This is maybe only peripherally (ha!) related to robotics, but it’s cool enough that I thought it was worth sharing… Besides, it’s Friday, and you deserve some nifty videos to watch. Anyway, we’ve posted before on all the cool things that roboticists have been able to do with Microsoft’s stupidly cheap and effective 3D camera system, and Willow Garage took some initiative and sponsored a contest to try and kick start even more open source Kinect innovation.

First place (and $3k) went to Garratt Gallagher’s ‘Customizable Buttons.’ Using a piece of paper and a pen, you can just draw your own touch-sensitive controls:

The second and third places went to robots we’ve covered before, namely UC Berkeley’s quadrotors and Taylor Veltrop’s teleoperation, while a real-time color 3D mapping tool from the University of Freiburg took home the most useful award.

Taking home no awards, but one of my personal favorite demos, was Kinemmings, a game of Lemmings played using your body and the Kinect sensor. Yes, it may not be advancing the field of robots or whatever, but it sure looks like fun:

Microsoft should absolutely pay those guys a bajillion dollars and hire them as game designers or something. Seriously, Kinect has way more potential than one company can possibly harness. And as for robots, great strides are obviously being made, and the future is (hopefully) limitless. If any of these projects are of use to you personally, remember that since they’re on ROS, you can just download them and put them to work yourself.

[ ROS 3D Contest ]

It looks like that desert testing we wrote about in May of last year has paid off, and UPenn’s KodLab has developed a new version of their RHex wheeled/legged robot called X-RHex. X-RHex is about the same size and weight as RHex, but it’s stronger, more durable, and has as longer run time of up to two hours. It’s also got a couple mil-spec rails mounted on top along with standardized electrical connections, which could be just for convenience or could be because X-RHex has a probable military future, or both.

X-RHex doesn’t seem as capable of the speeds exhibited by other leg/wheel hybrid robots such as Whegs, but its strength is in its adaptability and the way it can make it through basically any sort of terrain, even things that would challenge conventional wheeled or tracked robots.

[ X-RHex ]

Here’s one way to make an inherently safe robot arm: use balloons. Siddharth Sanan, a Ph.D student at Carnegie Mellon, has been working on ways to make robots less dangerous for humans to be around, and he’s come at the problem differently by not using rigid components. This technique makes precision control of the robot more difficult, but for assistive robots that spend a lot of time interacting closely with humans, it could still make for a good solution. Just don’t let any of these guys near it.

While we’re here, we should also have a look at another ‘soft’ manipulator arm by Sanan, the Tubot. It’s a ‘continuum type soft manipulator,’ but I’m just going to go ahead and call it a tentacle:

The tentacle version is a slightly different solution to the the same potential issue, which is ensuring that even if a robot arm really really REALLY wants to stave your head in, it won’t be physically able to.

Also, pudding. Mmm, pudding.

[ Siddharth Sanan ] VIA [ Robots.net ]

Update- probably should have seen this coming: the video had ‘Eye of the Tiger’ as background music and YouTube pulled it. The new version above is on mute, which makes it 10x less awesome. If iCub’s trainers are reading this, you can add the track directly through YouTube legally, but until then, everyone else will have to click here and just let the second video run in the background.

No, I have absolutely no idea why iCub is being tasked with a work out, but I do know why his trainer is berating him: those are sissy push-ups! C’mon, get those knees off the ground and keep your robobutt down! Otherwise, how are you gonna work off all that, uh…

…Flab?

You know, it’s probably worth mentioning that exercise is actually counterproductive for robots, in that it’s likely to make their servo motors weaker over time. But that’s not the point! iCub hasn’t bulked up in years, so it’s high time this robotic baby gets to work.

[ iCub ]

Those adorable little ZMP robot cars we wrote about in July of last year 2009 have spawned a giant new family member, the “RoBoCar.” Yes, apparently they can’t drum up enough creativity to put together a trendy name, so they’re just messing with the capitalization instead. Sigh.

The Robocar (not gonna do it, sorry) is really more of a RoBoGoLfCaRt (see? it’s dumb!), but it’s something that you could realistically drive around in. Or, be driven around in, since it’s capable of autonomous speed adjustments, braking, and steering. The deluxe model comes complete with a stereo camera, an IMU, and laser rangefinders, and only costs about $80k. If you’d rather take care of everything but speed control yourself, a stripped down version with fewer autonomous capabilities will only set you back about $30k. I should point out that there’s a discrepancy of several orders of magnitude between a couple different sources on the price, but since I can’t believe that this system costs $8 million, I’m inclined to blame Google Translate… If it does end up costing $8 million, email me, ’cause I’m sure I can work out a way to get you a similar system for just $7.5 million.

In all seriousness, though, a platform like this has potential to enable the same type of development as the PR2 has: it’s got all the hardware and it’s ready to go, which means that if you want to do work on autonomous navigation, you don’t have to spend time and money building your own RoBoTiC CaR first, you can just buy one of these instead and get right to work.

[ ZMP ] VIA [ Akihabara News ]

Back in July, we wrote about how UPenn’s GRASP Lab had taught their quadrotors to work together to grasp and move things. The next step, it seems, is teaching the quadrotors to work together to grasp and move things and actually build buildings. The video above shows a team of quadrotors cooperating to construct the framework of a (rather small) building. The building’s structure is held together with magnets, and the quadrotors are able to verify that the alignment is correct by attempting to wiggle the structural components around, which is pretty cool.

It’s fun to speculate about how this technology might grow out of the lab into the real world… To build actual buldings, you’d either need much bigger quadrotors (which is possible), lots of small quadrotors cooperating in big pieces (also possible), or buildings built out of much smaller components (which might be the way to go). The quadrotors probably wouldn’t be able to do all the work, but they have the potential to make construction projects significantly more efficient.

[ GRASP ]

With all of the new competition in the consumer robotics field, it’s about time for iRobot to show that they’re still capable of innovating new and exciting things. AVA, their technology demonstrator, definitely fits into the new and exciting category.

AVA is short for ‘Avatar,’ although iRobot was careful not to call it a telepresence robot so as not to restrict perceptions of what it’s capable of. AVA is capable of fully autonomous navigation, relying on a Kinect-style depth sensing camera, laser rangefinders, inertial movement sensors, ultrasonic sensors, and (as a last resort) bump sensors. We got a run-down a few days ago at CES, check it out:

All of the sensor data crunching is taken care of by a heavyweight on-board computer, but the brains of the operation is really whatever AVA happens to be wearing for a head, in this case, a tablet PC. This makes it easy to develop applications to control the robot, which is a concept not unlike the iRobot Create: the building a robot part is done for you, leaving you to focus on getting said robot to do cool stuff.

There are also a bunch of interesting ways to interact with AVA. You’ve got the tablet of course, if you want to do things the hard way. A second Kinect camera on the bot can detect people and recognize gestures, and an array of microphones can detect and interpret voice commands. Finally, AVA’s round ‘collar’ piece has touch sensors all the way around, offering an intuitive way to steer AVA around.

While iRobot wouldn’t speculate on what’s coming next for AVA (disappointing), telepresence is an obvious first application. AVA also has a bunch of expansion ports that you can attach stuff to, which obviously makes me think manipulators. Personally, I’m hoping that now that AVA is out in the open, iRobot will keep us updated with some of the new ideas that they’re playing around with.

[ iRobot ]

Robots are potentially dangerous, but it’s usually hard to tell just how dangerous they are. You can make up as many ludicrous warnings as you want, but the only way to tell for sure is to let the robots just beat on people a whole bunch and see how bad it gets. At least that way, you get a worst-case scenario.

If you’re not quite that brave, you can be like Japan and use crash test dummies in a specially designed facility instead. Less entertaining and less accurate, but also less risk of death, and that’s probably good. Japan’s New Energy and Industrial Technology Development Organization (NEDO), National Institute of Advanced Industrial Science and Technology (AIST), Automobile Research Institute (JARI) have all banded together and decided that it would be kinda cool to form a Robot Safety Center to test out robots to make sure that, among other things, they won’t go bonkers and kill you every time you turn on your microwave.

Most joking aside, this is a serious first step towards the acceptance of an industry that will (hopefully) be producing large consumer robots sometime in the near future. You’re probably not worried about your Roomba breaking your ankles, but when you’ve got something the size of a PR2 grabbing beers for you, it’s good to know just exactly how hard and how accurately it’s capable of chucking a bottle, you know?

For better or worse, this type of testing also means that we’re going to have to have to make some serious (and legally binding) decisions about what happens if a safety certified robot has an accident and hurts someone. At the moment, issues like these are a significant roadblock to the development of consumer robots: why should companies spend a bunch of money developing an awesome robot if they’ll be sued into oblivion the first time one of their creations has a little accident? There needs to be some sort of legal framework in place to deal with this stuff before it happens, and knowing what can go wrong is a good way to help plan for what might go wrong.

VIA [ Plastic Pals ]

This robot (you might recognize it, it’s an HRP-2) has been programmed to NOT AVOID OBSTACLES. I know, crazy right? Instead, it’s smart enough to either move obstacles out of its way when it needs to, or actually use obstacles to help it get around, as you can see in the vid above.

The system breaks down tasks into two stages. In the first stage, software developed by Lengagne’s colleague Karim Bouyarmane identifies objects in the robot’s surroundings that it can use to help complete a task – for instance, leaning on a table with its forearms to sidle past it and into a nearby chair. The software then calculates a number of poses that the robot could strike to make best use of the table for stability while it shuffles towards the chair and sits on it. Lengagne’s software then converts these static poses into one smooth motion, taking into account the forces operating on the robot in each position to ensure it does not lose balance.

I really don’t know why New Scientist makes it sound like using obstacles to your advantage has to be an old person thing… I’m not old (okay, I’m not THAT old) and I use objects to support my weight and maintain my balance all the time. It might not be strictly necessary that I do so, but I’m super lazy and it saves me energy, so why not? For robots, being super lazy just means that they’re more energy efficient and they put less wear on their motors and joints, which is almost as important.

As I’ve pointed out before, creative compromises like this are a great way to make progress in robotics. I’m sure it’s possible (and perhaps even ideal) to make a humanoid robot that can sit at desks and kick soccer balls without any form of support, but why bother? Humans are so capable because we know how to efficiently adapt ourselves to our surroundings, and robots are getting better at doing the same.

VIA [ New Scientist ]

IEEE Automaton scored a sneak peak at Aldebaran Robotics’ newest version of their Nao robot at the Humanoids 2010 conference in Nashville recently. Nao’s body has been completely reworked to be more robust, and longer curved arms give the bot more space in which to pick stuff up and throw it at you. A new motion engine helps Nao move more fluidly, and as you can see in the demo above, it exhibits some fetchingly human moves.

Nao also got a new head, along with an upgraded brain that helps it to recognize speech and images. It can do some form of facial recognition and it sounds like it’s capable of reading text as well, which is pretty handy. There also seem to have been a few, um, attitude adjustments… This latest version of now is the spunkiest yet.

Incidentally, I never really noticed this before, but doesn’t Nao sound an awful like those freaky sentry guns from Portal? Oh well, it’s probably just a coincidence.

Probably.

VIA [ IEEE ]