6
$\begingroup$

Any one can advice me on the ideal perception sensors for pick and place application using a robotic manipulator with ROS support. I have generally looked at things like Kinect and stereo cameras (Bumblebee2) which provide depth that can be used with PCL for object recognition and gripper positioning. Are there any other sensors would be preferred for such application and if not what are the drawbacks of stereo cameras in comparison to Kinect or other sensing capability.

Thanks,

Alan

Improve this question
$\endgroup$
7
  • $\begingroup$ In a typical Pick and Place machine, your machine is already knowledgeable about the width, length and height of an object so I am not sure what stereo (or RGB-D) will do for you. How were you planning to use that? $\endgroup$
    – Spiked3
    Feb 12, 2015 at 11:25
  • $\begingroup$ In my case, the packages can be arbitrary and is not like a typical pick and place machine where it is in a fixed environment. This will essentially be a Mobile Manipulator. So the question is the Stereo or RGB-D camera sufficient for the arm to recognise and pick up an object? with PCL / OpenCV for processing. And what are the main differences between the two sensors? $\endgroup$
    – Alan
    Feb 12, 2015 at 11:37
  • $\begingroup$ Will the manipulator be a Serial or Parallel manipulator? If it is a top-down parallel manipulator then you may not need depth (just assume it is a constant planar surface). Will the camera be mounted on the end-affector? You can do stereo without 2 cameras by having accurate pose feedback. $\endgroup$
    – Gouda
    Feb 15, 2015 at 0:19
  • $\begingroup$ It is a serial manipulator from crustcrawler attached to a moving platform. I understand the case of top=down manipulator but I believe this is more difficult scenario, as the placement of objects to pick up are random. $\endgroup$
    – Alan
    Feb 16, 2015 at 9:58
  • $\begingroup$ Your criteria for making this judgment aren't very clear. Is this a cost problem or are you concerned with either speed or accuracy? $\endgroup$
    – Ian
    Apr 16, 2015 at 18:11

3 Answers 3

Reset to default
4
$\begingroup$

The Kinect is certainly a popular choice these days for robotics. However, time-of-flight, structured light, and stereo cameras all have their own strengths and weaknesses. These two threads have a good discussion:

I think the simple answer is that stereo requires visual texture in the scene, and you can alter your baseline for different min/max ranges. TOF cameras might have trouble with certain materials, and can give you false readings when an object is too close to the camera.

Improve this answer
$\endgroup$
2
$\begingroup$

The Structure sensor is a "3D sensor for mobile devices". Reading over the details it sounds like a smaller version of Kinect. It has open source drivers, openNI support etc. It's been on my to buy list for awhile but I don't have an immediate application just yet.

From the site,

The magic of 3D depth sensing begins with the ability to capture fast, accurate, dimensions of objects and environments.

I'm am in no way associated with the company that sells the sensor.

Improve this answer
$\endgroup$
4
  • $\begingroup$ That is quiet interesting, but slightly different applications I guess more into ipad based mobile robots. $\endgroup$
    – Alan
    Feb 13, 2015 at 15:37
  • $\begingroup$ yeah they definitely target it to iPad, but have the drivers for windows and linux as well. $\endgroup$
    – Matt Brown
    Feb 13, 2015 at 17:59
  • $\begingroup$ I wonder if you can use multiple of those camera simultaneously, will there be any interference from the projected infrared, just as with the Kinect $\endgroup$
    – Alan
    Feb 16, 2015 at 10:00
  • $\begingroup$ But last time I checked it is at least 3 times more expensive as the Kinect, $\endgroup$
    – Mehdi
    Jun 28, 2015 at 18:27
1
$\begingroup$

Kinect is an active 3D depth estimation setup that employs IR laser structured patterns for Depth calculation and are reliable for Indoor applications only.

Whereas,

Stereo Camera setup is a passive 3d depth estimation setup that typically involves use of Stereo calibration procedure in order to compute projection matrix that will transform a 2D point(generally observed in left camera) into a 3D point in the left camera coordinate system(assuming left camera is at origin[0,0,0]). These stereo camera setups performs way better than Kinect in case of outdoor applications.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.