Teams competing in Amazon's third-annual contest tackle a problem that has kept companies from automating warehouses entirely.

July 27, 2017, 8:00 AM EDT

Sixteen teamsofrobotics researchersare traveling to Japan this weekto help Amazon.com Inc. solve its warehouse problem. The company has a fleet of robots that drive around its facilitiesgathering items for orders. But it needs humans for the last step picking up items of various shapes, then packing the right ones into the correct boxes for shipping. Its a classic example of an activity thats simple, almost mindless, forhumans, but still unattainablefor robots. Starting Thursday, the company is running theAmazon Robotics Challenge, the third annualcontest for robots that push those limits.

Amazon gets nothing out of this, directly. But their own robotics team can potentially pick up techniques, or even new colleagues -- it has hired people who have entered past contests. More broadly, having robots that could reliably carry out the tasks from the challengeon their own would be a big steptowardsfully autonomous warehouses, which theoretically could run faster,cheaper, and around the clock.

This raises uncomfortable questions aboutthe future prospects for warehouse workers. In May, therewere949,000 people working inthewarehouseand storageindustry in the U.S., making an average wage of just under $20 an hour,according to the Bureau of Labor Statistics. The number of people working in the warehouse industry has grown 43 percent overthelast decade, and wages have kept pace with inflation, even as a first wave of automation has taken place. Optimists argue that more automation leads to more growth, creating better jobs elsewhere. Pessimists are basically predicting that artificial intelligence will usher in an economic apocalypse.

Startupslike Right HandRoboticsand Universal Logic claim that theirsystemsare far more sophisticated than what has come out of Amazons challenge so far. Yaro Tenzer, a co-founder of Right Hand Robotics, is in Japan for RoboCup 2017, the conference where Amazon's contest takes place. He says he may recruit participants, but sees little reason to show off his company's techniques publicly. "The value for us is staying ahead of everyone else," he said.

Alberto Rodriguez, a professor at MIT's department of mechanical engineeringwho leads a team from MIT and Princeton, puts it in more idealistic terms. He sees value in getting a bunch of researchers pointedin exactly the same direction. "Theres some notion of common knowledge that has been generated because so many people have been motivated to work on the same problem," he said.

Theteams havebecomeincreasinglysophisticated in their approaches. They started withalgorithms that required them to program rules so robots coulddistinguish specific objects in the contest. They now useneural networks, a form of artificial intelligence that helps robots learn to recognize objects with less human programming.The biggest difference this year is that Amazon isnt tellingthe teams whichitems theyll see in advance. Instead, it gives them 40 items to traintheirsystems on, then replaces 20 of them with new objects ahalfhour before the contest starts. This undermines a basic strategy from last year, when teams fed the systems hundreds of images of each item theyd see from all different angles and in different lighting.That worked, but it was an unrealistic solution in a real world scenario,saidRodriguez.

Whether Amazon will be able to leverage the contest to leapfrog othercompaniesworking on similar problems has yet to be seen. The company hasnt incorporated anything from the contest into itsactual operations, according to Robinson.Kris Hauser,thefaculty advisor for this year's team ofstudents from Duke University,says a warehouse staffed with fullyautonomous picking robots is still several years away.Amazons guidance, hesays,keeps academics like himself from straying too far into the theoretical. This is really forcing us to look at these problems from the point of view of a potential commercial technology,"he said. "When we take research products and try to put them out in the real world, were oftentimes surprised at how bad they perform."

More here:

Amazon Enlists Researchers to Build Box-Packing Robots - Bloomberg