Fizyr

World class algorithms

Fizyr applies deep learning to enable automated picking of unknown items for years. Our algorithms provide over 100 grasp poses each second, including classification to handle objects differently, but also perform quality controls and detect defects to prevent damaged items from being placed on a sorter. Fizyr vision software enables a high level of autonomy in robotic picking solutions to deal with unstructured environment. It helps picking solutions to smoothly handle complex conditions such as deformation, damage, wrinkles, texts or any other varying pattern on the items/packages .

Fizyr algorithms provide all relevant information, including:

• Segmentation (incl. white on white flats or reflective bags)
• Classifiers of type of parcel (incl. box, bag, envelope/flat, tube, cylinder, deformable, etc.)
• Determining outliers or non-conveyables(i.e. damaged goods)
• Best possible grasp poses in 6 DoF
• Multiple ordered poses per object