You know, I kinda hate to say it, but that actually looks pretty good. Or at least, relatively good. Last year, AIST’s HRP-4C robot was somewhat woodenly singing J-Pop, but this performance is borderline believable if you squint really hard while trying your level best to willfully disbelieve that she’s a robot. Maybe she took some pointers from their newer HRP-4?

I guess what I’m saying is, this seems to me (from a purely artistic and non-technical perspective) to be a significant improvement. Much of the credit likely goes to AIST’s new dance choreography software, which prevents users without robotics experience from planning dance that might sending their robot sprawling. Dancing might be a bit of a novelty for robots, but it’s certainly a good way to try and teach fluid and non-robotic movement, which is a big step towards less-uncanny humanoids.

[ AIST Press Release (Translated) ] VIA [ Pink Tentacle ]

See this? This is an honest to goodness, real, working, commercially available jetpack. Or maybe a ducted fanpack, but whatever… The point is, YOU’RE TOO LATE, because the Martin Jetpack is now robotic and has no use for humans. Yep, that one piece of the future that would have been totally awesome has just passed us by.

Martin Aircraft Company has been working on a practical jetpack for years now, and we’ve been following it over on OhGizmo. The lowdown is that the jetpack uses two huge ducted fans that you wear kinda like a backpack, and will propel you 8,000 feet up at 60 miles an hour for 30 minutes. It runs on the same gas your car does, doesn’t require a pilot’s license, and includes a ballistic parachute (that works at low altitudes) just in case.

From the beginning, Martin had autonomy in mind for their jetpack, for one simple reason: nobody really wanted to be the guy who had to strap it on and see how fast it would go, or who had to check if the emergency parachute system worked. So, it was a natural step to turn the robotic testing system into a total robotic flying system, and now Martin is hoping that their ‘Skyhook’ will be able to fill a niche between man-portable reconnaissance UAVs and larger, infrastructure dependent drones like Predators. Skyhook can take off and land vertically while carrying up to 100 kilos of payload, which would be ideal for local resupplying of isolated units. Plus, like, it’s a jetpack. Think StarCraft 2.

Currently, Martin needs some funding to make this possible, so do yourself (and them) a favor and go buy a jetpack… It’ll be the best $100,000 you’ve ever spent.

[ Martin Jetpack ] VIA [ Fox News ]

We knew that Innvo Labs was working on some upgrades to Pleo, but all has now been revealed over at Bob The Pleo forums, where Innvo Lab CEO Derek Dotson discussed the new “Pleo Reborn.” If you’re a fan of Pleo, you pretty much have to read the entire interview, but I’ve condensed most of the new features if you’d rather just skim:

-Pleos are now male or female (blue or pink), and will react to each other accordingly: females make gentle noises at each other, males step back and shout at each other, and a male and female will make noises and lean against each other

-Pleo skin coloring will be randomized slightly, so that two Pleos produced at the same time will look distinctive. There will also be 10 different eye colors.

-Pleo skin durability improved, should now last 5x longer

-New lithium polymer battery more than doubles lifetime to 120 – 150 minutes, LED battery indicator added underneath Pleo

-Pleo will have a ‘seed’ personality from the factory. Some will learn faster than others, and some will tend to be happier (or more mopey).

-Pleo now knows what time it is and will alter its behaviors accordingly; for example, it will want to be fed in the afternoon and act sleepy in the evening

-Pleo can ‘smell’ RFID tags

-Pleo now has voice recognition, and you can name it, and it will respond to that name… As long as it’s you saying it, not anyone else

-By combining RFID tags that instruct Pleo to perform specific behaviors with voice recognition, it’s now possible to train Pleo to respond to different commands, such as “bow” or “come to me”

-Many more touch sensors have been added, along with corresponding behaviors. For example, if you pet Pleo’s side, it will lean into you.

-Pleo now has a G sensor that lets it detect acceleration and impacts as well as touch

-Pleo’s nose cam now allows for target tracking

-Motor speed and response have been improved, especially in the tail, head, and neck

More awesome stuff, plus video, after the jump. (Read more…)

There’s only really one way to figure out how much is too much when it comes to the more, shall we say, direct (and maybe unintentional) forms of robot human interaction. In other words, to figure out how hard a robot can punch a human before said human a.) complains or 2.) suffers permanent injury, you kinda just have to get a robot and start punchin’ some humans. A robotics lab in Slovenia has made this happen, using a small robot arm with both blunt and sharp attachments to strike humans at varying velocities to correlate velocity with pain threshold.

“We are taking the first steps to defining the limits of the speed and acceleration of robots, and the ideal size and shape of the tools they use, so they can safely interact with humans.”

The overall idea seems to be that the information gathered from this research will be used to restrict robots working around humans to moving at what is determined to be a safe velocity.

On one hand, I understand why this research is relevant and potentially important. But at the same time, I feel like limiting robots in this way is to some extent counter-productive, and is sort of akin to limiting the speed of traffic on a road when humans are walking on the sidewalk. For the humans, the idea is that you don’t just walk out into the middle of the road. And for the cars, they rely on their ability to stop quickly if a human does, for some reason, end up in their path. And I don’t see why robots couldn’t operate the same way… I mean, why restrict robots to moving at a speed where hitting humans won’t cause permanent injury when you could just program the robot to avoid hitting people entirely? I think the data that are being collected here are important, but I’m just not sure whether they should be applied in the manner that the researchers are suggesting.

Where I think it SHOULD be applied is to adaptive safety solutions like ABB’s SafeMove system. We wrote about it last year, but here’s the video:

See? Just keep the robot from hitting people in the first place, and everybody will end up much happier. It’s worth mentioning, of course, that accidents will happen… But it’s important to remember that humans are the ones programming the robots, and ultimately, any mistakes that they make can be traced back to human error.

For a slightly different take on this research, this Register article (sent to us by Aaron) offers what I can only assume is a tabloid article writer’s perspective on robot human interaction… I’d be outraged if it wasn’t so laughable.

VIA [ New Scientist ]

As we commented in our review, Mint takes a different approach to robotic cleaning than we’ve seen before: it eschews the vacuum for simple, silent, and efficient sweeping and mopping. Despite its simplicity, however, Mint is also able to localize itself, which is a pretty neat trick for a $250 robot. With all this in mind, we had some questions about how Mint came to be as well as what the future holds, and Evolution Robotics’ President and CEO Dr. Paolo Pirjanian was kind enough to help satisfy our curiosity. It’s a long interview packed with interesting info on the development process for Mint and the NorthStar system (as well as hints about what’s next), and you can read it all, after the jump. (Read more…)

Remember all those questions you had about Mint? Well, we now have answers. Answers part one, anyway. Tomorrow, we’ll be posting an interview with Evolution Robotics president and CEO Dr. Paolo Pirjanian, where we’ll be talking about the history of Mint, as well as what Evolution Robotics is planning for the future. But today, we have answers to some of your more specific questions about Mint, from Mike Dooley, the vice president of product development at Evolution Robotics.

-Why did you decide not to include an automatic charging system?

We gave serious consideration to having a self-charging dock, and with NorthStar already on board to guide Mint back home, it was tempting to add (folks may recall that Rovio already uses NorthStar to self-dock). Ultimately we decided to go without one based on feedback from consumers.

The most common comment was that when Mint was done cleaning, they’d prefer just to put it away – just like they would their mop. For many, having a robot and a charging dock sitting out on the floor all of the time added more clutter to the room, even though Mint is pretty styling! :) So, we worked with the Fuse Project to give Mint a very slim vertical footprint, making it easy to tuck away by standing it on its end.

We were also not sure how much time and effort a self-charging dock would really save. As you mentioned in your review, other “automated” robots aren’t fully automatic. With robotic vacuums that self-charge, you still have to empty the bin and do things like check the brush. Instead, we looked at the total user experience, and how to make it as seamless as possible. That led us to things like making it super-easy to change the cloth, with features like the magnetic pad and zip-to-lock grip strips.

Lots more on carpet detection, Rovio beacons, the NorthStar system, and hacking, after the jump. (Read more…)

It’s almost always exciting to see something new from iRobot, but since the 5xx series of Roomba showed up in 2007, “new” is a relative term when it comes to their cleaning robots. The Roomba 572 Pet Series is “new” in that it’s got a new number, but as far as I can tell, the only things that make the 572 different from other 500 series Roombas is the following:

-It comes with three different bins, which you can buy separately
-It comes with replacement brushes and filters, which you can buy separately
-It costs $500

The 572 also includes other features common to higher end 500 series Roombas, such as scheduling, Lighthouse compatibility, and a remote control (sweet!).

Maybe I’m missing something, but it’s kinda disappointing when a “new” Roomba is just the same as pretty much every other Roomba, just with a slightly different mix of features and accessories. I mean, iRobot might as well offer a build-a-Roomba option on their website, where you can toss in all the options you feel like you need and assign it a random three digit number starting with 5 and they’ll quote you a price. You know, come to think of it, that would be pretty cool…

It’s certainly worth mentioning, though, that the Roomba still beats out the Neato Robotics XV-11 and Mint Sweeper robots when it comes to pet hair and carpet… I would just have to recommend that you get a cheaper 500 series that comes with fewer accessories but still cleans just as well.

[ iRobot Roomba 572 ]

Remember 5 years ago when a bunch of robotic cars managed to navigate through the desert all by themselves? And remember 3 years ago when a bunch of robotic cars managed to navigate through a (fake) urban area all by themselves? Well, today it’s the future, and autonomous robotic cars from Google have already logged 140,000 miles on busy, complex city streets and highways with only occasional human intervention, and 1,000 miles without any human control whatsoever.

Writing about this kind of thing makes me all tingly, because ever since I saw that autonomous Passat park itself at Stanford a year ago, it’s become clear that robotic cars aren’t some far-off futuristic dream, but that this technology is actually achievable in the near term. I mean, consider how much time you spend in your car effectively doing nothing, and then think about how much things would change if you could be productive (or asleep) instead. And of course, it’s not just that: autonomous cars have the potential to reduce traffic by driving closer together, drastically improve gas mileage with cooperative drafting, and (most importantly) significantly reduce the number of car accidents, which cause 1.2 million fatalities worldwide and exponentially more injuries plus untold emotional (and financial) trauma.

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

Do you own a robot? Are you are a robot? Either way, Carnegie Mellon wants to hear from you as part of their 2010 Robot Census. Initially, the idea was to just count up all the robots at CMU (547), but the project has since expanded to all robots. Everywhere. So that they can get proper representation and federal funding, or something.

Of course, in order to qualify for the robot census, a robot has to be, uh, a robot. So what’s a robot? According to CMU’s Heather Knight, who’s running the show, “everyone agrees there are 3 minimum requirements. These are the minimum, but not sufficient requirements: They must act in the world, sense the world, and they need to have computation.”

The “minimum but not sufficient” bit is in there to preclude registering a thermostat as a robot, but this brings up all kinds of questions about just what exactly a robot is. I would just say that robots are like profanity: you know it when you see it.

Register your robot here.

[ Robot Census ]

I’m sure you remember Diego-San, whom we spotted in an issue of Kokoro News back in January. Reactions to these pictures were… Well, let’s just say, reactions were decidedly mixed. And by decidedly mixed, I mean predominantly negative. Diego-San’s createor, Dr. Javier Movellan, has been exploring possible alterations to Diego-San’s face, and has made this concept public:

As Dr. Movellan pointed out in one of his comments on our post, a lot of what’s relevant about designing the appearance of a humanoid robot is simply about trial and error:

“Everybody has strong opinions about why the current version generates such negative reactions: face too large, robot babies are freaky, skin texture is wrong, mixing mechanical body with biological face is scary, giganto-babies are scary … For just about every theory examples can be given that contradict the theories. The truth is nobody really knows. It is a trial and error process.”

With that in mind, Dr. Movellan is looking for some feedback (constructive feedback, please) on what you do and don’t like about this new concept for Diego-San’s face. Personally, I’d say it’s a good start, with the helmet, antenna and exposed electronics all reinforcing the fact that the robot isn’t intending to fool you into thinking it’s real. However, I’d be curious as to what the effect would be if more of the human features were removed. Like, what is strictly necessary for the robot to accomplish its research goals, which may not necessarily involve a substantial amount of expression recognition? Does Diego-San need ears, for example? A nose?

While one route might be to make it less human, the other route would be to make it much more cartoony. So basically, keep all the human features, just make it look intentionally fake… Again, the idea being that you’re reinforcing the fact that the robot isn’t trying to fool you into thinking it’s human.

Anyway, please let Dr. Movellan know what you think by posting a comment. For more background, read through some of the comments on our original post, and Plastic Pals has a very interesting interview with Dr. Movellan here.

[ UCSD Machine Perception Lab ] VIA [ Plastic Pals ]
[ Original Kokoro News Article (*.PDF) ]