r"""Fundamental environment class for :ref:`habitat`. :data observation_space: ``SpaceDict`` object corresponding to sensor in sim and ta

r"""Base class for a goal specification hierarchy.

r"""Represents a set of sensors, with each sensor being identified through a unique id.

A dictionary of ``EmbodiedTask`` actions and their argument spaces. .. code:: py self.observation_space = spaces.ActionSpace({

r""" I can't believe this isn't supported https://github.com/pytorch/vision/issues/157

r"""JSON Encoder that sets a float precision for a space saving purpose and encodes ndarray and quaternion. The encoder is compatible with JSON

r"""Class for episode specification that includes initial position and rotation of agent, scene name, goal and optional shortest paths. An epi

r"""Object goal provides information about an object that is target for navigation. That can be specify object_id, position and object categor

r"""ObjectGoal Navigation Episode :param object_category: Category of the obect

r"""Specifies additional objects, targets, markers, and ArticulatedObject states for a particular instance of an object rearrangement task. :prop

Semantic_Mapping

r"""Convenience wrapper to track if a connection to a worker process should have something to read.

r"""Convenience wrapper to track if a connection to a worker process can be written to safely. In other words, checks to make sure the result

Defines an AABB Receptacle volume above a surface for sampling object placements within a scene.

Create a simple end-to-end predictor with the given config that runs on single device for a list of input images. Compared to using the

Proxy class for _multiprocessing.Connection which uses ForkingPickler to serialize objects. Will use the Pickle5 backport if available.

Support class for simple visual debugging of a Simulator instance. Assumes the default agent (0) is a camera (i.e. there exists an RGB sensor

r"""Specification of episode that includes initial position and rotation of agent, goal, question specifications and optional shortest paths.

A ``gym.Space`` that reflects arguments space for action that doesn't have arguments. Needed for consistency ang always samples `None` value.

r"""Episode Iterator class that gives options for how a list of episodes should be iterated. Some of those options are desirable for the inte

r"""Implements an extendable Enum for the mapping of action names to their integer values. This means that new action names can be added, but

A ``gym.Space`` that describes a list of other Space. Used to describe list of tokens ids, vectors and etc. .. code:: py observ

A data structure to track information about markers in the scene. These are automatically updated based on the position of the articulated li

r"""Represents a set of Measures, with each :ref:`Measure` being identified through a unique id.

r"""Dictionary containing measurements.

A Pydantic model representing a model card, which provides metadata about a machine learning model. It includes fields like model ID, owner,

The Object Goal Navigation environment class. The class is responsible for loading the dataset, generating episodes, and computing evaluation

r"""ObjectViewLocation provides information about a position around an object goal usually that is navigable and the object is visible with specif

r"""Dictionary containing sensor observations

r"""Class inherited from PointNavDataset that loads Rearrangement dataset.

Generator class encapsulating logic for procedurally sampling individual episodes for general rearrangement tasks. Initialized from a provided co

Manages the agent grasping onto rigid objects and the links of articulated objects.

r"""Utility class for extracting the action on the shortest path to the goal. :param sim: HabitatSim instance. :param goal_radius: Di

r"""Specification of episode that includes initial position and rotation of agent, goal specifications, instruction specifications, reference path

This is the ground truth object position sensor relative to the scene coordinate frame.

Relative position from end effector to target object

r""" An action that can be performed by an agent solving a task in environment. For example for navigation task action classes will be: ``

r"""Abstract class for defining agents which act inside :ref:`core.env.Env`. This abstract class standardizes agents to allow seamless benchmarki

AnswerAccuracy

The arm motor targets are directly set to the joint configuration specified by the action.

The arm is kinematically directly set to the joint configuration specified by the action.

An arm control and grip control into one action space.

Uses inverse kinematics (requires pybullet) to apply end-effector position control for the robot's arm.

The arm motor targets are offset by the delta joint values specified by the action

The arm motor targets are offset by the delta joint values specified by the action

The robot base motion is constrained to the NavMesh and controlled with velocity commands integrated with the VelocityControl interface. Opt

r"""Benchmark for evaluating agents in environments.

Samples multiple articulated states simultaneously with rejection of invalid configurations.

CorrectAnswer

r"""Base class for dataset specification.

The measure calculates a distance towards the goal.

Embodied Question Answering Task Usage example: env = habitat.Env(config=eqa_config) env.reset() for i in range(10)