OffWorldMonolithDiscreteSim-v0¶

class offworld_gym.envs.gazebo.offworld_monolith_env.OffWorldMonolithDiscreteEnv(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]

Bases: offworld_gym.envs.gazebo.offworld_monolith_env.OffWorldMonolithEnv

Discrete version of the simulated gym environment that replicates the real OffWorld Monolith environment in Gazebo.

env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.DEPTHONLY, random_init=True)
env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.RGB_ONLY, random_init=True)
env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.RGBD, random_init=True)

__abstractmethods__ = frozenset({})

__init__(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]: Initialize self. See help(type(self)) for accurate signature.

__module__ = 'offworld_gym.envs.gazebo.offworld_monolith_env'

_abc_cache = <_weakrefset.WeakSet object>

_abc_negative_cache = <_weakrefset.WeakSet object>

_abc_negative_cache_version = 54

_abc_registry = <_weakrefset.WeakSet object>

_send_action_commands(action_type)[source]

Sends an action command to the robot.

Parameters: action_type – FourDiscreteMotionActions instance.
Returns: The real time factor for the move (sim-time elapsed/wall-time elapsed)

step(action)[source]

Take an action in the environment.

Parameters: action – An action to be taken in the environment.
Returns: A numpy array with rgb/depth/rgbd encoding of the state observation. An integer with reward from the environment. A boolean flag which is true when an episode is complete. Info containing the ratio of simulation-time / wall-time taken by the step

OffWorldMonolithContinuousSim-v0¶

class offworld_gym.envs.gazebo.offworld_monolith_env.OffWorldMonolithContinuousEnv(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]

Bases: offworld_gym.envs.gazebo.offworld_monolith_env.OffWorldMonolithEnv

Continous version of the simulated gym environment that replicates the real OffWorld Monolith environment in Gazebo.

env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.DEPTHONLY, random_init=True)
env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.RGB_ONLY, random_init=True)
env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.RGBD, random_init=True)

__abstractmethods__ = frozenset({})

__init__(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]: Initialize self. See help(type(self)) for accurate signature.

__module__ = 'offworld_gym.envs.gazebo.offworld_monolith_env'

_abc_cache = <_weakrefset.WeakSet object>

_abc_negative_cache = <_weakrefset.WeakSet object>

_abc_negative_cache_version = 54

_abc_registry = <_weakrefset.WeakSet object>

step(action)[source]

Take an action in the environment.

Parameters: action – An action to be taken in the environment.
Returns: A numpy array with rgb/depth/rgbd encoding of the state observation. An integer with reward from the environment. A boolean flag which is true when an episode is complete. Info containing the ratio of simulation-time / wall-time taken by the step

OffWorldMonolithObstacleDiscreteSim-v0¶

class offworld_gym.envs.gazebo.offworld_monolith_obstacle_env.OffWorldMonolithObstacleDiscreteEnv(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]

Bases: offworld_gym.envs.gazebo.offworld_monolith_obstacle_env.OffWorldMonolithObstacleEnv

Discrete version of the simulated gym environment that replicates the real OffWorld Monolith environment in Gazebo.

env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.DEPTHONLY, random_init=True)
env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.RGB_ONLY, random_init=True)
env = gym.make('OffWorldMonolithDiscreteSim-v0', channel_type=Channels.RGBD, random_init=True)

__abstractmethods__ = frozenset({})

__init__(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]: Initialize self. See help(type(self)) for accurate signature.

__module__ = 'offworld_gym.envs.gazebo.offworld_monolith_obstacle_env'

_abc_cache = <_weakrefset.WeakSet object>

_abc_negative_cache = <_weakrefset.WeakSet object>

_abc_negative_cache_version = 54

_abc_registry = <_weakrefset.WeakSet object>

_send_action_commands(action_type)[source]

Sends an action command to the robot.

Parameters: action_type – FourDiscreteMotionActions instance.
Returns: The real time factor for the move (sim-time elapsed/wall-time elapsed)

step(action)[source]

Take an action in the environment.

Parameters: action – An action to be taken in the environment.
Returns: A numpy array with rgb/depth/rgbd encoding of the state observation. An integer with reward from the environment. A boolean flag which is true when an episode is complete. Info containing the ratio of simulation-time / wall-time taken by the step

OffWorldMonolithObstacleContinuousSim-v0¶

class offworld_gym.envs.gazebo.offworld_monolith_obstacle_env.OffWorldMonolithObstacleContinuousEnv(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]

Bases: offworld_gym.envs.gazebo.offworld_monolith_obstacle_env.OffWorldMonolithObstacleEnv

Continous version of the simulated gym environment that replicates the real OffWorld Monolith environment in Gazebo.

env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.DEPTHONLY, random_init=True)
env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.RGB_ONLY, random_init=True)
env = gym.make('OffWorldMonolithContinousSim-v0', channel_type=Channels.RGBD, random_init=True)

__abstractmethods__ = frozenset({})

__init__(channel_type=<Channels.DEPTH_ONLY: 1>, random_init=True)[source]: Initialize self. See help(type(self)) for accurate signature.

__module__ = 'offworld_gym.envs.gazebo.offworld_monolith_obstacle_env'

_abc_cache = <_weakrefset.WeakSet object>

_abc_negative_cache = <_weakrefset.WeakSet object>

_abc_negative_cache_version = 54

_abc_registry = <_weakrefset.WeakSet object>

step(action)[source]

Take an action in the environment.

Parameters: action – An action to be taken in the environment.
Returns: A numpy array with rgb/depth/rgbd encoding of the state observation. An integer with reward from the environment. A boolean flag which is true when an episode is complete. Info containing the ratio of simulation-time / wall-time taken by the step