You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For the 'object_in_gripper', 'object_motion_during_closing_angular', and 'object_motion_during_closing_linear' fields, why are they single array of 2000 numbers instead of something like a 2000 SE3 matrices? How can these numbers be translated to describe the full position and orientations of a 3D object?
For the 'object_motion_during_shaking_angular' and the 'object_motion_during_shaking_linear' field, are these the rotation in radian and mm as described in the paper during shaking?
I understand that maintaining a dataset is a lot of work. I really appreciate this open-source dataset and the effort you put into it. Any response would be appreciated.
The text was updated successfully, but these errors were encountered:
Hi!
Everything under /grasps/qualities/.... are scalar values that describe aspects of grasp quality. In particular, ..._linear is the integral over the linear velocity ("speed"), whereas ..._angular is the integral over angular velocity of the object to be grasped (both relative to the hand frame, i.e., the lower this value the "better"). They are not the poses of the object.
The physical interpretation of the absolute values is limited since even for an equilibrium grasp the physics simulator will generate non-zero velocities. It makes more sense to use these numbers in a relative sense, to compare different grasps of the same object.
Hi,
I have some questions regarding the following fields in each of the grasp files:
For the 'object_in_gripper', 'object_motion_during_closing_angular', and 'object_motion_during_closing_linear' fields, why are they single array of 2000 numbers instead of something like a 2000 SE3 matrices? How can these numbers be translated to describe the full position and orientations of a 3D object?
For the 'object_motion_during_shaking_angular' and the 'object_motion_during_shaking_linear' field, are these the rotation in radian and mm as described in the paper during shaking?
I understand that maintaining a dataset is a lot of work. I really appreciate this open-source dataset and the effort you put into it. Any response would be appreciated.
The text was updated successfully, but these errors were encountered: