TRA Young Research Winners - Road Award Winners
Road Award Winners
For the Road Mode Young Competition, we introduce all winners:
|
Milan Tešić, from University of Belgrade (Serbia), he proposed the project “Star rating Road Safety Performances and Identifying the most significant Road Safety Indicators of a Territory”. |
| Pier Giuseppe Anselma, Claudio Maino, Alessia Musa from Politecnico di Torino - IT presented the proposal, “THEO: a tailored hybrid emission optimizer for the drivers of tomorrow”, aims at developing an intelligent and custom-made Tailored Hybrid Emission Optimizer (THEO), i.e. an hybrid electric vehicle (HEV) controller capable of maximizing the fuel economy performance according to diverse real-world driving conditions and to the specific driver. Trip data is initially collected for a set of personal driving missions. The operation of the powertrain is optimized off-line for each driving mission considered. An artificial intelligence (AI) agent to be embedded in THEO is later implemented through a learning process for each driver considered using the data collected from HEV off-line optimization. The custom-made controller can be loaded in the on-board control unit before the corresponding user starts driving. Numerical results show that the THEO developed can improve remarkably the performance of current heuristic HEV control strategies. |
| Ahmed Ayadi, Jakob Pfeiffer, Mohamed Ali Razouane from Technical University of Munich (Germany) presented a project named “Self-Learning Enhancement of Measurement Quality with Artificial Intelligence”, which aims at minimizing measurement variations in the power trains of Electric Vehicles (EVs). A low measurement quality can cause severe problems with EVs, such as inaccurate performance coordination and unnecessary power limitations during driving or charging. Their goal is to minimize these deviations and correct measurement inaccuracies. They propose a fleet-based framework to classify hardware faults and measurement faults; the detected measurement faults are then corrected with Compressed Sensing. To correct the deviations caused by time delays, they introduce a variance minimization-based time delay detection. Results show that the proposed methods can minimize the deviations from 25% to less than 5% of the maximum current. |
➡️ Register here to attend the Remote Award Ceremony: https://vtt.videosync.fi/tra-visions-2020/register
🗓️ 29th September at 9:30 AM (CEST)
