in Germany at University of Paderborn The researchers did just that with the Golfi, a machine that uses a neural network to figure out how to line up a hit and how hard to hit the ball to get it into the hole from anywhere on the course.
Robot, Microsoft Kinect 3D camera It takes a snapshot of the green and simulates thousands of random shots taken from different locations. It also takes into account factors such as the rolling resistance of the turf, the weight of the ball and the starting speed. Paderborn PhD student Junker, to IEEE Research He said it took five minutes to train Golfi on simulated golf shots, while it took the team 30-40 hours to do so, adding data from real-life shots to the system.
Kinect technology is now used in robots!
golf Once it finds the right position for the kick, it moves towards the ball and uses a belt-driven gear shaft with a putter attached to deliver the kick. Still, the robot can’t get the ball into the hole every time. Junker, says the robot has a shot percentage of 60-70. That’s still a better shot rate than most amateur golfers, and at least when missing Golf Happy Gilmore Like it’s not getting out of control. However, Golfi sometimes goes over the ball and takes it out of position.
researchers robot for now only They’ve tested it in the lab, so real conditions like pothole greens or steep slopes can pose problems for this system.
In any case, researchers PGA Tour He didn’t set out to build a robot that could compete with his pros. They hope the techniques they used at Golfi could be used in other robotic applications.