NeurOSmart

Increase the energy efficiency of data processing by at least two orders of magnitude.

• Integration of intelligence directly into the sensor system (co-design of sensor-HPC architecture)
• Use of an open scanning LiDAR system as the data access basis
• Combination of AI-supported preprocessing pipeline and neuromorphic in-memory accelerator
• Close coordination between sensor development and hardware adaptation

• Open scanning LiDAR system as sensor basis for direct data stream access
• AI-supported preprocessing pipeline for fast, local evaluation
• Neuromorphic in-memory accelerator chip for ultra-low-power inference

• Autonomous vehicles and logistics robotics
• Precautionary and safety systems in mobility applications
• Real-time data analysis at the sensor periphery

Fraunhofer ISIT is the coordinator of the NeurOSmart project. Its research expertise includes the development and integration of piezoelectric and ferroelectric materials for microelectronic and electromechanical applications. Within the project, Fraunhofer ISIT is primarily responsible for evaluating AIScN as a revolutionary “next-generation” ferroelectric for use in ferroelectric field-effect transistors.

One of the primary research competencies is the development of memory technologies in advanced node CMOS implementations. For this purpose, Fraunhofer IPMS has an innovative ferroelectric memory technology (FeFET) at its disposal. Within the NeurOSmart project, memory emulation is used, among other things, for software blocks to control the in-memory hardware blocks and to manage data streams.

The Fraunhofer IWU's area of expertise ranges from machine tools, forming, joining, and assembly technology to precision engineering and mechatronics, digitalization in production, and virtual reality in the context of mechanical engineering. In particular, Fraunhofer IWU has many years of experience in researching and developing safe human-robot systems and sensitive robots. As part of the project, the institute will evaluate the sensor system in an industrial environment to determine its suitability for use.

Fraunhofer IAIS has research expertise in the areas of distributed learning, language assistance systems, and computer vision for autonomous driving. The institute has a powerful speech recognition system for automatic transcription and speech signal recognition. As part of NeurOSmart, the institute is pooling its expertise in areas such as neural network training.

The core competencies of Fraunhofer IMS lie in the development of embedded software and AI, smart sensor systems in the business areas of health, industry, mobility, space, and security. The institute has developed AIfES (Artificial Intelligence for Embedded Systems), a platform-independent and constantly growing machine learning library in the C programming language. AlfES is also an important prerequisite for NeurOSmart in the development of the hardware platform for sensor and scanner control.