Playing pilot wings using Human Level Artificial Intelligence
Note: To make this website free to the public
please click on an ad to support my sponsors or you
can make a tax-deductable donation using Paypal
(click on the donation icon on the left).
A robot with human level
artificial intelligence is a robot that can do any
human task. It can drive a car, fly a plane, play any
videogame, play any sports game, etc.
This video
demonstrates how a robot thinks while flying a plane
and skydiving. There are no sound in this video
because I wanted the viewers to focus on the robot's
thoughts while playing the game.
The robot's conscious
contains computer programs that manipulate data.
Within these computer programs are primarily 5
containers: task container, rules container, planning
container, identity container, and strategy
container. The computer program in the robot's
conscious manipulate data in these 5 containers.
At the beginning of
the game, instructions are given to the robot. The
instructions state that there are two objectives in
order to get a flying certificate. 1. fly a plane 2.
skydive. As the robot is reading in the instructions,
knowledge pours into the 5 containers. When it is
time to do the first objective, the commander gives
specific instructions on flying a plane. These
instructions changes the information in the 5
containers. New data is being inserted, existing data
are being modified, and old data are being deleted
from the 5 containers.
The first objective
is to fly a plane, so the 5 containers contain
information about flying a plane. The robot also
knows that the upper task is to accomplish 2
objectives. After completing the first objective, the
robot moves on to the second objective, which is to
skydive. The commander will give specific
instructions on skydiving. These instructions will
change the 5 containers and populate them with
information about skydiving.
In this video I
wanted to show that the robot is doing hierarchical
tasks: the upper task is to accomplish 2 objectives
and the first objective is to fly a plane and the
second objective is to skydive (each objective is a
sub-task).
In addition, I wanted
to show that as the robot is given instructions, data
from the 5 containers changes. For example, if the
robot was given instructions to fly a plane, the 5
containers will have information about flying a
plane. If the robot was given instructions to
skydive, the 5 containers will have information about
skydiving. Thus, information in the 5 containers
changes based on the current environment.
All knowledge is
learned from teachers in school. Following
instructions are learned from teachers, doing tasks
are learned from teachers, and following linear
instructions are learned from teachers. If the robot
is given many examples, his brain will be able to
formulate "universal" pathways to read and do "any"
instruction.