Foot placement during error and pedal applications in naturalistic driving

•Foot placements were examined using video and driver data collected from naturalistic driving data.•Pedal application types were categorized into notable pedal responses and pedal errors.•Random forest tree and multinomial logistic regression were used to predict the pedal application and foot placement types.•A driver assistance system can be developed to detect an anomalous foot pedal application in the context of the drive. Data from a naturalistic driving study was used to examine foot placement during routine foot pedal movements and possible pedal misapplications. The study included four weeks of observations from 30 drivers, where pedal responses were recorded and categorized. The foot movements associated with pedal misapplications and errors were the focus of the analyses. A random forest algorithm was used to predict the pedal application types based the video observations, foot placements, drivers’ characteristics, drivers’ cognitive function levels and anthropometric measurements. A repeated multinomial logit model was then used to estimate the likelihood of the foot placement given various driver characteristics and driving scenarios. The findings showed that prior foot location, the drivers’ seat position, and the drive sequence were all associated with incorrect foot placement during an event. The study showed that there is a potential to develop a driver assistance system that can reduce the likelihood of a pedal error.