Language

unilab.tasks.motion_tracking.g1.manager_terms.BoxMotionCommand¶

class unilab.tasks.motion_tracking.g1.manager_terms.BoxMotionCommand[source]¶

Bases: MotionCommand

Parameters:

cfg (BoxMotionCommandCfg)
env (ManagerBasedRlEnv)

Methods

`__init__`(cfg, env)
`compute`(dt[, env_ids])	Advance the command state by dt.
`post_compute`()	Refresh state that depends on committed command-side simulation writes.
`reset`(env_ids)	Resets the manager term.

Attributes

`anchor_ang_vel_w`
`anchor_lin_vel_w`
`anchor_pos_w`
`anchor_quat_w`
`body_ang_vel_w`
`body_lin_vel_w`
`body_pos_w`
`body_quat_w`
`box_motion`
`command`
`joint_pos`
`joint_vel`
`name`
`num_envs`
`object_pos_w`
`object_quat_w`
`object_state_b`
`robot_anchor_ang_vel_w`
`robot_anchor_lin_vel_w`
`robot_anchor_pos_w`
`robot_anchor_quat_w`
`robot_body_ang_vel_w`
`robot_body_lin_vel_w`
`robot_body_pos_w`
`robot_body_quat_w`
`robot_joint_pos`
`robot_joint_vel`
`cfg`

cfg: BoxMotionCommandCfg¶

__init__(cfg, env)[source]¶

Parameters:

cfg (BoxMotionCommandCfg)
env (ManagerBasedRlEnv)

property box_motion: BoxMotionData¶

property object_pos_w: ndarray¶

property object_quat_w: ndarray¶

property object_state_b: ndarray¶

post_compute()[source]¶

Refresh state that depends on committed command-side simulation writes.

Return type:: None

__call__(*args, **kwargs)¶

Returns the value of the term required by the manager.

Return type:: Any

property anchor_ang_vel_w: ndarray¶

property anchor_lin_vel_w: ndarray¶

property anchor_pos_w: ndarray¶

property anchor_quat_w: ndarray¶

property body_ang_vel_w: ndarray¶

property body_lin_vel_w: ndarray¶

property body_pos_w: ndarray¶

property body_quat_w: ndarray¶

property command: ndarray¶

compute(dt, env_ids=None)¶

Advance the command state by dt.

With env_ids=None (the per-step path) all envs are updated; with env_ids (the reset path) timers and the command update are scoped to those envs. Metrics are refreshed each call; terms may scope per-row metric work to env_ids since other rows are unchanged since the per-step update, or defer row-wise metric work to reset() when reset is the only consumer (e.g. MotionCommand, issue #1355).

dt may be a scalar (all envs) or a per-env tensor (auto-reset path, where freshly reset envs get zero to keep their timers full). A tensor dt requires env_ids=None.

Parameters:

dt (float | ndarray)
env_ids (ndarray | None)

Return type:

None

property joint_pos: ndarray¶

property joint_vel: ndarray¶

property name: str¶

property num_envs: int¶

reset(env_ids)¶

Resets the manager term.

Parameters:: env_ids (ndarray | slice | None)
Return type:: dict[str, float]

property robot_anchor_ang_vel_w: ndarray¶

property robot_anchor_lin_vel_w: ndarray¶

property robot_anchor_pos_w: ndarray¶

property robot_anchor_quat_w: ndarray¶

property robot_body_ang_vel_w: ndarray¶

property robot_body_lin_vel_w: ndarray¶

property robot_body_pos_w: ndarray¶

property robot_body_quat_w: ndarray¶

property robot_joint_pos: ndarray¶

property robot_joint_vel: ndarray¶

metrics: dict[str, np.ndarray]¶