soldierofhell

See the cost implementations in https://github.com/rst-tu-dortmund/mpc_local_planner/tree/master/mpc_local_planner/include/mpc_local_planner/optimal_control They subclass corbo::StageCost mostly by implementing computeXXXTerm() cost terms

I'd check the output of optimizer

Do you mean something like [lift&drag plugin](https://gazebosim.org/tutorials?tut=aerodynamics&cat=physics) in gazebo?

Thanks. To me it seems like they overdo with this cleanup. They should let people decide what "style" they wanna use. But yes, lets wait for what will happen, e.g....

@simutisernestas, but if we take arbitrary pointcloud then we have to fill holes in the projected image. There's no guarantee it will have proper sematic meaning for detector. To me...

Hi @Achllle, can you upload anything you have so far that can help in robot_description creation? Regards,

I've tried oldest available image (v93) (with run.sh from v93 tag) and 1. some errors after container startup disappeared, but not all ``` SHA1 Fingerprint=84:18:A8:5D:10:5F:A8:F2:91:17:09:87:08:21:B4:68:9E:BC:F5:37 SHA256 Fingerprint=6B:D8:3D:16:A7:0C:6E:B9:89:ED:E8:41:14:23:8D:24:50:D1:15:A8:AE:D3:B4:A2:7E:E5:98:0C:18:1F:AC:87 [20230613-20:23:27] [INFO ]...

BTW I hope I will succeed in make it work, because I've read previous "success story" for NVIDIA GPU (vide https://github.com/hectorm/docker-xubuntu/issues/7#issuecomment-841833211). Unfortunately that was before v93 tag, but I guess...

I went back to v69, added parameters required by Nvidia Container Toolkit to run.sh and it works! Now I'll try to narrow down what works and what causes troubles

@afathi3, @HRLTY, any update on pretrained models?