Chuan Xu,Xuesong Wang,Xiaohong Chen
Abstract：Fatigue while driving leads to significant deterioration on driver’s lane keeping ability and increases the risk to crashes. Also, the lane keeping indicator may be good predictors to fatigue. A study using Tongji high fidelity driving simulator investigated the relationship between fatigue and lane keeping indicators. During about 1 hour monotonous highway driving for each driver, driving data of 30 participants including lateral position, speed and steering wheel movement data was collected. Meanwhile, Karolinska Sleepiness Scale (KSS) was recorded to measure driver’s fatigue scale. To estimate driver’s lane keep ability appropriately, stand deviation of lateral position(SDLP), lane crossing time-space area (LCTSA), stand deviation of steering wheel speed (SDSWS), steering wheel reversal rate (SWRR) were measured. While controlling other contribution factors including driving speed, road alignment, multilevel ordered logistic model were established using Winbugs software. The research found that experienced driver has higher threshold for KSS.SDLP, SDSWS and SWRR show significant positive relation to fatigue level. Another finding is that the differences between two adjacent KSS threshold increase with KSS value.