Page 268 - Introduction to AI Robotics

251
6.10 Exercises
most common color coordinate systems are RGB and HSV. HSV treats color
in absolute terms, but RGB is favored by equipment manufacturers. A color
space used in biomedical imaging, SCT, appears to be less sensitive to light-
ing conditions than RGB and RGB-derived HSV. Many reactive robots exploit
color as an affordance. This can be done by thresholding an image and iden-
tifying regions of the appropriate color. A color affordance method which
works well for objects with multiple colors is color histogramming. Stereo
range finding is an important class of algorithms for navigation, though the
computational complexity has prevented it being ported to many mobile ro-
bot applications. Laser range finders, particularly the inexpensive planar
rangers, have grown in popularity over the past few years.
Despite the diversity of sensors and affordances inherent in the environ-
ment, reactive robotics is remarkable for its lack of sophistication in sensing.
This may stem from the split between computer vision and robotics in the
formative years of the field. Many roboticists still assume algorithms de-
veloped by computer vision specialists are too computationally expensive
to work on commercially available on-board processors. This is no longer
true, in part because of the increased computational power of general pur-
pose chips. Readers are encouraged to explore the large body of literature on
computer vision and free tools on the web.

6.10 Exercises
Exercise 6.1
Define sensor suite, active/passive sensors, dead reckoning, computer vision. y

Exercise 6.2
Compare and contrast the RGB and HSV color representations specifying the advan-
tages and disadvantages of each type. y
Exercise 6.3
Ultrasonic sensors have many positive and negative attributes. Name and describe
three positive and three negative attributes. y

Exercise 6.4
What is the difference between physical and logical redundancy? y
Exercise 6.5
Describe the three major problems of ultrasonic sensing, and define a hypothetical
instance in which a robot would encounter each problem (such as a room with a
large amount of glass surfaces). y