unilab.tasks.manipulation.stewart.balance.StewartTiltAction¶
- class unilab.tasks.manipulation.stewart.balance.StewartTiltAction[source]¶
Bases:
ActionTermVectorized tilt IK using only the public entity state/control facade.
- Parameters:
cfg (
StewartTiltActionCfg)env (
ManagerBasedRlEnv)
Methods
__init__(cfg, env)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
Whether
apply_actionsneeds state produced by the previous physics substep.- cfg: StewartTiltActionCfg¶
- __init__(cfg, env)[source]¶
- Parameters:
cfg (
StewartTiltActionCfg)env (
ManagerBasedRlEnv)
- leg_control_for_tilt(target_tilt_rad)[source]¶
Return six actuator controls for
(roll, pitch)radians.
- requires_substep_state_feedback: ClassVar[bool] = False¶
Whether
apply_actionsneeds state produced by the previous physics substep.Falsedeclares 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 withTrue.