Fit Pose from Feature Points

You are currently viewing the documentation for the latest version (2.2.0). To access a different version, click the "Switch version" button located in the upper-right corner of the page.

■ If you are not sure which version of the product you are currently using, please feel free to contact Mech-Mind Technical Support.

Function

This Step calculates the optimal pose of the target object by performing a best-fit alignment between multiple real-time feature points and their corresponding reference feature points. It enhances adaptability in scenarios where the target object may be deformed.

Usage Scenario

This Step is suitable for scenarios where target object deformation during loading or unloading causes recognition errors, such as multi-hook loading, unloading into bins, or windshield assembly.

This Step can be directly connected to the Output Step to send the pose for subsequent tasks.

Input and Output

Input

Input port Data type Description

Taught TCP

Pose[]

The TCP taught on the reference target object. This value is read from the teach pendant in the robot reference frame.

Real-Time Feature Points

Pose[]

Multiple feature points recognized in the current scene, which must correspond one-to-one with the reference feature points in order.

Reference Feature Points

Pose[]

Multiple feature points on the reference target object.

Output

Output port Data type Description

Transformed Target Object Pose

Pose

The target object pose obtained by applying a rotational transformation to the input taught TCP and performing best-fit alignment with multiple feature points.

Feature Deviation Validation

Bool

Used to determine whether the maximum distance (i.e., maximum deviation) between all transformed real-time feature points on the target object and their corresponding reference feature points after best-fit alignment is within the threshold. If the maximum deviation does not exceed the threshold, the output is True; otherwise, the output is False.

Parameter Description

Parameter Description

Pose Display Settings

Parameter description: This parameter is used to set the display type of poses.

Value list: Only reference feature points, Only transformed real-time feature points

Default value: Only reference feature points

Maximum Feature Deviation Threshold

Parameter description: This parameter is used to set the maximum allowable distance (i.e., maximum deviation) between the transformed real-time feature points on the target object and their corresponding reference feature points after best-fit alignment. If the maximum deviation exceeds this threshold, "Feature Deviation Validation" will output False.

Default value: 5.000 mm

Is this page helpful?

You can give a feedback in any of the following ways:

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.