Driving Pattern Fusion Using Dempster-Shafer Theory for Fuzzy Driving Risk Level Assessment

This paper addresses identification of risk level of the driver from the statistical analysis of sharp maneuvering tasks ensuing with the human being who is controlling the technical system. In particular, risk level is predicted by processing offline time stamped and geographically referenced driving maneuver information occured due to exceeding a given threshold acceleration in both longitudinal and lateral direction and a speed limit given as the static attribute of the road map data. A data set in terms of vehicle numbers and time period is analyzed and driving activites are fused using Dempster-Shafer theory to assess risk level related to vehicle driving performance. The level in accident making prediction accuracy is reached at 82%.