On supporting science journalism
If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.
By most accounts, this holiday season has been a slow one for merchants due to the economic downturn (though you wouldn't know it by the lines at the stores where I did my last-minute shopping). Still, this is the time of year when inventory turns over rapidly. For major retailers like Staples and Walgreens, efficiency is key to making sure the right products (read: those selling like hotcakes) get to stores as quickly as possible, while less popular items remain tucked in warehouses.
Helping make sure that happens: artificially intelligent robots, who are part of companies' efforts to design their warehouses in a way that enables them to have big sellers at the ready, easy for workers to access. Such bots are programmed with maps of the warehouse in which they operate, have software that instructs them to use logic to find the most direct paths from point A to point B and use optics to read specially placed markers on the floor to navigate, says Peter Wurman, chief scientist at Kiva Systems, Inc., a Woburn, Mass., maker of autonomous robots.
Kiva's robots resemble ground-hugging iRobot Roombas more than the humanoid robot Sonny from the 2004 movie I, Robot. Kiva robots and Roombas, however, are the reality of artificially intelligent robotics. They may not be able to run, jump or speak, but they can efficiently move shelves laden with heavy inventory and clean up messes. And with customers like Staples and Walgreens populating their distribution centers with Kiva's creations, "we're finally seeing massive, multirobot systems at the commercial level," Wurman says. "As the scale becomes bigger, the decision-making skills become more important."
Each Kiva robot communicates wirelessly with the central computer network in a warehouse to get direction when needed, but, for the most part, these little, orange metal men are on their own.
"After a robot visits a pick station and the worker there takes an item from or deposits an item on the robot's shelves, the robot will contact the central server to determine where it will go," Wurman says. "The server will tell the robot where to take the shelves, but it will not tell the robot how to get there." The robot will figure this out using a map of the warehouse stored in its memory as well as its own internal software to navigate the area without running into anything.
Could this be the workplace of the future?
"One thing that really excites people developing artificial intelligence is seeing hundreds of robots working autonomously," Wurman says. Getting dozens of robots to move around in the same space without crashing into one another or creating traffic jams is a bit like choreographing a dance. (See Kiva's "Dance of the Bots" video for more on this.)
Other companies are beginning to join the dance as well. Medical device maker DJO, Inc., will by March begin using Kiva's robotic fulfillment system at its primary U.S. distribution center in Indianapolis. Online retailer Diapers.com is also planning to install Kiva robots in all three of the company's distribution centers to help store, move and sort a variety of baby products, including diapers, wipes, formula, bottles and clothes.
One of Kiva's goals is to enable more and more robots to be able to work in concert. "We want to scale these systems up to 5,000 robots," Wurman says.
The reason today's robots are not as agile as the T-800 of the original Terminator movie is because creating artificial intelligence is not as easy as it looks in Hollywood.
"AI suffers from the fact that it's so easy to imagine the human-level intelligence in a robot that you could interact with like you interact with people," Wurman says. "But the AI field has made a lot of progress. Twenty years ago, a chess program that could beat a world chess champion was a big deal. Now, it is not seen as such, because it's been done. AI has come to stand for only the things we haven't figured out how to do, so it's not really fair."
