Generation of
Ego
Will have a
model of the self. The robot's self-image will contain a catalog
of what the robot can and cannot do (or has been able to do and
has not been able to doi.e., a record of its successes and
failures). Gaining an insight will improve the robot's opinion of
itself. This will take the form of improving the robot's
self-image and creating a temporary, small-to-medium increase in
voltages, clock speeds, with a reduction in gravidity and
internal critique. Might be motivated to work in ways that
improve some internal box score, providing feedback at an
abstract level. In other words, improving its self-image box
score may be an important motivator for the robot.
There will
be competing urges (drives). The ego (control unit) will balance
and make choices, and will develop different response patterns
depending upon its experiences.The ego or controller will
evaluate the situation and will try to project the effects of
alternate courses of action upon its welfare. The controller will
constantly evaluate its performance and will feel good when it
decides that it has done well and bad when it concludes that it
has done poorly.i.e., a critical parent. It will generate a
catalog of its successes and failures in order to know what it
can do (or at least has done) and what it can't do. When it
succeeds in doing something new or challenging, it will reward
itself with good feelings. (The tensions between the parent
parts, the ego, the child parts, and all the drives, emotions,
and evaluation processes are a crucial part of what makes us
human.) The efficacy of the advice provided by the parent part
will also be evaluated over time.
The
parental part would probably first be characterized by tallying
and making available statistics regarding prior outcomes.
Anticipations of unpleasant outcomes generated by abbreviated
reruns of prior, painful experiences could come from the
"parental part" program subsection.
From a
programming standpoint, how the robot responds will depend upon
choices which reflect all of the various influences which emanate
from different parts (subprograms) within its psyche.
How It Might Work:
When the
robot sets out to achieve a goal and "bumps its shins",
it may be puzzled (the first time), it may cry, or it may react
with angry determination. At the same time, the parental program
would record a failed sequence. It would raise a level of caution
in the robot, influencing its responses on the cautious side. If
the robot started to do the same thing again, the parent program
would replay the tape from the last similar occurrence. And how
would the robot know when a similar occurence is about to occur?
That's a good question. Objects have well-defined boundaries but
animation tracks (video tapes) don not. One way to do it is to
maintain a record of the camera's location and to associate film
clips with camera location. A time track is certainly necessary.
Starting points for short "film clips" may be stored
and associated with objects. Repetitive events like the diurnal
cycle could lead to generic expectations, with daily-event tags
such as when the robot enters the kitchen for the first time that
day. If nothing unusual happens, the details of the day's events
could soon be expunged, while the unusual would be recorded for
longer retention (i.e., at a greater weight).
Now how do
we program all this?
The
capabilities record might take the form of a record of the
"success scores" the robot assigned itself for the most
recent experiences in which the robot tried to do whatever it was
that is relevant to current demands.
How do we
simulate pain? There are many ways to punish the robot, including
intermittent failure of subsystems or confusion at critical
times. However, physical pain is still a mystery to me. I'm
thinking that pain must be electrical because we feel pain
instantly. If it were chemically-transmitted, a few seconds would
be required before the chemical messengers reached the brain.
Granted that pain messages may release neurotransmitters in the
brain, but how do they make a neural network hurt?
For that
matter, how do we make the robot care what happens to it?
The role of
play (let's pretend). Strong appetites. Tendency to imitate.
Imprinting.