BALTIMORE — We've all heard about the torpedo bat fad that's taken over Major League Baseball.
For anyone unaware, teams and players around the league have begun using a newly developed bat many believe can boost home run capability.
The torpedo bat is the brainchild of a physicist from MIT.
Teams buying into the idea include the New York Yankees.
Now student researchers at Johns Hopkins University are trying their hand at analyzing baseball bats, using artificial intelligence (AI).
They've partnered with the hometown Baltimore Orioles, using AI powered “computer vision” to improve custom lumber designs.
The goal is to speed up the normally slow process of manually measuring specific bat dimensions. Sometimes just one bat can take up an hour.
According to members of the Johns Hopkins University Sports Analytics Research Group, half the battle entails customizing a bat aligned with a hitter’s preferences.
“Subtle differences in handle diameter and contour can affect a batter’s comfort, control, and confidence at the plate,” said Xiaojian (Jason) Sun, a graduate student, and Kevin Wu, a junior at JHU. “For professional players who are closely attached to their bats, even minor variations in the handle can significantly influence performance. That’s why analyzing the full profile of a bat, from knob to barrel, is essential.”
So how is this done?
By using high-resolution images of each bat allowing for the computer to calculate its length and diameter at precise one-inch intervals.
Within minutes a complete digital profile of the bat is downloaded, which researchers say far exceeds manual methods.
“This opens the door to faster iteration, better data-driven decisions, and the ability to tailor bats more effectively to players’ needs—without compromising on compliance with league regulations,” said Sun and Wu.
The University says talks are underway to create a lab at a Baltimore Orioles team facility.
