| Summary: |
Objectives/Activities: The impairing effect from inattention is a major contributor to road crashes. Current estimates suggest that drowsiness effect accounts for 20% of all fatal and severe crashes. Based on epidemiological research, the European Commission stated that about 5 to 25% of car accidents have been attributed to driver distraction but when focusing truck drivers, a much higher estimate of 70% has been found. However, because no objective device, such as breath alcohol content level as with drink driving, is used the exact incident levels are suggested to be greater than current estimates. On the other hand, the observed differences in estimates between studies may be connected with differences in operational definitions, in research methods and in driver populations. In this context, the AWAREE project aims to explore new insights and to gain new knowledge through the factors that lead to the driver distraction and drowsiness phenomenon. In this sense, driver's patterns are studied to really understand the factors that lead to the distraction and drowsiness phenomenon. The project included the following tasks: T1. State-of-the-art modelling/inference of driver inattention and driving patterns; T2. Scenarios development, driving simulator experiments and data collection: driving performance and driver physiological signals; T3. Analysis of experiment results: mapping risky drivers' and journeys' characteristics; T4. Dissemination of project outcomes.
Results/Impact: Under the driving simulator experiments, distinct data were collected throughout questionnaires, driving performance and from monitoring equipment that identify drowsiness and distraction. Several studies were developed using statistical analyses, allowing to better understand the driver characteristics that are related to drowsiness and distraction. This knowledge contributes to the development of novel algorithms capable of interpreting the data and information avail  |
Summary
Objectives/Activities: The impairing effect from inattention is a major contributor to road crashes. Current estimates suggest that drowsiness effect accounts for 20% of all fatal and severe crashes. Based on epidemiological research, the European Commission stated that about 5 to 25% of car accidents have been attributed to driver distraction but when focusing truck drivers, a much higher estimate of 70% has been found. However, because no objective device, such as breath alcohol content level as with drink driving, is used the exact incident levels are suggested to be greater than current estimates. On the other hand, the observed differences in estimates between studies may be connected with differences in operational definitions, in research methods and in driver populations. In this context, the AWAREE project aims to explore new insights and to gain new knowledge through the factors that lead to the driver distraction and drowsiness phenomenon. In this sense, driver's patterns are studied to really understand the factors that lead to the distraction and drowsiness phenomenon. The project included the following tasks: T1. State-of-the-art modelling/inference of driver inattention and driving patterns; T2. Scenarios development, driving simulator experiments and data collection: driving performance and driver physiological signals; T3. Analysis of experiment results: mapping risky drivers' and journeys' characteristics; T4. Dissemination of project outcomes.
Results/Impact: Under the driving simulator experiments, distinct data were collected throughout questionnaires, driving performance and from monitoring equipment that identify drowsiness and distraction. Several studies were developed using statistical analyses, allowing to better understand the driver characteristics that are related to drowsiness and distraction. This knowledge contributes to the development of novel algorithms capable of interpreting the data and information available about the driver and the journey in a dynamic way, supporting the development of novel detection and warning systems.
|