A Smart Workcell for Automatic Pick and Sorting for Logistics

Vision guided robots are enjoying growing success in industry, thanks to their adaptability to unstructured contexts and applications. In typical bin-picking applications, a robot is guided to pick known rigid objects randomly placed inside a container. Given the objects' CAD models, it is possible to accurately estimate the object pose and to perform the grasp synthesis in a closed form. Unfortunately, in logistics, as in many other sectors, robotcs are required to manipulate polymorphic and deformable objects. In this work, we present a complete robotized pick and place solution for logistics able to address these challenges related to the variability of shapes of the objects. It exploits a model-less data-driven approach to bin-picking to detect boxes and parcels both randomply placed in containers or palletized. The proposed system will be easily adaptable to a wide range of applications, thus greatly improving its potential impact.