search

psc0628 / SCVP-Simulation

MIT License
4 stars 0 forks source link

Question about input octomap #2

Open jjpatino-byte opened 2 weeks ago

jjpatino-byte commented 2 weeks ago

Hi! I am wondering how to get the input Octomap (M). Should it be created from the obtained pointcloud with respect to the sensor frame, or should they be transformed to the global frame (e.g. robot base frame)?

psc0628 commented 2 weeks ago

Thanks for your question. The point cloud obtained from the sensor should be transformed to the global frame (where Z+ is the normal vector of the horizontal plane, e.g., the tabletop or the ground) since the output from our pre-trained network is constrained to a predefined view space in the global frame.

jjpatino-byte commented 2 weeks ago

Taking into account that the pointcloud should be transformed to the global frame. Does it matter where the object center (which is the same as the hemisphere center) is with respect to global frame?

Thanks for your question. The point cloud obtained from the sensor should be transformed to the global frame (where Z+ is the normal vector of the horizontal plane, e.g., the tabletop or the ground) since the output from our pre-trained network is constrained to a predefined view space in the global frame.