![\"Stowe](\"https:\/\/miro.medium.com\/fit\/c\/96\/96\/0*5GJqY-_BZs9Kxfzo.jpg\")
<\/div>\n<\/a><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
One of the barriers to robots taking over in warehouses has been demolished.<\/p>\n The day we were worried about has arrived.<\/p>\n Remember all the pundits telling us that robots were not up to the task of manipulating objects they way that humans can, and as a result automation of much of the manufacturing, logistics, and shelf stocking that humans do will remain at least decades away?<\/p>\n Not so fast:<\/p>\n A Warehouse Robot Learns to Sort Out the Tricky Stuff<\/a> | Adam Satariano and Cade Metz<\/p>\n As millions of products move through warehouses run by Amazon, Walmart and other retailers<\/a>, low-wage workers must comb through bin after bin of random stuff \u2014 from clothes and shoes to electronic equipment \u2014 so that each item can be packaged and sent on its way. Machines had not really been up to the task, until now.<\/p>\n \u201cI\u2019ve worked in the logistics industry for more than 16 years and I\u2019ve never seen anything like this,\u201d said Peter Puchwein, vice president of Knapp, an Austrian company that provides automation technology for warehouses.<\/p>\n Standing nearby at the Obeta warehouse, the California engineers who made the robot snapped pictures with their smartphones. They spent more than two years designing the system at a start-up called Covariant.AI, building on their research at the University of California, Berkeley.<\/p>\n Their technology is an indication that, in the coming years, few warehouse tasks will be too small or complex for a robot. And as the machines master tasks traditionally handled by humans, their development raises new concerns about warehouse workers losing their jobs to automation.<\/p>\n Because the online retail business is growing so quickly \u2014 and most companies will be slow to adopt the latest robotic technologies \u2014 economists believe the advances will not cut into the overall number of logistics jobs anytime soon. But the engineers building these technologies admit that at some point most warehouse tasks will be done by machines. Human workers will need to find other things to do.<\/p>\n<\/blockquote>\n And it\u2019s not just warehouses that will soon be transformed by Covariant.ai. They\u2019ve cooked up so-called a technique called reinforcement learning, which allows robots to learn through trial and error:<\/p>\n First, the system learned from a digital simulation of the task \u2014 a virtual recreation of a bin filled with random items. Then, when Mr. Chen and his colleagues transferred this software to a robot, it could pick up items in the real world.<\/p>\n The robot could continue to learn as it sorted through items it had never seen before. Inside the German warehouse, the robot can pick and sort more than 10,000 different items, and it does this with more than 99 percent accuracy, according to Covariant.<\/p>\n This represents a significant change for the online retail and logistics<\/a> industries.<\/p>\n Late last year, the international robot maker ABB ran a contest. It invited 20 companies to design software for its robot arms that could sort through bins of random items, from cubes to plastic bags filled with other objects.<\/p>\n Ten of the companies were based in Europe, and the other half were in the United States. Most came nowhere close to passing the test. A few could handle most tasks but failed on the trickier cases. Covariant was the only company that could handle every task as swiftly and efficiently as a human.<\/p>\n<\/blockquote>\n And of course, as individual robots get better at their tasks, that \u2018knowledge\u2019 can be extracted and fed into other robots. And there is a humanitarian argument:<\/p>\n\n
\n
\n