Robot Arm Uses AI to Get a Better Grip

SCHUNK displays its intelligent gripping solutions at Hannover Messe 2019.

Imagine a robotic hand that can identify, examine and handle objects autonomously, without needing a human operator to guide it. That’s what SCHUNK aims to create with its line of intelligent grippers.

At this year’s Hannover Messe SCHUNK will showcase its flagship PGM-plus-P pneumatic gripper, a DGUV-certified gripper for collaborative applications, and a flexible mechatronic gripper controlled through PROFINET. The company has already brought to market its Co-act JL1 Gripper, which SCHUNK claims is the world’s first intelligent gripping module for human-robot collaboration.

These robots use AI to learn how to identify and manipulate objects—and are less reliant on a human controller to tell them what to do. SCHUNK’s intelligent grippers adjust their behavior in real time depending on what it’s gripping. The gripper uses a decentralized control architecture with diagnosis and safety functions carried out in parallel—allowing it to quickly identify and react appropriately. This in-hand calibration technology will enable the implementation of extremely flexible, autonomous gripping scenarios.

SCHUNK PGN-plus-P gripper and change system

“Industrial handling will be reinvented in the coming years,” said Dr. Markus Gluck, Managing Director of Research and Development at SCHUNK. “Tomorrow’s handling solutions will act more independently. The market is already demanding gripping systems that are quick and easy to set up and that automatically adapt to varying gripping situations.”

Currently, each step of a robotic gripping task is programmed ahead of time and the robot performs its tasks without variation. This means that a specific arm and gripper are needed for each specific task. Grippers are an essential part of robotic functionality, especially for material handling and pick-and-place applications where a robot picks up and puts down objects. And these tasks are often performed in high-speed, high-volume work environments—meaning the robot has to perform quickly and accurately each time. As industrial processes become more efficient and more automated, the demand on gripper technology is evolving.

In addition, robotic automation is moving away from replacing human workers to working alongside them—which means the grippers must have the ability to collaborate with humans safely and efficiently.

“It is much more important to make people, rather than the technical system, the main focus of all the considerations,” said Gluck. “The worker has to trust the robot. The gripper has to adapt to the human—not the other way around.”

Read more about how AI is improving factory processes at AI Could Help Improve 3D Printing Accuracy.