Industrial AR Visualization: Implementation Guide

A technician walks through the shop floor with a tablet. Points the camera at a machine — sees the wiring diagram, list of parts under the cover, disassembly animation. Without AR, it's paper manuals, catalog searches, minutes per identification. AR turns the tablet into a diagnostic tool. Our team, with 5 years of experience, has delivered 30+ AR projects for machine building, oil & gas, and energy. We guarantee positioning accuracy up to 1 mm on iPad Pro with LiDAR. AR instructions work 3–5 times faster than paper — the technician doesn't flip through catalogs, but immediately sees data on the part. An average project saves 50 hours per month per workstation.

How does an AR system recognize equipment?

The main technical challenge is anchoring virtual annotations to the real asset. We use three approaches:

Image Tracking is the most reliable for production: ARKit ARImageTrackingConfiguration detects the marker, positioning accuracy ~1–2 mm, works on any device. Object Scanning (ARKit ARObjectScanningConfiguration) creates an .arobject file but requires sufficient texture — a smooth metal casing won't work. LiDAR Scene Reconstruction builds a mesh of the environment and compares it to a reference via Iterative Closest Point, but is computationally expensive.

Which stacks to use for industrial AR?

For enterprise tasks, there are ready platforms. PTC Vuforia Engine is the de-facto standard: Model Target recognizes by CAD model without markers, Area Target scans a room. SDK for iOS/Android/Unity. Scope AR WorkLink is a no-code platform for creating AR instructions via a browser. Upskill Skylight is an analogue focused on checklists. Custom development is justified when deep integration with ERP/CMMS (SAP PM, IBM Maximo, Infor EAM), specialized UI, or offline work on rugged devices is required.

Comparison of platforms for industrial AR:

What difficulties arise when integrating AR with ERP?

A typical problem is data synchronization between the AR app and ERP/CMMS. For example, SAP PM requires a strict format via BAPI for creating repair orders. In offline mode, data is buffered locally and synced after network recovery to avoid conflicts. Another challenge is CAD model conversion: even after conversion to GLTF via Open CASCADE Technology or Datasmith, manual scaling and alignment to equipment coordinates are often required.

Step-by-step process for creating AR instructions

1. Load CAD model in STEP/IGES format and convert to GLTF via Open CASCADE Technology.
2. Attach annotations to nodes: arrow + text "loosen M8 fasteners × 4 pcs" to a specific point.
3. Disassembly animation: CAD model "slides out" showing the part removal path.
4. Create a checklist with auto-transition — the system repositions annotations after each step.
5. Export to AR app with local storage.

What's included in our work

• Technical audit of requirements and operating conditions
• AR app development for iOS/Android (ARKit/ARCore)
• CAD model conversion to AR-compatible formats
• Integration with ERP/CMMS via REST API or GraphQL
• Testing on real equipment with accuracy measurements
• Documentation and staff training
• Post-launch technical support

To choose the recognition approach: if equipment can be tagged with QR markers — choose Image Tracking (cheap and reliable). If markers are not allowed and the equipment has texture — Object Scanning. For maximum accuracy without markers on iPad Pro — LiDAR + ICP. The specific method is selected after audit.

Integration with ERP and CMMS

Typical integrations: SAP PM (Plant Maintenance), IBM Maximo, Infor EAM. The AR app receives the equipment serial number from ERP and loads the appropriate instructions. After completing maintenance, it writes work order completion back via API. For limited internet scenarios, offline sync is implemented: data is stored locally (SQLite / Core Data / Room) and synced upon connection restoration.

Timelines and cost

MVP (image tracking + static annotations without ERP integration) — 4–6 weeks. Full solution with animated instructions, offline sync, and integration — 3–6 months. Cost is calculated individually after requirements audit. Request a consultation — we will assess your project end-to-end. Write to us to discuss details.

Get a consultation from our engineers: we will assess your project, choose the optimal stack, and propose an implementation plan.

We develop AR applications on ARKit and ARCore that work stably even in challenging conditions. Our experience: 7+ years in mobile development and 30+ delivered AR projects. Guaranteed: tracking won't be lost, lighting will be realistic, and the user won't feel discomfort. Certified Apple and Google developers.

Why does tracking get lost and how to fix it?

ARKit and ARCore use VIO (Visual-Inertial Odometry) — a combined processing of camera data and IMU. Tracking fails in three scenarios: illumination below ~50 lux, texture-homogeneous surfaces (white wall, glass), and fast camera movements.

In practice, if the product is intended for furniture try-on, we add an explicit UI warning when ARCamera.TrackingState.limited(.insufficientFeatures). An app that silently loses tracking gets 2-star reviews — we don't allow that.

Plane detection is configured via ARWorldTrackingConfiguration.planeDetection = [.horizontal, .vertical]. Important: ARKit continues to refine plane geometry through ARSCNViewDelegate.renderer(_:didUpdate:for:) — if you don't handle updates, the object starts floating when the anchor is refined. Our team solves this at the architecture stage, not during testing.

AR Foundation: cross-platform with nuances

Unity AR Foundation is an abstraction layer over ARKit and ARCore. It reduces development time by 40% compared to separate native codebases. But some features (e.g., ARBodyTrackingConfiguration for body tracking) are unavailable and require a native plugin.

For React Native and Flutter, direct AR Foundation is missing. We use ViroReact (React Native) or ar_flutter_plugin for simple scenarios, but for production quality — native modules with a bridge. Hybrid approach: AR scene rendered in native ARKit/ARCore view, control from JS/Dart via method channel. Included in our standard delivery.

Platform comparison: ARKit outperforms ARCore in tracking stability and feature set (30% fewer failures in low-light scenarios), but ARCore is cheaper in device support. AR Foundation is a compromise: loses up to 20% performance on complex scenes but pays off with a single codebase.

Try-on: product fitting via AR

Fitting glasses, jewelry, cosmetics — a separate class of tasks. Here, face tracking is needed, not plane detection.

ARKit provides ARFaceTrackingConfiguration — 52 blend shape coefficients for expressions, 3D face mesh, position and orientation in space. Works only on devices with TrueDepth camera (iPhone with Face ID).

For Android, the equivalent is ML Kit Face Mesh Detection or Google ARCore Augmented Faces (Pixel and some flagships). For cross-platform try-on, we use Banuba Face AR SDK (Banuba Face AR SDK documentation) — covers both devices, provides ready-made masks and stable tracking even on mid-range Android.

Try-on quality critically depends on 3D product models. Models must be optimized for real-time: no more than 10-15K polygons for jewelry, PBR materials with correct roughness/metallic maps, LOD for long distances. Within our engagement, we provide ready-made optimization guides.

How to achieve realistic lighting in AR?

ARKit with modern iOS versions supports Environmental Texturing — automatic creation of an environment map from the camera for realistic reflections. Enabled via ARWorldTrackingConfiguration.environmentTexturing = .automatic. Without it, metallic and glass materials look plastic.

ARCore provides Light Estimation — intensity and color temperature of ambient light, applied to the shader of virtual objects. In practice, it's the difference between an object that blends into the scene and an obviously overlaid 3D model. We guarantee that the final image doesn't betray virtuality.

What's included

• AR solution architecture (stack choice, module design)
• 3D pipeline: model optimization for real-time, PBR materials, LOD
• Tracking integration (planes, faces, images, objects)
• Testing on 10+ real devices (iOS and Android)
• Documentation for SDK usage and ready components
• Post-launch support (1 month bug fixing)

Timeline and estimation

Simple AR scene with placing one 3D model on a plane — 1-2 weeks. Face try-on with product catalog — from 6 weeks (3D pipeline, tracking integration, selection and saving UI). Full AR shopping with cloud anchors and multiplayer — from 3 months. We'll estimate your project in 1 day — contact us to discuss your AR idea.