The ANDANTE project (AI for New Devices And Technologies at the Edge) aims to leverage innovative hardware platforms to build robust hardware/software platforms for Artificial Neural Networks (ANNs) and Spiking Neural Networks (SNNs) as the foundation for future products in the Internet of Things (IoT) at the edge, combining high energy efficiency with strong neuromorphic computing capabilities, demonstrating these in key application areas. The project brings together the expertise and infrastructures of Imec, CEA, and FhG, along with semiconductor companies, system integrators, AI SMEs, and application experts to explore and demonstrate the capabilities provided by the developed technologies.
The project will evaluate various applications in key areas where Europe is strong (automotive, digital agriculture, digital industry, mobility, and digital life). The goal is to strengthen and maintain strong leadership in these areas by connecting the industry with future memory technologies at a low TRL level (MRAM, OXRAM, FeFET). These interdisciplinary efforts will lead to the development of innovative hardware/software Deep Learning solutions, based on high-TRL RRAM/PCM and FeFET, to enable future products that combine high energy efficiency with robust cognitive computing capabilities. This new type of computing technology, combining ANN and SNN capabilities, will open up new possibilities, such as environmental monitoring and wearable electronic devices.
Within the ANDANTE project, Gradiant will participate in the use case of robust autonomous landing for smart mobility and transportation, providing video analysis-based algorithms for object detection and aerial image capture. Gradiant will also work on the optimization of these algorithms for FPGAs, as well as their evaluation on FPGAs and, optionally, on the neuromorphic hardware resulting from the project. Additionally, Gradiant will take on the role of Dissemination Manager.