Andrew Sun-Zhuang built a $260 AI pitching machine with 94% strike accuracy

Andrew Sun-Zhuang, a 7th grader at The Evergreen School in Shoreline, Washington, plays baseball and is constantly trying to improve his batting performance. His hit rate is 95 per cent against a batting machine but only 35 per cent in real life.

According to the Society for Science, he decided to train an AI to produce a better pitching machine. Using a Raspberry Pi, a camera, servos and motors, he built VisionStrike, a portable AI-powered pitching machine. It pitched with 86 per cent accuracy within a strike zone for front-toss pitching and threw fastball strikes with 94 per cent accuracy. The final prototype cost only $260.

How did Andrew build the $260 AI pitching machine

Andrew began by building his own pitching machine. He used a microcontroller, a Raspberry Pi, a camera, servos and motors.

The Raspberry Pi later ran the AI model that controls the machine. For the AI itself, Andrew trained a model on 200 different pictures of a batter, himself. The model detected six key points on every image: the end of the bat, the wrist, elbow, shoulder, hip and knee. The model used these points to determine where the bat strike zone should be.Once the model is loaded onto the Raspberry Pi, it calculates the right angle after a batter has stood still for two seconds, according to the project description.

The machine then launches the ball. This allows the machine to vary pitch location based on the batter, which Andrew identified as the missing feature in other pitching machines.The results were measured in two settings. The machine pitched with 86 per cent accuracy within the strike zone for front-toss pitching. For fastball pitching, it "threw" strikes with 94 per cent accuracy and balls with 97 per cent accuracy.

How much did Andrew’s final AI pitching machine prototype cost

Andrew's final prototype cost only $260. The project description states that this is a major improvement over pitching machines, which usually cost much more. Baseball has been part of Andrew's life since he was five, when he started in Little League. Last summer, he played both All-Star Majors baseball and water polo. "I love baseball because of the connections I build with my teammates and the challenges I face during games," he says.

"The pressure of competition pushes me to stay focused, build resilience, and constantly strive to become a better player." Andrew also enjoys robotics and has taken part in several robotics programmes. "I have a deep passion for robotics because it is an active, hands-on blend of STEM that can solve real-world problems," he says.