Skip to content

Conversation

@xieleo5
Copy link
Contributor

@xieleo5 xieleo5 commented Oct 13, 2025

What this does

  1. Add a external torque compensation flag, enables user to pass torque. This feature can better align sim and real envs
  2. Support timestep in observables to make sure playback not diverge
  3. Add qacc for robot joints to support WBC, add imu sensor to support WBC

How it was tested

The G1 locomanip repo will be open-sourced soon. It will include unit test for these features.

@xieleo5 xieleo5 changed the title add qacc for gripper Support G1 Locomanip Oct 13, 2025
@xieleo5 xieleo5 changed the title Support G1 Locomanip [Draft] Support G1 Locomanip Oct 13, 2025
self.torques = None

# External torque compensation
self.external_torque_compensation = 0
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry if I am missing something, but right now it looks like there isnt any way to pass in any custom value for external_torque_compensation right?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

G1 will use this flag to make sure that the gravity compensation is the same between sim and real.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

But how will you set the value of the flag? right now it seems like there is no way to pass in any values to the class?


self.desired_torque_as_acceleration = kwargs.get("desired_torque_as_acceleration", True)
self.use_torque_compensation = kwargs.get("use_torque_compensation", True)
self.use_external_torque_compensation = kwargs.get("use_external_torque_compensation", False)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

would it be possible to add in desired_torque_as_acceleration and use_external_torque_compensation as parameters instead of using the **kwargs?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants