estimate_and_update_pose

Skill class for ai.intrinsic.estimate_and_update_pose skill.

Uses Intrinsic's pose estimation algorithms to estimate the pose of an object and update its location (rotation and translation) in the belief world. The skill collects an image from the specified camera, then runs inference using the specified pose estimator. The skill succeeds if at least one object instance is detected and within the expected pose tolerance. The skill updates the pose of the object in the belief world. One may also apply several image correction methods to the image before pose estimation. The correctors are applied in the order they are specified. Note: The pose of the object in the belief world will be updated to match the location of the pose estimate with the highest score.

Prerequisites

This skill does not have any prerequisite.

Usage Example

This skill does not have any usage example yet.

Parameters

pose_estimator

Id of the pose estimator.

object

Reference to the object for which the pose will be estimated in the world.

expected_pose_tolerance

Acceptable distance (meters) of estimated from expected position. The expected position is defined by the placement of the object in the world. If zero or negative, do not apply this criterion and include all pose estimates.

timeout_sec

Maximal allowed time in seconds to finish the estimate pose skill. This includes the creation of a camera, frame retrieval, pose estimator creation and the actual pose estimation.

occluders

Optional list of world objects which may occlude parts of the image. The provided objects will be rendered from the current camera view into an occlusion mask which the pose estimator uses to mask out the occluded regions. Note that not all pose estimators will actually use the mask, so for some pose estimators this parameter will have no effect.

object_to_update

Optional reference to the object whose pose will be adjusted in the world. The reference must be either the object itself, or one of its ancestors. This parameter can be used to update an ancestor object when the estimated object is a part of a larger whole that should be moved together. If not specified, the object_to_update is set to be the object.

image_intensity_corrections

List of image intensity corrections to be applied to the acquired image before running pose estimation. The corrections are applied in the order in which they are specified.

capture_data

If specified, the skill uses the capture_result_location within to retrieve an image captured earlier.

If not specified, the skill captures a new image directly from a camera.

Capabilities

camera

Resource with capability CameraConfig

Error Code

The skill does not have error codes yet