Robotic Arms Are Using Machine Learning to Reach Deeper Into Distribution

- Advertisement -

Advances in Technology Moving Automated Picking Systems from Lab to Labor-Strapped Warehouse

- Advertisement -

Experts say the technology isn’t going to replace human workers anytime soon. But the latest moves show warehouse robots are evolving as the computer vision and software that guides them become more sophisticated, allowing them to perform more tasks that have largely been done by people.

- Advertisement -

Puma North America Inc., a division of Puma SE,

is using multiple robotic arms to collect orders for clothing and shoes at a distribution center in Torrance, Calif.; The company plans to install more robots at another site outside Indianapolis. Nimble Robotics Inc. technology, whose customers include Best Buy Co.

- Advertisement -

And Victoria’s Secret & Co., uses a combination of cameras, grippers and artificial intelligence to break items out of bins that another automated system delivers to workstations typically staffed by people. If the robot has trouble lifting an object, remote operators are on hand to assist.

The robots perform with about 99% accuracy, as well as their human counterparts, and can run for two shifts straight, said Helmut Leibrandt, Puma’s senior vice president of supply-chain management for Americas.

“I believe automation is the future,” said Mr. Lembrandt. “It does not mean that we reduce manpower… it is largely the labor shortage that we face.”

Interest in robotic picking has increased significantly in the pandemic as e-commerce orders rise and competition for workers intensifies, fueling widespread demand for logistics automation.

“Robotic picking technology has a niche in the warehouse automation market these days, but it is growing rapidly,” said Ash Sharma, managing director of market-research firm Interact Analysis. That share of the market will reach $1.34 billion in 2025, compared to an estimated $137 million last year, the firm projects. Interact Analysis estimates that the broader warehouse automation market was worth about $36 billion last year.

Last year SB Logistics Corp and SoftBank Robotics Corp, subsidiaries of Japan-based conglomerate SoftBank Group Corporation

, opened a highly automated fulfillment center in Ichikawa, Japan. Center uses robotics technology from SoftBank-backed provider Berkshire Gray Inc.

To pick up and pack items including electronics, household products and packaged goods. The facility stores about 50,000 products, with robots doing about half the picking, and aims to eventually automate all tasks, said Steve Johnson, president and chief operating officer of Berkshire Grey.

Some businesses are deploying high-tech mechanical weapons for other delivery tasks. Bimbo Bakery USA, a division of Mexico’s Grupo Bimbo SAB, uses robotic grasping technology from startup Dexterity Inc. to pick up and pack bread at certain locations.

Greenwich, Conn.-Based GXO Logistics Inc.

The camera is using a robotic arm equipped with vision to help speed up the order fulfillment process at a warehouse in the Netherlands.

The system, developed by Austrian logistics-automation company Knapp AG and AI startup Covariant for a GXO apparel customer, places manually selected items into an overhead sorting system that can store items in holding areas to ensure to ensure that the items are picked up in a different order. At the same time the human gets to the packer.

The company also uses mobile robots that don’t pick up objects to help workers navigate corridors to locate objects.

“The growth opportunity is to be able to tie three things together” – the picking arm, the ability to recognize and understand AI-enabled objects, and mobility, said Phil Shaw, operations director for GXO Logistics Europe. “To take it down the aisles, that’s the future.”

The developers are still working on the kinks. Machines excel at repetitive tasks in certain environments, but teaching them to handle a variety of items in warehouses has been a challenge.

A shortcut to help machines learn faster is a strategy used by providers including Nimble and San Antonio, Tex.-based Plus One Robotics Inc. in which humans monitor machines and handle if a robot stumbles. Takes.

“It’s possible that we may never achieve 100% automation,” said Julian Cunihan, general partner at Planned Ventures, which he invested in Plus One in 2017 because of its remote-monitoring approach.

Right now, using robots to take orders makes the most financial sense in 24/7 operations with a limited number of products, said Hassan Dandashali, chief executive of Atlanta-based Dimatic Corp., a subsidiary of KION Group. AG

It is one of the largest providers of logistics and manufacturing automation.

“The pace of adoption is still evolving,” said Mr. Dandashali. “I don’t think we’re on the verge of not having human pickers any time soon.”

Write Jennifer Smith at [email protected]


- Advertisement -

Stay on top - Get the daily news in your inbox

DMCA / Correction Notice

Recent Articles

Related Stories

Stay on top - Get the daily news in your inbox