Title Promoter Affiliations Abstract "From ad-hoc code development to code reuse through middleware for networked embedded control systems." "Wouter Joosen" "Robotics, Automation and Mechatronics, Informatics Section" "The proposed knowledge platform brings together expertise in middleware and embedded control software, and addresses the lack of non real-time software management support to integrate and configure a networked embedded control system. The proposed knowledge platform will target software configuration tool providers, technology providers and system integrators in various application domains including robotics, e-logistics, e-healthcare, building management, and automotive control. It will provide them with a software development kit consisting of middleware, best practices for compliance monitoring, and domain-specific software configuration languages and tools. Enabling the transition from ad-hoc development of control software to a model-driven approach is key, because the risk and the associated cost of creating reusable middleware are too high for an individual player in the market. The proposed knowledge platform defines a sustainable revenue model based on industrial projects, consultancy services, and software licensing." "Embedded and distributed systems." "Jan Steckel" "Co-Design of Cyber-Physical Systems (Cosys-Lab)" "Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. As the system has to operate in real environments using real sensors, the environment where the system operates in has to be included in the model as well. Simulating physical quantities and realistic environments can become very complex very quickly. The time that has to be invested for achieving accurate simulation results can become too much. Experimental setups can provide the data which is needed to avoid the need for complex simulations. Therefore, a Hardware-in-the-loop and Sensor-in-the-loop approach will be adopted to provide the relevant data at the right time of the modeling process. Strategies for the right spatio-temporal sampling and the right moment to apply HIL/SIL methods are important questions to answer. Once the complete system has been modeled using the realistic models and the platform-specific constraints, hardware generation (VHDL, analog schematics, etc.) and code generation (C-code for embedded processors) from the high-level model can be used to accelerate the design cycle. Large functional changes often translate to small changes in the high-level model, and results often in large changes in the low-level representation. Using the right type of code- and hardware-generation can accelerate the design cycle significantly. Code generation can also be used in the form of prototyping platforms such as large FPGA's to accelerate certain sub-models of the MBD-design. HIL/SIL systems also allow for real-time performance to give rise to sensor flow, which is very important in a wide range of applications." "Embedded and distributed systems." "Jan Steckel" "Co-Design of Cyber-Physical Systems (Cosys-Lab)" "Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. As the system has to operate in real environments using real sensors, the environment where the system operates in has to be included in the model as well. Simulating physical quantities and realistic environments can become very complex very quickly. The time that has to be invested for achieving accurate simulation results can become too much. Experimental setups can provide the data which is needed to avoid the need for complex simulations. Therefore, a Hardware-in-the-loop and Sensor-in-the-loop approach will be adopted to provide the relevant data at the right time of the modeling process. Strategies for the right spatio-temporal sampling and the right moment to apply HIL/SIL methods are important questions to answer. Once the complete system has been modeled using the realistic models and the platform-specific constraints, hardware generation (VHDL, analog schematics, etc.) and code generation (C-code for embedded processors) from the high-level model can be used to accelerate the design cycle. Large functional changes often translate to small changes in the high-level model, and results often in large changes in the low-level representation. Using the right type of code- and hardware-generation can accelerate the design cycle significantly. Code generation can also be used in the form of prototyping platforms such as large FPGA's to accelerate certain sub-models of the MBD-design. HIL/SIL systems also allow for real-time performance to give rise to sensor flow, which is very important in a wide range of applications." "A Framework to Increase the Resilience of Embedded Systems – FIRES" "Jeroen Boydens" "Distributed and Secure Software (DistriNet)" "Embedded systems, now used in many (safety-critical) domains, suffer from run-time errors introduced by external disturbances. Systems regulated by functional safety standards are even required to use techniques which enable the detection of anomalous behaviour. While our previous research focused on detection techniques for different types of errors, simply merging and applying them to the entire code base imposes too much overhead onto the system, making this approach infeasible for the industry. Therefore, this project exploits previous research and gathered knowledge to develop an automated framework that 1) identifies the vulnerable parts of the embedded software through the injection of bit-flips and 2) proposes the necessary techniques to increase the resilience of these vulnerable parts. Through service agreements, this automated framework can be used by industry, making their products more resilient and giving them a competitive advantage." "Study of µTCA as a new standard in the design of FPGA-based embedded (data acquisition) systems." "Nick Van Remortel" "Particle Physics Group" "TERA-Labs, a joint research group of the Karel De Grote Hogeschool specialised in Embedded Systems, datacommunication and ICT partners with the experimental Elementary Particle Physics group of the University of Antwerp in research of high performance distributed FPGA-based data acquisition systems based on µTCA, a promising new standard in embedded technology. The aim is to establish and expertise platform in the hardware-software co-design of complete data acquisition systems with pure scientific and industrial measurement and automisation applications." "High-performance Embedded Systems (KIS)" "Jan Van Campenhout" "Department of Electronics and information systems" "The association research group KIS combines the strongholders within the Ghent University Association in the theme of embedded systems, and more in particular vision systems. The research subjects vary from algorithmic design of vision systems to the physical design of the vision system and optimized software that is executed on a computer architecture or specific hardware, reconfigurable or not." "A design process for parallel data processing in embedded systems." "Nick Van Remortel" "Co-Design of Cyber-Physical Systems (Cosys-Lab), Particle Physics Group" "The application domain of embedded systems is in need of design processes for parallel data processing in FPGAs. This project will develop a concrete design process based on a case study of simple pattern recognition by means of a high-level synthesis tool. This will lead to new generic insights in the design process of FPGA-code, as well as the efficient development of algorithms being used in current particle physics experiments." "Middleware for Distributed Deep Learning Networks in Embedded Systems" "Hans Hallez" "Distributed and Secure Software (DistriNet)" "Machine Learning and more in particular deep learning are gaining much more interest as a means to process and classify data. This is caused by growing experience in this domain, but also due to the availability of data. Indeed, many machine learning models greatly rely on data as the deep learning technologies need to undergo a training phase. Hence, the maturation of Internet of Things has led to a huge availability of data which, in its turn, boosted the adoption of deep learning across many application domains. This project aims at designing and developing a middleware framework to enhance the connectivity and information exchange of distributed deep learning architectures. We will investigate the ability to adapt to changing configurations and provide security measures to provide access control and secure data exchange between the distributed networks." "EPSim - Embedded Platform Simulator." "Paul De Meulenaere" "Co-Design of Cyber-Physical Systems (Cosys-Lab)" "When designing a complex cyber-physical system, components of the system are often designed by different engineers, each with their own expertise in a particular domain, e.g. software, control, and mechanical engineering. In later design stages, the integration of the designed components into one system needs to be performed. This integration phase however often leads to unexpected problems such that the system does not function as it was intended. The goal of this project is to develop EPSim, an engineering tool which tackles an important integration problem between embedded engineering and control engineering. EPSim will focus on the particular problem that embedded platforms introduce time delays on the signal path that is used by the control engineers. Hereto, EPSim will allow for the virtual integration of embedded components into control loops already in early stages of the design process. This will ultimately lead to optimised design processes by reducing, or even avoiding, costly design iterations. The foundations of this idea have already been developed in our lab; the related method and tool is now situated at TRL 3. The current status is attracting attention from some mechatronic companies in the framework of an ICON-project, which is an appealing starting point for further valorisation. By means of this project, we intend to further develop the method and tool towards TRL 5." "High Performance and Embedded Architecture and Compilation" "HiPEAC is a support action that aims to structure and strengthen the European academic and industrial communities in computing systems: (i) by increasing innovation awareness and by encouraging researchers to engage in innovation activities; (ii) by professionally disseminating program achievements beyond the traditional scientific venues; (iii) by producing a vision document including recommendations on how to improve the innovation potential of H2020 projects, and (iv) by growing the computing systems community beyond 2000 active members in Europe. The HiPEAC support action is meant to be the continuation of three successful FP7 networks of excellence with the same name (HiPEAC1-3). This support action will leverage the existing community, the expertise and the set of instruments that were developed since 2004 and work on the objectives of this support action: cross-sectorial platform-building, clustering of related research projects, structuring the European academic and industrial research communities, dissemination of programme achievements, impact analysis, constituency building and roadmapping for future research and innovation agendas. The overall approach of the HiPEAC support action is that it wants to bring together all actors and stakeholders in the computing systems community in Europe - especially EU-funded projects and SMEs - in one well managed structure where they can interact, disseminate/share information, transfer knowledge/technology, exchange human resources, think about their future challenges, experiment with ideas to strengthen the community, etc. The HiPEAC support action will support its members and projects with tasks that are too difficult/complex to carry out individually: vision building, professional communication, recruitment, event management at the European level. By offering such services a burden is taken away from the projects and members. They can then focus on the content, and the impact of their efforts is amplified."