme
Technology initiative for disabled and elderly people (TIDE) programme of the European Union
began in 1991 as a pilot action with 21 development projects and a budget of ECU18 million. The
SENARIO project (SENsor Aided intelligent wheelchair navigatIOn), one of the initial projects
within TIDE, includes 6 member companies from Greece, Germany, the UK, and France to
introduce intelligence to the navigation system of powered wheelchairs.
The system consists of five subsystems: risk avoidance, sensoring, positioning, control panel,
and power control. The risk avoidance subsystem includes the central intelligence and inputs
information from the sensoring and positioning subsystems. The sensoring subsystem includes
ultrasonic, odometer, and inclinometer sensors. The positioning subsystem identifies the initial
position of the chair by means of a laser range finder and allows the chair to be used in known
environments. The control panel subsystem accepts user’s instructions and the power control
subsystem converts the system’s instructions into vehicle movements.
Desirable characteristics of robots for the handicapped
Background
Since around 1992, AAI began a number of exchanges with people with various handicaps and
the individuals who assist them. This was preceded by a few years of on-going interactions with the
handicapped community through marketing, installing, servicing, and training individuals on a
speech-to-text voice interface system for computers. This device proved to be effective for people
with several types of handicap, particularly for individuals who had lost arm/hand usage. Since late
1995, voluntary work has been attempted by members of AAI at two institutions for the mobility
handicapped in Japan: a senior citizen’s hospice for severe physical/mental problems, and an
institution for people with severe physical handicaps. A considerable amount of time practising
physical assistive work has been carried out by members of the R&D team, including the designer
involved in the conceptual design of the robots, engineers and a technician responsible for the
construction of the robots, and the project manager and administrators of the robotics projects. In
early 1995, an individual with a severe physical disability (a quadriplegic) joined AAI as a regular
data entry/bookkeeping clerk and as a future tester of autonomous wheelchairs.