# Hand eye calibration Queries

**URL:** <https://get-help.theconstruct.ai/t/hand-eye-calibration-queries/18600>\
**Category:** Open Discussions\
**Tags:** error, howto\
**Created:** [August 7, 2022, 9:04am UTC](https://get-help.theconstruct.ai/t/hand-eye-calibration-queries/18600 "2022-08-07T09:04:27Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![varungoyal](https://get-help.theconstruct.ai/letter_avatar_proxy/v4/letter/v/ec9cab/32.png) [@varungoyal](https://get-help.theconstruct.ai/u/varungoyal)\
**Post date:** [August 7, 2022, 9:04am UTC](https://get-help.theconstruct.ai/t/hand-eye-calibration-queries/18600/1 "2022-08-07T09:04:27Z")

</div>

Hi ,

I have below mention queries :

a) After calibration is done successfully (I did not face any error), while pickup and place object, I realized the coordinate of object was return not correct (published by find\_object\_2d)? As it was some plus/minus x/y/z ? What might be issue for this ?

b) Is there any way or tool , I can identify the calibration is correct or not after generating the file easy\_handeye\_on\_base.xml?

c) Is there any guideline to keeping the EE and camera . As I can see xArm has limit upto 700mm along x/y/z axis, when I move the robot to starting/observing position at x=500mm and Z=500mm (which I think suitable) it observe the object. Thereafter it has very limited scope in X/Z axis for pickup the object. What should I do for this.

d) While using Move IT , I observed object was just kept vertical down to gripper , but move It return fraction of 15% , and sometime also I feel that the trajectory from this position is quite easy and can pick by robot but then I found fraction is \<90% . What might be the issue , and what needs to be done for this ? How can I check trajectory and why move it is returning fraction (computeCartesianPath) which is \<90% for simple locations?

e) Suppose object is in rectangular shape having 8 sides. When I choose the object from QT tool , I can choose only one frame and realsense-camera identify that frame only. What if I need to provide all 8 sides/frame of object as object detecion/descriptor . How can I do it.

f) How can I provide the object detection for multiple objects (square, circle or rectangle any shape) and can provide to pick the object for particular shapes e.g. square one only

g) I observer Coordinate return from camera to End effector was not center of object , I think I might be the center of frame only. How Can I return the coordinate of Centre of object? I tried to do manually plus/minus X position ,it works fine . But when I kept the object at some angle to camera then it fails. Is there any generic algorithm for returning the center coordinate of any object ?

Thanks

---

<div class="post-metadata">

**Author:** ![system](https://get-help.theconstruct.ai/uploads/default/original/2X/9/9d3ce8305cc0d0d9b6e07d15767a6f245c526f1b.jpeg) [@system](https://get-help.theconstruct.ai/u/system)\
**Post date:** [August 14, 2022, 9:04am UTC](https://get-help.theconstruct.ai/t/hand-eye-calibration-queries/18600/2 "2022-08-14T09:04:43Z")

</div>

This topic was automatically closed after 7 days. New replies are no longer allowed.