Amazon robot competition won by shelf stacking AI that could one day be used in warehouses

The latest winner of Amazon's annual robotics competition is a robot arm that uses deep learning AI to stock shelves

Emma Boyle
Tuesday 05 July 2016 18:21 BST
Comments
Amazon's ‘fulfilment centre’ in Marston Gate, Milton Keynes
Amazon's ‘fulfilment centre’ in Marston Gate, Milton Keynes (Getty Images)

Your support helps us to tell the story

This election is still a dead heat, according to most polls. In a fight with such wafer-thin margins, we need reporters on the ground talking to the people Trump and Harris are courting. Your support allows us to keep sending journalists to the story.

The Independent is trusted by 27 million Americans from across the entire political spectrum every month. Unlike many other quality news outlets, we choose not to lock you out of our reporting and analysis with paywalls. But quality journalism must still be paid for.

Help us keep bring these critical stories to light. Your support makes all the difference.

The Amazon robotic Picking Challenge is a now annual competition that searches for robots that could one day work in the company’s vast warehouses and its second champion has been announced.

This year’s winner was a joint effort, created by TU Delft Robotics Institute from the Netherlands and the company Delft Robotics. The team’s robotic arm used a combination of a suction cup, a gripper, a depth-sensing camera, and deep learning artificial intelligence to pick and stow items from a mock Amazon warehouse shelf with greater speed and accuracy than the 15 other entries in the competition. TU Delft’s creation’s greatest asset was its adaptive deep learning which allowed it to scan the different shapes and sizes of the objects it was picking up and adjust how it manipulated them accordingly.

The robot was able to pick items from the shelf with a speed of over 100 items per hour which is an impressive three times faster than last year’s winner, even though Amazon had made the challenges much tougher “with denser bins, occluded items, and products that are more difficult to see and grasp.”

That said, though TU Delft’s robot arm significantly improved on the performances of last year’s competitors it still has nothing on human workers who can typically manage to pick over 400 items per hour without anywhere near the same failure rate.

The competition is essentially Amazon's Next Top Robot, but Amazon stresses that it has no intention to completely replace its human workers with robots, telling TechRepublic “Robotics enhances the job for employees but does not replace them.” Amazon also pointed out that since it bought Kiva robotics in 2014 and started using Kiva robots in its worldwide fulfilment centres, the number of human employees in these warehouses has only continued to grow: ”the data shows that the more robots we put into our FCs, the more jobs we create.”

The Kiva robots that Amazon currently uses don’t actually have any dexterity and are instead used to move and lift items. Amazon hopes that this annual competition will encourage innovation and result in robot workers capable of more complex actions to further augment the human workforce.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in