Or maybe computer scientists are simply letting football players think they matter, and they are really just data.
For artificial intelligence to get out of its 20-year rut, a computer has to be able to observe a complex operation, learn how to do it, and then optimize those operations or accomplish other related tasks. What if a computer could watch video of football plays, learn from them, and then design plays and control players in a football simulation or video game?
It can't. Not yet, anyway. As it turns out, football is very complex, and computers struggle to see and understand plays a coach or even an average fan would find routine, just like a 4-year-old could see a cartoon drawing of a chicken and say "that's a chicken" while a computer could not.
A new study in AI Magazine moves the ball forward a little.
As a computer tries to analyze this football play, the superimposed boxes show where the computer thinks the players are at the moment – and usually it’s right. This type of analysis is helping to develop artificial intelligence systems that can see, learn from and eventually improve complex operations. Graphic courtesy of Oregon State University
“Football actually makes a pretty good test bed, because it’s much more complicated that you might think both visually and strategically, but also takes place in a structured setting,” said Alan Fern, an associate professor of computer science at Oregon State University. “Using football, we created learning algorithms that allow the computer to see the plays, analyze them and learn from them. Ultimately these systems should be able to see what is happening, understand it and maybe even improve upon it.”
An OSU Beavers passing play, which is very fast-paced, designed to confuse the opponent, and based on complex rules; the ball could be thrown to any of several receivers and it still only works about half the time. For a computer that initially has no concept of pass routes and blocking, that’s difficult.
Our brains work easily in those sorts of tasks and it's one of the things 'Singularity' fans don't understand, and instead relegate to future advancements in computing power - consider driving home in your car. What you actually have to do is walk to the parking lot, check for other traffic as you cross the street, select the correct key to put in the ignition, back it up, consider the anticipated traffic to plan a route home, slow down and move a little out of your lane to avoid the child wobbling down the street on a bicycle, make sure you have enough gas. And so on.
The work could have multiple applications. Control and logistics planning is hugely important in industry, and even small improvements in efficiency could save billions of dollars. Computer vision and controls might be useful in hospitals or nursing homes to help monitor patients and see who needs care. Large operations such as an airport offer multiple control challenges, or the military could use such approaches to improve supply chains for troops in the field.
The research is still at a basic stage but could have commercial applications within a few years. The new study outlines a clear “proof of concept” in action recognition, transferring that recognition into procedural knowledge, and adapting those procedures to new tasks, the scientists said in their conclusion.
“One thing I’d also like to do is return the favor to the football team,” Fern said. “The study of these football plays is helping us to create intelligent computer system. When this is more fully developed, we should be able to actually apply it to football, maybe help coaches analyze an upcoming opponent, let the computer determine what they are doing and suggest a strategic nugget to the coach.”
The research has been supported by the National Science Foundation and the Defense Advanced Research Projects Agency of the U.S. Department of Defense. It is a collaboration of OSU and the Institute for the Study of Learning and Expertise in Palo Alto, Calif.