---
title: "Description"
product: "LumiScan VGR"
component: "lumiscan-vgr"
version: "1.8.4"
display_version: "1.8.4.6"
latest_version: true
language: "en"
url: "https://docs.hdvisionsystems.com/en/lumiscan-vgr/1.8.4/description.html"
---

# Description – LumiScan VGR

LumiScan VGR is software that can be used for a variety of applications, such as bin picking or automated assembly.

The high-quality data received from the camera is used to generate accurate point clouds for object localization.

Two approaches are used:

- The generated point cloud is compared with 3D models of the objects.
- Machine learning algorithms are used for more complex scenes.

This makes LumiScan VGR highly adaptable to different object textures.

The robot kinematics and collision network calculate the robot’s path and enable collision-free movement.

LumiScan VGR is organized into modules that contain one or more cameras, pipelines, and robots (Fig. 1).

**LumiScan VGR: modules, PLC and robot**

```mermaid
%% LumiScan VGR - modules, PLC and robot. Rendered by Mermaid in the browser; edit and preview at https://mermaid.live
flowchart LR
  sensor["LumiScan X"]
  subgraph vgr["LumiScan VGR"]
    direction LR
    cam["`**Camera module**
    changeable`"]
    pipe["`**Pipeline module**
    changeable`"]
    robotmod["`**Robot module**
    changeable`"]
    cam -- data --> pipe -- objects --> robotmod
  end
  plc["`**PLC**`"]
  robot["Robot"]
  sensor --- cam
  plc -- TriggerCamera --> cam
  plc -- ComputeObjects --> pipe
  plc -- "GetBestResult, GripBestResult" --> robotmod
  robotmod -- grip points --> plc
  plc -- grip points --> robot
  class cam,pipe,robotmod key
  classDef key fill:#faf6dc,stroke:#a8961f,color:#1f2328
```

At any given time, one set of modules is active, and all functions refer to this active configuration. The active modules can be switched through either the user interface or the PLC.

The general workflow is as follows:

1. A LumiScan camera captures an image and generates a point cloud.
2. Objects are detected in the captured image.
3. The 6-DoF pose of each detected object is calculated using the point cloud.
4. A set of possible grip points is calculated for each object.
5. The best available grip point is transmitted to the PLC via PROFINET.

The software can be configured extensively using JSON settings files.