Foundation of our services
Our cloud-edge infrastructure
Even the best algorithms cannot unfold their full power without the right infrastructure to run on. Our hybrid architecture concept combines the scalability of the cloud with the speed and security of edge computing.
Full flexibility for your IT
Our software runs on-premises, in the cloud, or both
The API runs on virtual machines in the cloud, or computers on a local network inside the factory, or a combination of both. Our solution satisfies the requirements of your company's IT department, no matter where your own application runs, be it inside a secure network on the shop floor or on devices with full access to the internet.
Long-running operations such as the training of AI models, are carried out in the cloud. Their results are asynchronously copied to one or multiple edge devices which run inference independent of an internet connection.
The edge device receives image data directly from a connected sensor. Robots and other clients trigger the capture and access the result of image evaluation via the local network.
The application of the customer is responsible for image capture. For evaluation, images are uploaded to the cloud.
A hybrid cloud-edge infrastructure is particularly advantageous for machine learning/AI applications. These typically involve complex computations such as the synthesis of training data or the optimization of neural networks. Performing these on a central entity (a public or private cloud) and sharing the results with one or multiple consumers has obvious advantages. Inference can be run on every consumer separately and in secure isolation from the training instance in the cloud.
# Combines the advantages of cloud and edge computing
# Scalable, fast, and secure
# Central storage location for all data
The API runs on a piece of hardware within an isolated network on the shop floor. All resources necessary for operation (applications, trained AI models, configurations, etc.) must be uploaded to the device prior to deployment or through a VPN tunnel, so that it is able to process all necessary requests made by the external application (e.g., the robot motion program).
Capable of real-time processing
No internet connection required
Free selection of suitable device type
When network latency is not of concern, all API functions are initiated by making HTTPs requests directed to one of our cloud endpoints. This way, our software integrates into any application with access to the internet — without the hassle of commissioning dedicated hardware.
Direct connection via HTTPs
No extra hardware needed
No tedious installation and configuration