The August 29, 2011 edition of ACM TechNews:
Football Analysis Leads to Advance in Artificial Intelligence
Oregon State University News (08/18/11) David Stauth
Oregon State University (OSU) researchers have developed an artificial intelligence-based tool that combines computer vision, machine learning, and automated planning to create a system that could improve a variety of fields. The researchers used football to train the system to learn a complex activity. The goal was for the computer to watch video of football plays, learn from them, and then design plays and control players in a video-game setting. “This is one of the first attempts to put several systems together and let a computer see something in the visual world, study it, and then learn how to control it,” says OSU professor Alan Fern. He says that this type of system could be useful in hospitals to help monitor patients, at airports, or by the military to improve supply chains for troops in the field. “Ultimately these systems should be able to see what is happening, understand it, and maybe even improve upon it,” Fern says. The OSU researchers outlined a proof of concept in action recognition, transferring that recognition into procedural knowledge, and adapting those procedures to new tasks.