Playing missile command 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).
This video shows a robot
playing missile command. There are no sound in the
video because I wanted to show the viewers what the
robot is thinking while playing the game. The
flashing text and freeze frames are the internal
thoughts of the robot and not instruction text for
the viewers. These internal thoughts describe the
details of how the robot produce intelligence.
My robot doesn't use:
planning programs/heuristic searches (used by MIT and
Stanford University), Bayesian's probability theories
for decision making, Bayesian's equation for
induction and deduction, semantic networks for
natural language understanding, predicate calculus,
common sense systems, first-order logic, rule-based
systems, genetic programming, or MACHINE LEARNING.
In the game, there are 3
bases and each base is armed with 10 intercept
missiles. The robot's mission is to destroy any
missiles from the sky and to protect the cities and
bases. In order to destroy a missile from the sky,
the robot has to predict the future path of the
missile. Next, he has to calculate where the
intercept point is. The goal is to shoot intercept
missiles to destroy missiles from the sky.
To make the game more
difficult, the robot has to shoot down multiple
missiles (about 20 per level). His task includes
identifying priority threats and systematically
destroying threats.
To make the game even
more difficult, the levels are based on the speed of
the missiles. The higher the level, the faster the
missiles come. Notice that the robot had a very easy
time at the beginning of the game and hard time at
the ending of the game. The reason is because of the
speed of the missiles. This robot has human
intelligence and it is very hard to think and act
when missiles are charging at you very fast.
I filed patents on a
super intelligent robot to solve this problem. The
super intelligent robot can slow time so that he can
think and act faster than normal humans. This type of
robot is kind of like superman, whereby the
environment slows down and it gives someone time to
process information.
People out there might
think that this is a very old Atari game and building
a robot to solve this problem is a waste of time.
The fact of the matter is that the military is
currently searching for this type of software to
control missiles to protect cities and bases from a
nuclear attack. Let's say that a country was under
attack and hundreds of nuclear missiles are fired at
them, their missile defense system has to intercept
and destroy hundreds of missiles in the sky. Also,
their missile defense system has to work from
multiple sites to destroy missiles from the sky in an
optimal manner -- these military bases has to work
together in order to take out the threat missiles
quickly.
The difference between
my robot and other missile defense system is that my
robot can handle complexity. You can add features to
the game to make it more complex, my robot will still
have the ability to adapt. Through practice, it can
get better and better at the game. The end result is
a robot that can protect a country from a nuclear
attack, regardless of how much missiles are fired.
This robot can also do the opposite, whereby he can
launch missiles to a enemy country to take out
important bases and cities in the fastest time
possible. Or the robot, with the help of software,
can attack a country and protect the homeland at the
same time. There are pros and cons to this type of
technology.