I would like to know How to extract robots localization from the icp or ndt algo, currently I'm using scan registration for this reason

  • $\begingroup$ The question is not clear. The result of ICP is robot localization. Your scan registration lib is likely using ICP. NDT is a variant of ICP. $\endgroup$ Commented May 3, 2021 at 14:26
  • $\begingroup$ thx for your reply, as I know the ICP algo gives as a result the transformation T matrix, so my question is how to find the coordinates of the robot using this transformation T. If all this explanation is wrong please fee me with some books or articles or even if it exist a python package for that. $\endgroup$
    – ANAS.C
    Commented May 4, 2021 at 0:25
  • $\begingroup$ Welcome to Robotics ANAS.C, but I'm afraid that it is not clear what you are asking. We prefer practical, answerable questions based on actual problems that you face, so it's a good idea to include details of what you want to achieve, what you tried, what you saw & what you expected to see. Please take a look at How to Ask & tour for more information on how stack exchange works and work through the Robotics question checklist to edit your question to make it clearer. $\endgroup$
    – Ben
    Commented May 5, 2021 at 17:27

1 Answer 1


The transformation T itself contains the location and orientation of your robot. Try to search for some related information regarding SE3 pose representation.

Keywords: SE3, SO3, Rigid Body Kinematics, Matrix pose representation, coordinate transform

Some related materials: https://www.seas.upenn.edu/~meam620/slides/kinematicsI.pdf

Important: don't try to understand lie algebra.

T is composed of rotation and translation. The rotation is 3x3 matrix that is starting from left-top of your T. Each column of the rotation matrix is the x,y,z axis direction of the robot. And the translation which start from the left-most column of your T is just xyz location of your robot with respect to the world coordinate.

Direction is important. You need to find out if your T is world to robot or robot to world.

  • $\begingroup$ very useful for me, thank you $\endgroup$
    – ANAS.C
    Commented May 10, 2021 at 13:59

Your Answer

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

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