The Sundance Film Festival that took place last week featured a couple interesting robot films… This first one, by director Spike Jonze, is called I’m Here:

The film is 30 minutes long, and Entertainment Weekly says that it “feels like a modern-day retelling of Shel Silverstein’s The Giving Tree, with two crudely constructed robots serving as the protagonists.” It may show up in its entirety on the Independent Film Channel later this year.

VIA [ io9 ]

Honda was also at Sundance to screen a wonderful 8 minute documentary called Living With Robots, which is totally worth watching simply because of how well it sums up so many of the issues relevant to robotics today and in the near future:

Honda’s got it exactly right: the biggest hurdle to overcome when it comes to the future of robotics is not technical, but rather an issue of public perception. At the end of the video, Mark Rowlands says “whatever robots turn out to be, will largely be a function of us, and the decisions we make.” This is an excellent point… If we have concerns about robots, it’s important to acknowledge that those concerns generally can’t, by definition, be about the robots themselves. Rather, we must understand that robots are a reflection, or perhaps more accurately a physical embodiment, of human desire, and it’s those desires and how we act on them that need to be examined.

So if there are issues surrounding things like, oh, I don’t know, military robots, we need to recognize that military robots only exist because of human conflict. They’re not terminators, they’re not out to get us, they’re there because we made them and decided that they were important and necessary. This doesn’t answer the question of whether they’re a good idea or a bad idea, but the point is that you can’t look at robots as something separate from the human experience.

You can see more footage of those ASIMOs wandering around an office environment in this post from 2007.

[ Honda Press Release ]

Just in case you’re not familiar:

1. Robots aren’t supposed to squish humans.
2. Robots have to sweep up when humans tell them to.
3. Robots are allowed to shoot humans if they’re unhappy.

Today only, shirt.woot. $10 shipped.

[ shirt.woot ]

If we ever find ourselves with our own household robots, they’re going to need to be able to learn from us, because there will be all kinds of wild and crazy stuff that we want our robots to be able to do that the robot designers won’t have thought of. So, the ability to teach robots new tasks is rather important. But even more important is teaching robots to generalize one thing or task and apply it to many different variations on that thing or task. Back in September, we wrote about an ASIMO that learned to generalize different types of objects: show it a chair, and ASIMO could figure out what other objects were chair-like.

PR2 has taken this concept of generalization a step further by applying it to actions, not just things. When you teach PR2 an action (by providing an example of the action), PR2 can understand the fundamental components of the action and apply them to different variations of the action. So like, if you teach PR2 to pour a beverage out of a can into a cup, it then doesn’t matter what kind of can or what kind of cup or where they are relative to each other or if you move them around in the middle. This is hugely, hugely important for robots to be able to do, because having to teach a robot an action for “pour from can into cup on counter” and then a separate action for “pour from can into cup on low table” isn’t just tedious, it’s one of those things that is going to keep anyone from wanting to be involved with the robot at all.

There are a lot of major obstacles to surmount when it comes to creating a robot that can be practical and useful around people who know nothing about robots… From stuff like plugging into a normal outlet to recharge to not squeezing things too hard. It’s awesome to see Willow Garage and PR2 tackling these critical objectives and finding solutions that work.

[ Willow Garage ]

GetRobo has the scoop on a presentation made by Toyota executives entitled “Realization of Moon Exploration Using Advanced Robots by 2020.” Sending robots to the moon is certainly not a new idea, but slick looking humanoid robots? Building rock gardens and doing calligraphy? I guess the robots can do whatever they want once they get there, and Toyota has some fairly specific ideas on hardware and capabilities:

-joints are protected from regolith

-small capacity solar battery onboard

-internal status shows on screen on chest

-arms exchangeable for different tasks

-able to jump with springs in legs

-keeps warm during night covered in metal cloak

There isn’t a lot of detail beyond the info here, but I’d say it’s certainly possible to have bots like this in 2020 based on the current capabilities of Toyota’s partner robots. The first robots back to the moon might look more like this, but Toyota has a real shot at the solar system record for lunar calligraphy.

VIA [ GetRobo ]

Could someone please explain to me why, exactly, roboticists seem to think that it’s such a good idea to give their creations swords? Like, I get that it’s a way to demonstrate grasping and dexterous movements, but if you start with robots demonstrating swords, you move on to robots fighting each other with swords, and this will be our terrifying future. And swordplay seems to be a bad idea for HUBO here more than most, since it repeatedly hits itself in the head with a sword that is thankfully not made out of anything dangerous.

HUBO is one of an elite group of humanoid robots able to perform complicated dynamic tasks like running. Also in this group are Toyota’s Partner robots, and Honda’s ASIMO (of course). I understand that these robots are very complicated and expensive and stuff, but I can’t imagine a better way to convince people whether they’d really rather buy a Toyota Prius or a Honda Insight than sticking a couple of these bots in a ring with some swords or tasers or something and just letting them go at it. Yeah, they’d get damaged, but you’d totally recoup all of that through ticket sales and car sales. Just trying to make a helpful suggestion… You know, for the good of the car companies.

[ Plastic Pals ] VIA [ CrunchGear ]

Robot Watch attended ASIMO’s 9th birthday party last September, and took a bunch of pictures of the precursors to the capable little robot that we’re familiar with today. Check out pics of the whole series, after the jump. (Read more…)

Some robots are, granted, awesome dancers, but most are just too robot-y. If you think about it, it’s a lot like early computer animation… It’s hard to convincingly mimic all of the subtle movements that humans use when dancing (or doing pretty much anything else). This is exactly why the motion capture suit was invented, and it’s a wonder that nobody’s used them to program a robot before. Or maybe they have, but this is the first video I’ve seen of it in action. And it really does seem to make a difference to the robots’ moves… I’d venture to call them significantly more lifelike.

The research team from South Korea that’s developing this technique is focusing specifically on hip movements, because as you know, your hips are what keep the rest of your body from falling over when you’re bustin’ those crazy dance moves, yo. It still appears to be a fairly restrained system, but if it does for robots what motion capture did for CGI, Dancing With The Stars could get a lot more interesting.

That’s a show, right? I wouldn’t know, ’cause I of course wouldn’t watch anything of the sort.

Unless it had robots in it.

[ IROS Paper ] VIA [ Robots Dreams ]

If this little guy looks familiar, it’s because he was designed by Tomotaka Takahashi of Robo Garage, who also designed the Tmsuk T-52 Enryu Rescue Dragon. What, you can’t see the family resemblance? Okay, how about with that little record breaking Evolta robot? ROPID is Takahashi’s latest creation, and it shows: using three gyros (one in each leg plus one in the chest) and a bunch of awfully strong servos linked by belts ROPID can jump and even kinda run:

Technically, it’s not running unless ROPID manages to get both feet off the ground at the same time, and from the videos, it doesn’t look like that happens… Even ASIMO (who is several orders of magnitude larger and more complicated) barely manages to do this. So ROPID is really more of a power walker. But that’s okay, we won’t hold it against him, because he’s just so adorable with those glowy eyes and that cute little mouth. ROPID is a good listener too, able to respond to voice commands. What really sells him, though, is the fact that he emotes so well… Maybe that’s why he’ll be starring in a short film, coming soon to a film festival near you. For real.

[ ROPID @ Robo Garage ] VIA [ Robot Watch (Translated) ]

Man, that Cracked video just keeps giving up gems. Turns out that the bit about ASIMO being able to identify objects by class came from a BBC show called James May’s Big Ideas… being a long-time Top Gear fan, I was able to immediately recognize his shaggy locks in the 0.5 second that they were visible in the video. Anyway, I’d like to reiterate what May says in the beginning of the segment, because it’s something that we tend to point out a lot around here:

“Robots and computers are very very good at things we find very difficult, such as long division and VAT returns. But they’re very very bad at things we find extremely easy and instinctive, such as walking, talking, and seeing.”

Lots more, after the jump. (Read more…)