it is often possible to just pop off the existing head and replace it with a new head for the new labels.
Transfer Learning
2 Matching Annotations
- Oct 2021
-
manipulation.csail.mit.edu manipulation.csail.mit.edu
-
- Sep 2021
-
manipulation.csail.mit.edu manipulation.csail.mit.edu
-
Here is a simple example of loading a floating Schunk gripper and a brick, computing the grasp / pregrasp pose (drawing out each transformation clearly), and rendering the hand relative to the object.
For the Colab, shouldn't the comment, "Define (again) the gripper pose relative to the object when in grasp" be, "Define the pose of the object in grasp relative to the gripper"? The math doesn't seem to match up for me if it really is the gripper pose relative to the object. Please correct me if I'm mistaken; I'm still quite new to it all.
-