ZMP’s 1/10 scale robot cars are designed so that groups who are working on DARPA Challenge style autonomous vehicles won’t have to shell out for the real thing, but can instead test their software on something a bit more affordable. The ZMP car has integrated stereo vision along with an optional image recognition module, as well as a gyro, accelerometers, IR distance sensors, and an optional laser rangefinder. The car runs on a Linux OS and can be controlled over WiFi.

The ZMP car costs $7000, and that’s just for the guts: the fancy plastic shell will set you back another six thousand (!) dollars. Hmm, if only there were some way to make something like this yourself, with the same basic functionality, only about a hundred times cheaper…

[ Press Release ] VIA [ Robot Watch (Translated) ]

AeroVironment, makers of the Raven UAV and the Dragon Eye UAV (among other things), have been working for several years now on a DARPA funded program to develop micro nano air vehicles that use flapping wings as a lift and propulsion source. Now, we’ve seen a lot of robots that use flapping wings, but only one other robot that could use them to hover, like an insect or a hummingbird. The AeroVironment “Mercury” NAV isn’t as small as an insect, but it is about the size of a hummingbird, and surprise surprise, DARPA has asked AeroVironment to dress up the next prototype in a little costume:

Okay, so it’s a little hokey looking, but honestly, I bet it gets the job done: nobody who sees something that looks like that flying around on wings is very likely to think it’s a robot… Except for maybe you, right now, after reading this. Psst… They’re watching you.

From the look of things, this bot is just about ready to go: it has already demonstrated fully controllable untethered flight, so the next step is to get it carrying a payload and perhaps some autonomous capability. Hopefully we’ll get to see more of this thing in action, but probably the clearest indication of the success of this robot will be if the program suddenly ends, and we’re never told anything else about it ever again.

[ AeroVironment ]

This is the second whiskery rat-bot we’ve seen in just a few weeks, which is a little random, to say the least. SCRATCHbot hails from the Bristol Robotics Laboratory, and has been in development since 2003. It’s designed to seek out humans “in environments where visually dominant predators perform badly.” Not to imply that SCRATCHbot is a predator (not yet, anyway)… Quite the opposite, in fact: SCRATCHbot is designed to be released into areas with zero visibility, and use its whiskers to find people who might need help. ‘Cause, you know, if you’re stuck in some dangerous pitch dark place, a big robotic rat with motorized carbon fiber whiskers is just what you want to have snuffling at your pantleg.

[ SCRATCHbot ] VIA [ Engadget ]

The Navy has a few different programs in the works when it comes to detecting mines underwater, a tedious and inefficient process when done by humans in boats. For a while now, they’ve been using trained dolphins to sniff ping out mines, with a reasonable amount of success… The picture above shows a Navy dolphin about to place a marker on a training mine. The problem is that dolphins require constant attention and supervision and mackerel, and certain people are (somewhat understandably, I suppose) upset that dolphins are being tasked with this sort of thing. So obviously, it would be great if the Navy could just get some robots to take care of the whole business.

Yes, it would be great, but it’s turning out to be tougher than it might seem. You can blame the dolphins for that: they made the job look easy. Robots, on the other hand, have some issues when it comes to differentiating mines from other things, say for example, the rest of the ocean. The solution that several research groups are working on is not to make smarter robots per say, but rather to make dumb robots that are capable of teaching themselves. After all, you can spend a whole bunch of time and effort programming a robot to do one specific task, or you can spend a whole bunch of time and effort programming a robot to learn how to do many specific tasks all by itself. It’s a much more efficient way to go, and it means that the dolphins can go back to molesting UAVs and toying with Pleo.

VIA [ Danger Room ]

For robots to really become useful to humans on a day to day basis, they’re going to have to learn to do some thinking on their own. They’ll have to go beyond their programming to some extent, with the ability not just to learn, but also to draw on past experiences to predict how to accomplish unfamiliar goals, both independently and cooperatively. Researchers from the European Joint Action Science and Technology project are working on an artificial intelligence system that not only allows robots to learn tasks from humans (we’ve seen that before, both directly and indirectly), but also to predict how to assist a human with an unfamiliar task.

In the video above, both the robot and the human have been presented with an unfamiliar object to be created from a set of parts. As the human puts pieces together, the robot is able to ‘visualize’ the parts required to assemble the finished object and follow along with the human, suggesting what part might go next and keeping an eye out for mistakes. This is a big deal because for the robot is able to anticipate a series of commands without relying on an explicit program, and in the future, AI like this might help robots do what you want without you even having to ask.

The next step, I can only assume, is to give the robot the capability to say, “give me those pieces, you stupid slow meatsack, I’ll do it myself.”

[ JAST ] VIA [ PopSci ]

We wrote about Piskarpaks Psiharkax this robotic rat last week, and he’s just shown up on video. The little guy is cuter than I would have thought, albeit a little slow, and that’s the longest tail on any rat I’ve ever seen. Especially interesting is the visual representation of how the robot uses its whisker input to sense different types of surfaces from touch patterns… It’s an innovative and robust method of sensing, and it’ll be interesting to see how it gets developed.

[ AnimatLab ] VIA [ DVICE ]

Dean Kamen’s brain controlled cyborg arm, which we first saw over a year ago, has received an additional three years of research funding. This time, it’s not from DARPA, but from the VA’s Prosthetics and Sensory Aids Service. This is a big step; even without knowing all the details, when funding shifts from the crazy world of DARPA to the Veteran’s Administration, actual availability seems and lot closer. And this appears to be the case: “veterans fitted with the arm will provide feedback to guide engineers in refining the prototype, before it is commercialized and also made available through the VA health care system.” So, it’s very possible that in just a few years, and 18 DoF thought controlled cyborg arm will be available to people who need one.

[ Press Release ] VIA [ Robots.net ]

Rather than develop a robot that’s programmed to solve problems like a human, researchers at the AnimatLab in France are starting with a much simpler (and some might say more effective) problem solver: a rat. Psikharpax (I have no clue how to pronounce that, so don’t even ask) is a robot that not only looks like a rat, but is designed to operate using nearly all of the same sensory organs as a rat, including a set of sensitive whiskers. The software that controls the roborat is also designed to mimic real rats, relying on simple sensor inputs to dynamically build mental maps of complex environments.

So far, Psikharpax has eyes, ears, 32 whiskers per side, and (in a minor departure from its biological counterpart) battery powered wheels. A nose is in the works, and eventually Psikharpax will be able to sit up and grasp things with a set of front paws. At 50 centimeters long, Psikharpax will ultimately be fully autonomous, able to explore new environments and use learning behaviors to develop foraging techniques. And in case you were wondering (I know I was), “Psikharpax” was the King of the rats in the Batrachomyomachy, a parody of the Iliad written in Greek verses and (falsely) attributed to Homer. The name means “crumb robber”.

Crumbs, nothing. Robotic black plague, here we come.

[ AnimatLab ] VIA [ Physorg ]

In this test run, Willow Garage’s PR2 robot (which we’ve covered before) was instructed to navigate a typical office environment consisting of eight doors, and was supposed to plug its power cord into ten outlets. One of the outlets was behind a locked door, but PR2 was able to understand that the door was locked and move on. It was also able to understand when it failed to do something, and then tried again, which is a crucial skill for robots that need to adapt to new and changing environments: there’s a difference between a task which cannot be completed, and a task which can be completed but might take a few tries.

I love the idea of a robot that is able to plug itself into an electrical outlet. Pretty much every other robot that is capable of self charging depends on a base, which is something else to buy, something else that can break, something the robot has to find, and something that can only be in one place at a time. As you can see, it takes a bunch of tries for PR2 to plug itself in, but who cares? This is one of those situations where developing a robot that’s able to plug into a socket 20% of the time (but try over and over) is (I imagine) much more efficient than developing a robot that’s able to plug into a socket 100% of the time.

[ Willow Garage ]

It takes a demonstration like this to make you realize just how critical body language is to conveying emotion. Kobian is a humanoid robot developed by Takanishi Lab at Waseda University (remember them?) to explore how robots might get better at natural human communication. Among its many physical talents (walking, tactile/visual/olfactory sensing, etc.), Kobian is able to bodily express a variety of different emotional states, including happiness, fear, surprise, sadness, anger, and disgust. See if you can guess which one this is:

Kobian isn’t just doing this passively, either… It’s actually been programmed to select appropriate emotional responses based on a “mental state,” which in turn is influenced by internal and external stimuli. So yes, if you try, I’m sure you can get it to make its disgusted face. Eventually, Kobian might end up in nursing, or in some other environment where realistic human interaction is a priority.

[ WE-4RII ] VIA [ Pink Tentacle ]