safsin
commented
4 months ago These are the descriptions I could find in the README of RT1 dataset:
- world_vector - commanded end-effector displacement, in base-relative frame
- rotation_delta - rpy commanded orientation displacement, in base-relative frame
- gripper_closedness_action - continuous gripper position
In the below function , what does world_vector , rotation_delta , gripper_closedness_action mean ??
def step_map_fn(step): return { 'observation': { 'image': tf.image.resize(step['observation']['image'], (128, 128)), }, 'action': tf.concat([ step['action']['world_vector'], step['action']['rotation_delta'], step['action']['gripper_closedness_action'], ], axis=-1) }