Decentralized Edge Intelligence: Advancing Trust, Safety, and Sustainability in Europe

Project Information

EdgeAI-Trust

Grant agreement ID: 101139892

DOI

10.3030/101139892

EC signature date 27 June 2024

Start date 1 May 2024

End date 30 April 2027

Funded under

• Digital, Industry and Space

Total cost

€ 38 033 913,75

EU contribution

€ 10 983 593,97

Coordinated by

TrustMotion Germany GmbH
Germany

Periodic Reporting for period 1 - EdgeAI-Trust (Decentralized Edge Intelligence: Advancing Trust, Safety, and Sustainability in Europe)

Reporting period: 2024-05-01 to 2025-04-30

Summary of the context and overall objectives of the project

EdgeAI-trust aims to develop a domain-independent architecture for decentralized edge AI along with HW/SW edge AI solutions and tools, which enable fully collaborative AI and learning at the edge. The edge AI technologies address key challenges faced by Europe's industrial and societal sectors such energy efficiency, system complexity and sustainability. EdgeAI-trust will enable large-scale edge AI solutions that enable interoperability, upgradeability, reliability, safety, security and societal acceptance with a focus on explainability and robustness. Toolchains will provide standardized interfaces for developing, optimizing and validating edge AI solutions in heterogeneous systems.

The generic results will be instantiated for automated vehicles, production and agriculture, thus offering innovation potential not only in the generic HW/SW technologies and tools, but also in the three target domains. These technological innovations are complemented with business strategies and community building, ensuring the widespread uptake of the innovations in Europe. EdgeAI-trust will establish sustainable impact by building open edge AI platforms and ecosystems, with a focus on standardization, supply chain integrity, environmental impact, benchmarking frameworks, and support for open-source solutions.

The consortium consists of major suppliers and OEMs encompassing a broad range of application domains, supported by leading research and academic organizations.

By embracing the opportunity to specialize in Edge AI, Europe can maintain its position in the global context, especially as it aligns with decentralized and privacy-driven European policy. Furthermore, as AI is closely connected with the Green Deal, this project can provide proper solutions for environmental issues. Ultimately, the project will enable AI to be connected with other strong sectors and industries, improving the innovation process and decision-making in Europe.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

WP1 focused on defining comprehensive requirements and specifications for decentralized Edge AI solutions across component, subsystem, system, and operational levels in multiple supply chains. These requirements provide the foundation for guiding research, system design, and validation activities in subsequent phases of the project. The main outcomes include:
• A consolidated set of functional and non-functional requirements for decentralized Edge AI solutions.
• Specifications addressing interoperability, scalability, security, and real-time performance across heterogeneous environments.
• Alignment of requirements with the demonstrator objectives in each supply chain.
WP2
T2.1: Reference Architecture Definition
A modular, decentralized Edge AI reference architecture was defined, consolidating its main components and establishing a clear mapping of the demonstrators in each supply chain to the proposed architecture. This ensures consistency and interoperability across all demonstrators.
T2.2 – T2.6: System-Level Design Consolidation
Significant progress was achieved in accelerating the consolidation of the main elements of the system-level design for the demonstrators. This preparatory work ensures readiness for the next work packages, where implementation and validation will take place.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

WP1 (Requirements & Specifications).
WP1 delivered a cross-supply-chain, multi-level requirement baseline (component → subsystem → system → operations) that explicitly captures non-functional metrics—security, safety (incl. real-time behavior, robustness, resilience to hardware faults), and trustworthiness—together with traceability to demonstrators. This unified requirements model enables domain-independent validation criteria and consistent design decisions across heterogeneous edge environments.
WP2/T2.1 (Architecture).
A preliminary modular, decentralized Edge AI architecture was proposed that:

Is domain-agnostic and deployable across heterogeneous edge devices and supply chains.
Promotes modularity and scalability, allowing component replacement/evolution without system-wide redesign.
Ensures interoperability across diverse software stacks, hardware platforms, and network protocols.
Balances performance efficiency with flexibility to adapt to varying applications and environments.
Natively incorporates non-functional guarantees (security, safety, trustworthiness) as first-class design objectives.

Together, WP1’s rigorous, cross-domain requirements and T2.1’s architecture specification constitute a step beyond monolithic, domain-specific approaches—establishing a portable, interoperable, and assurance-driven foundation for decentralized Edge AI.