At the Embedded World Exhibition and Conference in Nuremberg, the Fraunhofer Institute for Industrial Mathematics ITWM, together with the Rhineland-Palatinate Technical University Kaiserslautern-Landau (RPTU), is presenting a system that fundamentally accelerates the development of embedded AI applications: »Neural Architecture Search Engine (NASE)« with Hardware in the Loop.
With NASE Fraunhofer ITWM presents an agentic system that designs and optimizes AI models for edge and embedded platforms. Instead of laboriously adapting existing models to a target platform, the neural search develops tailor-made architectures directly for the respective hardware, eliminating the need for additional model porting.
Software Tool for Hardware-Optimized Models in Weeks Instead of Months
»In practice, developers often resort to freely available models that do not function satisfactorily on the target hardware,« explains Dominik Loroch from Fraunhofer ITWM. »The necessary adaptation requires expertise in both hardware and AI design. NASE Hardware in the Loop takes care of precisely this complex optimization process.«
A special innovation is agentic AI: a language model queries the requirements for the application and automatically configures the search to achieve the best results. This eliminates the need for long training periods in tool operation.
The system reduces development times from several months to a few weeks – while delivering higher model quality compared to manual design processes.
NASE is particularly interesting for developers who need to port and optimize AI models on embedded hardware.
Typical areas of application include computer vision, production and condition monitoring, healthcare applications, and industrial assistance systems. Basically, all companies that want to use embedded AI in their products benefit, especially where computing power, energy consumption, and costs are strictly limited.
Demonstrator Shows Complete Pipeline
At the trade fair stand, the demonstrator shows visitors the complete development chain from the initial interaction to the executable application on the target hardware. The agentic system first queries the target variables, such as accuracy or runtime, and assists with the configuration of the search. It then generates models that work measurably faster and more efficiently on the respective platform than typical off-the-shelf models from the Internet.
In this context, »Agentic Artificial Intelligence« means that users simply formulate the goal, for example, what task the AI should perform on the embedded platform and what performance indicators must be achieved. The system decides independently how this goal is to be implemented technically. It uses a language model, calls up external tools, checks intermediate results, and optimizes iteratively until the requirements are met. Developers no longer have to specify how the AI model should be structured in detail; they only define the »what,« not the »how.«
Hardware in the Loop: Real Measurement Data Instead of Estimates
In the embedded sector in particular, the actual performance of an AI model is difficult to predict. That is why »Hardware in the Loop« is so important: models are executed and measured directly on real hardware. The RPTU in Kaiserslautern has developed a system for this purpose that can be used to automatically evaluate different hardware platforms. The measurement data obtained flows directly back into the architecture search. This results in models that are not only theoretically, but also demonstrably optimally matched to the target hardware.
Fraunhofer ITWM has been exhibiting at Embedded World for several years now and has observed a clear trend: »Embedded AI will become even more integrated into our everyday lives and industrial processes in the future,« says Loroch. At the same time, the challenge of developing these technologies efficiently and in a scalable manner in line with demand is growing. »Smarter development tools are the key to increasing productivity,« reports the Fraunhofer ITWM scientist. »Agentic systems in particular are a promising approach that we are researching intensively at Fraunhofer ITWM.«
With NASE Hardware in the Loop, Fraunhofer ITWM is demonstrating at Embedded World how embedded AI can be implemented faster, more efficiently, and in a hardware-optimized manner – a decisive step toward making intelligent systems widely available in the future.
Another Highlight: STANCE Networking Evening
As part of the trade fair, Fraunhofer ITWM and Fraunhofer IIS will also be hosting the STANCE networking evening at JOSEPHS in Nuremberg on March 11, 2026.
STANCE is an alliance of industry and research founded by Fraunhofer ITWM and Fraunhofer IIS that promotes neuromorphic and spiking-based, particularly energy-efficient, and extremely fast AI technologies for industrial applications. The event offers compact, practical insights into neuromorphic computing and creates space for exchange between industry, science, and start-ups.
Experience NASE Hardware in the Loop live at Embedded World and talk to our experts about your specific application. You can find us at the Fraunhofer-Gesellschaft’s joint booth in Hall 4, Booth 422. We look forward to seeing you there!
More about our division »Analytics and Computing«
