Tic tac toe player Turkish Robot

[yaskil]

We have completed our project and want to share with you . The project is about creating a robotic arm which can play Tic Tac Toe game dynamically.

The arm relocates itself dynamically by the help of image processing.
It can distinguishes among different type of objects (arm, board and pieces).
It has unbeatable artificial intelligence.
It can automatically play tic tac toe game with a human.

Playing with it is very funny after working so much on it  you can watch the movie in the following link. We appreciate your comments.

http://www.youtube.com/watch?v=HFuBMOLuAn0

[Somchaya]

Cool, I think it's a really neat robot to have  I can't imagine how long you spent calibrating the arm though.. unless it was all done with visual feedback, which would be extremely impressive!

[yaskil]

We spent plenty of time on calibrating arm. That was the real challange we had to handle. The arm is completely automated. There is no human based input while it is moving, thinking or detecting items. I can play with it face to face it is really great feeling...

[annoyin_kid]

so... is it better than you?

[yaskil]

yes of course. it is checking all possible game paths. it is better than all of us.

[Admin]

how does the arm know where the pieces are? camera, or do you input it into the computer?

whats the device thingy on the gripper that picks up the pieces? got a diagram?

and i wouldnt call it AI . . . if you follow a short set of basic rules its impossible to lose at tic-tac-toe
now if the arm learned to do slight of hand to cheat and move the opponents pieces, that would be AI!

[yaskil]

The system has a camera. Our software stream images from web cam to a computer and processes image by the help of image processing techniques. After image processing, the arm determines which physical coordinate of an item that human inserted.

By term AI which I have used is not the reaction of arm for some type of specific inputs. So as you mentioned before a short set of basic rules can be adequate for making an interaction. In our system, we collate some useful information by the help of camera. We process this information and create a searchable game tree which consists of all possible game board states. At this point the AI itself takes place. Searching through all possible board states, deciding which move is better or worse and providing an output which can be called best move is the actual thing AI does. So in software litrature there are so many accepted decision making AI algorithms. We are using one of them. So it is impossible to win againts it because mathematically it is impossible, it is proofed.

As a gripper we have used a programmable electro magnet which is specially designed for this project. Behaviour of gripper can be controlled with our software.

[annoyin_kid]

yes of course. it is checking all possible game paths. it is better than all of us.

ah damn the robots have beat the humans again

[yaskil]

yes of course. it is checking all possible game paths. it is better than all of us.

ah damn the robots have beat the humans again

It depends on your point of view.

[JesseWelling]

and i wouldnt call it AI . . . if you follow a short set of basic rules its impossible to lose at tic-tac-toe

Sounds like First Order Logic to me

[Admin]

As a gripper we have used a programmable electro magnet which is specially designed for this project.

got info on that electromagnet? part numbers, design info?

a few years ago i tried making a robot that could play chess by using a $100 electromagnet . . . but all the magnet did was overheat and could barely lift a paperclip

soon after i gave up . . .

[yaskil]

As a gripper we have used a programmable electro magnet which is specially designed for this project.

got info on that electromagnet? part numbers, design info?

a few years ago i tried making a robot that could play chess by using a $100 electromagnet . . . but all the magnet did was overheat and could barely lift a paperclip

soon after i gave up . . .

Hmm I am sorry about that. If I were you I wouldn't have given up. We had same type of difficulties while doing this project. Chess is very complicated game for a robot. You may have mechanical problems, such as calibration. Also if you want to have completely automated project you need some detailed image processing. In chess there are 12 different items (in tic tac toe there are 2). Your algorithms might be capable of distinguishing all these. In my oppinion you should try something simple at first.

We have electro magnet done. I don't have very detailed information about this equipment.

[dosprompt007]

I enjoy the Turkish Tic-Tac-Toe Playing Robot as it relates historically to the Chessplaying Turk in the 18th century.  Of course, the original Turk was a hoax...