Skip to content
Discussion options

You must be logged in to vote

I reckon that the red ball demo is not a good example in that it makes use of a monocular approach. Only one camera is used and the depth (thus, the 3D position of the ball) is triangulated knowing the geometry of the ball.

Cameras in Gazebo are handled in the corresponding URDF model. For example, look at iCubGazeboV2_5_visuomanip:

This model is used in icub-gazebo-grasping-sandbox, where a stereo approach is adopted.


Try to remove the env variable YARP_CLOCK=/clock. It's an easier solution.

Replies: 1 comment 4 replies

Comment options

You must be logged in to vote
4 replies
@jimingda
Comment options

@jimingda
Comment options

@jimingda
Comment options

@pattacini
Comment options

Answer selected by pattacini
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants