Redefining robot precision and speed with AI vision

High-Precision Imaging at Ultra-Long Range and Ultra-Wide Field of View

CameraPoint cloud
Point-cloud cases

  • Capture an entire tray across a 3.5-meter field of view without multiple shots or image stitching.
  • Built for large-part handling, such as loading stamped parts into containers.

  • Maintain high precision and fast scanning across a wide field of view for reliable guidance of large workpieces.
  • Locate a full tray of parts in a single shot, shortening workstation cycles.

  • High-density point clouds preserve contours and surface details for reliable recognition.
  • A depth-completion algorithm fills in point-cloud data lost to stacked or occluded parts.

Solutions

Loading and Unloading

AI + 3D vision guided workpiece handling

AI + 3D vision guide robots to pick randomly stacked or closely packed parts from bins for transfer or further processing. The solution supports workpiece handling in automotive, logistics,construction machinery, and steel manufacturing.

Learn more
Loading and Unloading

AI + 3D vision guided workpiece handling

AI + 3D vision guide robots to pick randomly stacked or closely packed parts from bins for transfer or further processing. The solution supports workpiece handling in automotive, logistics,construction machinery, and steel manufacturing.

Learn more
Positioning and Assembly

AI + 3D vision guided positioning and assembly

AI and 3D vision identify workpiece position and orientation in real time to guide precise picking, positioning, and assembly. It handles different part sizes and flexible production lines, improving assembly consistency and cutting changeover time.

Learn more

Specifications

Product model
FINCH-W
FINCH-W
Field of view (H/V)
Dimensions (mm)
Weight (kg)
Baseline (mm)
Resolution (px)
Interface
Computing unit
Rated voltage
Operating temperature range (℃)
Certifications
Protection rating
Near field of view (mm)
Far field of view (mm)
Recommended distance (mm)
Z-axis accuracy
Z-axis repeatability σ (μm)
Pixel pitch
Typical acquisition time (s)
Output data
Operating systems
SDK interfaces
57°/48°
465×130×69
2.7
400
Mono: 1624×1240 Color: 2272×1648
Gigabit Ethernet
NVIDIA Jetson nano
DC 24V ≥2A
-0~30
CE、FCC、RoHS、KC
IP65
1844×1332
3796×3109
1500-3500
0.65mm@3m
72@1.5m-3.5m
Mono: 1.13mm@1.5m,2.63mm@3.5m Color: 0.93mm@1.5m,2.17mm@3.5m
0.8-2.0s
Point cloud, depth map, grayscale image (color)
Windows, Linux (Ubuntu 20.04)
C/C++/C#/Python