Publicação
A driver monitoring system towards the automotive cockpit of the future
| Resumo: | Despite the massive technological evolution experienced by the automotive industry over the past decades, driver safety is still an area of big concern. The lack of attention during the driving task is, till nowadays, considered as a major risk factor for fatal road accidents around the world. Actually, the motor vehicle traffic crashes are among the leading causes of death in some countries, like United States of America. Most of the registered accidents arose due to driver fatigue or distraction. In the near future, the paradigm shift from manual to autonomous driving will impose new serious challenges, increasing substantially the range of concerns in the automotive industry. Notwithstanding the significant contribution of this technology to long-term road safety, the fact is that all vehicles available at the moment only feature semi-autonomous technology, demanding frequent driver action. In reality, the current technology has a limited operational design domain, requiring the driver to retake control over the vehicle in a short amount of time, as soon as the automation limits are reached. However, the monotony of such scenario may lead the driver to engage in non-driving related activities or even induce fatigue, reducing his/her driving awareness and degrading the quality of the fallback operation. In this context, this MSc thesis proposes a system to monitor the driver in terms of fatigue, distraction and activity. Regarding the fatigue assessment, it must detect microsleeps and situations of drowsiness. In terms of distraction, the following types must be supervised: (i) visual, (ii) manual and (iii) cognitive. The activity monitoring module must recognize four out of ten deadliest driving non-related activities: (i) using cell phone, (ii) looking to an external event, (iii) interacting with the infotainment and (iv) interacting with passengers. This system will be part of an automotive HMI, developed under the Bosch InnovCar project, which aims to develop new solutions for the cockpit of the future. |
|---|---|
| Autores principais: | Costa, Miguel Ângelo Peixoto da |
| Assunto: | Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
| Ano: | 2018 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | Despite the massive technological evolution experienced by the automotive industry over the past decades, driver safety is still an area of big concern. The lack of attention during the driving task is, till nowadays, considered as a major risk factor for fatal road accidents around the world. Actually, the motor vehicle traffic crashes are among the leading causes of death in some countries, like United States of America. Most of the registered accidents arose due to driver fatigue or distraction. In the near future, the paradigm shift from manual to autonomous driving will impose new serious challenges, increasing substantially the range of concerns in the automotive industry. Notwithstanding the significant contribution of this technology to long-term road safety, the fact is that all vehicles available at the moment only feature semi-autonomous technology, demanding frequent driver action. In reality, the current technology has a limited operational design domain, requiring the driver to retake control over the vehicle in a short amount of time, as soon as the automation limits are reached. However, the monotony of such scenario may lead the driver to engage in non-driving related activities or even induce fatigue, reducing his/her driving awareness and degrading the quality of the fallback operation. In this context, this MSc thesis proposes a system to monitor the driver in terms of fatigue, distraction and activity. Regarding the fatigue assessment, it must detect microsleeps and situations of drowsiness. In terms of distraction, the following types must be supervised: (i) visual, (ii) manual and (iii) cognitive. The activity monitoring module must recognize four out of ten deadliest driving non-related activities: (i) using cell phone, (ii) looking to an external event, (iii) interacting with the infotainment and (iv) interacting with passengers. This system will be part of an automotive HMI, developed under the Bosch InnovCar project, which aims to develop new solutions for the cockpit of the future. |
|---|