TNLROBOTICS
VIEN
Discuss a pilot
Home / Solutions / AI footwear inspection

Footwear inspection · R0 design

AI footwear inspection
with a robotic arm.
Every pair recorded.

A proposed robotic quality control cell for footwear manufacturing: a 7-axis arm presents shoes to cameras in controlled lighting. AI flags suspect areas; a QC operator reviews the images and decides.

In development · Simulated visuals · No pilot results yet

QC CELL / 001DESIGN SIMULATION
ROBOT + VISION + HUMAN REVIEWR0 / 10.2026
0.097 mm/pxSide-camera spatial resolution
EU 48Maximum shoe size in the booth design
≥ 50 kluxTarget strobe illumination · CRI ≥ 90
7 axesReference robot arm architecture

R0 DESIGN / SIMULATION VALUES — not hardware measurements. Spatial resolution in mm/px is not the smallest detectable defect size.

01 / Factory quality control

Consistent shoe inspection.
Across every shift.

Footwear visual inspection needs consistent criteria as styles change. When a quality complaint arrives, the factory needs the inspection record for that specific pair of shoes.

01 — PEOPLE

Different judgements

The same glue mark may be judged differently by different inspectors or shifts. Factory standards need to become usable reference data.

02 — PRODUCT VARIATION

Styles keep changing

New materials, colours and shapes change imaging conditions. Robot poses and capture routines need to be configured for each shoe style.

03 — EVIDENCE

Find the exact pair

A pass/fail result alone is not enough. Each decision should link to images, defect locations and inspection time for traceability.

02 / One cell, four components

See clearly. Present precisely.
Keep the evidence.

The proposed cell combines robotics, machine vision and human review for factory quality control. Robot and cameras handle repetitive tasks; QC operators retain judgement and decision-making.

Simulation of a QC operator reviewing a flagged area beside a robot presenting a shoe
SIMULATION — proposed inspection station and operator interface
01

7-axis robotic arm

Pick, present and rotate each shoe through a sequence of capture poses. Motion paths and visual coverage need experimental validation.

02

Controlled light booth

Control lighting, working distance and image background. Automatic doors exchange coordination signals with the robot.

03

AI vision

Designed to flag suspect defects against the factory's reference samples, defect list and acceptance criteria.

04

Recording & traceability

Pair-linked records are planned to include multiple views, suspect areas and operator decisions.

03 / From conveyor to decision

Six inspection steps.
One connected record.

Select a step to explore how robotics, machine vision and the QC operator work together in the proposed process.

Simulation of a robot picking a shoe from a conveyor
Process simulation — not footage of an operating system.
01 / 06 — PICK

Pick from the conveyor

A depth camera estimates the shoe pose. The robot approaches and picks along a configured path before presenting the shoe for inspection.

04 / Image-based QC traceability

Every pair of shoes.
Its own visual record.

The goal is to answer “how was this pair inspected?” with linked inspection images and a history of QC decisions.

  • Multiple views and close-ups of suspect areas
  • Pair ID, PO, style code, time, station and shift
  • Defect location and operator decision
  • Proposed on-premise storage and CSV/API integration

QC feedback can supply data for the next training cycle. Each new model version needs evaluation before deployment.

QC RECORD / DEMO-001INTERACTIVE MOCK-UP
SUSPECT AREA · AWAITING REVIEW

Left shoe · outer side · heel

ILLUSTRATION
PAIR ID
DEMO-001
VIEW
Outer side · illustration
SUSPECT DEFECT
Excess glue near the sole edge
SOURCE
Illustrative interface data

Try a QC decision. No real inspection data is stored.

05 / Engineering notes

Machine vision and robotics.
Specifications to validate.

Values are drawn from the R0 design dossier. Lighting, motion and imaging targets must be measured on prototypes and validated during a pilot.

Design model of a footwear QC light booth with 2020 aluminium frame, modular panels and camera position
LIGHT BOOTH / R0 — design model

QC light booth

ParameterDesign value
Internal space466 × 466 × 640 mm
Opening / travel300 × 300 mm / 290 mm
Open / lower time≈ 0.52 s / ≈ 0.71 s (simulation)
Maximum shoe sizeEU 48 · 340 × 130 × 120 mm
Frame & panels2020 aluminium extrusion · PETG-CF/ASA tiles

Not yet validated on hardware. Door movement time is not the inspection cycle time per pair.

Watch the light booth door simulation ↗

Light booth simulation, not hardware test footage.

Sources: landing-page content brief R0, 19 October 2026; light booth design dossier and DAMIAO robot direction R0, 8 October 2026.

06 / Footwear visual inspection scope

The defects that matter.
At the right process step.

Target defect categories for automated shoe inspection. Each must be evaluated by shoe style, material, defect size and factory standard. No detection rate has been established.

Glue & sole edges

Excess glue and visible signs of bonding gaps.

Stitching

Misaligned stitching, skipped stitches and loose threads.

Upper surfaces

Wrinkles, scratches and dirt in captured areas.

Colour consistency

Colour differences between shoes in a pair.

Logos & labels

Placement, printed content and alignment.

Barcodes & sizing

Check labels against the product identifier.

Left & right

Assess consistency within each pair.

Factory-specific criteria

Agree on the defect list during pilot planning.

Incoming materials→Upper stitching→Sole bonding→Final inspection / pilot focus→Packing

Visual images cannot establish bond strength or detect all internal defects. Factory QA must approve the full-inspection or sampling plan.

07 / For researchers & engineers

Repeatable image capture.
Data with context.

The proposed research architecture connects robot pose, multi-view images and QC feedback. The aim is a reproducible process that can be evaluated and improved.

Depth poseGraspMulti-view captureDetection / segmentationPair consistencyHuman reviewActive learningModel registryEdge deploy

Pose-linked images

Planned 6D pose metadata links images to robot position, with synchronised camera capture and strobes to reduce variation between inspections.

Human-in-the-loop review

QC decisions help select training examples. Few-shot learning and synthetic defect images are research directions, not demonstrated results.

Open hardware, local data

The R0 dossier references OpenArm v2.0 under CERN-OHL-S-2.0. Edge GPU processing and on-premise storage are proposed; the pilot will define the configuration.

A dataset card, source code and research technical note have not been publicly released. Use the pilot contact to discuss collaboration.

08 / Safety & factory integration

Designed for
factory integration.

The actual cell requires a safety assessment before operation. Features described here are design requirements, not safety certifications.

  • Emergency stopping, energy isolation and robot work-zone protection
  • Hold the door open while the robot occupies the opening; detect obstructions during closing
  • Assess door and brake behaviour on power loss
  • IO/PLC coordination of conveyor, robot and cameras
  • CSV/API for MES/ERP, access control and image retention

ToF, beam sensors and StallGuard are proposed sensing components. They have not been validated as PL/SIL-rated safety functions.

09 / Pilot roadmap

One inspection cell.
One metric. One agreed test.

Start with a defined scope. Plan a trial alongside the current process with factory approval, and expand based on evidence.

01

Survey the line

Work with QA and engineering to establish the process step, installation conditions and current inspection method.

02

Agree on acceptance criteria

Select defect categories, good/defective samples and comparison metrics. Agree on acceptance criteria before testing.

03

Test real production samples

Record images, measure cycle time, and assess missed defects and false alarms for each shoe style.

04

Report and decide

Compare results with the baseline. The factory decides whether to refine, continue testing or expand.

The factory provides good/defective samples, visual standards and a technical contact. Pilot duration, cost and throughput are discussed after the survey.

10 / Development status · 19 October 2026

Transparent from
the first design.

This page presents the development direction and design dossier. QC performance can only be established through real test data.

● DESIGN DOSSIER AVAILABLE

Design & simulation

Light booth model, door simulation, mechanical/electrical design review, lighting specifications and a 7-axis robot direction.

◐ IN DEVELOPMENT ACCORDING TO R0 BRIEF

Build & component testing

Tabletop robot, LED/driver electronics and material-lighting trials. No validated hardware measurement package is published on this page.

○ NEXT STEP

Factory pilot

Validate imaging conditions, coverage, cycle time and detection performance on the partner's real samples.

11 / Frequently asked questions

Before starting a pilot.

Which footwear defects does the proposed AI cell target?

Excess glue, visible bonding gaps, stitching, surface, colour, logo and label issues. The acceptance list must be agreed using real samples; no detection rate has yet been validated.

Does a new shoe style require reconfiguration?

Capture poses, lighting, reference samples and defect criteria need configuration or adjustment. Model reuse across styles must be assessed during the pilot.

How many pairs can one cell inspect per hour?

Not yet established. Throughput depends on views, robot motion, image processing and human review. The pilot will measure cycle time on the actual line.

Can it inspect glossy leather, mesh or black shoes?

The design considers diffuse lighting, cross-polarisation and strobed capture. Visibility of each defect type must be tested on the actual material and colour.

Where are inspection images stored? Is internet required?

The proposed architecture processes and stores images on-premise. Capacity, retention, permissions and offline operating requirements will be agreed in the pilot configuration.

What is the QC operator's role alongside the robot?

The operator reviews flagged areas, confirms defects, handles exceptions and provides feedback against factory standards. AI supports assessment; decisions and acceptance still require human oversight.

How would the cell integrate with existing conveyors and MES?

IO/PLC signals are proposed for motion coordination and CSV/API for data exchange. Each factory's protocols, pair identification and safety requirements need a survey.

How long is a pilot, and what should the factory prepare?

The schedule is agreed after a survey. Prepare good/defective samples, visual inspection standards, process information and a QA/engineering contact to define acceptance metrics.

12 / Let's build the evidence

Start with one cell.
Build the evidence.

Tell us which process step and defects you want to control. Together we can define a footwear quality control pilot with a clear scope and acceptance criteria.

FOR FACTORIES & RESEARCH TEAMS
Shoe samples · Defect standards · Data / open-hardware collaboration

Pilot contact: +84 903 869 447. This form prepares a local request file for your discussion. It does not submit or store information on a server.