search

Unity-Technologies / Robotics-Object-Pose-Estimation

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.
Apache License 2.0
293 stars 75 forks source link

Is this project compatible with Ubuntu 18.04? #44

Closed tensarflow closed 2 years ago

tensarflow commented 2 years ago

Hello there,

I am trying to install this under Ubuntu 18.04. In the Readme's I can't find any OS requirement so I just went ahead and did it. Catkin_make works as expected but when I try to run roslaunch ur3_moveit pose_est.launch I get python 2.7 related errors. Probably because ASFAIK, Melodic is Python 2 based and Noetic Python 3 based. I think there are ways of enabling Python 3 in Melodic. I will try that and post the update here.

Environment

tensarflow commented 2 years ago

Update: I decided it wasn't worth the effort and installed Ubuntu 20.04 :)