If freshly laundered towels or bed sheets from the industrial laundry are to be made ready for delivery to a hotel, a number of steps are required, including taking the laundry out of the basket and placing it lengthways on a conveyor belt before it is folded by the folding machine. This task can now be performed by industrial robots from setws, a start-up founded almost five years ago. A gripper arm pulls a piece of laundry out of the container and drops it onto a conveyor belt. A few meters further on, a second robot arm grips the piece of laundry at a corner, clamps it on one side and hands it over to the so-called sliding robot, which pulls the textile along the width. The stretched textile is transferred to the folding machine within a few seconds.

The materials that the founders of the start-up sewts are particularly fond of are tight in tension and loose in compression. So-called anisotropic materials have long been a challenge for gripper robots. This is because "textiles are flexible", as sewts co-founder Alexander Bley explains, "they change their shape when I hold them up". The founders laid the foundations for their later innovation during their studies at TUM. At the Chair of Carbon Composites, Alexander Bley studied the properties of technical textiles, which behave differently depending on the direction of loading. In a 'draping simulation', he developed an idea for handling flexible materials. Co-founder Till Rickert worked on autonomous driving at the Chair of Automotive Engineering. An important part of his research involved using synthetic training data to train AI algorithms. And Tim Doerks, who like Bley comes from the Carbon Composites Chair, is a specialist in building and testing prototypes.

The technical challenge for the first application was that the robot first had to learn how to grip an item of clothing in order to hand it over in a suitable form. Depending on how a towel is placed, for example, it can take on many different shapes. It can also be lined or checked, white or colorful. The founders of sewts play tricks to teach the robot these countless variations. They simulate the different shapes that a towel can take in the computer and generate their own (artificial) training data for the system. Instead of photographing or filming a towel from all sides and in all shapes and styles and feeding the system with this photo or video data, the computer generates these images itself. And now makes them available to the robot as training data. "We use synthetic data to train our AI algorithms," says Bley, who, like co-founders Doerks and Rickert, completed his Master's degree in Mechanical Engineering at TUM.

The company launch

The founders of swets - Till Rickerts, Tim Doerks and Alexander Bley (from left to right) - use robots and AI to prepare laundry for the folding machine.

© Andreas Heddergott / TUM

But it is not just this case study that keeps the three founders busy. In the 'Xplore' program of the UnternehmerTUM Innovation Center, in which start-up teams develop their business ideas, the future entrepreneurs have already come up with around 70 possible applications, from vehicle seat covers to awnings and cable harnesses. An important aspect of Xplore was to identify products that fit particularly well into individual markets. For the first application, the 'Xpreneurs' incubation program was about finding out who the customers of industrial laundries are, how big the market is in Germany and worldwide and what barriers to entry are important. The real starting signal was given after the Federal Ministry of Economics gave the green light for the 'Exist' grant, which supports start-ups over the course of a year. Meanwhile, the start-up secured a small six-figure sum as additional support via the 'Initiative for Industrial Innovators', in which UnternehmerTUM and the European Investment Fund were also involved.

The company, which has just under 30 employees, has already generated millions in sales with the systems it has sold to date. And the potential is far from exhausted: Alexander Bley estimates that 5,000 to 6,000 folding machines are sold in Europe and the USA every year.

Case study returns business

The second major case study now involves returns processing in online fashion retail. In a pilot with a large German retailer, the use of the new robot system has already been tested with returned garments. The difference to the use in the industrial laundry is that the range of garments is now much wider. T-shirts with long and short sleeves, with buttons, V-necks, pants with zippers: In future, the AI will have to learn all of this in order to prepare the garment for the folding machine.