Experience-based Computation: Learning to Optimise
Period: 01.04.2018 – 31.03.2022
ECOLE is a Marie-Skłodowska Curie Innovative Training Network (ITN) for Early Stage Researchers (ESR) based on novel synergies between nature inspired optimisation and machine learning. The training programme is targeted at the automotive industry, but the skill set of the ESRs will be equally valuable to other fast-moving innovative industries.
ECOLE is the first project of its kind in terms of studying Learning to Optimise systematically. It aims explicitly to understand and characterise “experience” in engineering optimisation and apply such
abstracted experience to optimise different, but related, engineering problems. It aims at solving a series of related optimisation problems, instead of treating each problem instance in isolation. In order to study these research issues synergistically, 8 different ESRs are employed to tackle different aspects of the whole research challenge.
ECOLE consortium members are the University of Birmingham (coordinator), Leiden University, the Honda Research Institute Europe and NEC Laboratories Europe.
Dynamic Data Analytics through automatically Constructed Machine Learning Pipelines
Period: 15.01.2018 – 15.01.2022
The DACCOMPLI project aims at developing a platform for dynamic data analytics that is based on techniques for automatically constructing data analytics pipelines for the task at hand.
The project will develop algorithm configuration approaches for composing, configuring, and parameterizing such pipelines from scratch – thereby automatically generating the best solution method for the application task at hand. For decision making, multiple objective optimization will then use the resulting models to generate optimal decisions in each application.
DACCOMPLI consortium members are University of Leiden, Honda Research Institute Europe, Technical University of Delft and Technical University of Eindhoven. The project is carried out in cooperation with Qualogy and LUMC.
Cross-Industry Predictive Maintenance Optimization Platform
Period: 01.09.2017 – 01.06.2022
The CIMPLO project aims at developing a cross-industry predictive maintenance optimization platform, which addresses the real-world requirements for dynamic, scalable multiple-criteria maintenance scheduling. To achieve the full business advantages in terms of safety, time and financial savings, the CIMPLO-project combines predictive maintenance with dynamic multi-objective scheduling, such that maintenance events and the required assets can be dynamically (re-)scheduled.
CIMPLO consortium members are University of Leiden, Honda Research Institute Europe, KLM Engineering and Maintenance and Centrum voor Wiskunde en Informatica (CWI), Amsterdam. The project is carried out in cooperation
with Damen, Tata Steel, DAF Trucks and the University of Amsterdam.
Vision-Inspired Driver Assistance Systems
Period: 01.09.2016 – 31.08.2019
The VI-DAS project is positioned to address the goals of improved road safety by development and deployment of Advanced Driver Assistance Systems and navigation aids in societally acceptable and personalised manner. VI-DAS will progress the design of next-generation 720° connected ADAS (scene analysis, driver status). Advances in sensors, data fusion, machine learning and user feedback provide the capability to better understand driver, vehicle and scene context, facilitating a significant step along the road towards truly semi-autonomous vehicles. On this path there is a need to design vehicle automation that can gracefully hand-over and back to the driver.
The VI-DAS consortium is coordinated by Vicomtech and has academic and industrial partners from six different EU member states.
Data Mining on High Volume Simulation Output
Period: 01.01.2016 – 31.12.2019
The DAMIOSO project focuses on developing algorithms and tools for managing and mining massive volumes of engineering data as well as using this data for optimization and for model learning. Computer-aided simulation tools play a central role in modern design processes for various industries such as the automotive industry. The simulations provide feedback to the designers without the costs of, for example, creating a real-life model for wind-tunnel testing.
To usefully manage these volumes of data, new automated methods are needed. The DAMIOSO project aims to create such methods, with a focus on three main topics: data storage, knowledge extraction and automated optimization. Combined, this leads to a toolbox of general-purpose methods that can be used for many applications.
DAMIOSO consortium members are University of Leiden, Honda Research Institute Europe and Centrum voor Wiskunde en Informatica (CWI), Amsterdam.
Low Cost GNSS and Computer Vision Fusion for Accurate Lane Level Navigation and Enhanced Automatic Map Generation
Period: 01.01.2015 – 30.06.2018
The INLANE project focused on the development of a low-cost, lane-level, precise turn-by-turn navigation application through the fusion of European Global Navigation Satellite Systems and computer vision technology enabling a new generation of Advanced Driver Assistance Systems.
The INLANE consortium is coordinated by Vicomtech and has academic and industrial partners from six different EU member states.