AI News, Team Delft Wins Amazon Picking Challenge

Team Delft Wins Amazon Picking Challenge

With warehouses full of robots that can move shelves from place to place, the only reason that Amazon needs humans anymore is to pick things off of those shelves and put them into boxes, and pick other things out of boxes and put them onto those shelves.

From a “stationary and lightly populated inventory shelf” just like the ones that Kiva robots carry around, teams had to train their robot arms to autonomously do the following: Stow Task — The stow task is to move 12 target items from a tote into bins on the shelf.

The actual items involved were selected “to represent popular kinds of products,” potentially including “books, cubic boxes, clothing, soft objects, and irregularly shaped objects.” Each robot had to do as much picking or stowing as it could in 15 minutes, and points were awarded for

And this is all totally autonomous, which the rules are unambiguous about: “no human interaction (remote or physical) is allowed with the Robot after uploading the work order and starting the robot.” Got all that?

By way of comparison, humans can pick something like 400 items per hour at full speed, while Delft’s robot is currently clocking in at about 100 items per hour, with a failure rate of just over 16 percent.

Delft managed 214 points in the Stow task by cramming 11 items into densely packed bins, and 105 points in the Pick task, which was a tie with Team PFN from Japan(as a tie breaker,judges had to use video replay to determine which team had the fastest first pick).


As the largest on-line retailer in the world, Amazon has numerous warehouses stocked with millions of items that must be ready to be packed and shipped at a moment's notice.

To this end, the Amazon Robotics Challenge has become an excellent venue for research groups and companies to show case their latests solutions and compete against the best.

The challenge consisted of 2 tasks: a pick task to remove 12 specific items from an Amazon Robotics shelf and place them into a tote, and a stow task to move 12 items from a tote and place them into a partially full shelf. For the stow task 12 units started in the tote and the remainder were in the shelf.

Before the challenge the teams were given a rough distribution of how many 2 item bins versus 5 item bins there would be, but not told specifics of how items would be arranged.

The finalists included renowned robotics groups like Mitsubishi Motors, UC Berkeley, Georgia Tech among others. Amazon held the first ever Amazon Picking Challenge at ICRA conference 2015 Team MIT is striving to solve the general problem of autonomously retrieving objects from warehouse-type shelves.

The robot has purpose-built canals that allow routing all cables and airlines internally, this enables the robot to perform manoeuvres in tight spaces without risking pulling on a connector.

Amazon Milton Keynes - Stowing

MKWeb reporter James Averill follows a Kindle Fire as it makes it way through the Amazon distribution centre in Milton Keynes.

Amazon Warehouse's processing