Massive adoption of computing in all aspects of human activity has led to unprecedented growth in the amount of data generated. Machine learning has been employed to classify and infer patterns from this abundance of raw data, at various levels of abstraction. Among the algorithms used, brain-inspired, or “neuromorphic”, computation provides a wide range of classification and/or prediction tools. Additionally, certain implementations come about with a significant promise of energy efficiency: highly optimized Deep Neural Network (DNN) engines, ranging up to the efficiency promise of exploratory Spiking Neural Networks (SNN). Given the slowdown of silicon-only scaling, it is important to extend the roadmap of neuromorphic implementations by leveraging fitting technology innovations. Along these lines, the current project aims to sweep technology options, covering emerging memories and 3D integration, and attempt to pair them with contemporary (DNN) and exploratory (SNN) neuromorphic computing paradigms. The process- and design-compatibility of each technology option will be assessed with respect to established integration practices. Core computational kernels of such DNN/SNN algorithms (e.g. dot-product/integrate-and-fire engines) will be reduced to practice in representative demonstrators.

Mid-air, near mid-air, and-on ground collisions are one of the most important cause of accident in general aviation. For this reason, engineering an affordable sensor helping pilots in preventing it could be very important in order to prevent accidents. Present sensors, indeed, are very expensive and cannot be affordable for small aircraft and helicopters. The idea of ODESSA (Obstruction DEtection Sensor for Surveillance on Aircraft) is to provide a small, light, and low-cost sensor (comparing it to the present ones) that could be installed on both airplanes and helicopters, but on unmanned aerial vehicles too. This is possible adopting the modular avionics concepts of on-board system independency, reducing maintenance efforts, granting different platform applicability. Using millimetric radar, learning techniques from automotive worlds, gives different advantages. One is that automotive technologies are well tested and reliable. These solutions are small, light and cheap too. Inheriting characteristics from automotive technologies, ODESSA allows to detect small object, increasing on-ground safety during handling and taxing. An issue of these mission phases is the possibility of collision not only with aircraft (that could be minimized by using new generation ADS-B systems), but with other kinds of object (as pushbacks, cars, signals, personnel, birds…) not well detectable from aircraft unless mounting the terrestrial version of ADS-B (that requests the adaptation of the whole airport infrastructure). ODESSA system makes possible that safety in landing and ground procedures is independent from different component of the airport system, granting danger acknowledgment in different sceneries.

na

Digitalization has been identified as one of the key enablers for renewal and competitiveness of European manufacturing industries. However, grasping the digitalization and IoT-related opportunities can be limited by the harsh environmental conditions of the manufacturing processes and end use environments. The ECSEL-IA 2019 project initiative CHARM aims to contribute to solving this problem by developing ECS technologies that tolerate harsh industrial environments. The project concept centres around real industrial challenges from different types of end use industries. The synergies and impacts arise from similarities in technology solutions serving different applications and industry sectors. The CHARM Use Cases include six different industry sectors, majority of them presented by innovative cutting-edge large enterprises that belong to the world-wide market leaders of their own sectors – while most of them being new to the ECSEL ecosystem: mining (Sandvik Mining and Construction Oy, FI), paper mills (Valmet Technologies Oy, FI), machining (Tornos SA, CH), solar panel manufacturing lines (Applied Materials Italia SRL, IT), nuclear power plants maintenance and decommissioning (ÚJV Řež a.s., CZ), and professional digital printing (Océ-Technologies B.V, NL). The planned demonstrators engage these big players with European ECS value chains and showcase capabilities that serve manufacturing industries’ needs at large. The new technologies to be developed include novel multi-gas sensors, robust high temperature and pressure sensors, flexible sensors for paper machine rolls, wireless power transfer systems, connectivity solutions for rotating parts, advanced vision systems, and enablers for autonomous driving. The project consortium includes 12 SMEs, 14 LEs and 12 RTOs, and covers the industrial value chains from simulations, sensors and components to packaging, integration and reliability as well as connectivity, cloud and cyber security solutions.