GAIN is a deep learning-based sorting add-on for TOMRA’s AUTOSORT machines.
By classifying objects from sensor data, GAIN enables the sorting of objects which could previously not be separated with high levels of purity.
In contrast to classical machine learning, deep learning does not require any programming but learns individually from huge amounts of collected data.
Learning individually allows for the adaption to the ever-changing waste streams and to detect new and covered objects, which could not be sorted before.
The first version of GAIN has been trained to eject silicon cartridges from PE-streams by using camera information.
GAIN learned to separate common forms of a silicone cartridge and nearly all smaller double-cartridges.
TOMRA reinvests approximately 8% of its revenue developing sensor-based technology geared to serving our customers while protecting our precious resources.
TOMRA is a leading provider of sensor-based sorting technologies in the waste and metal recycling industries. With over 6,000 of TOMRA Recycling’s sorting machines installed worldwide TOMRA ensures that high-purity fractions are extracted from varied recycling and waste streams for further processing and recycling.