Regardless of all the software smarts that may be used by computers to outsmart humans in chess, robots are clumsy at manipulating real-world objects and humans are still better off at playing if it taken into the physical world.
For example, a robotic chess competition held at the Association for the Advancement of Artificial Intelligence annual conference in San Francisco, California, in August showed that even robotic arms used for precise work face trouble when they are asked to negotiate a noisy, chaotic real-world environment, New Scientist reported.
A number of robots competed with each other to see who could best move pieces quickly, accurately and legally in accordance with the rules of the game.
Some teams even used vision systems to identify where pieces were, but none of them attempted to differentiate between a rook and a knight in the game.
Instead, they relied on remembering where pieces were last placed to identify them and make their next move.
The robots quickly ran into difficulties as their vision systems often misread moves, which lead to confusion as to what piece had moved, and where the other pieces were on the board.
Road Narrows, a robotics company, used the approach of a commercially available fixed robotic arm, which is normally used for light industrial applications without any vision at all.
The winner was a team led by Mike Ferguson at the University of Albany, in New York, which had a mobile robot with an attached arm.
Despite the introduction of many variables to move a robot around, the droid's vision system managed to keep track of the board as well as the pieces as it moved about, according to Mike Stilman, one of the event's organisers from Georgia Institute of Technology, Atlanta.
