Exhibitors & Products
Event Search

SCHUNK GmbH & Co. KG is in Hannover to address the radical change sweeping through industrial gripping solutions. Although gripping processes used to be mainly geared towards high productivity and process reliability, the focus is now also on flexibility in conjunction with the smart factory. Until recently, industrial gripping has been relatively rigid - not only do gripping systems have to know the geometry of the parts, but also the exact pick and place position. This means a reliable handling process can currently only be guaranteed when parts are always fed into the handling system in exactly the same way via predetermined travel paths and by specifying target point coordinates. However, as digitization progresses, the highly automated, fully networked and autonomous production system is beginning to take shape.

There is no denying that the use of Artificial Intelligence (AI) plays a role in this. There are already initial cognitive intelligence applications for grippers that use cameras, enabling the robot to learn intuitively from operators and then carry out the gripping tasks independently. SCHUNK deliberately designs practical - i.e. industry-oriented - handling processes for these applications by limiting the number of component variations, thus streamlining the classification and training process. As part of an initial use case that utilizes machine learning to classify workpieces and gripping processes, interlocking building blocks are randomly combined and presented to a lightweight robot in a random arrangement on a working surface. By interacting with 2D or 3D cameras, the self-learning system rapidly increases gripping reliability after only a few learning cycles. With each grip, the gripper learns how to successfully pick up and move the workpiece.

After only a few training sessions, the network classifies how to handle the range of workpieces and the resulting combination options. The gripper knows how to pick up and move the workpiece based on learned experience. Thanks to the intelligence of the algorithm, the gripper can classify future combinations and arrangements of workpieces on its own after only a short period of training. According to the developers, this allows the system to handle parts autonomously depending on the situation. The algorithms are continuously adapted using AI methods, which means previously unrecognized correlations and be explored and the handling process further refined.