unilab.tasks.manipulation.stewart.balance.StewartTiltAction

class unilab.tasks.manipulation.stewart.balance.StewartTiltAction[source]

Bases: ActionTerm

Vectorized tilt IK using only the public entity state/control facade.

Parameters:

Methods

__init__(cfg, env)

apply_actions()

leg_control_for_tilt(target_tilt_rad)

Return six actuator controls for (roll, pitch) radians.

process_actions(actions)

reset([env_ids])

Resets the manager term.

Attributes

action_dim

executed_action

name

neutral_leg_lengths

num_envs

raw_action

requires_substep_state_feedback

Whether apply_actions needs state produced by the previous physics substep.

target_tilt_deg

cfg

cfg: StewartTiltActionCfg
__init__(cfg, env)[source]
Parameters:
property action_dim: int
property raw_action: ndarray
property executed_action: ndarray
property target_tilt_deg: ndarray
property neutral_leg_lengths: ndarray
leg_control_for_tilt(target_tilt_rad)[source]

Return six actuator controls for (roll, pitch) radians.

Parameters:

target_tilt_rad (ndarray)

Return type:

ndarray

process_actions(actions)[source]
Parameters:

actions (ndarray)

Return type:

None

apply_actions()[source]
Return type:

None

reset(env_ids=None)[source]

Resets the manager term.

Parameters:

env_ids (ndarray | slice | None)

Return type:

None

__call__(*args, **kwargs)

Returns the value of the term required by the manager.

Return type:

Any

property name: str
property num_envs: int
requires_substep_state_feedback: ClassVar[bool] = False

Whether apply_actions needs state produced by the previous physics substep.

False declares that the generated control is invariant across all physics substeps in one control step, so the env may apply it once before a batched backend step. State-feedback terms must override this declaration with True.