Language Language English 简体中文

unilab.envs.mdp.commands.pose_command

Generic pose and posture command terms for Manager-Based tasks.

Classes

UniformPoseCommand	Uniformly sampled vector command held until the next resample.
UniformPoseCommandCfg	Sample a fixed-width pose vector independently per dimension.

class unilab.envs.mdp.commands.pose_command.UniformPoseCommand

Bases: CommandTerm

Uniformly sampled vector command held until the next resample.

Parameters:

• cfg (UniformPoseCommandCfg)

• env (ManagerBasedRlEnv)

cfg: UniformPoseCommandCfg

__init__(cfg, env)

Parameters:

• cfg (UniformPoseCommandCfg)

• env (ManagerBasedRlEnv)

property command: ndarray

metrics: dict[str, ndarray]

class unilab.envs.mdp.commands.pose_command.UniformPoseCommandCfg

Bases: CommandTermCfg

Sample a fixed-width pose vector independently per dimension.

Parameters:

• resampling_time_range (tuple[float, float])

• debug_vis (bool)

• ranges (tuple[tuple[float, float], ...] | list[list[float]])

• zero_command_prob (float)

ranges: tuple[tuple[float, float], ...] | list[list[float]]

zero_command_prob: float = 0.0

build(env)

Build the command term from this config.

Parameters:

env (ManagerBasedRlEnv)

Return type:

UniformPoseCommand

__init__(*, resampling_time_range, debug_vis=False, ranges, zero_command_prob=0.0)

Parameters:

• resampling_time_range (tuple[float, float])

• debug_vis (bool)

• ranges (tuple[tuple[float, float], ...] | list[list[float]])

• zero_command_prob (float)

resampling_time_range: tuple[float, float]

Time range in seconds for command resampling. When the timer expires, a new command is sampled and the timer is reset to a value uniformly drawn from [min, max]. Set both values equal for fixed-interval resampling.