This robotic pitcher can replicate any human litter

Who is your favorite baseball pitcher? Shane McClanahan? Sandy Alcantara? Justin Verlander? Whoever you said, two of the top sports tech companies in the US – Rapsodo and Trajekt Sports – have teamed up to build a robotic version of it, and the results are reportedly eerily accurate.

Okay, so we’re not talking about walking, talking, and standing standalone robots, great as a sci-fi-tinged MLB ad would be. However, Rapsodo and Trajekt have combined their considerable powers to throw a range of different technologies at the problem of building a machine capable of accurately simulating the pitching style of the player you wish to practice batting against – and they may have just made it, too.

Their solution brings together the Trajekt Arc, a pitching robot that uses super-precise motor control, image processing and machine learning to throw perfect, consistent pitches, and Rapsodos PRO 3.0, a ground-based radar and image-based surveillance system designed for accurate pitch- and measure litter data.

Traject Arc™ Explainer Video (2022 Limited Release)

Hell, the setup even has a video projection system that lets you see life-size footage of the player slamming straight at you. (This features pitcher footage by default, although teams can also upload their own video for additional customization.) Think of it as the future of pitching training as we know it.

“We seek to be at the forefront of building baseball pitching machines that can replicate and control all the degrees of freedom required to replicate a human pitcher,” Joshua Pope, CEO and co-founder of Trajekt told Digital Trends.

“It’s really designed and geared towards improving the player’s performance on the field,” added Seth Daniels, product director at Rapsodo.

A Brief History of Pitching Machines

The first baseball pitching machine was invented by Princeton professor Charles Howard “Bull” Hinton in 1897. Hailed somewhat menacingly as a “baseball gun” and using gunpowder to blow up baseballs, it was alternately reportedly inaccurate and dangerous. Luckily, technology has evolved from there.

A variety of pitching machines were invented throughout the 20th century, with one notable creation being Paul Givagnoli’s 1952 arm-style pitching machine. This machine flung the ball onto the plate with a pitching style intended to mimic that of a real pitcher’s arm-throwing action. For the first time, a player could practice endlessly in a batting cage against a machine capable of recreating what it’s like to face off against a human pitcher.

For most of us, pitching machine development could probably stop right there. Add in some incremental tweaks and mods and a machine that can hit a little like a human is enough to work with us to improve our batting average. If you really need to imagine hitting a superstar pitcher, just do what most of us do when we’re standing in front of a basketball hoop in the backyard: use a little imagination.

But the pros are different. At this level, the differences that separate an MLB home run leader from a follower are barely noticeable. For these elite athletes looking for the slightest edge over their opponents, the idea of ​​being able to train against a pitcher’s exact arsenal and pitch characteristics before stepping onto the pitch could make all the difference. This is where the combination of Trajekt Arc and Rapsodos PRO 3.0 comes into play.

Train your pitcher

“The way it works is that any tracking technology used to measure the player’s pitch can be used as a data source that is fed into Trajekt,” said Joshua Pope.

In many training cases, this involves getting your pitcher to throw pattern pitches, which are then used to teach the device thanks to its ball-tracking technology. A few throwing patterns are enough to teach the Traject Arc the necessary pitching metrics like speed, spin, movement and shot zone location. Once this data is collected, this pitch is added to the device’s system to be available for future training sessions. Think of it like the Netflix of pitches.

LA Dodgers pitcher Tony Gonsolin

But what if you want to recreate the court of a specific opposing player—let’s say the Los Angeles Dodgers’ Tony Gonsolin—that you’re going to play against in an upcoming game? A call to Gonsolin (“Hey, Tony. We’re playing you next week and we were just wondering…”) is probably out of the question, but you’re out of luck. It’s also possible to train the trajectory arc with pitch tracking data from a source like Hawk-Eye, which tracks pitches for MLB games, still allowing you to create a convincing recreation of a competing pitcher’s performance on the field .

“There’s such a thing as the nine-parameter fit that completely defines the ball’s trajectory, break parameters, and speed-spin,” Pope said. “What Trajekt does is we control the release state with high precision. As long as you have measured these release positions with any tracking system, you can use this as an upload. This data is ubiquitous at all levels of baseball.”

A secret weapon

Spoiler alert: sport is competition. This competition does not only take place on the pitch, court, track or field. Teams compete for the most promising players and yes, the best new technologies to support them.

Because of this, neither Daniels nor Pope have been able to disclose which MLB teams are currently using their pitching technology, although they noted that it is currently being used on the practice pitches of seven such teams. (Previous Rapsodo technology is used by all 30 MLB teams.)

“No, we can’t tell [that information]’ said Pope. “I think a lot of people see that as a competitive advantage that they want to keep. We respect that and [therefore] to be treated confidentially.”

However, if it turns out to live up to its promise, you can bet such technology will catch on to other teams — and maybe outside of MLB, too.

“Our flagship product…is the most accurate replica of a pitcher we’ve ever seen on a pitching machine,” said Pope. “That will always be our premium offering and I think the use case with the greatest value will be with the MLB teams that can upload video data that can upload all the field data that they have from games for premium training . However, we are working on lighter versions that are more portable and retain some key features such as pitcher hoist video projection [and] the Sphere Alignment Control.”

Coming to a batting cage near you soon? Hey, there are worse ways to up your game than taking on MLB Allstars – virtual or not.

Editor’s Recommendations

Comments are closed.