Research on Driving Workload Characteristics of Drivers Under Various Dangerous Scenarios Based on EEG

In order to study the driving workload characteristics of drivers under various dangerous scenarios, the electroencephalography (EEG) data of drivers under different dangerous scenarios are analyzed based on real driving experiments. The ErgoLAB human-machine environment synchronization platform was used to collect and extract the driver’s EEG signal. Meanwhile the appropriate EEG index was selected. The statistical analysis method was used to study the EEG data of the drivers, and the EEG variation rates of the driver under various dangerous scenarios was obtained to reflect driving workload. Two conclusions are reached from the experiment designed to figure out the relationship between driving workload and dangerous scenarios. Two conclusions were reached from analyzing indicators. First, various dangerous scenarios have significant impacts on driving workload. When there exists one dangerous scenario with fewer non-motor vehicle protection measures easily causing serious traffic accidents such as pedestrians or bicycles, there will be a higher driving workload. Besides, the impact on the EEG variation rates of the driver in various dangerous scenarios caused by the external factors such as turning and encountering pedestrian (bicycle) or a relatively sound protection measures taken like vehicle interactions is small, resulting in lower driving workload. Second, driving workload is not only affected by dangerous scenarios but also by driving experience and the age of driver.