Miguel Riem de Oliveira

Hi @manuelgitgomes , Sorry but I am still not convinced. So the argument against touching the urdf is that: > the same JointSpace will achieve different robot poses on different...

Hi @v4hn , thanks for the detailed comments. My responses inline. > > I think the best is to change the xacro. If you change the xacro you can use...

> The thing is that all the other joint parameters do not have another standard place to be, whereas these joint offsets have, just like @v4hn explained. > I reiterate...

Hi @manuelgitgomes , where is the repo for the calibration package? I wanted to look at the config.yml. Also, please post the pdf that summarizes the calibration.

> As @manuelgitgomes just noticed when we looked at this, orientation is swapped for the example pictures which leads to a huge error. I am not sure to what @v4hn...

> It is in: > > https://github.com/manuelgitgomes/tams_pr2 > > The package is tams_pr2_atom_calibration. The config.yaml looks ok (the calibration pattern definition).

Concerning the pdf, it looks strange:  1. the transformation that has parent head_plate_frame has twice the word "to be calibrated". The problem is that in the config.yaml you defined...

> It should not, as I discussed with @v4hn. > Calibration patterns are asymmetrical. > Left corners have black squares, right corners have white squares. > The detection should not...

> @miguelriemoliveira is that block of code important or can be deleted? That was written by @eupedrosa . Eurico, do you remember why it was there? For now just comment.

I am still underwhelmed by the results. We are getting 8 pixels of average error. We should have less, or have a good explanation as to why we cannot get...