Naturalistic Driving and GIS Data

UMTRI's Engineering Systems Group is the birthplace of naturalistic driving studies, including field operational tests of safety technology. Naturalistic driving is becoming a method of great interest outside the technology arena and is being put to use in the study of at-risk populations such as younger and older drivers and those drivers with specific risk factors, such as disease. Furthermore, the method is contributing to the study of driving with new powertrains such as extended-range electric vehicles.

UMTRI has developed large driver-vehicle databases since the mid-1990s. These not only answer specific questions about the systems being tested (e.g., adaptive cruise control), but also contain a rich resource of general driving data, representing how people drive in the real world. Current resources represent over 1 million vehicle miles traveled, and much of this data is highly detailed, containing hundreds of signals measured from the subject vehicle, radar measurements of nearby vehicles, and video data of both the forward scene and the driver's activities. UMTRI also has an extensive SAVME (System for the Assessment of the Vehicle Motion Environment) database of highly detailed vehicle motions, with over 35,000 vehicle trajectories analyzed and recorded based on video motion capture. The next-generation SAVME system will record even more detailed data of the same type, particularly related to vehicle kinematics at intersections.