Slashdot Mirror
Kinect Revolutionizing Robotics
HizookRobotics writes "The Bilibot Project, an open-source robot platform based on Microsoft's Kinect, was just announced by MIT researcher Garratt Gallagher on Hizook.com. Bilibot is just the first in what will likely be a torrent of robots (both hobbyist and professional) utilizing the Kinect. This sentiment was echoed in an essay by Fred Nikgohar, CEO of RoboDynamics, who believes we've reached a watershed moment in robotics enabled by cheap 3D sensing. While much of the attention for the Kinect has focused on video gaming, perhaps robotics will be its greatest beneficiary."
Important advice: Always put a screen on your robot!
I've thought for a long time that companies have been missing out on the prospect of just giving people toys to play with. All these tablets, portable gaming systems, calculators, kinect, etc. would be so much more useful if they were opened up and just plain allowed to let people play and/or tinker with them but the companies involved have been oddly non-forthcoming in this regard. It's like how with basic legos (yes, legoS!) you can build whatever you want but with the trend towards highly specific, pre-determined builds it's just so limiting. One (ridiculously expensive) thing vs. almost unlimited possibilities, which would you rather have?
Kinect was actually developed by PrimeSense.
This is not entirely correct. One part of Kinect was licensed from PrimeSense, the range camera. Microsoft developed the software technology internally. People can argue, and do, what is the most important part, but I think it is the combination that is unique.
http://en.wikipedia.org/wiki/Kinect#Technology
It's revolutionary because prior to the launch of the Kinect, if you wanted both visual input and a depth map on a robot, you had to spend hundreds, possibly thousands of dollars on LIDAR sensors, which are fussy pieces of equipment at the best of times. Within its design range, Kinect is as accurate as any LIDAR sensor, much more reliable, and waaaaay cheaper. For this reason, a lot of robot designers don't bother with LIDAR, which means you have to estimate distance and range with GPS, direct image data, or a host of other not-quite-as-accurate means. Not to mention it handles skeletal tracking, gesture recognition and other unpleasant programming tasks itself, leaving the robot designer free to do other things.
Kinect really has kind of changed the game overnight. People are very excited about being able to equip accurate depth sensors on all kinds of robots that they wouldn't have bothered with before. Even if no "new" innovations were to ever appear from Kinect, the increase in accuracy of old standbys like manipulator arms will be tremendous now that they can have depth maps. I'm at Cornell at the moment, and many of the grad students in robotics already have Kinect-based projects well underway, and even in the undergrad robot learning classes (where you typically do one semester-long project) the professor is pushing Kinect as an option.
Dislike the Electoral College? Lobby your state to join the National Popular Vote Interstate Compact.
Yes, and the combustion engine automobile was invented in 1862, but wasn't available to the general public at a low price point until 1903. Do we remember Lenoir, or Carhart, or the Duryea brothers? No, we remember Ford, who built the assembly line process that standardized and cheapened the production of automobiles.
The robotics field needs this jump to standardization of components, APIs and functionality. Yes, academia is coming up with designs all of the time, but each one is custom hardware & software, akin to Professor Carhart's steam-powered automobile in 1871. After that, it needs to move into the consumer markets, where the masses can tinker, hack and tweak the designs to add functionality, and truly innovate.
<quote><p>makes it available to the general public at a low price point. </p></quote>
Point me to the item that does what the Kinect does, with the simplicity and cheapness of that Kinect. Cheapness, and how easy it is to use can be a game changer in any market.
On the hardware side, it is nothing MAJOR, such as an easy universal robotic language(which everyone uses) would be. However, it does mean more interactive robots that can navigate and recognise objects better. It will add all that, at a dirt cheap price and the implementation of it is only getting easier.
Cheapness and how easy it is may be a game changer in the consumer market, that's not even accurate here. What are you going to do buy a 360 and kinect and stick it in your robot? That's not a cheap solution. What makes the Kinect work is not the hardware, but the software behind it. Cheap digital hardware has been available for a long time. Japan has produced robots that "see" and "navigate" and adapt for quite some time now. It's true they aren't cheap, but sticking a kinect in one of them won't change the price point as that is such a small part of the price.
If you are going to use the kinect for robotics, the hardware cost of something other than the kinect unit is not the obstacle. Even with the kinect unit, hardware is not the problem. Developing the software to make your robot do what you want it to is the hard part. Making the software be able to adapt to unplanned situations is even more difficult. The kinect doesn't provide any of that.
Don't get me wrong, having a game console use software that can figure out what my hands and/or feet are doing is impressive, but in terms of revolutionizing robotics, it doesn't. At best it might be evolutionary, but definitely not revolutionary.
The Kinect is a simple, convient package that they've figured out how to use the input from to work into all of the existing algorithms. And it's at a cheap enough price point that you don't see it as a hurdle.
If you wanted to, you could produce an IR emitter and hack a web cam into an IR web cam. Add in microphones and a color web cam. So it isn't the technology that is revolutionary. It isn't the software because they are just using the hardware and running the input into existing robot software.
It's the same thing with the Wii-mote. It isn't that you couldn't do it for youself, but it's become a cheap, off-the-shelf solution. What that means is that it's at a price point that you don't fret over spending it and it's been tested by the manufacturer, so you can get it fixed if it isn't working right. All of this lead to an explosion of "wouldn't it be cool if" and then people doing it. And that's where the revolution is.....people stop worrying about the how and start thinking about the what.
I love the kinect; I've done some great stuff in my robotics research with it already. It's a great sensor for testing out algorithms because of the high definition of the data, but it's next to useless as a long term solution for mobile robotics due to the nature of structure light sensors; the dot pattern projected by the IR camera can be easily interfered with by other kinects.
While there has been one example of two cameras working orthogonally, I can't see it expanding much more beyond that. To use more than a couple, you'd have to time the sensors to work together, or something more ingenious. Regardless, right now they're great in the lab, but the state of mobile robotics is still such that good sensors cost >$10,000.
Actually, the iPod was a revolutionary because it took disparate technologies and put them together in a new way to produce a new product. The kinect, from a gaming perspective might be revolutionary, but from a robotics perspective is just a consumerized version of what already was in the robotics field. Sure it is at a cheaper price point, and that may benefit research, but that doesn't revolutionize the robotics industry.
Do you really believe that the makers of industrial robots are going to stick kinects on all of their robots? Do you really believe that the military will use kinects as the brains of their drones? Do you really believe that future cars will have a kinect sitting in the grill for accident avoidance? Kinects provide a way to do rapid development, but it is not a robust enough or harden enough for other than consumer applications.
Now, one may argue that it will be hardened and it will be improved, but what that actually means is that different software will be developed to control it, which at that point, it no longer is a kinect.
Years ago, Lego came out with their Mindstorm robotics kit. It used a lot of the same technology that was being used in real robotic research at the time. Nobody claimed it was revolutionary. It was useful for turning kids on to robotics and computers. It was useful in the laboratory for prototyping things, but nobody actually developed a robot for outside the lab that was powered by Mindstorm. Likewise, the kinect may turn people onto robotics. I am sure it will be useful in the lab to prototype things, but actually being integrated, as is, into a product? No, that won't happen.
Again, using the military or manufacturing robots as an example, the cost of the sensor being a $100 or $1000 is not the issue. It is the underlying software that is the expensive part. The kinect provides the cheap hardware sensor. It does not nor cannot provide the underlying software that is specific to the task at hand.
I am not doubting that the Kinect is changing the game. I just question whether it is revolutionary or not.
Kinect is changing the game but it's not revolutionary? What's your definition of a revolution then? Before the kinect, it cost me close to $10,000 for a good 3d point cloud data. If I had more room on my robot, I might put a Hokuyo LIDAR on a pivot but that still put me back 6 grand. Today I use industrial sensors from IFM, re-purposed for Robotics. They cost about $1500, and only provide 50x64 pixels of range data, as compared to the Kinect's 320x240.
So the cheapest feasible sensor I can buy costs $1500. So here comes Microsoft. They're selling a sensors 10 times cheaper with 24 time the resolution. Now any old schmuck can buy this and test their idea for a new image segmentation algorithm. This has NEVER been possible before.
So yeah, Kinect is changing the game. That's the definition of a revolution. Just because it was done in a lab before by Ph.D.s after 10s of thousands of dollars of time, effort, and equipment doesn't diminish it. If a company started selling robot cars to the public, that would be revolutionary too, even though we can do that in the lab (for $1,000,000+).
And Microsoft can't get all the credit; none of this would be possible without ROS and the amazing Point Cloud Library. This is a second component of the kinect revolution, which, in itself is revolutionary.
Physical rehabilitation at home, where the machine can truly tell if your doing your exercise correctly?
This device has so many uses we have only begun to scratch the surface.
My opinion, one of the most important innovations available to the public for working with computers/etc since the mouse. Microsoft could have really screwed this up but they really hit a homerun. While it may not pan out for as well as they want for its original purchase the ideas it sparks will show its true worth. When I played with one it was the first time I had the feeling that the future really is getting closer.
* Winners compare their achievements to their goals, losers compare theirs to that of others.
Do you really believe that future cars will have a kinect sitting in the grill for accident avoidance?
Actually they're using sensors from Velodyne, which are doing to LIDARs what the Kinect is doing to 3D sensors. It used to be that you needed an array of 2D LIDARS to create a 3D image. These could cost upwards of $100,000, where prone to failure, time consuming to create, and one of a kind. Then came Velodyne with their $70,000 3D LIDAR now being used on any serious autonomous vehicle. Of all the cars that finished the DARPA urban challenge, only one didn't use a Velodyne. Even Google's autonomous car has one. Now Velodyne released a new model for $20,000 the size of a coffee mug.
Yes in 2005 we could create a 3D image using lidars. That was 5 years ago, and at the time we couldn't get a car to drive through the desert. Now, because of Velodyne and the ubiquity of their sensors, cars are driving themselves through crowded streets.
Was the Velodyne revolutionary? Absolutely. Was it brand new? No, we had 3D sensors on our cars before. But it was smaller, cheaper, and easier to integrate, which is exactly what the kinect is.
the kinect isn't revolutionary because it holds a very small percentage of the market.
What market? I don't know a robotics lab without at least a couple kinects, or a robotics hobbyist, who doesn't have one or isn't planning to get one.
As many have posted, it is being used in robotic research right now. It has the potential to revolutionize that field. It just hasn't had time to do that, yet.
I do robotics research, and I can uneqivocally tell you it has already changed the course of robotics in a way we never thought possible. On of the biggest problems in robotics, and even in computer science in general, is reproducibility. Every lab has their own sensors, their own robot platforms, and their own software to run their robots. If I develop an algorithm for detecting pole features in my lab, there's no guarantee you can get it to work on your robot without a lot of work, if at all.
ROS is one part of the equation, as it provides a common software basis for robotics development. This is great, and in itself is revolutionary, but we're still not there unless labs can share a common sensor to capture data with. The kinect is this sensor, and it has allowed robotics researches to develop algorithms, publish them, and reproduce them in a way never before seen in robotics.
Even further, hobbyists can download the very same cutting-edge algorithms being developed in universities and use them on their robots. Maybe they can even improve them! The Kinect sensor, along with ROS, is taking robotics development out of the universities and putting it into the hands of actual users. This is not a small feat, and I feel like you're marginalizing it without really understanding what the implications are.