Obsolescence, "the transition from the state of availability to the state of unavailability of an entity from its manufacturer according to the original specification" is inevitable. Changes in technology and requirements generate obsolescence that makes repair or maintenance or upgrading difficult. Component obsolescence exposes the value chain to various risks (financial, etc.) that can lead to the operational unavailability of systems. Obsolescence management seeks to delay its occurrence, provide a long time window for action, and determine the least costly solution. Management approaches are either reactive or proactive. A reactive solution is applied after the obsolescence has occurred. Proactive methods seek to predict obsolescence in order to anticipate it, but they are complex and benefit from little work. Both approaches are necessary and complementary. The work of the EOS project seeks to define a method to assist in the activE (i.e. reactive and proactive) management of system obsolescence in order to 1) Maximise the operational availability of a system or a fleet of systems via a simulator. Availability is assessed by the Operational Availability Rate (OAR) which is the ratio of the number of hours of proven operational availability to the total number of hours. 2) Define or characterise and evaluate any remediation strategy by a set of indicators such as the total cost of implementing remediations or the immunity time (the time before the OAR is impacted). 3) Size the spare parts inventory and determine the replenishment plan for components at risk. 4) Optimise the time window for action by accepting a threshold of acceptability of the risk of stock shortage with regard to costs and the target OAR.

The development of algorithms for Autonomous Vehicles (AVs) faces important challenges throughout the design and implementation pipeline. The high cost and complex operation of real-world test-beds limits the experience an embedded Artificial Intelligence (AI) can gather, as it originates from a few vehicles that cannot be kept online extensively. For this reason, development often goes through a simulation stage or a testing step on a simplified system (e.g., smaller vehicles, standalone sensors or robotic models). In MultiTrans the focus is on the perception stage of AVs, which needs to provide a very accurate representation of the driving environment(s), that is used as an input for the following decision and control steps, while allowing a clear discrimination between similar but different contexts. The project takes the perspective of vision-based embedded systems (i.e., relying on cameras or similar sensors) that are among the most promising perception solutions. Their underlying sensing technologies however make them sensitive to an important research challenge: facing adverse conditions (such as bad weather or sun glare). In addition, knowledge transfer between different (real or virtual) environment suffers from two additional issues: reality gap, when a simulation/model fails to capture all the particularities of a real system, and the extended development time caused by the inherent repeated iterative process of adapting an algorithm from a system/domain to a different one. In MultiTrans, we propose to address these research issues by tackling autonomous driving algorithms development and deployment jointly. The idea is to enable data, experience and knowledge to be transferable across the different systems (simulation, robotic models, and real-word cars), thus potentially accelerating the rate an embedded intelligent system can gradually learn to operate at each deployment stage. The research hypothesis acting as a starting point of MultiTrans corresponds to the current state of deployment of autonomous driving technologies: AVs can be programmed (or are able to learn) to react and operate in controlled (or restricted) environments autonomously. The focus of our proposal is on the AI-side : research is needed to help these systems during the perception stage, enabling AVs to be operational and safer in a wider range of situations. The project is expected to contribute to substantial advances with respect to state of the art, by resulting in (i) A novel theoretical framework and new algorithms on transfer and frugal learning in virtual and real environments; (ii) Advances in multi-domain and multi-source computer vision for semantic segmentation and scene recognition applied to safe autonomous driving and (iii) The development of a robotic autonomous vehicle model demonstrator combined with a virtual world model. The novelty in this project is to develop an intermediate environment that allows to deploy algorithms in a physical world model. This additional step will allow to re-create more realistic use cases that would contribute to a better, faster and more frugal transfer of perception algorithms to and from real autonomous vehicle test-beds. This robotic platform will also enable to lead research focusing on multi-domain and multi-actor transfer by reducing the time and efforts required to build relevant use cases and multiple variants of these scenarios, thus allowing to achieve domain generalization. We will also explore frugal learning techniques such as few-shot learning would reduce the amount of samples require for the recognition/segmentation tasks to converge before transferring them. Thanks to the platform, we will be able to evaluate solutions for complex configurations in the virtual environment and then transfer them on the platform, bridging the gap between behaviour cloning (through imitation learning) and simulation.

REALHOLO is a project to develop an advanced micro-mirror-based piston type spatial light modulator SLM for real holographic 3D mixed reality MR display applications, active illumination and sensing. The plan is to create a micro-mirror-array MMA, modulating the phase of visible light with optical features far superior to any liquid crystal-based alternative and to binary micro-mirror SLM. The core technology will be developed in a high bandwidth CMOS backplane design and interfaces, in MEMS mechanics and optics for very small mirrors, in semiconductor micro-mirror fabrication and packaging technologies, in real-time computation and driving of real holographic content, in projection optics. The goal is an application-specific demonstration of the MMA in automotive use in real holographic MR head-up display HUD and active head lamp projection system; enable future applications like real holographic head-mounted displays HMD. To achieve the goals REALHOLO will develop dedicated core hardware concepts and modules for integration in desired phase SLM, based on consortium partners’ selected prior design development, simulation results, practical tests of key technological and optical aspects and use case research. A further development is the corresponding high speed and high bandwidth control hardware and software for generating and driving signals for the new SLM. The developed module solutions will be integrated in a packaged optical system for further integration with validation use case in real holographic 3D image system. With REALHOLO the consortium enables a revolutionary next generation light modulating device for a variety of new and proprietary applications with unique features in natural 3D imaging, highly efficient active illumination, irradiation, sensing, etc. This will strengthen the European research, development and manufacturing in industries and institutions ranging from optical, electronics, automotive to bio/-medical, agricultural and outer space.