Edge AI Platform 3.0: AI Development For Businesses Is Becoming Easier, Faster, And More Cost-Effective

Edge AI Platform« project is entering its third funding round: Three Fraunhofer Institutes are continuing to develop the platform into version 3.0 to provide companies with even more efficient access to embedded artificial intelligence (AI) and to significantly accelerate the integration of intelligent functions into products.

More and more products require built-in AI capabilities—yet traditional development processes are often complex, time-consuming, and require specialized expertise. This is exactly where the Edge AI Platform comes in: it enables companies to develop their own AI models directly for their products and seamlessly integrate them into embedded systems—even without in-depth expert knowledge.

Complete AI pipelines can be created, evaluated, and rolled out via a web-based application. The platform automates key steps such as training, optimization, and deployment. Users simply define their application and provide data—as a result, they receive optimized software libraries, detailed performance analyses, and concrete recommendations for suitable hardware.

Technological Advancements in Version 3.0
In the third project phase, the project team is expanding the platform with targeted new features. The focus includes automated data labeling for complex use cases, expansion to new and related image classes, and retraining modern vision-language models to annotate previously unknown objects. Additionally, methods for time-series analysis are being integrated—such as through self-supervised learning—and functions for object recognition and tracking are being further developed.

The project is also opening up new possibilities at the hardware level: specialized AI accelerators increase energy efficiency and processing speed and enable real-time applications directly on edge devices. This is complemented by approaches such as knowledge distillation to optimize powerful models for resource-constrained hardware.

Focus on Economic Benefits for Companies
The economic value for companies is central to this: »With the Edge AI Platform, we significantly lower the barriers to entry for using AI in product development. Companies can move from idea to a deployable model much faster and integrate AI into their products cost-effectively,« says Dr. Christian Wiede, Head of Embedded AI at Fraunhofer IMS.

Development times and time-to-market are significantly reduced, while prototypes and proofs of concept can be implemented quickly and with minimal resource expenditure. At the same time, new opportunities arise to relieve the workload on existing teams and make development processes more efficient. This allows companies to test new use cases early on and make informed decisions regarding the integration of AI into their products.

With a total budget of approximately 860,000 euros and a duration from December 2023 to November 2026, the project will be implemented in three sequential subprojects—ranging from model development and optimization of AI pipelines to integration into edge devices. Participants include the Fraunhofer Institute for Microelectronic Circuits and Systems IMS, the Fraunhofer Institute for Integrated Circuits IIS, and the Fraunhofer Institute for Manufacturing Engineering and Automation IPA. Funding is provided by the Fraunhofer Cluster of Excellence Cognitive Internet Technologies.

Contribution to Industrial Competitiveness
With this third round of funding, the project underscores its role as an innovation platform for the industrial use of AI and makes an important contribution to the competitiveness of companies in the age of intelligent, connected products.

Further information is available on the project website: Edge AI Platform - Fraunhofer IMS (https://www.ims.fraunhofer.de/de/projekte/edge-ai-plattform.html)