ARTIFICIAL INTELLIGENCE
BEFORE AND AFTER: Intelligent automation was a no-brainer for the Osterman Laundry in Germany (see box copy, below)
Jensen-Group has long championed the benefits of robotics and artificial intelligence having tied up with innovative AI developer Inwatec some years ago. Now Inwatec is very much part of the Jensen family. Inwatec’s ODIN.Xray scanner is capable of scanning and subsequently rejecting garments containing harmful foreign objects, such as pens or needles. To achieve the best possible results, cutting-edge AI software is utilised to continuously train the machine according to the specific requirements of each laundry. The quality of detection ultimately depends on the types of garments being scanned. Jensen has collected millions of images, which are segmented into samples for training a neural network with approximately five million of those samples. Jensen’s goal is to provide the neural network with enough samples to have seen most, if not all, items that pass through a laundry. Neural networks excel at identifying items they have encountered before. Hence, we aim to provide as many examples as possible of what accepted items should look like (buttons, zippers) and what foreign, unwanted objects (knives, scalpels, scissors) should look like. Detecting metal is relatively straightforward, but identifying plastic items is more challenging. “The initial version of ODIN did not rely on AI. By transitioning to normal computer vision with AI, we have increased the detection rate to up to 99%. Taking a picture with an X-Ray scanner is not a complex task, but finding all the undesired items while accepting items belonging to a garment is. The AI in ODIN ensures the system differentiates between
@LCNiMag FROM LAUNDRY CART TO ROBOT
“I believe that laundries will not be able to survive without robots in the future. All laundries are experiencing a shortage of staff,” says managing director Bernhard Ostermann of Ostermann Textilpflege, based in Esterwegen in north-west Germany, which has been in business for almost 60 years. The laundry’s recipe for success includes a constant drive to modernise. “Over the decades, we have always pushed ahead with further developments. “The next step is robotics: since 2023, the automatic dry work line by Kannegiesser has been the heart of the laundry. The special feature here: Pre-sorted laundry batches are loaded manually from the laundry trolleys into the dry work line - without a fully automatic monorail bag storage system.
“The robot has the advantage for us that we are much faster in production. This means that the items come out of the machine more continuously,” says Bernhard Ostermann. “At 700 items per hour, the output meets Kannegiesser’s specifications.” He adds that the system achieves this output, for example, when processing mixed batches for hotel customers with hand towels, shower towels, bath towels and bath mats. After drying, the batch is pre-sorted manually: Employees sort out items that the robot cannot process. For example, these are fitted sheets and incontinence pads. The pre-sorted batches are then loaded from laundry carts into the automatic dry work line, which then feeds, folds, sorts and stacks each item fully automatically. Finally, the finished stacks receive packing slips via the Kannegiesser Pack & Label system. “With the Pack & Label connected, the robot can develop its full potential,” says Bernhard Ostermann. In this way, he adds, the laundry can prepare its goods directly for shipping. Of course, the dry work line only unfolds its full potential in fully automatic operations with
modern monorail bag systems. However, Ostermann Textilpflege shows that it is also a perfect solution for a semi-automatic operation with laundry carts.
laundry items that need to be rejected due to the presence of unwanted objects.’ The
HEIMDAL.camera is built upon AI to sort products based on their visual characteristics, such as colors, patterns, textures, and even size. CouUpled with intelligent software, HEIMDAL can distinguish between different types of laundry articles. Each project receives its unique set of data, which requires training for the specific sorting composition and product portfolio. Currently, we have
various systems in operation for workwear, linen, and mixed products. Even without RFID, HEIMDAL can achieve higher sorting accuracy than manual sorting.
The input for HEIMDAL is also an image, but unlike the X-Ray image, it is a real color photograph. The system is similar to ODIN in that it employs a neural network to create a fingerprint of the item, enabling precise identification, distinguishing between items such as small towels and large towels.
May 2024 | LCNi 25
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37
