Playing football 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 football. 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.
When playing
football, the robot understands that the team works
together in order to beat the opponent's team. Each
member of the team knows what they have to do. The
defensive line players have to block opponent players
from reaching the quarterback, and give the
quarterback enough time to throw the ball. The
receivers have to run in formation so the quarterback
knows where to throw the ball. The runningback has to
get ready to run the ball if the quarterback hands
the ball to him.
In order to
coordinate the team's objectives, the quarterback
will give coded instructions to members. Like he
would say formation3 and each members know exactly
what to do. The quarterback will have an easier time
to do his job because he knows what the teammates are
going to do in the future. On the other hand, the
opponent players are trying to predict the
quarterback's thinking and to counter the gameplay.
In the video, the
robot plays as the quarterback and occasionally other
players. Just because this is a videogame, doesn't
mean real life is any different. In real life
football, the same kind of thinking is used to play
the game. The robot has to follow rules and
objectives of the game, use strategies that work,
adapt his game plans if opponent is winning,
coordinate team members, identify threat areas, etc.
The robot has to also
analyze the game and to keep track of scores. For
example, if the robot was at the end zone and he had
2 more yards until touchdown, he won't throw the
ball. Most likely, he will give the ball to the
runningback. The reason is because there are risks
involved in throwing the ball. Mainly the ball can be
intercepted by opponent players. If you give it to
the runningback, most like he can get at least 3
yards. Thus, the robot has to make important
decisions in the game based on the current situation.