Piece Picking 

Robotic piece picking is the process of automated order fulfillment, by picking various individual items (SKUs) from an inventory bin and place them in an order container for shipping to customers. The choice of the vision system, particularly the 3D camera, impacts the robot’s ability to successfully detect, pick, and place all types of pieces. Learn how to increase SKU coverage using your Zivid 2 machine vision camera - without compromising on speed.



Zivid 2 delivers high resolution and extreme precision, native color 3D point clouds with minimal occlusion and excellent artifact suppression. Significantly improving object recognition and increasing the number of detectable SKUs.



Zivid 2 enables more reliable detection of object boundaries for grasp planning, and a true to reality representation of object size, rotation, and absolute position in relation to the robot coordinate system. Essential for accurate picking, avoiding mispicks and crashes.



Zivid 2 with its groundbreaking trueness, enables more demanding place operations. Dimensioning of objects, and placing for packaging with known position and orientation, with minimal gaps and tight fit, and without colliding or damaging the objects.

Schedule a demo

Work faster. Zivid Two delivers significantly higher quality at much faster speeds than typical stereo 3D cameras used in piece picking today. Capture speeds <100ms for low to medium dynamic range scenes of some typical material handling items in a picking warehouse.

Challenges & Solutions

Piece picking and bin picking are still a challenge for robots. The detection and picking of unknown SKUs of various shapes, sizes and materials is still one of the biggest problems in logistics. Unpickable objects goes under many terms, such as “uglies” or “pathologicals”, and the difficulty stems from the inherent uncertainty in physics, perception, and control.

Download piece picking ebook

See tiny and detailed objects, densely stacked, or randomly arranged.

Zivid 2 provides high resolution and precision point clouds with minimal occlusion, capturing shapes and sizes with all the fine details.

  • Distinguish features smaller than 5mm for reliable object recognition and separation of boundaries for picking.
  • Very small, thin, porous, deformable, or highly irregular objects. Densely stacked with little gap or randomly arranged and piled on top of each other.
  • Low occlusion with almost no shadowing contrary to bigger baseline cameras that can potentially miss smaller objects hidden by shadows in the bin, e.g. close to corners and edges.

Get access to our piece picking tutorial →


Point cloud example with Zivid 2 - Randomly arranged, densely packed and thin objects. View in 3D here

See shiny, reflective, glossy, and plastic wrapped objects.

3D HDR and Artifact Reduction Technology (ART) ensures excellent suppression of imaging artifacts from reflections, interreflections, specular highlights and high contrast transitions.

  • Shiny and reflective plastic, aluminum, ceramics, cosmetics, glossy packaging, translucent, semitransparent, and plastic wrapped items.
  • Avoiding artifacts from the highly reflective plastic bins often used in logistics.
  • Capture speeds < 300 ms for high dynamic range scenes such as shiny and reflective

Get some tips on how to deal with highlights and shiny objects

Plastic wrapped objects

Point cloud example with Zivid 2 - Plastic wrapped objects. View in 3D here

See a wide variety of objects.

The unique combination of native color and high dynamic range enables imaging of a broad range of SKUs

  • Plastic, ceramic, metal, cardboard, wood, colored, textured, light, dark and absorptive. Single or mixed SKU bin scenarios.
  • Non-laser-based white light for broad material coverage and native color capabilities.
  • 2D and 3D data from the same sensor.
  • Capture speeds < 300 ms for high dynamic range scenes, including shiny and dark absorptive.

Learn more about our 2D + 3D Capture Strategy

Wide variety of objects

Point cloud example with Zivid 2 - Wide variety of objects. View in 3D here. 

Zivd 3D cameras

Get started with 3D development today!

Zivid development kit

Customer Stories

DHL Beringe Robot Picking Cell_1-1

DHL's 3D Vision Warehouse

Increasing e-commerce operation efficiency with 24/7 3D vision robots.

Learn More →
SHEFF Foodpicker

SIXPAK's SHEFF Foodpicker

Detect, select, classify, and pick any food components in a short time.

Learn More →

Vision Online's Flexible Picking System

A comprehensive bin-picking solution that is flexible, intuitive, and easily adaptive. 

Learn More →

Choose the right camera for your business


Meet our vision engineers for free demo →


Apply for a loan program →


Order a 3D camera →