Accomplishing DARPA's robot challenge (pt 4) 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).
DARPA, a defense
agency of the US government has announced the Robot
Challenge 2012 and the first contest will be held on
Dec. of 2013. Their mission is to give money to
Universities and technology companies to build them a
robot that can do "mundane human tasks". According to
the government, the reason for the the contest was to
build robots that can do search and rescue missions.
They wanted to build robots that can go into
dangerous zones to do tasks. The Japan earthquake was
one example.
There were several
tasks (about 8 tasks) the human robot has to
accomplish in the robot challenge. 1. walk around
dangerous terrains. 2 open a locked door. 3. identify
a broken pipe. 4. climb a ladder. 5. use tools, like
a sledge hammer. 6. fix a broken pipe. 7. control
vechicles with simple functions. 8. push buttons.
In this video, a
robot soldier is trying to rescue a hostage, called
Paez from a terrorist organization. According to
intel, the only bit of information given to the
soldier was the location of Paez. No information
about how many enemies are guarding the place is
given. The team of soldiers work together to take out
the enemies and to find and rescue Paez. There are no
sound in the video because i wanted to show the
viewers what the robot is thinking while working as a
soldier. The flashing text and freeze frames are the
internal thoughts of the robot and are not
instruction text for the viewers.
The first part of the
video shows the robot finding and rescuing Paez. The
second part shows the team of soldiers getting Paez
to the extract point. Their mission is to find Paez
and to escort him safely from house2 to the
extraction point.
One purpose of this
video is to show viewers that the robot has knowledge
about team work. The robot knows what other soldiers
in the team are supposed to do. When the commander
gave the order to create a diamond formation, each
member of the team knows exactly what to do.
In Star Trek, the
Borg are a bunch of robots that have a collective
mind. In human beings, each person thinks and acts,
individually. Knowledge of team work and verbal/body
language allows us to work in a team. The commander
can give an order to stop firing and to move to the
extraction point instead. All soldiers in the team
will follow orders from the commander. Individual
soldiers can disagree or question authority, but the
rules of engagement is to follow orders from the
commander and that is what each soldier should do.
Another purpose of
this video is to show viewers that the robot soldier
can do multiple tasks at the same time. In the
mission, he had primarily 3 tasks he had to do: 1.
protect a hostage 2. kill enemies. 3. navigate to
extraction point. All decision making from the robot
is based on these 3 tasks. Sometimes the robot has to
stop navigating and engage enemies. Other times, the
robot has to shoot enemies and navigate. And in other
times, the robot has to push the hostage lower and
navigate at the same time. Thus, the robot is
constantly doing muliple tasks simultaneously during
the mission. In addition, the robot has to follow
orders from the commander. If the robot commits
itself to a decision and the commander gives a brand
new order, the robot has to abandon his previous
commited decision.
How does the robot
learn the skills to be a soldier? The answer is
knowledge from school. In particular, knowledge from
military school. A programmer doesn't have to use
machine learning to teach the robot military skills.
The robot doesn't need expert software that
coordinates a team. It learns all knowledge from
watching lectures, reading books, and participating
in bootcamp.