Autonomous driving cars hopefully could improve road safety. However, they pose new challenges, not only on a technological level but also from ethical and social points of view. In particular, social acceptance of those vehicles is a crucial point to obtain a widespread adoption of them. People nowadays are used to owning manually driven vehicles, but in the future, it will be more probable that the autonomous driving cars will not be owned by the end users, but rented like a sort of driverless taxis. Customers can feel uncomfortable while riding an autonomous driving car, while rental agencies will need to differentiate the services offered by their fleets of vehicles. If people are afraid to travel by these vehicles, even if from the technological point of view they are safer with respect to the manually driven ones, customers will not use them, making the safety improvements useless. To prevent the occupants of the vehicle from having bad feelings, the proposed strategy is to adapt the vehicle driving style based on their moods. This requires the usage of a neural network trained by means of facial expressions databases, of which there are many freely available online for research purposes. These resources are very useful, but it is difficult to combine them due to their different structures. To overcome this issue, a tool designed to uniform them, in order to use the same training scripts, and to simplify the application of commonly used postprocessing operations, has been implemented.
Passengers’ Emotions Recognition to Improve Social Acceptance of Autonomous Driving Vehicles / Sini, Jacopo; Marceddu, Antonio Costantino; Violante, Massimo; Dessì, Riccardo (SMART INNOVATION, SYSTEMS AND TECHNOLOGIES). - In: Progresses in Artificial Intelligence and Neural SystemsSTAMPA. - [s.l] : Springer, 2021. - ISBN 978-981-15-5092-8. - pp. 25-32 [10.1007/978-981-15-5093-5_3]
Passengers’ Emotions Recognition to Improve Social Acceptance of Autonomous Driving Vehicles
Sini, Jacopo;Marceddu, Antonio Costantino;Violante, Massimo;Dessì, Riccardo
2021
Abstract
Autonomous driving cars hopefully could improve road safety. However, they pose new challenges, not only on a technological level but also from ethical and social points of view. In particular, social acceptance of those vehicles is a crucial point to obtain a widespread adoption of them. People nowadays are used to owning manually driven vehicles, but in the future, it will be more probable that the autonomous driving cars will not be owned by the end users, but rented like a sort of driverless taxis. Customers can feel uncomfortable while riding an autonomous driving car, while rental agencies will need to differentiate the services offered by their fleets of vehicles. If people are afraid to travel by these vehicles, even if from the technological point of view they are safer with respect to the manually driven ones, customers will not use them, making the safety improvements useless. To prevent the occupants of the vehicle from having bad feelings, the proposed strategy is to adapt the vehicle driving style based on their moods. This requires the usage of a neural network trained by means of facial expressions databases, of which there are many freely available online for research purposes. These resources are very useful, but it is difficult to combine them due to their different structures. To overcome this issue, a tool designed to uniform them, in order to use the same training scripts, and to simplify the application of commonly used postprocessing operations, has been implemented.File | Dimensione | Formato | |
---|---|---|---|
camera-ready.pdf
Open Access dal 11/07/2022
Descrizione: Articolo principale
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
2.42 MB
Formato
Adobe PDF
|
2.42 MB | Adobe PDF | Visualizza/Apri |
capitolo_versione editoriale.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
316.98 kB
Formato
Adobe PDF
|
316.98 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2840471