In short




2020-05-01 > 2022-10-31


EUR 1 893 197,50


EUR 1 606 108,75



The BUBBLES project aims at defining separation minima and methods for unmanned air systems (UAS) flying in the very low level airspace (VLL), to improve the overall performance and safety therein. BUBBLES follows an operation-centric, risk-based approach, assigning the separation minima and methods within the framework of the U-space Concept of Operation (ConOps) and the corresponding risk level assessed using standard methodologies like specific operations risk assessment (SORA).

The project also develops algorithms to compute the collision probability between drones and between them and manned aircraft operating in the VLL, using separation minima to keep it under acceptable levels. Moreover, the project investigates how artificial intelligence (AI) can contribute to dynamically manage these minima using different separation methods and agents (from ground-based strategic conflict resolution to distributed self-separation). The mitigation effect of U-space services is also being taken into account, as well as the external and system induced risks (included those derived from the use of AI). Finally, BUBBLES extends the concept of Performance Based Communications, Navigation and Surveillance (CNS) to the drone operations to draft safety and performance requirements and developing monitoring tools in order to ensure that their actual performance complies with them.

BUBBLES develops Artificial Intelligence (AI) based algorithms to compute the collision risk of UAS leading to separation minima and methods so that a Target Level of Safety (TLS) stated in terms of overall probability of collision can be defined and maintained.

These algorithms are being applied to a set of generic ConOps for UAS operations defined by BUBBLES, detailed enough to cover most of the envisaged applications, but generic enough not to be linked to any particular one. They are classified in terms of risk using the SORA methodology.

These separation minima and methods are assigned to the ConOps using AI techniques, leading to the definition of a set of generic OSEDs from which safety and performance requirements for the CNS systems are derived applying a performance based approach.


Universitat Politècnica de València

Universidade de Coimbra

Università degli Studi di Roma "La Sapienza"


Indra Sistemas

This project has received funding from the SESAR Joint Undertaking under the European Union's Horizon 2020 research and innovation programme under grant agreement No 893206

European Union