This report documents the results of a study to characterize episodes of driver drowsiness and to assess the impact of drowsiness on driving performance. This data mining effort performed additional analyses on the data collected in an earlier FMCSA study of the effects of fatigue on drivers in local/short haul operations. The primary objectives of the study were to investigate drowsiness as a naturally occurring phenomenon by identifying and characterizing episodes of drowsiness that occurred during every period of driving and to determine the operational or driving-environment factors associated with drowsy driving. A total of 2,745 drowsy events were identified in approximately 900 total hours of naturalistic driving video data. Higher levels of drowsiness were found to be associated with younger and less experienced drivers. In addition, a strong and consistent relationship was found between drowsiness and time of day. Drowsy driving events were twice as likely to occur between 6 a m. and 9 a m., as compared to baseline, or non-drowsy driving, and approximately 30 percent of all observed instances of drowsiness occurred within the first hour of the work shift. Some interesting insights about the relationship between driver fatigue or drowsiness and driver distraction and inattention are provided. This study presents an analytical framework for quantitatively assessing driver fatigue and drowsiness as a function of driver characteristics and the driving environment.