Page 88 - Introduction to AI Robotics

71
3.1 Overview
man (or any warm blooded animal). If the mosquito senses a hot area, it
flies toward it. The roboticist can model this process as: input=thermal
image, output=steering command. The “black box” is how the mos-
quito transforms the input into the output. One good guess might be
to take the centroid of the thermal image (the centroid weighted by the
heat in each area of the image) and steer to that. If the hot patch moves,
the thermal image will change with the next sensory update, and a new
steering command will be generated. This might not be exactly how the
mosquito actually steers, but it presents an idea of how a robot could
duplicate the functionality. Also notice that by focusing on the process
rather than the implementation, a roboticist doesn’t have to worry about
mosquitoes flying, while a search and rescue robot might have wheels. At
Level 2, agents can exhibit common processes.

Level 3: How to implement the process. This level of the computational the-
ory focuses on describing how each transformation, or black box, is imple-
mented. For example, in a mosquito, the steering commands might be im-
plemented with a special type of neural network, while in a robot, it might
be implemented with an algorithm which computes the angle between the
centroid of heat and where the robot is currently pointing. Likewise, a re-
searcher interested in thermal sensing might examine the mosquito to see
how it is able to detect temperature differences in such a small package;
electro-mechanical thermal sensors weigh close to a pound! At Level 3,
agents may have little or no commonality in their implementation.

It should be clear that Levels 1 and 2 are abstract enough to apply to any
agent. It is only at Level 3 that the differences between a robotic agent and
a biological agent really emerge. Some roboticists actively attempt to em-
ulate biology, reproducing the physiology and neural mechanisms. (Most
roboticists are familiar with biology and ethology, but don’t try to make exact
duplicates of nature.) Fig. 3.1 shows work at Case Western Reserve’s Bio-Bot
Laboratory under the direction of Roger Quinn, reproducing a cockroach on
a neural level.
In general, it may not be possible, or even desirable, to duplicate how a
biological agent does something. Most roboticists do not strive to precisely
replicate animal intelligence, even though many build creatures which re-
semble animals, as seen by the insect-like Genghis in Fig. 3.2. But by focus-
ing on Level 2 of a computational theory of intelligence, roboticists can gain
insights into how to organize intelligence.