Validation of Automotive ADAS Systems in Hardware-in-the-Loop Test Environments for European General Safety Regulation Homologation
ADAS technologies play a crucial role in enhancing road safety, and their compliance with safety regulations is of utmost importance. Hardware-in-the- Loop (HIL) testing offers an efficient and repeatable validation approach, ensuring Advanced Driver Assistance Systems (ADAS) meet the stringent requirements of the European General Safety Regulation.
This Master's thesis focuses on the validation of automotive ADAS within HIL test environments, specifically for tests related to homologation according to the European General Safety Regulation. The study presents the HIL test bench setup, defines specific ADAS test scenarios, and analyzes validation results compared to real-world testing.
Challenges and recommendations for future improvements are identified. The research aims to enhance ADAS regulatory compliance and contribute to safer mobility on European roads.
Contact: Ing. Giuseppe Mercurio - mercurio_g@fev.com
Tutor:
Requirements:
Speed Profile Prediction for energy management tailored to the driver-style
Predicting the driver behavior is an enabler for the prediction and therefore the reduction of vehicle emissions. Given real-time data on route and traffic, it is possible to design an adaptive speed profile prediction, which matches the driver style. This master thesis focuses on completing the porting of the Speed Profile Prediction (SPP) function from a prototype Hybrid Control Unit (HCU) Simulink model, to an portable Python implementation. The SPP shall be tested on several platforms, including an Infotainment System and finally as service in the Cloud. To validate the SPP and adapt the driver style parameters, synthetic driving data will be generated using dSpace ASM Traffic simulator. Finally, traffic participants are introduced in ASM to reproduce the driver behavior, given navigation data from map service provider.
Contact: Ing. Giuseppe Mercurio - mercurio_g@fev.com
Tutor: Prof.ssa Barbara Masini
Ing. Alessandro Bazzi
Requirements:
The European Commission is going to publish the new Euro 7 standard shortly, with the target of reducing the impact on pollutant emissions due to transportation systems. The incoming regulation will point out the role of On-Board Monitoring (OBM) as a key enabler to ensure limited emissions over the whole vehicle lifetime, necessarily taking into account the natural aging of involved systems and possible electronic/mechanical faults and malfunctions. In this scenario, this research activity aims to study the potential of data-driven approaches in detecting emission-relevant engine and after-treatment faults. For this purpose, machine learning models can help to detect and identify different faults of components and sensors , by taking as input measurements and Engine Control Unit (ECU) signals already present on-board. The models shall be firstly optimized, trained, and tested on simulation data generated by a validated 0-D Simulink model and by the engines at the test cells. In view of vehicle on-board application, the developed model shall be implemented on a real-time hardware to evaluate its real-time capability. The activity research will be carried out in collaboration with international partners and it will require a period abroad.
Period: 01/11/2024 – 31/10/2027 (3 years)
Contact: Ing. Stefano Longhi - longhi@fev.com
Tutor: Prof. Nicolò Cavina
Ing. Fabio Mallamo
Requirements:
Application deadline: 07/08/ 2024 (open)
Useful links: Call for applications
Full Professor at the University of Bologna, Co-founder of the Green Mobility Research Lab
Functional Safety & Cybersecurity Manager at FEV Italy
+39 342 5472575
Senior assistant professor at the University of Bologna
+39 051 20 9 3880