I don't think I've mentioned it this week -- you might be interested to look at LeapMotion's new device for gestural recognition -- I'm suspecting (on darned little evidence) that they MAY have found a way to commercialize a spin-off of lenseless imaging, such that they're able to extract position data on-the-fly (under 30mSec latency, with a precision of 0.01mm). If you know anyone into virtual reality and heads-up display goggles, those have pretty much ALWAYS suffered from head-movement latency interference with "staying IN the virtual space". And (as I've pointed out to a few people) a device designed to be stationary with high-precision motion and gestural detection can just as easily be used as a spatial "mouse" to detect motion and orientation of goggles. And pretty much anything else. Expect to be seeing more of their stuff.
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This discussion will examine what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.