Input specific location for an object for a trained policy #2186
Unanswered
ZachAtkins0n
asked this question in
Q&A
Replies: 1 comment
-
Thanks for posting this discussion. Have you considered training an object detection task using camera images and using the object detector as input to your manipulator? Isaac Sim has a list of examples that may give you good ideas about how to do this here. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I was wondering what would be the best way to about having a input for a block location that is read from a camera sensor for a manipulator? Would it be possible to use a trained robot model that was trained to move towards a block that was randomly spawned originally and then after training use a camera sensor to tell the robot where the block location is instead?
Beta Was this translation helpful? Give feedback.
All reactions