It's not Colonel Mustard in the drawing room with the lead pipe that made the news this week, but scientists at Duke University with a brand new AI mathematical model.
Researchers have created an algorithm for winning at Cluedo that they believe could lead to better artificial intelligence systems, such as mine-cleaning robots in urban areas.
At the simplest level, both activities are governed by the same principles, according to the Duke University scientists. A player, or robot, must move through an unknown space searching for clues.
"The key to success, both for the Cluedo player and the robots, is to not only take in the new information it discovers, but to use this new information to help guide its next move," said Chenghui Cai of the University's Computer and Electrical Engineering department.
The Taliban in Afghanistan with the IED?
"This learning-adapting process continues until either the player has won the game, or the robot has found the mines."
For the past three years, Cai has been developing a mathematical way of representing the choices and acquisition of information in such activities. After completing the new algorithm, he tested it against experienced Cluedo players, as well as players employing other types of game-playing algorithms.
Players using the new algorithm defeated players using artificial intelligence strategies such as constraint satisfaction, Bayesian networks and neural networks around 70 per cent of the time.
Cai and his team hope that the new algorithms will help in developing systems that attempt to mimic human thought processes and react quickly in the face of changing circumstances.
This would be useful not only in mine-sweeping applications, but such activities as security surveillance, airborne drone guidance and even criminal profiling.
