In Brief
A robot with deep learning capabilities and depth-sensing cameras has won this year's Amazon Picking Challenge.

Deeper Learning

While everyone keeps saying that robots are not a job security threat, it is also true that robots are steadily getting better at tasks. Enter this little bad boy, the robot that won Amazon’s Picking Challenge. A team of engineers from Netherland’s TU Del have won this year’s challenge, both in the picking and stowing finals. They dubbed their creation “Delft.” The cool thing is their robot is no ordinary warehouse bot; it relies on a suction cup, a “two-fingered” gripper, and the combination of deep learning artificial intelligence and depth-sensing cameras to get the job done.

The machine uses and studies 3D scans of the stockroom items to help it decide how to manipulate items. The arm got a near-flawless score in the stowing half of the event. Also, Delft was over three times faster at picking objects than last year’s champion (100 per hour versus 30).

The robots were scored on their ability to correctly select individual items from shelves. Picking items mixed in with other objects would score a contender more points. The items used represented a cross section of products commonly found in Amazon’s warehouses.

Enhancing, Not Replacing

There’s no need for Amazon’s human workforce to fear. Even though this year’s numbers are impressive, Amazon is quick to point out that there is no move to replace workers just yet. Human workers typically pick 400 items per hour, and they won’t suffer the 16.7 percent failure rate of the Picking Challenge leader.  “Robotics enhance the job for employees but does not replace them…In fact, we continue to hire. Many of those roles are being created in buildings where employees are working alongside Amazon robotic drive units,”said an Amazon spokesman to TechRepublic.

Amazon currently uses robots in 13 of its 123 warehouses worldwide. It also has plans to use delivery drones to bring packages to consumers in less than 30 minutes.