July 12, 2021
End-of-line packaging automation firm Pearson Packaging Systems and robotics software company Plus One Robotics have announced a partnership to offer easier solutions for complex packaging challenges for manufacturers, warehouses, and eCommerce fulfillment and distribution centers.
Plus One Robotics uses 3D cameras to identify three-dimensional geometric surfaces, edges, and corners of products to determine the size, shape, height and location in real time. A second layer integrates machine learning to boost the robot’s ability to accurately pick when vision data alone isn’t entirely conclusive. A third layer is a human-led supervision system called Yonder that closes any remaining performance gaps by enabling a remote robot controller to solve exceptions without delay while training the AI to adapt over time.
For the collaboration, Pearson plans to integrate Plus One Robotics’ PickOne and Yonder software into its depalletizing cell to enable handling of mixed or rainbow pallets. The companies said that this task could not be addressed efficiently before because reflective or newly introduced cases would cause frequent stoppages that required manual intervention, resulting in downtime and lack of labor savings. PickOne, however, scans the pallet layers to determine optimal pick positions. If the vision data is inconclusive, the system consults its library of AI data. If neither of those results in a high enough pick confidence, the system generates a Yonder request to call in human intervention. With a response time of under six seconds, a remote robot controller can efficiently handles the exception by manually selecting an item and its pick point. Yonder stores the responses to facilitate ongoing machine-learning and increased efficiencies over time, and crew chiefs can oversee several robots as part of Plus One’s 24/7 remote service offering.
“Imagine a spectrum of autonomy,” said Erik Nieves, CEO of Plus One Robotics. “On the left, you have a huge force multiplier but no flexibility. All it can do is what it was programmed to do. On the right, no force multiplier but a lot of flexibility. Both are successful business models but what’s missing and where the real action happens is the missing middle of supervised autonomy. One person responsible for many robots.”
The companies said AI-driven vision can be beneficial in warehouse, eCommerce fulfillment and distribution centers that handle a multitude of SKUs. In manufacturing, those that offer popular party mixes or variety packs are also increasingly interested in improving efficiencies through the help of AI and vision-powered automation, they added.
Michael Senske, president and CEO of Pearson Packaging Systems, said the partnership would be an opportunity to automate increasingly complex tasks with consistency and simplicity. “Since we are nowhere near replacing humans with the ability to think, reason and learn, supervised autonomy gives us the ability to handle tasks such as sorting random, overlapping or overhanging products or introducing new SKUs without programming in an efficient way,” said Senske.