Experts Warn of ‘Terminator’-Style Military-Robot Rebellion:

Autonomous military robots that will fight future wars must be programmed to live by a strict warrior code, or the world risks untold atrocities at their steely hands.

The above headline and quote is how Fox News decided to lead their story on an Office of Naval Research report on military robot ethics. You can read the full report here (*.PDF).

Firstly, just let me say that this is certainly a relevant issue, and it’s something that needs to be carefully thought about, discussed, and addressed. But this is not how to go about doing that. The media has tenaciously latched onto the idea of military robots killing innocent people, because it happens in the movies and it gets people upset. But it’s not accomplishing anything, and is just encouraging the public to be that much more resistant to (and even afraid of) robotics. This sucks, and it sucks that so-called “robotics experts” are encouraging this sort of behavior, since it sets us all back.

I’d like to spend a little time discussing this issue, mostly because I think it’s important, but partially because I’m seriously pissed off. Don’t worry, I’m not going to rant (much), but I am going to try to explain why I think battlefield robotics are the future and why it’s possible and reasonable and a good thing, and also why in a lot of ways, we are experiencing (and benefiting from) that future already. (Read more…)

It’s a battle station! It’s a galactic shuttle! It’s a cosmic tank! It’s a solar creature! It’s a robot!

It’s pure, unapologetic 80s genius, is what it is.

VIA [ Retro Thing ]

That’s right: now they’re reproducing. Run for the hills!

Noelle is a robotic birth simulator with all the bells and whistles, including breathing and a pulse. Her anatomy is functionally correct and she can simulate all kinds of delivery situations in order to help train people. Just a mild warning; the video could be considered NSFW in a weird medical sort of way as it includes simulated robotic lady parts.

If you’re lonely, you can get your own Noelle (complete with a newborn babybot named HAL) for just shy of $38,000… Military-grade carrying cases are optional for another $2k.

[ Gaumard Scientific ]

Unless you want to invest in an entire fleet of smaller robotic mowers, your golf course might require something a little more… You know… Beastly, when it comes to maintenance. I know mine does. The RG3 (Robotic Greens Mower 3) weighs a hulking 650 pounds, goes 3.5 miles per hour, and has been engineered specifically for the golf industry. It’s powered by 3 lead-acid batteries that give you 3 hours worth of “whisper-quiet” mowing.

Rather than use a boundary wire like most other robotic mowers, the RG3 relies on ultrasonic detectors, infrared sensors, and a system of four 7 pound, several foot tall beacons to determine its position on an otherwise mostly featureless green. The operator (so okay, it’s not entirely autonomous) positions the beacons around each green, and with their assistance, the RG3 can navigate its way precisely enough that it covers the entire green in one pass. It can even mow in patterns, if you’re the fancy type.

You probably won’t be shocked to learn that the RG3 costs nearly $30,000. Additional modules are planned that will eventually allow the robot to mow entire fairways, rake sand traps, spot treat the grass with pesticides and fertilizers, and nuke gophers.

Okay, not actually nuke gophers. Gophers are cute, I like gophers, unlike some people…

[ Precise Path RG3 ] VIA [ CNET ]

When Americans finally make it back to the moon, we’re gonna need a base. It’s going to have to have (among other things) laboratories, a powerplant, housing, and a landing pad for resupply craft. CMU’s William “Red” Whittaker (whom you may especially remember from here), explains why robots may have a little bit of work to do before we start taking up residence: “for efficient cargo transfer, the landing site needs to be close to the outpost’s crew quarters and laboratories. Each rocket landing and takeoff, however, will accelerate lunar grit outwards from the pad. With no atmosphere to slow it down, the dry soil would sandblast the outpost.”

That leaves two options: build a big hill to keep dust contained, or pave the landing area to keep dust from getting kicked up in the first place. Either one of these options involves a lot of tedious work… For example, building a protective hill (8.5 feet tall in a 160 foot semi-circle around the landing area) would involve something like 2.6 million pounds of lunar soil. That sounds like a lot, but but two 330 pound robotic rovers the size of riding lawnmowers could get the job done in just six months. Similarly, a couple robots could sift soil in the area around the pad to collect rocks suitable for paving. These particular robots have been developed by Astrobotic Technology, who plan to send robots to the moon and then license the scientific and engineering data that they collect to space agencies and other aerospace companies.

Figuring out which dust reduction method would be best will most likely involve sending a scouting mission (robotic scouting mission, I bet) to the as yet undecided site for the lunar outpost, which is expected to begin operations by 2020.

[ CMU Press Release ]
[ Astrobotic MoonDigger Presentation (PDF) ]

Starting next week, NYC L line subway trains will be completely under the control of the Communications Based Train Control (CBTC). At first, the system will only be used in the middle of the night and during off-peak hours, but ultimately the Metro Transit Authority wants CBTC trains to be running full time, since it should help relieve overcrowding. At first, human conductors will supervise everything hands-off from the cab of the train, but this isn’t because anybody is worried about the safety or performance of the system… Rather, “the MTA had wanted to remove conductors from trains in automatic mode but had to back off because the move violated the transit workers’ contract.”

Hm.

I wonder if they have a “no robots” clause in their contract? I also wonder how long humans will continue to monitor the CBTC system, and how many future jobs are going to contractually degenerate into humans watching robots do the jobs they used to have faster and more efficiently. Now, I’m not siding with the robots on this one, I’m just saying that it’s not a very adaptable system that we have going now… Barring the manufacturing industry, I don’t think most job sectors are really prepared for what may happen in the next decade or so. Think about it: could a robot do your job?

[ NY Daily News ] VIA [ Engadget ]
Random weird robot train pic VIA [ Modern Mechanix ]

Searching for a picture that would somehow be appropriate for “chaos robot” for the previous article, I came across the Chaos high mobility robot, developed by Autonomous Solutions. It’s sort of like a PackBot, except instead of two tracked flippers and two tracks, it’s got four big tracked flippers that not only let it power through all kinds of terrain, but also let it tow a Hummer. Over slippery concrete. With two guys standing on top of it:

The tracks are independently controllable, and Chaos can even stand up on them and “walk,” enabling it to take 45cm vertical steps and cross 60cm gaps. The robot itself weighs 55kg, and can travel at a top speed of 8 kph for up to 2 hours. It comes with a color video camera in the front, but is primarily designed to accept modular equipment packages for surveillance, EOD, HAZMAT, or just about anything else you want to bolt on there. It’s not as light or as portable as a PackBot, but it certainly seems to offer some pretty robust mobility options.

[ Chaos High Mobility Robot ]

Autonomous robot navigation in complex environments is tricky. When I say “complex,” what I really mean is complex environments that may change. For example, a software algorithm can compare two very complex scenes and determine if they are more or less identical, even from different angles or under different lighting conditions. But, say your complex scene is a busy city street. The exact same perspective at the exact same time each day might be radically different, as there are different cars in the street, different people on the sidewalk, and different signs in store windows. Even though the content of the scene is different, the scene itself is the same, and this is a hard thing for robots that rely on sensor similarity analysis to understand.

Researchers from the Oxford Mobile Robots Group have developed a mapping system called FabMap (Fast Appearance Based Mapping) that compares two scenes the same way that people do to determine whether or not they’re looking at the same place. Instead of analyzing every detail of a scene, humans group things into units, and figure out how different scenes are based on that. For example, when comparing an occupied and vacant driveway scene, a robot might say, “this scene is missing a red boxy object on top of some round objects that took up a significant percentage of the previous scene, therefore this scene must be different.” A human would know that despite all of the different details, there is only actually one difference in the scene: there’s no car in it. This is what FabMap does: it allows robots to group objects into units and recognize when a single unit has changed as opposed to many discrete features. This attention to specific units rather than discrete features also makes the system much better at recognizing when two scenes which look almost the same, aren’t.

In the image pairs above, green circles represent similarities while red circles represent changes. Even when there are significant differences like the absence or presence of a person, the software is still able to recognize major similar units in the images and match them with a high probability.

The obvious advantage to this technique is that it doesn’t require any complex hardware or external guidance (like a GPS signal), meaning that it works just as well indoors. Plus, it’s more adaptable than GPS outdoors, providing actual information about the environment rather than just a set of coordinates.

[ FabMap ] VIA [ New Scientist ]

The CirculaFloor intelligent floor tile system was designed in late 2004 at the University of Tsukuba in Japan as a way to enable unrestricted static movement in virtual reality. Sounds like an oxymoron, I know, which is why it’s a tricky problem that has resulted in one or two interesting and different solutions. CirculaFloor is the most portable of these, and evidently the most adaptable, since the latest version allows for movement in all three axes, more or less:

Each robotic tile cycles in sequence (on holonomic bases) such that the next step is always available to the user. At the same time, the entire assembly moves slowly in reverse so that you feel like you’re going somewhere without actually moving (a 5 meter square of area is sufficient for continuous movement in any direction). The tiles also incorporate lifts sufficient to replicate the feeling of climbing stairs… After you step up, the tile slowly descends, bringing you back to ground level in time to step up onto the next tile. I imagine descending stairs works the same way, just in reverse.

The original CirculaFloor system used magnets attached to the user’s shoes along with sensors in the tiles to figure out the direction of movement, although it looks like you probably have to be pretty careful lest you walk in a direction in which the tiles are not expecting and fall on your ass. Also, the cycle speed of the tiles is obviously not fast enough to allow for a true immersive VR experience. But, it works, and if it keeps pace with the rate of progress that the rest of the robotics industry tends to exhibit, you should be running around in WoW (for real) in maybe just a few years.

VIA [ Robot Watch (Translated) ]

I could have sworn I’d posted about Humans Are Dead before… It’s a song by the New Zealand band Flight of the Conchords, with awesome lyrics and an awesomer music video. A talented seamstress named Lily whipped up this piece of embroidery for a FOTC swap meet, and it’s just about the best thing ever. If you’re a little lost as to the significance, I’ve posted the music video below:

[ Lily Blogs ] VIA [ Neatorama ]