Al + 3D vision guided workpiece handling

Unordered Part Recognition

Unordered Part Recognition

Unordered Part Recognition

Recognizes randomly stacked parts, with no fixtures required.

Precise Pick and Load

Precise Pick and Load

Precise Pick and Load

Guides the robot to pick parts and load them into the machine.

Automatic Unload Transfer

Automatic Unload Transfer

Automatic Unload Transfer

Unloads finished parts after machining, ready for the next step.

Advantage

Large-model object recognition and application templates

A pre-trained model covering common industrial parts and materials, generalizing across part types without per-part training. Built-in palletizing, depalletizing, and bin picking templates, validated in simulation, shorten deployment.

images_en

Trained in Simulation, No Sample Data Required

Import a part CAD model and the DexVerse engine trains in a digital twin environment using synthetic data. Covers real-world lighting, shadows, texture, and surface contamination. No photos or manual labeling required.

3D Vision Algorithms for Hard-to-Image Parts

Proprietary ambient light rejection combined with deep learning reduces missed and false recognition in tightly packed parts. Handles overexposure and underexposure, and images reflective, dark, oily, or complex parts reliably.

3D Vision Algorithms for Hard-to-Image Parts

Value

%

Recognition accuracy

mm

Picking accuracy

s

Fastest recognition

hours

Fastest deployment

Related Product

XEMA-LCW

XEMA-LCW

Key Specifications

Learn more
Near field of view (mm)965×569
Far field of view (mm)2462×1453
Working distance (mm)1000–2500
Z-axis repeatability σ (μm)80@1.0–2.5m
Pixel pitch0.55mm@1.0m / 1.37mm@2.5m
Acquisition time (s)0.5–1.5
Operating systemsWindows、Linux (Ubuntu 20.04)
SDK interfacesC/C++/C#/Python