Automaton

Spectrum's current issue has a great article on Microsoft's quiet yet bold robotics initiative. Senior Associate Editor Steven Cherry spent a day in the "Broom Closet," the small office area tucked somewhere in the Redmond campus where a small software development group is trying to do for robotics what Microsoft did for personal computing. Below, a Q&A with Cherry:

Automaton: So Microsoft has set out to dominate the robotics universe with its Robotics Studio, which is not an operating system. So what is it?

Cherry: MSRS, as they call it, has the same goal as an operating system—to create a common platform for developers. And it includes what are in effect libraries of code that let higher-level developers create software without delving much into the physical details of this company’s robotic limbs or that one’s sensors. If you start with one arm and switch to another, for example, the commands for up, down, grasp, release, and so forth will be the same.

Automaton: And who is using it? Or who will use it?

Cherry: The platform is still quite new, but my understanding is there are quite a few companies working with it already, from the German automation giant Kuka to iRobot, which makes the Roomba.

Automaton: You were in the Broom Closet. When did you come out?

Cherry: Very funny.

Automaton: So what's the mood there?

Cherry: Well, for one thing, it’s fun. Imagine you took a regular software group and plunked it down into Willy Wonka's factory. You may see all sorts of things crawling around, but sometimes there are just programmers quietly staring at their screens. The group does believe they're doing something important. That's the atmosphere. They are just 11, actually now 12, people out of 76 000 Microsoft employees. But they are dreaming big.

Check this out -- Kiva Systems' robots in action in a Staples warehouse. I've seen one of these up close before (carrying a person, actually)... it's pretty neat. The bearings used to keep the payload in the same orientation must be pretty crazy. When I saw one in action, it used little bar-code type labels to follow on the floor, but there's some net intelligence directing them because these guys are all moving in an overall organized fashion -- this article from the video producer, Fast Company, suggests that "blinking blue lights" help coordinate them somehow. At some point in the future we'll talk with the creators and see what we can find out!

Video by Fast Company

* Transformer Optimus Prime prevented a burglary in the U.K. This transformer is made of wood and stands 7 feet tall in the living room of one Michael Clarke, in Gravesend, Kent. The robot has motion sensors that activate a stereo, piercing purple eyes, and it matches the owner's couch.

* More robots from iRobot. The Roomba maker says it is mutating. The company wants to keep expanding its product line. Three years ago, it had only one domestic robot, the Roomba; by the end of this year it wants to have six domestic robots in the market. I wonder if Masseur Bot is on that list.

* Peter Crouch, the elongated (2 meters/6 feet 7 inches) British soccer player who celebrated some of his goals with an ridiculous robot dance, said the moves were because he's been "messing about" with robotics since he was a child. He also said no more robotic celebrations this season. That's a good thing.

Having attended a wonderful wine tasting last night at a former professor's house, I've been feeling particularly oenophilic. During the tasting the professor told us about a lot of the technology vineyard owners have started using to track their crops. Since vines produce different fruit depending on shade, temperature, amount of water, type of soil, and so on, a good vineyard owner needs to know all about the different conditions all over his or her vineyard -- and small, cheap sensor technology only makes that easier. This of course led me to the natural conclusion: my wine could only be better if a robot is involved!

So what can robots do for a wine geek like me? I could purchase my very own "Robo-sommelier" to see if I'm actually getting what I'm buying -- using infrared light, it can tell what the type of the wine is without even opening it -- or it could learn my tastes and be able to recommend a wine to pair with my dinner.

Before the wine gets to my table, a vineyard owner might use an automated tractor to care for the vines. It can navigate using the wires that the vines grow on and can tow a sprayer or other equipment, preventing a human from having to do the long, dull task of driving the tractor through a huge vineyard. A 5-DOF robotic hand combined with a vision system might be doing some of the harvesting or care for the bunches of grapes on the vine. A friend at the wine tasting with me mentioned having seen one vineyard in which a robotic system rotated and tipped bottles slightly each day as they aged.

The agriculture industry is really embracing robotics and automation (Rocona is one example; John Deere and others are following suit), but it will be interesting to see if the wine industry actually adopts the technologies being created for them. Vineyard owners pride themselves on understanding their crops and how climate conditions will affect their output; sommeliers and wine aficionados are proud of their tasting abilities and standards. Will these people really want to hand over their art to machines?

iRobot just released their new line of Roombas today. They look awesome -- a lot more like the space-age robots I expect to have in my home. It looks from the new specs that they've added some great new features, too, like onboard scheduling and voice interaction.

Although some people claim their mouths operate independently of their brains, that's not usually the case. The brain sends neurological signals to the larynx, which converts them into sound. Now, what if we could use those larynx nerve signals to control things?

That's exactly what a company called Ambient is doing. Its Audeo technology basically converts "unspoken speech" (neurological signals flowing through larynx nerves when a person thinks about speaking) into control commands that can be used to guide a motorized wheelchair (video above) or synthesize speech. Pretty amazing!

The company apparently stole the show this month at National Instrument's NI Week in Austin. Ambient's founder and CEO, Michael Callahan, gave a demonstration of the company's "thought-controlled" wheelchair and "thought-to-speech" translation system. (You can see the demo at the NI Week video page; it's the last segment, called "Algorithm Engineering," on the August 7 list.)

To use the system, a person wears a lightweight sensor band around the neck. The band picks up the larynx nerve signals and transmits them wirelessly to a remote computer (don't worry about "mind wiretapping" -- the transmission is encrypted.) The remote computer uses NI LabVIEW and signal processing algorithms to interpret the nerve-impulse patterns and translate them into the right commands.

The system is not plug-and-play. It does require some training until its algorithms learn to "read your mind" (accuracy is above 70 percent). But at least it doesn't require Matrix-style brain interfaces or a tangle of EEG electrodes wrapped around your head.

Callahan, a graduate student at the University of Illinois at Urbana-Champaign, hopes to commercialize the technology to improve the lives of severely disable people with spinal cord injuries or such neurological disorders as ALS and cerebral palsy. (The company is backed by the Rehabilitation Institute of Chicago.)

OK -- not exactly related to robotics, but very cybernetic nonetheless. I wonder what things we might control with this technology one day. Any guesses?

I finally had time to read Robin Marantz Henig's 8000-word piece on sociable robots in the New York Times Magazine. In the article, Henig, a contributing writer for the magazine, describes what scientists mean when they talk about "sociable robots," how such robots were designed to learn by interacting with their environments, and what are the issues involving robot learning, robot emotion, and robot boyfriends.

Henig does a great job explaining how the robots work, sometimes by "peeking behind the curtain" -- the robots are mostly MIT robots, old and new, including the metal torso Cog, the bushy-eyebrowed Kismet, the talkative head Mertz, the mop-topped Autom, the Gremlinlike Leonardo, the skyscraperish Domo, and the rubbery bulgy-eyed Rodney (OK, joking about this last one).

More interesting, perhaps, Henig describes instances in which the robots misbehave, or work in a somewhat disappointing way, and hey, that's how engineering happens in the real world, so it was neat to see that in the article as well (by the way, I loved the cover headline, which to me captures the essence of this emerging field: "It Understands (Sort Of)." An excerpt:

Today’s humanoids are not the sophisticated machines we might have expected by now, which just shows how complicated a task it was that scientists embarked on 15 years ago when they began working on a robot that could think. . . . They are, instead, hunks of metal tethered to computers, which need their human designers to get them going and to smooth the hiccups along the way.

But these early incarnations of sociable robots are also much more than meets the eye. Bill Gates has said that personal robotics today is at the stage that personal computers were in the mid-1970s. . . . In much the same way, the robots being built today, still unwieldy and temperamental even in the most capable hands, probably offer only hints of the way we might be using robots in another 30 years.

After reading the article, I wanted to see some of those machines in action, and it's just great you can find so many videos of them (the Times posted a bunch on the article's web page). But as a writer myself I also wanted to know more about Henig's experience writing the article. Having just returned from vacation, she was kind enough to promptly answer my questions -- thanks, Robin! (Follow the link below to read the Q&A.)

The folks at Kiva Systems pointed us to this little video they put together for the holiday season. Watch the 24 Kiva warehouse-automation bots dance to the tune of "March" from Tchaikovsky's "The Nutcracker."

The robotic ballet, choreographed by Kiva's Ryan Gariepy and Rob Stevens, took place at the company's headquarters in Woburn, Mass. "We didn't really choreograph it," Stevens told us, "it was more free-form dance!"

Professor Bruno Siciliano, of the Robotics and Automation Group
at the University of Naples, Italy, tells us that the autonomous two-armed robot his team is using to demonstrate such dexterous manipulation tasks as making coffee is a German creation.

The humanoid manipulator, he says, was developed by a team at the Institute of Robotics and Mechatronics, which is part of the German Aerospace Center (DLR), in Wessling, Germany.

Oh, and the robot is called Justin, not Justine -- "so it's a 'male' robot eventually," Siciliano adds.

Siciliano is the coordinator of the DEXMART project, an ambitious European Union-funded initiative to improve robotic dexterity and related fields. He says that DLR's Institute of Robotics and Mechatronics, headed by Gerhard Hirzinger, is a partner in the project, which started this month.

Siciliano's team is using Justin "as one of the experimental platforms for dexterous and autonomous bimanual manipulation tasks." One of those tasks involves using the robot as a barista.

So, yes, the bot makes great coffee. But a more important question, raised by my blog colleague Mikell, remains unanswered: is it programmed in Java?

UPDATE: There's no better way to understand Kiva's systems than seeing it in action. Here's a video Josh Romero and I prepared:

There's been a lot of press about Kiva Systems, the Boston-area startup that developed mobile robots to automate pick-and-pack warehouse operations. No article, however, has really explained the technology that lets the Kiva robots do what they do -- swarm a warehouse by the hundreds and in a highly coordinated bot ballet deliver inventory to workers, racks of products arriving one after another in seconds, flawlessly.

Photo: Joel Eden Photography/Kiva Systems

In other words, there have been few or no details about the robots' control system, their mechanical design, and the overall resource-allocation algorithms. Until now. Spectrum has filled this gap with an in-depth article ("Three Engineers, Hundreds of Robots, One Warehouse") by yours truly in the July issue.

There's been quite a bit going on with the Boston-based robotics companies lately. Here's a quick roundup:

• iRobot can't seem to go long without making news, and the last couple weeks have been no exception. Not only did CTO Rod Brooks leave to start a new company (as reported last week), but a couple new Roomba versions were released and news of another underwater robotic technology acquisition was announced. The Nekton purchase, together with the Seaglider license they acquired back in June, shows they're making an aggressive grab for a piece of the UUV market.

• A company called North End Technologies has spent the last couple years showing up at robotics-related events in Boston but they haven't shed any light on what they've been up to. A recent Mass High Tech article says they're "incorporating robotics into multi-media technology", and their website says they're going to "dramatically change how people interact with the world." Perhaps they're jumping on to the telepresence bandwagon?

• Roomba designer Joe Jones left iRobot several years ago to start a company called Q Robotics with a mission to build "low-cost, practical robots." Now Q Robotics is Harvest Automation, and their first product is a small robot that can pick up and move potted plants that may be used in greenhouses or nurseries to organize their stock.