[RoboTwin-MeM] find_seal_and_seal_stamp/demo_clean episode 13 appears to be an erroneous trajectory

[yunlyuyuan]

We replayed all 50 released HDF5 trajectories in:

RoboTwin-MeM/hdf5/find_seal_and_seal_stamp/demo_clean

using the released RoboTwin-MeM environment and cached trajectories.

Episode 13 is the only episode where the strict check_success() returns False.

For episode 13:

At around 12 s, the robot arm accidentally collides with a cover. This causes cover 3 to be knocked away later in the trajectory, making the episode fail the task success check.

The other 49 released episodes do not show this issue.

Could you please confirm whether episode 13 should be considered a valid training demonstration?

Thanks for releasing RoboTwin-MeM.