Interdisciplinary Training Network in Multi-Actuated Ground Vehicles (ITEAM)
Funder
Horizon 2020
Value to Coventry University
£201,634
Project team
Partners
Technishe Universität Ilmenau, Flanders’ Drive, Infineon Technologies AG, Katholieke Universiteit Leuven, Skoda Auto a.s., Università degli studi di Pavia, Université de technologie de Compiègne, Das virtuelle Fahrzeug, Forschungsgesellschaft mbH, Volvo Car Group, IPG Automotive GmbH, Jaguar Land Rover, Technische Universiteit Delf, The University of Liverpool, Ústav teorie informace a automatizace AV ČR, v.v.i.
Duration of project
January 2016 - December 2019
Project overview
A consortium of sixteen partners started the Interdisciplinary Training Network in Multi-Actuated Ground Vehicles (ITEAM). ITEAM is aimed at establishing and sustainably maintaining the European training network with a high grade of interdisciplinarity by training strong specialists to research and develop cutting-edge technologies in the field of multi-actuated ground vehicles (MAGV). In this framework, the ITEAM consortium developed new hardware and software solutions to enhance the driving performance, improve vehicle safety and reduce the pollutants emissions. In concert with the research goals, the consortium facilitated a sound and close collaboration between the academia and industry in order to improve the career perspectives of the talented graduates.
A distinctive feature of the ITEAM network is the concept of interaction of three research clusters: “MAGV integration”, mainly aimed at developing subsystems for active control of the chassis and the powertrain; “Green MAGV”, focused on the development of innovative solutions to improve the efficiency and to reduce the emissions of MAGV; “MAGV Driving Environment” that deals with the realization of semi-autonomous and fully automated driving of MAGV. In particular, the research effort involved in three clusters stems from fifteen individual projects that will lead to doctoral thesis. All the participants were trained in the domains of control engineering and computational intelligence, vehicle dynamics and human machine interface, assessment of the proposed solutions by means of the development of virtual and real testing facilities for MAGV.
Project objectives
The main expected research outcomes will result from complex integration, processing and interpretation of available data from the ground vehicle and environment, taking care of safety, high performance, and low-emissions operations. The ITEAM consortium created a set of research databases and open source software to provide wide access to shared electronic research and technical material of the participating members. For the sake of the open access to research data, the project results and assets will also be made available to a wide international audience in order to share the acquired knowledge outside of the consortium. A number of publications have been produced accordingly.
-
Impact statement
This project contributed to the development of novel algorithms that have been subsequently utilised by Jaguar Land Rover for the improvement of their tyre modelling processes.
-
Outputs
Weber, Y., & Kanarachos, S. (2019). The Correlation between Vehicle Vertical Dynamics and Deep Learning-Based Visual Target State Estimation: A Sensitivity Study. Sensors, 19(22), 4870.
Acosta, M., & Kanarachos, S. (2018). Teaching a vehicle to autonomously drift: A data-based approach using Neural Networks. Knowledge-Based Systems, 153, 12-28.
Acosta, M., Kanarachos, S., & Fitzpatrick, M. (2018). Robust Virtual Sensing for Vehicle Agile Manoeuvring: A Tyre-Model-Less Approach. IEEE Transactions On Vehicular Technology, 67(3), 1894-1908.
Acosta Reche, Manuel & Kanarachos, Stratis & Fitzpatrick, Michael. (2017). A Virtual Sensor for Integral Tire Force Estimation using Tire Model-Less Approaches and Adaptive Unscented Kalman Filter.
Acosta, M., & Kanarachos, S. (2017). Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares. Neural Computing And Applications, 30(11), 3445-3465.
