The following is copied from IEEE Spectrum, October 1997. It gives us
a better idea of the capabilities of the GuideCane from the
University of Michigan.
I didn't find very much useful information on the inventor's web page:
http://www-personal.engin.umich.edu/~johannb/
but maybe I didn't look in the right place.
[INLINE
________________________________________________________________
Seeing-eye cane steers the blin
A new type of electronic navigational aid for the blind may soon joi
white canes and seeing-eye dogs. Developed by scientists at th
University of Michigan in Ann Arbor, the GuideCane is an array o
ultrasonic obstacle-sensors attached to a wheeled handle, or cane
Operation is simple. The user selects a direction of travel--say
ahead--by using a joy stick on the cane. He or she then pushes th
GuideCane forward with one hand, much as if it were a golf cart. T
turn right or left, the person presses the joy stick to the right o
left, whereupon a servo turns the wheels in the appropriate direction
When the sensors detect an obstacle, an on-board 25-MHz 486 compute
determines the best path around it and directs the servo to turn th
guide wheels. Through the cane, the user feels the change in directio
and follows. After the obstacle is passed, the cane brings the use
back to the desired direction of travel
The GuideCane weighs only 4 kg, because it does not have to supply it
own driving power. As a result, it may be picked up and carrie
upstairs or down, if necessary, explained the unit's inventor, Johan
Borenstein, head of the Mobile Robotics Laboratory in the university'
department of mechanical engineering and applied mechanics
The prototype GuideCane, built by graduate student Iwan Ulrich, has 1
sensors and can sense any obstacle within a 120-degree angle in fron
of the user [see figure]. The sensors, made by Polaroid Corp.
Cambridge, Mass., are the same as those used to focus camera
automatically, and they operate in much the same way. They each emit
pulse of ultrasound and wait for the echo. The interval between th
two events determines the distance to the obstacle, while th
orientation of the particular sensor that detects the reflected puls
determines the angle. Whenever a sensor detects an obstacle, th
information is passed along to the computer for it to enter the new
on a two-dimensional occupancy grid of 10-by-10-cm squares. Thus a
all times the computer possesses a map of the obstacles in the are
around the cane
"But what good is a map of obstacles," asked Borenstein, "if th
GuideCane doesn't know where it is on the map?" So the uni
incorporates odometry to keep track of its location. Encoders on th
guide wheels measure their rotation to a fraction of a revolution
This is translated into the distance traveled from a point of origin
When the GuideCane swivels, one wheel moves farther than the other
and the information is related back to a direction. To eliminate th
errors that accumulate in this type of measurement, Borenstein plan
to add a compass so that all measurements can be tied to magneti
north
The inventor has added a couple of his own patented algorithms to th
GuideCane's arsenal of obstacle avoidance techniques. One of the
calculates the best path around obstacles, based on information fro
the occupancy grid. The other addresses the uncertainty that
reflection received by a sensor echoes its own pulse. In a typica
environment, the pulses undergo multiple reflections. Other thing
being equal, the uncertainty could force a wait to fire a pulse unti
the echoes from a previously fired sensor have died away. Bu
Borenstein's method attaches signatures to the pulses so that eac
sensor can determine whether an echo came from its own or another'
pulse. Because the sensors can now fire more often, much faster trave
speeds are open to the user
At the moment Borenstein is grappling with more immediate issues, suc
as the GuideCane's ability to detect different surfaces. The use
should be able to recognize that he is veering off onto someone'
lawn, for example. To solve this problem, Borenstein plans to fring
the sides of the GuideCane with whiskers, which will sense the edge o
the grass. Normally, the tips of the whiskers will be a couple o
centimeters above the cement; but if the Cane starts to veer off th
sidewalk, the user will feel and hear the whiskers brushing along th
lawn
A second problem is less tractable and is due to specular reflection
When ultrasound pulses from a sensor bounce off smooth surfaces lik
windows or mirrors, they do not reflect back to the sensor unless th
surface is directly ahead. So if the person is approaching, say,
glass wall at an oblique angle, the wall may be invisible to th
GuideCane, and a collision may result. This is not the worst thin
that can happen, Borenstein believes, since it is the GuideCane tha
is colliding with the surface and not the blind user. Nevertheless, i
is inelegant. "There is no good solution for this," Borenstein tol
IEEE Spectrum. "The most practical solution is a good bumper aroun
the GuideCane.
"A preliminary version of the prototype has been tested by visuall
impaired individuals and the reaction was extremely positive," sai
Borenstein. "But more development will be required before the devic
is ready for widespread commercial use.
________________________________________________________________
Linda Geppert, Edito
________________________________________________________________
contents feedback search hom
IEEE Spectrum October 1997 Volume 34 Number 1
(c) Copyright 1997, The Institute of Electrical and Electronic
Engineers, Inc
This archive was generated by hypermail 2b29 : Sun Dec 02 2012 - 01:30:04 PST