unilab.envs.locomotion.go2w.rough.Go2WJoystickRoughCfg

class unilab.envs.locomotion.go2w.rough.Go2WJoystickRoughCfg[source]

Bases: Go2WJoystickCfg

Go2W rough terrain task with procedurally generated sub-terrains.

Parameters:

  • scene (SceneCfg)

  • sim_dt (float)

  • max_episode_seconds (float)

  • ctrl_dt (float)

  • render_spacing (float)

  • render_offset_mode (str)

  • motrix_max_iterations (Optional[int])

  • post_step_forward_sensor (bool)

  • control_config (ControlConfig)

  • noise_config (NoiseConfig)

  • sensor (JoystickSensor)

  • asset (Asset)

  • init_state (InitState)

  • commands (Go2WRoughCommands)

  • reward_config (RewardConfig | None)

  • domain_rand (Go2WDomainRandConfig)

  • terrain_scan (HeightScanConfig)

  • termination_config (RoughTerminationConfig)

  • terrain_curriculum (TerrainCurriculumCfg)

Methods

__init__([scene, sim_dt, ...])

validate()

validate the config

Attributes

ctrl_dt

max_episode_seconds

max_episode_steps

return the max episode steps

motrix_max_iterations

post_step_forward_sensor

render_offset_mode

render_spacing

reward_config

scene

sim_dt

sim_substeps

return the number of simulation steps per control step

commands

terrain_scan

termination_config

terrain_curriculum

init_state

sensor

domain_rand

noise_config

control_config

asset

scene: SceneCfg = None
commands: Go2WRoughCommands
terrain_scan: HeightScanConfig
termination_config: RoughTerminationConfig
terrain_curriculum: TerrainCurriculumCfg
__init__(scene=<factory>, sim_dt=0.005, max_episode_seconds=20.0, ctrl_dt=0.02, render_spacing=1.0, render_offset_mode='grid', motrix_max_iterations=None, post_step_forward_sensor=False, control_config=<factory>, noise_config=<factory>, sensor=<factory>, asset=<factory>, init_state=<factory>, commands=<factory>, reward_config=None, domain_rand=<factory>, terrain_scan=<factory>, termination_config=<factory>, terrain_curriculum=<factory>)
Parameters:

  • scene (SceneCfg)

  • sim_dt (float)

  • max_episode_seconds (float)

  • ctrl_dt (float)

  • render_spacing (float)

  • render_offset_mode (str)

  • motrix_max_iterations (Optional[int])

  • post_step_forward_sensor (bool)

  • control_config (ControlConfig)

  • noise_config (NoiseConfig)

  • sensor (JoystickSensor)

  • asset (Asset)

  • init_state (InitState)

  • commands (Go2WRoughCommands)

  • reward_config (RewardConfig | None)

  • domain_rand (Go2WDomainRandConfig)

  • terrain_scan (HeightScanConfig)

  • termination_config (RoughTerminationConfig)

  • terrain_curriculum (TerrainCurriculumCfg)

ctrl_dt: float = 0.02
max_episode_seconds: float = 20.0
property max_episode_steps: int | None

return the max episode steps

motrix_max_iterations: Optional[int] = None
post_step_forward_sensor: bool = False
render_offset_mode: str = 'grid'
render_spacing: float = 1.0
reward_config: RewardConfig | None = None
sim_dt: float = 0.005
property sim_substeps: int

return the number of simulation steps per control step

validate()

validate the config

init_state: InitState
sensor: JoystickSensor
domain_rand: Go2WDomainRandConfig
noise_config: NoiseConfig
control_config: ControlConfig
asset: Asset