3D Trajectory Recognition
Function
This Step is integrated with vision processing functions such as point cloud preprocessing and 3D matching, facilitating a rapid recognition of target objects and generation of trajectories.
Usage Scenario
This Step is suitable for applications that require robotic motion along the surface or edge of a target object, such as welding, gluing, cutting, and grinding. This Step usually follows the Capture Images from Camera Step and is followed by the pose adjustment Step.
Input and Output
Input
| Input port | Data type | Description |
|---|---|---|
Camera Depth Map |
Image/Depth |
Original depth map of the target object. |
Camera Color Image |
Image/Color |
Original color image of the target object. |
Output
| Output port | Data type | Description |
|---|---|---|
Object Center Points |
Pose[] |
List of the object center points. |
Target Object Names |
String[] |
Names of the target objects. |
Original Point Cloud |
PointCloud/XYZRGB |
Point cloud of the target object acquired by the camera. |
Target Object Confidences |
Number[] |
Confidence values of the target objects. |
Point Cloud with Normals |
PointCloud/XYZNormal[] |
Point cloud of the target object with normals. |
Preprocessed Point Cloud |
PointCloud/XYZNormal |
Preprocessed point cloud. |
Trajectory Points |
Pose[] |
List of trajectory points of the target objects. |
Trajectory Point Labels |
String[] |
Trajectory point labels. |
Parameter Description
| Parameter | Description |
|---|---|
Select Target Object |
Parameter description: Select a target object to recognize from the drop-down list. The target object should be added in advance via the config wizard.
|
|
After selecting "Trigger Control Flow Given No Output" for the "3D Trajectory Recognition" Step, the control flow will still be triggered even if the output of the Step is empty. Note:
|