CRIS Current Research Information System
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishIn the context of behavioral change for a more sustainability mobility, we designed and implemented an in-vehicle human machine interface for electric vehicles, on the basis of an approach we propose that exploits gamification and machine learning techniques. Our main goal is to equip the driver with instant and accurate ecodriving strategies, obtaining an optimization of the energy consumption. More specifically, we have developed a prototype that collects data related to the driver's braking style and makes use of a machine learning model to forward-predict the resulting energy gain. It then accordingly fosters custom ecodriving behaviour by means of gamified interactions provided on an infotainment dashboard on the car. We have conducted some tests and this paper presents the preliminary and promising results we obtained.
| Titolo: | In-vehicle human machine interface: An approach to enhance eco-driving behaviors |
| Autore/i: | DI LENA, PIETRO; MIRRI, SILVIA; PRANDI, CATIA; SALOMONI, PAOLA; DELNEVO, GIOVANNI |
| Autore/i Unibo: | |
| Anno: | 2017 |
| Titolo del libro: | SmartObject 2017 - Proceedings of the 2017 ACM Workshop on Interacting with Smart Objects, co-located with IUI 2017 |
| Pagina iniziale: | 7 |
| Pagina finale: | 12 |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1145/3038450.3038455 |
| Abstract: | In the context of behavioral change for a more sustainability mobility, we designed and implemented an in-vehicle human machine interface for electric vehicles, on the basis of an approach we propose that exploits gamification and machine learning techniques. Our main goal is to equip the driver with instant and accurate ecodriving strategies, obtaining an optimization of the energy consumption. More specifically, we have developed a prototype that collects data related to the driver's braking style and makes use of a machine learning model to forward-predict the resulting energy gain. It then accordingly fosters custom ecodriving behaviour by means of gamified interactions provided on an infotainment dashboard on the car. We have conducted some tests and this paper presents the preliminary and promising results we obtained. |
| Data stato definitivo: | 23-apr-2017 |
| Appare nelle tipologie: | 4.01 Contributo in Atti di convegno |
File in questo prodotto:
Copyright © 2021