Modern industries such as healthcare, security, smart cities, and autonomous systems rely on rapid and efficient data processing. However, current technologies struggle to meet these demands, limiting performance and increasing power consumption. The NEHIL project, funded by ChipsJU (EU) and the Korean NRF, is set to revolutionize data processing through neuromorphic computing and heterogeneous integration with LiDAR technology.

This EU-Korea collaboration focuses on developing two innovative neuromorphic computing systems designed to tackle the challenges of high-speed, energy-efficient data processing. One system is based on FeFET-based Compute-in-Memory (CIM) accelerators, which enhance processing speed and efficiency by supporting hybrid models of Spiking Neural Networks (SNN) and Artificial Neural Networks (ANN). The other system leverages Photonic Integrated Circuits (PIC) using reservoir computing principles, enabling more efficient and scalable processing of dynamic data streams.

By integrating these neuromorphic architectures with Frequency-Modulated Continuous Wave (FMCW) LiDAR, NEHIL aims to redefine industry standards for accuracy, resolution, and power efficiency. This approach significantly reduces energy consumption, lowers costs, and improves performance in real-time applications. The project specifically targets a 50% reduction in power consumption for object recognition tasks and aims to demonstrate ultra-low latency LiDAR signal processing using the newly developed architectures.

NEHIL’s advancements extend beyond autonomous systems, benefiting a wide range of sectors, including telecommunications, healthcare, smart cities, security, predictive maintenance, infrastructure management, and industrial automation. Through this groundbreaking collaboration, the project is paving the way for the next generation of intelligent, high-performance computing solutions.