sample_calibration_poses

Skill class for ai.intrinsic.sample_calibration_poses skill.

Skill that samples waypoints which are to be used for hand-eye calibration, given a specific sampling strategy.

The waypoints are sampled as CartesianMotionTarget objects, specifying the 3D pose between the frame and the tool object in the world, or as robot joint configurations.

The following two cases are supported:

'stationary_camera': The camera has a fixed position in the workcell and the calibration object is mounted on the robot's flange.
'moving_camera': The camera is mounted on the robot's flange and the calibration object is placed in the workcell.

This skill returns a SampleCalibrationPosesResult which is a repeated Waypoint

Prerequisites

This skill does not have any prerequisite.

Usage Example

This skill does not have any usage example yet.

Parameters

calibration_case

Has to be one of 'STATIONARY_CAMERA' or 'MOVING_CAMERA'.

calibration_object

Uniquely identifies the object used for calibration. Typically a calibration pattern, but - with an appropriate detector - all kinds of objects can be used.

minimum_margin

Minimum margin between the moving object (calibration pattern for the 'STATIONARY_CAMERA' case, and camera for the 'MOVING_CAMERA' case) and all other world objects.

Set this parameter to a higher value if you are unsure about the exact positions of the objects in your world.

pre_calibration_params

Parameters specific to pre-calibration sampling.

randomized_box_params

Parameters specific to randomized box sampling.

seed

Seed for the random number generator. If not set, a random seed is used. If set, the sampling is deterministic. However, the output is not guaranteed to be the same across different versions of the skill. Note that the skill might return a different sequence of samples for the same seed across different runs of the skill, due to randomness in the motion planning as well as due to different robot positions. Setting a seed might make the execution of the skill quite slow, and therefore is not recommended to use.