DRONEAI | ESA Space Solutions

Objectives of the service

DRONE^AI project is integrating a set of technical and operational assets to deliver a quick, automated and field deployed solution.

DRONE^AI solution, as an end-to-end solution, will provide two major capacities:

a local data processing chain that will apply the AI models on the captured images following the requests of the field personnel,
a central solution allowing data-scientists or GIS specialist to create and distribute AI models.

The solution could integrated into the emergency.lu mobile, satellite-based, telecommunication platform.

Users and their needs

DRONE^AI has been designed to reduce the delay between the capture of the observation data and exploitation of assessment information.

Currently, the exploitation of the observation is performed locally by expert, analysing and manually annotating the observation. The mutual use of AI technologies and edge processing incredibly reduces the delay before the exploitation of information.

Service/ system concept

A full stack solution

DroneAI solution relies on the Max-ICS platform developed and operated by EarthLab Luxembourg. Drone.AI is using the Deep Learning factory (C) concept allowing to easily create, train, test and deploy machine and deep learning models. Max-ICS also provides a modern Platform as a Service solution covering all the requirements in term of application hosting, deployment, security and scaling.

AI on the edge

Thanks to the Max-ICS platform, DroneAI offers a complete coverage from the training to the inference of AI models.
Artificial Intelligence inference operations are very demanding in term of processing ressources and these inference operations are here performed on the field of operation, close to the capture of the observation information. To maintain a good level of performance, a dedicated edge component, relying on the nVIDIA AGX Xavier hardware, is integrated into the NoSaCo devices built by HITEC Luxembourg and used as terminals within emergency.lu platform. Max-ICS platform is managing this device performing automatically the maintenance operations, the configuration of the device avoiding complex IT operations from the field.

Large variety of AI operations

Max-ICS platform offers a large variety of computer vision tasks and trained models. In the context of the Drone-AI project, different models are already accessible to demonstrate the large capabilities of the solution. For example, models to detect the roof damages, to look for road destruction or building vulnerability detections, are directly accessible.
It is also possible to build new models or extend the existing ones using the model training features accessible from the Max-ICS platform.

Space Added Value

The DRONE^AI solution will heavily rely on different space assets. First, the system will be defined to work in the complex humanitarian environment.

Satcom is required in order to restore the required communications between the affected sites and the Head Quarters (HQ) or the other affected sites. For this, the project will rely on the existing NoSaCo terminals produced by HITEC Luxembourg S.A. and already in operations in different humanitarian operation within the emergency.lu project.

For the DRONE^AI solution, the Satcom will be used to allow the NoSaCo terminal to be used as an edge device for the application of Artificial Intelligence models. The models will be trained and maintain in a central platform and synchronised with the equipment on the ground either during preparedness operations or using the Satcom link.

Finally, Satcom will be used for the synchronisation of the information extracted from the analysed information using the various AI models and captured data.

The GNSS technologies are also used in different applications for the accurate positioning of different assets and people. It has been used for the tracking of the first responders and assets. With the DRONE^AI project, GNSS will be required for the drone positioning and projection of the captured data.

Finally, Earth Observation will be an important add-on to the solution. Indeed, the Copernicus Emergency Management Services (EMS) already provides a set of mapping services for the emergencies and drought. One of the main drawbacks of this service is the resolution of the based imageries. The DRONE^AI solution will offer a complementary solution with a high-resolution mapping completing Copernicus EMS. EMS services can also be embedded in the DRONE^AI solution as a background set of information.