sewts GmbH, a German tech startup based in Munich, creates autonomous robots that handle textiles, like clothing, and anticipate how they behave using 2D and 3D cameras from IDS Imaging Development Systems GmbH.
The textile and garment industry has faced supply and energy issues in recent years and is threatened by future issues that could further hinder production, like labor and equipment shortages. While moving the production of clothing to Europe can address some of the supply chain issues, it presents additional labor costs.
sewts hopes to alleviate these issues and has set its sight on a particular application, large industrial laundries. While many processes at industrial laundries are already automated, like the folding of clothes, human workers still need to manually spread out the laundry and feed it without creases into the machine, a monotonous and strenuous task that has a big effect on personnel costs.
The company’s robotic system can help alleviate these personnel issues by automating individual steps, like sorting dirty textiles or inserting laundry into folding machines. IDS cameras make up the image processing components of sewts’ robots.
Traditionally, clothing has been a challenge for robots to handle because of its malleability. Currently, available software systems and conventional image processing typically have limits when it comes to easily deformable material, limiting the abilities of commercially available robots and gripping systems.
VELUM, sewts’ robotic system, is able to analyze dimensionally unstable materials like textiles and handle them. This means VELUM can feed towels and similar linen made of terry cloth easily and without creases into existing folding machines.
This software combines commercially available robots, grippers, and cameras into one intelligent system. VELUM’s multi-camera system uses the Ensenso S10 3D camera and models from the uEye CP camera series.
These cameras are crucial for the system, as the robot needs to identify, both in 2D and in 3D, interesting features and gripping points on the textiles that are fed into the system after washing and drying. These textiles approach the system on a conveyor belt or in a container in an unordered manner, meaning the system can’t predict the shape or position of individual objects.
The cameras capture the different texture of the material and distinguish which hems there are on a towel and where its corners are.
“We match the images from the 2D and 3D cameras to have a higher 2D resolution together with the 3D data. So we use the respective advantages of the 2D camera, in this case the higher resolution, and the 3D camera, i.e. the precise depth data,” Tom Doerks, co-founder and CTO at sewts, said.
sewts developed AI software to process the data supplied by the cameras. This software uses features like the course of the seam and the relative position of seams to analyze the topology of the textiles. The program classifies these features according to textile type and class, and then translates these findings into robot commands.
“AI is at the core of our technology. Intelligent algorithms are needed to build adaptive systems that can cope with non-deterministic automation processes. That’s why we use the latest findings from AI research, refine them for our needs and finally put them together into a big whole,” Till Rickert, co-founder and CPO at sewts, said.
The company uses Convolutional Neural Networks (CNNs) and classical image processing to process the data, including IDS peak, a software development kit from IDS.
VELUM can significantly increase laundries’ throughput and increase their profitability, even in uncertain staffing situations. The company also hopes to add more applications outside of textiles to the system in the future.
Tell Us What You Think!