Cascaded Modules Commonly Used for 3D Robot Guidance

You are viewing an old version of the documentation. You can switch to the documentation of the latest version by clicking the top-right corner of the page.

This topic introduces common cascaded modules in 3D robot guidance and provides example projects for practice.

  1. Object Detection–Instance Segmentation (Click to download the example project)

    • Feature: Detect the target area and then locate the objects to be picked within the area.

    • Applicable scenarios: Pallet, bin, and stacking scenarios where the incoming material height varies greatly and the position of the incoming material is random, making a fixed ROI unable to cover all positions.

      object instance example

  2. Instance Segmentation–Classification (Click to download the example project)

    • Feature: Segment the individual objects in the image, then classify and label each object.

    • Applicable scenarios: Use the super models to recognize cartons and sacks, and differentiate between object classes based on surface color, patterns, and other features.

      instance classes example

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.

  • Preference
  • I accept
  • I don't accept