Tasks Were Harder, but Result Better, as a Dutch Team Wins the Price

Earlier this year, Amazon held its second robotic picking challenge in conjunction with the RoboCup 2016 event in Germany, but it just announced the winners last week.

The focus is on robotic "piece picking of individual items. On the contest web page, Amazon notes that "Commercially viable automated picking in unstructured environments still remains a difficult challenge. It is our goal to strengthen the ties between the industrial and academic robotic communities and promote shared and open solutions to some of the big problems in unstructured automation."

Supply Chain Digest Says... It appears to SCDigest that we are not far away from automating even the most difficult picking challenges in the distribution center. What do you say? Click here to send us your comments Click here to see reader feedback

The challenge was a bit different this year, but again the core of the contest is to automate the challenging piece-picking process in a distribution center. The contest was broken into two parts, basically a putaway task and then a picking task.

From a "stationary and lightly populated inventory shelf" just like the ones that Amazon’s Kiva robots carry around, teams had to train their robot arms to autonomously both putaway 12 items into bins on the shelf and then pick another 12 items from the shelf into a tote.

On the putaway task, the 12 target items in the tote represented about 10 different products and were arranged so that some items are partially or completely blocked below other items.

The picking tasking was to move 12 specified target items from the shelf into a tote, with each bin containing between one and 10 items.

The actual items involved were selected to represent popular kinds of products, 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 stowing and picking each item, with more points going to items that were stowed in or picked from bins that were cluttered up with other stuff.

In the end, a team from Netherlands formed by a Delft Robotics and an organization called the TU Delft Robotics institute – both named for a city there - won both parts of the challenge. The winning Dutch team smartly used two types of tools, a suction type device for most items and a grabber hand for a few items for which the suction approach would not work.

You can see a short clip of the winning robot in action at the contest below.

Team Delft's Winning Robot

The Delft team's robot managed to pick items from a mock Amazon warehouse shelf at a speed of around 100 an hour, with a failure rate of 16.7%. Team Delft walks away with a $50,000 prize - actually rather low for these types of contest, and the team says it will open source its control software.

(Article Continues Below)

While picking rates is still very slow compared to a human, the robots are making much progress.

The picking part of the challenge was much harder than in 2015, with a greater number of objects to choose from packed into more densely-filled bins. Despite this, just four teams failed to score any points at all, compared to 2015, when half of the robots failed completely. Six of the teams in 2016 also managed to score more than 40 points, which would have been enough to earn them third place in 2015.

In the case of the team from Delft, a key was use of was artificial intelligence. The researchers used so-called deep learning techniques - which can churn through vast amounts of data to look for recurring patterns - to analyze 3D scans of the objects their robot had to pick and replace. A custom gripper-suction arm attached to an off-the-shelf Yaskawa robotic arm was used to do the actual mechanical work, while the AI-powered software gave the robot an edge over the competition.

Although the picking challenge is essentially a try-out for Amazon's own warehouses, the company insists that its intention is not to make its human workers obsolete. "Robotics enhance the job for employees but [do] not replace them," a spokesperson for the company told TechRepublic. "In fact, we continue to hire. Many of those roles are being created in buildings where employees are working alongside Amazon robotic drive units." The spokesperson added that in the company's robot-filled warehouses the end result was "a symphony of humans and technology."

It appears to SCDigest that we are not far away from automating even the most difficult picking challenges in the distribution center.

Are we close to automation of the challenging piece picking process? Let us know your thoughts at the Feedback section below.

Your Comments/Feedback