Mech-Vision 2.1 Release Notes
This document introduces the new features, improvements, and resolved issues of Mech-Vision 2.1.
Mech-Vision 2.1.0 Release Notes
This document introduces the new features, improvements, and resolved issues of Mech-Vision 2.1.0.
New Features
Added the “Auto-Correct Accuracy Drift in Vision System” Feature
The Auto-correct accuracy drift in vision system feature was added to Mech-Vision 2.1.0. Deploying this feature in the Error Analysis Tool can correct the accuracy drift in the vision system, improving its stability and reducing subsequent maintenance costs.
Improvements
Monitoring of Accuracy Drift in Vision System
The Monitoring of Accuracy Drift in Vision System feature has been added to the production interface. After the Auto-Correct Accuracy Drift in EIH/ETH Vision System feature is deployed:
-
You can monitor real-time drift compensation in the status area of the production interface.
-
In the operation area of the production interface, click “Maintenance” and navigate to the “Drift correction (EIH/ETH)” tab, where you can monitor the accuracy drift and drift correction status in the vision system.
Target Object Editor Adaptation for “Auto-Correct Accuracy Drift in Vision System”
A “Collect data for drift correction” step has been added to the Jog robot and get point cloud workflow in the target object editor. If a target object model was created using the “Jog robot and get point cloud” workflow, an additional data collection for EIH/ETH drift correction is required after enabling the drift correction feature in the latest software version. This update allows for effective drift compensation and reverse correction, ensuring that pick points added through robot jogging remain precise and reliable.
Improved Steps
| No. | Step | Description |
|---|---|---|
1 |
Added the “Auto-Correct Accuracy Drift in Vision System” parameter. Once selected, the latest generated drift correction data will be used to correct the accuracy drift in the vision system. This parameter will only be displayed after the Auto-correct accuracy drift in EIH/ETH vision system feature is deployed. |
|
2 |
Added the “Display Range as Positive and Negative Values” parameter. Once selected, the range in the statistics file will be expressed using both positive and negative values. |
Resolved Issues
-
When an entire point cloud model is used for 3D coarse matching, if the target object was too thin, the downsampling interval could exceed the object’s thickness. This resulted in retaining the point cloud of a single view during matching, causing incorrect matching results.
-
When the “3D Matching” Step was used as an input within a Procedure and connected to a data flow, the software crashed if the “Input Type” of the “3D Matching” Step was adjusted.
-
If the “Auto-Set Voting Parameters” option was disabled in the “3D Matching” Step and voting parameters were manually adjusted, executing the single Step would apply the manual settings. However, even after re-enabling “Auto-Set Voting Parameters” and executing the single Step, the manually adjusted parameters were still used for matching.
-
For the “3D Fine Matching” Step, when the Operation Approach was set to “HighPrecision" and “Speed Up on Large Object Quantities” was unselected, the matching results for symmetric target objects were incorrect.
-
When a copy of the point cloud model generated by importing an STL file was created in the target object editor, the STL model dimensions became incorrect after returning to the “Configure STL file” step.
-
After modifying the axis of symmetry for the pick point array in the target object editor, the “Order of symmetry” and “Angle range” displayed in the parameter panel were incorrect.
-
When a copy of the target object model was created and used in the target object editor, the point cloud of the target object was not removed during project execution, even when the “Remove Target Object Cloud” parameter in the “Output” or “Path Planning” Step was selected.
-
In the EIH scenario, clicking the Get data button in the pose adjustment tool incorrectly updated the robot flange pose.