I know there are lots of consumer depth image sensors: kinect, primesense, structure.io, leap motion, ... But I'm looking for something that is more suitable for integration into robot, something without case or with proper mount, compact and available for at least next five years if robot is going to production. Something similar to the sensors used in this drone https://www.youtube.com/watch?v=Gj-5RNdUz3I
What kind of processing power are you hoping to carry to do the depth sensing/processing? I would recommend the ZED camera when paired with an Nvidia K1 it works great for mobile vision processing, it is not environmentally sealed so it can only operate in good weather. It works from about 2-30m for most applications. if you are looking for bigger objects (like building sized) it can work a little further, around 50m.
If you want a low cost vision sensor that does all the work for you I sugest you look here -> Pixy Cam
From here you can work with two cameras and build your application using stereo vision to achieve 3D. You will have some work, because you have to use some kind of controller (arduino, netduino, whatever), build your own algorithm, build a case, etc... but it's cheap and it works fine.
Also, look here -> Question regarding 3d scanning and camera choice