Watch this golf robot navigate to a ball by itself and sink a putt

1 year ago 103

Previous golf robots have required assistance from human operators, but Golfi can find golf balls on a green and work out how to hit them by itself

Technology 3 January 2023

By Alice Klein

A robot called Golfi is the first to be able to autonomously spot and travel to a golf ball anywhere on a green and sink a putt.

Golf-playing robots have been developed before, but they have needed humans to set them up in front of a ball and program them to make the correct swing. The most famous is LDRIC, a robot that hit a lengthy hole-in-one at Arizona’s TPC Scottsdale golf course in 2016.

In contrast, Golfi, engineered by Annika Junker at Paderborn University in Germany and her colleagues, can find golf balls and wheel itself into place thanks to input from a 3D camera that looks down on a green from above.

The camera scans the green and an algorithm then approximates the surface before simulating 3000 golf swings towards the hole from random points, taking into account factors such as the speed and weight of the ball and the friction of the green, which are described by physics-based equations.

This trains a neural network to work out how hard and from what angle the robot should hit any ball.

“It’s like how professional golfers often practise their strokes on a green the day before they play,” says Junker, who presented the robot at the IEEE International Conference on Robotic Computing in Naples, Italy, in December.

After this, Golfi and a ball can be placed anywhere on the green and the robot will navigate to the ball and try to hit it into the hole.

Golfi was able to sink more than 60 per cent of putts on a flat, 2-square-metre, indoor green. The robot isn’t suited to outdoor greens because it requires a power connection and the 3D camera to be mounted above the green.

However, the idea of Golfi isn’t to win golf tournaments. It is meant to show how robotic applications can be simplified by combining physics-based models with machine learning, says team member Niklas Fittkau, also at Paderborn University.