Integrate Low-latency Vision AI into Your Operations

Bring vision intelligence into production with Robovision Edge. Integrate models from our Robovision AI platform into our on-premise edge devices to power real-time applications with human-level predictions.

Talk to Our Expert
Robovision Edge can bridge the last mile of AI ingretion in an industrial environment

Bridge the Last Mile of  Vision AI Delivery

Integrating Vision AI into production is difficult, and so is maintaining it. Robovision takes care of both: our edge devices deploy AI on the lines but also capture and upload data to the platform, where your AI models are retrained and redeployed. Your vision applications will now remain accurate at all times with little to no downtime.

Achieve Complete Integration by Combining Platform and Multiple Edge Devices

Create your own specific vision solutions on our user-friendly and no-code Computer Vision AI platform. Then deploy them into your actual production environments through Robovision Edge. Each Edge device can cover multiple steps in the quality control process with standardised flexibility. Build and maintain low-latency AI solutions across factories with a complete toolset.


Managing an End-to-end AI Life Cycle

Robovision computer-vision AI can manage your entire industrial life cycle.

From gathering data to deploying models, our Robovision Platform and Robovision Edge devices cover every step of the AI life cycle. Quickly output new models for new products and maintain AI solutions yourself.

No Complication from the Start to Finish


1. Install Robovision Edge & Cameras

Mount the Robovision Edge device next to the production line. Connect the power supply and up to three cameras under a consistent angle and lighting, depending on your production line configuration.


2. Run the Application

In the device interface, set up the camera and choose which AI model to deploy. Start the monitoring. Your AI-powered computer-vision application is now up and running.


3. Continuously Improve Your Models

Model retraining needed? Set up the cameras to record data in the device interface. Upload these training images to the Robovision AI Platform and integrate the retrained model in the device afterwards.

With Robovision edge, you can create, update and deploy AI in a continuous life cycle

Closing the AI Life Cycle Loop

Together with our platform, you can now create, update, and deploy AI in a continuous cycle: perform data preparation and model training on the Robovision Platform, while data sourcing and model deployment on Robovision Edge.

Robovision Edge delivers low latency while running up to three cameras at a combined 40 fps.

Low Latency with High-performing GPUs

Run your applications at low latency with the NVIDIA Jetson Xavier AGX module. Its 32 TOPS of AI performance enables Robovision Edge to simultaneously run up to three cameras to capture, process, store, and upload images at a combined 40 fps.

Robovision is easy to integrate into your product life cycle process with an OPC-UA interfac

An Easy-to-integrate Solution

Harvest the value of your retrained AI model by integrating it with your PLC infrastructure through the built-in OPC-UA interface. Then selecting a model in the Robovision Edge interface is all it takes to deploy AI into your factory processes.

Robovision Edge operates in environments from -10 to 60 degrees calcius

Industrial-grade Hardware

Robovision Edge’s robust and fanless design enables it to operate anywhere between ‑10 and 60 °C even in dusty or humid environments. Being compact and ruggedised, Robovision Edge slots seamlessly into most factory configurations.

Companies with Robovision edge can standardise their hardware with Robovision Edge

Standardise Hardware

A different hardware set-up for each production line—that’s a thing of the past. Streamline the integration of AI across lines and factories with one, standardised edge device model.

Setting up a Robovision Edge device for each new line is all you need to do to expand your AI ambitions.


From the ground up, Robovision Edge was designed for scaling. Setting up a Robovision Edge device for each new line is all you need to do to expand your AI ambitions.

Out-of-the-box Algorithms for Standard AI Processes

Robovision platform supports standard algorithms such as image classification

For Label or Package Inspection & In-line Quality Control

Distinguishing different products is a fairly easy task for a human. Robovision goes one step further with deep learning. Based on a collection of labelled images, our out-of-the-box classification algorithm (EfficientNet) can distinguish different classes of images. For example, it can be a good versus bad classification or distinguishing different product variants or different defect types (depending on the use case of interest). This not only makes classification a great algorithm for label or package inspection, but also for in-line quality control. In this automatic defect detection system shown in the image, it classifies crops of laminate as accepted or not accepted across different laminate types and colours.

Robovision edge helps to integrate AI to a manufacturing process to help increase efficiency.

A Great Algorithm Addition for a Multi-line Conveyor

Classification alone is often not sufficient, especially in cases where the location of the object also needs to be known. Our object detection algorithm will provide additional help by drawing bounding boxes around the identified object of interest. In this way, the assembly can be verified for the presence of all its subcomponents or poor products can be identified and removed from the production line. This is especially useful when multiple lines converge on the same conveyor.

Robovision platform supports standard algorithms such as image segmentation

Richer insights for Quality Inspection or in Complex Environments

Instance segmentation (SOLOV2) adds another level of complexity compared to object detection as it demarcates the boundaries of the object of interest. It’s very useful for cases where metrics—surface, object or defect size—are key in the assessment of the quality of finished products. Furthermore, it can be used to locate objects in complex environments like a gas cylinder amongst other waste products as shown in the image.

Hassle-free Integration

Speed and efficiency is key in real-world production environments for which Robovision Edge is designed. The device’s powerful GPU makes fast and real-time processing on the conveyor possible. Furthermore, its integration with the Robovision Platform gives it the flexibility to efficiently adapt AI to changing data or business environments.

Learn More about the Robovision Platform
Robovision Edge offers hassle-free integration of AI applications in latency-critical operations

Boost Your Production Process with Faster AI Delivery

Use the Robovision Edge device for all kinds of computer vision applications—whether you need to retrieve gas cylinders or detect textile defects.

Robovision Edge together with the Robovision Platform can automate in-line quality control process

In-line Quality Control

AI for defect monitoring is here to stay. AI-powered visual inspection applications for quality control have already surpassed human capabilities. They ceaselessly deliver consistent output whereas human workers become tired and lose focus. This reduces costs, frees up manpower and ensures highly-consistent end quality.

Food Inspection Machinery

Agriculture is becoming a high-tech sector. Workers who used to manually sift through produce are now at the helm of intelligent food-sorting machines. Automation will be key towards solving challenges such as food waste and experienced labour shortages.

Technical Specifications

With a high-performing GPU, a flexible port configuration and efficient power consumption, Robovision Edge is industrial-grade hardware designed to operate in harsh industrial environments.

Dimensions (W x D x H) 192 x 230 x 87 mm (7.50 x 9.05 x 3.42 in)
Weight 4.5 kg (9.9 lbs)
Installation methods Desktop and wall-mounted fitting
Capturing frame rate 1 camera: 40 fps
2 cameras: 20 fps per camera
3 cameras: 13.3 fps per camera
GigE & USB 3.0 camera compatibility Basler Pylon SDK-supported RGB and mono area scan
Allied Vision Vimba SDK-supported  RGB and mono area scan
IDS uEye(+) SDK-supported RGB and mono area scan
Inference throughput Object Detection: 20 fps at a resolution of 640 x 640 x 3
Classification (EfficentNet): 40 fps at a resolution of 224 x 224 x3
Internal storage capability 1 TB
Jetson AGX Xavier GPU NVIDIA Volta architecture with 512 NVIDIA CUDA cores and 64 Tensor cores. 11 TFLOPS (FP16). 32 TOPS (INT8)
Industrial communication OPC-UA
2 x USB 2.0 and 2 x USB 3.0
16 bit (8-In 8-Out) DI/DO
COM: 2 x RS-232/RS-422/RS-485
2 x ethernet port (RJ45) at 10/100/1000 Mbps

Request more info about our Edge AI solution

Request More Info