internutopia.core.robot

robot

class internutopia.core.robot.robot.BaseRobot(config: RobotCfg, scene: IScene)

Base class of robot.

apply_action(action: dict)

Apply actions of controllers to robot.

Parameters:

action (dict) – action dict. key: controller name. value: corresponding action array.

clean_stale_rigid_bodies()

Removes stale rigid bodies from the scene.

cleanup()

Cleans up resources associated with the current instance by performing cleanup operations on controllers, sensors, and rigid bodies. Ensures that all associated objects are properly removed from the scene.

create_rigid_bodies()

Create rigid bodies.

get_obs() → OrderedDict

Get observation of robot, including controllers, sensors, and world pose.

Raises:

NotImplementedError – _description_

get_robot_articulation() → IArticulation

Get isaac robots instance (articulation).

Returns:

robot articulation.

Return type:

Robot

get_robot_base() → IRigidBody

Get the base link of this robot.

Returns:

rigid prim of the robot base link.

Return type:

IRigidBody

get_robot_scale() → ndarray

Get robot scale.

Returns:

robot scale in (x, y, z).

Return type:

np.ndarray

post_reset()

Set up things after the env resets.

classmethod register(name: str)

Register an robot class with the given name(decorator).

Parameters:

name (str) – name of the robot

restore_robot_info()

Restores the robot’s information and its state within the simulation environment.

save_robot_info()

Saves the current state of the robot’s articulation information.

set_up_to_scene(scene: IScene)

Set up robot in the scene.

Parameters:

scene (Scene) – scene to set up.

internutopia.core.robot.robot.create_robots(task_config: TaskCfg, scene: IScene) → OrderedDict[str, BaseRobot]

Create robot instances in task config.

Parameters:

• task_config (TaskCfg) – task config.

• scene (Scene) – isaac scene.

Returns:

robot instances dictionary.

Return type:

OrderedDict[str, BaseRobot]

controller

class internutopia.core.robot.controller.BaseController(config: ControllerCfg, robot: BaseRobot, scene: IScene)

Base class of controller.

abstract action_to_control(action: ndarray | List) → ArticulationAction

Convert input action (in 1d array format) to joint signals to apply.

Parameters:

action (Union[np.ndarray, List]) – input control action.

Returns:

joint signals to apply

Return type:

ArticulationAction

cleanup()

Operations that need to be cleaned up before switching scenes (or resetting)

get_joint_subset() → ArticulationSubset | None

Get the joint subset controlled by the controller.

Returns:

joint subset.

Return type:

ArticulationSubset

get_obs() → OrderedDict[str, Any]

Get observation of controller.

Returns:

observation key and value.

Return type:

OrderedDict[str, Any]

classmethod register(name: str)

Register an controller class with the given name(decorator).

Parameters:

name (str) – name of the controller

internutopia.core.robot.controller.create_controllers(robot_cfg: RobotCfg, robot: BaseRobot, scene: IScene) → OrderedDict[str, BaseController]

Create all controllers of one robot.

Parameters:

• robot_cfg (RobotCfg) – config of the robot.

• robot (BaseRobot) – robot instance.

• scene (Scene) – scene from isaac sim.

Returns:

dict of controllers with controller name as key.

Return type:

Dict[str, BaseController]

internutopia.core.robot.controller.inject_sub_controllers(parent: BaseController, configs: List[ControllerCfg], robot: BaseRobot, scene: IScene)

Recursively create and inject sub-controllers into parent controller.

Parameters:

• parent (BaseController) – parent controller instance.

• configs (List[ControllerParams]) – user configs of sub-controllers.

• robot (BaseRobot) – robot instance.

• scene (Scene) – scene from isaac sim.