Before You Upgrade

You are currently viewing the documentation for version 1.7.4. To access documentation for other versions, click the "Switch Version" button located in the upper-right corner of the page.

■ To use the latest version, visit the Mech-Mind Download Center to download it.

■ If you're unsure about the version of the product you are using, please contact Mech-Mind Technical Support for assistance.

1.7.2 Upgrade Notes

Mech-Vision 1.7.2 has introduced the Deep Learning Model Package Inference Step, which replaces the “Deep Learning Model Package CPU Inference” and “Deep Learning Model Package Inference (Mech-DLK 2.2.0+)” Steps.

Once Mech-Vision is upgraded to 1.7.2, the “Deep Learning Model Package CPU Inference” and “Deep Learning Model Package Inference (Mech-DLK 2.2.0+)” Steps used in projects that are created with software of previous versions will be automatically replaced with the “Deep Learning Model Package Inference” Step. The new Step covers all functions of the removed Steps, and therefore this replacement will not affect the normal functioning of the project.

If a model package that has been optimized with the software of previous versions is used in Mech-Vision 1.7.2, the execution time may be longer when the optimized model package is used in the “Deep Learning Model Package Inference” Step for the first time.

1.7.0 Upgrade Notes

This section introduces the upgrade notes for Mech-Vision 1.7.0, Mech-Viz 1.7.0, and Mech-Center 1.7.0.

Mech-Vision 1.7.0 Upgrade Notes

Notes for the New “Solution” Feature

Mech-Vision 1.7.0 has introduced the “solution” feature. With this feature, you can finish the vision application deployment in one solution, including selecting the robot, configuring the communication with the robot, building the vision project, and planning the robot path. Pay attention to the following notes:

  • When the Standard Interface or Adapter communication option is used, the project ID of the Mech-Vision project called by the robot program will no longer be obtained from Mech-Center, but from the Mech-Vision Project List.

  • For Mech-Vision projects built with earlier version software, you need to complete project migration after upgrading Mech-Vision. For details, please refer to 1.7.0 Project Migration Guide.

Notes for Integrating “Mech-Center’s Communication Service

As the interface communication service has been integrated into Mech-Vision 1.7.0, please note that:

  • If a Mech-Vision solution is used and Standard Interface or Adapter is used for communication, you do not need to open Mech-Center anymore.

    • The interface service will be automatically started when you click the Robot and Interface Configuration button on Mech-Vision’s toolbar, select the desired robot, configure the communication option, and click Apply.

    • For ABB, FANUC, YASKAWA, Kawasaki, KUKA, UR, TM, ELITE, and JAKA robots, the software has configured the default communication settings same as those specified in the example programs provided by Mech-Mind for these robots. For robots of other brands, TCP/IP is selected by default.

    • When configuring the interface communication, you can select the “Auto enable interface service when opening solution” option. When the solution is opened next time, interface service is started automatically and the project is ready for the communication with the robot side.

    • Communication-related logs will be displayed on the Console tab of the Mech-Vision Log panel.

    • When configuring Adapter communication, after you select the Adapter project folder, the folder will be automatically copied to the current solution’s folder.

    • If the Adapter program in the solution has been modified, please reboot the Adapter program and the interface service in order for the modifications to take effect.

    • You need to disable the “Run Mech-Center at PC startup” option in Deployment Settings of Mech-Center.

  • If Master-Control communication is used, or Mech-Viz is used to accomplish complicated tasks, you still need to use Mech-Center.

    • You need to open Mech-Center first, and then open Mech-Vision from Mech-Center. You can configure the communication in the same way as in earlier versions.

    • It is recommended to enable the “Run Mech-Center at PC startup” option for Mech-Center. Mech-Vision should be opened by Mech-Center.

Notes for Calibration

For pre-calibration configuration, Mech-Vision 1.7.0 has added the functions of selecting, integrating, and connecting to the robot. You can establish the connection to the robot during pre-calibration configuration. If projects do not belong to a solution, the calibration function cannot be used.

Notes for Steps

Please pay attention to the following notes for Steps in Mech-Vision 1.7.0.

Step Removal

Mech-Vision 1.7.0 has removed the following obsolete Steps.

Group Removed Step

2D Feature - Others

Detect Rectangles Given Corners and Sizes in Pixels

2D General Processing - Others

Place Polygons

Deep Learning - Novel Objects Picking

Calc Poses from Heat Map of Pickability, Predict Pick Points (Single Object Type) (Please use Predict Pick Points V2 instead), Pixel-Wise Pickability Evaluation

Measuring - 3D Length/Distance

Calc Distances from 3D Points to Intersection of Two Planes, Calc Distances from 3D Points to Plane

Legacy

Visualize Information on Image (Please use “Visualize Information on Image” instead), Adjust Targets by Obstacles

Pose - Adjust Translation & Orientation

Adjust Targets by Obstacles V2

Others

Detect Pickable Rectangles

Old Deep Learning Steps No Longer Being Maintained

Defect Detection, Detect Edges, Image Classification, Instance Segmentation, Object Detection, Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) are no longer maintained and will be removed in future releases.

  • If the deep learning inference is conducted with GPU, please replace the Steps Defect Detection, Detect Edges, Image Classification, Instance Segmentation, Object Detection, Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) with the new Step Deep Learning Model Package Inference (Mech-DLK 2.2.0+).

  • If the deep learning inference is conducted with CPU, please replace the Steps Image Classification, Instance Segmentation, Object Detection, Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) with the new Step Deep Learning Model Package CPU Inference.

Mech-Viz 1.7.0 Upgrade Notes

The robot model names in Mech-Viz 1.7.0 have been standardized, and numerous robot model names have been modified. You will need to re-select the robot in the robot model library.

In Mech-Viz 1.7.0, the maximum port number of DO for some of the robots are modified, and there may be pop-up alerts when you open a project built with earlier version software. If you want to remove the pop-up alerts, please modify the digital_out_range of the corresponding robot in robot_ability.

In Mech-Viz 1.7.0, you can customize the effective range for pose when a bin is used. For projects built with earlier version software, the effective range for pose will be adjusted from an infinite extension from the bottom of the bin upward to within 1 meter above the bin top edges.

The “Depalletizing vacuum gripper” operation mode in the “Vision Move” Step is completely restructured. Some old functions are divided into new ones, and therefore you will need to re-set the parameters related to multi-pick depalletizing.

In the “Vision Move” Step, when “Depalletizing vacuum gripper (multi-pick)” is selected, the model of the cartons to be picked together are displayed as multiple individual cartons instead of the single large carton in the earlier version software, and therefore the carton models can represent the actual situation better. However, the updated model may lead to extra collisions during path planning.

The vacuum gripper configurator is integrated into the Tool Configuration window, which you can open in the Resources panel. For projects that require configurations of the vacuum gripper, you will need to re-configure the control logic of the vacuum gripper in the Tool Configuration window.

Only OBJ format models can be used as the collision models for robot end tools, and STL format is not supported anymore. The STL-related collision detection parameters were removed from the “Collision detection configuration” interface.

If the file name and format of the collision model and visualization model of a robot end tool are the same, the visualization model will be replaced with the collision model automatically.

Mech-Center 1.7.0 Upgrade Notes

Mech-Center 1.7.0 must be used with Mech-Vision and Mech-Viz 1.7.0 or above.

If the Mech-Vision projects in a solution contain the “Path Planning” Step, then the new Standard Interface program must be loaded to the robot, and Robot and Interface Configuration in Mech-Vision must be completed.

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.