Inspection of Critical Infrastructures is a throughout and delicate process, so not all the drones available in the market have the correct specifications for supporting this operation.

The deployment of services on the drones, provide advanced capabilities to be able to process and analyse data while making the flights, which means extending its functionality from data capture to analysis.

The following types of drones can be used for inspections and due to its open configuration allow the deployment of services:

AEROTOOLS

Multi Rotor Drones

Fixed Wing Drones

Single Rotor Helicopter

Edge Devices

Edge Computing is playing an essential role in the technological transition to greater machine autonomy by allowing the delivery of essential data fast and reliably enough and managing applications and infrastructure lifecycles efficiently.

I-FLY considers both, Edge devices that can be installed on the drones to allow data processing and analysis on the drone itself with specific services, and Edge devices located on the ground that support the execution of services close-to-the-source from where the data is being gathered.

I-FLY services can be deployed in the following:

Nvidia Jetson Nano

Enables the development of millions of new small, low-power AI systems with embedded IoT applications, including entry-level Network Video Recorders (NVRs) and intelligent gateways with full analytics capabilities.

NVIDIA Jetson Nano is a small, powerful computer that runs multiple neural networks in parallel for applications like image classification, object detection, segmentation, and speech processing. All in an easy-to-use platform that runs in as little as 5 watts.

Raspberry Pi 4 - 2GB RAM

Offers ground-breaking increases in processor speed, multimedia performance, memory, and connectivity in comparison to prior-generation models, while retaining backwards compatibility and similar power consumption.

The key features of the 2GB RAM include a high-performance 64-bit quad-core processor, dual-display support at resolutions up to 4K via micro-HDMI ports, hardware video decode at up to 4Kp60, dual-band 2.4/5.0 GHz wireless LAN, Bluetooth 5.0, Gigabit Ethernet, USB 3.0, and PoE capability.

Raspberry Pi 3

Using UBUNTU Mate 18.04 LTS OS, the Raspberry Pi 3 B+ it’s a perfect device to run an execute AI and CV algorithms and models. The third-generation single-board computer has 1.4GHz 64-bit quad-core processor, dual-band wireless LAN, Bluetooth 4.2/BLE, faster Ethernet, and Power-over-Ethernet support (with separate PoE HAT).

Ubuntu offers other type of benefits such as:

  • Ubuntu kernel, with direct support from the Ubuntu Linux kernel development and security teams
  • Automatic online file system expansion
  • Support for Ethernet and WiFi (when available).
  • Support for Bluetooth (when available).
  • Audio output through the 3.5mm or HDMI analog jack.
  • Access to GPIO via GPIO Zero, pigpio and WiringPi.
  • Support for Python Wheels for Raspberry Pi.
  • USB boot support.

Atos Bull Sequana Edge

Designed to provide leading AI acceleration capabilities for resources and video streaming analytics. The server can host up to two powerful Nvidia Tesla T4 GPUs or optional FPGA’s. This enables the inference of complex AI models right at the edge with lowest possible latency. Together with its powerful 16 core Intel® Xeon® processor, BullSequana Edge provides an outstanding compute power-pack for the implementation of most demanding machine learning applications.

This end-to-end service enables, maintains Edge devices and provides secure access locally on both human and machine-interface level. Atos makes sure that functionality and secure connectivity are up-to-date by automatic monitoring of edge devices and identifying unusual events in real time. When needed, software updates are carried out. Most Edge services are delivered remotely.

IT Infrastructure & Cloud Computing

To offer automated IT software services on distributed UAV, Edge and Cloud element services, a solid workflow in data management has been established with an emphasis on acquiring data and storage in order to have control of the service with the conditions selected.

A robust infrastructure supports the marketplace for the fast and easy deployment of IT services on the selected device. The IT infrastructure is composed by Docker containers that allow quick deploy and scale application into any environment, and by Kubernetes to deploy and manage containerized applications at scale. The following Cloud providers support the deployment of services.

Amazon Web Services

Amazon Elastic Container Service (Amazon ECS)

Highly scalable, high performance container management service that supports Docker containers and allows to run applications, such as I-FLY services, on a managed cluster of Amazon EC2 instances.

Amazon Elastic Kubernetes Services (Amazon EKS)

Managed Kubernetes service that runs Kubernetes on AWS without the need to install, operate, and maintain Kubernetes control plane. It automatically manages the availability and scalability of the Kubernetes nodes that are responsible for starting and stopping containers, scheduling containers on virtual machines, storing cluster data, and other tasks.

Microsoft Azure

Azure Kubernetes Service (AKS)

Deploy and manage containerized applications more easily with a fully managed Kubernetes service that offers an integrated continuous integrations and delivery experience with enterprise-grade security and governance.

Docker on Azure

Quick and easy migration of I-FLY services to increase security and modernize app services. It allows to run modern apps while driving down operational costs and improve efficiency with a uniform operating model and supply chain for apps in Docker containers.

Google Cloud

Google Kubernetes Engine

Enterprise-ready containerized solutions with prebuilt deployment templates, featuring portability, simplified licensing, and consolidated billing. Automatic scaling the node pool and clusters across multiple node pools, based on changing workload requirements.

GCloud Docker

Container Registry is a private container image registry that runs on Google Cloud. Container Registry supports Docker Image Manifest V2 and OCI image formats. You can access Container Registry through secure HTTPS endpoints, which allow you to push, pull, and manage images from any system, VM instance, or your own hardware. Additionally, you can use the Docker credential helper command-line tool to configure Docker to authenticate directly with Container Registry.

FogAtlas

FogAtlas (evolution of the former Foggy platform) is a software framework aiming to manage a geographically distributed and decentralized Cloud Computing infrastructure that provides computational, storage and network services close to the data sources and the users, embracing the Fog Computing paradigm. FogAtlas is able to manage the so called Cloud-to-Thing Continuum offering service-aware workload placement and zero-touch deployment. It is an evolution of the well known paradigms of IaaS and PaaS adding the concept of “locality” to the traditional Cloud Computing model and easing the operations of a Fog Computing infrastructure.