Abstract
Drivers’ behaviors and decision making on the road directly affect the safety of themselves, other drivers, and pedestrians. However, as distinct entities, people cannot predict the motions of surrounding vehicles and they have difficulty in performing safe reactionary driving maneuvers in a short time period. To overcome the limitations of making an immediate prediction, in this work, we propose a two-stage data-driven approach: classifying driving patterns of on-road surrounding vehicles using the Gaussian mixture models (GMM); and predicting vehicles’ short-term lateral motions (i.e., left/right turn and left/right lane change) based on real-world vehicle mobility data, provided by the U.S. Department of Transportation, with different ensemble decision trees. We considered several important kinetic features and higher order kinematic variables. The research results of our proposed approach demonstrate the effectiveness of pattern classification and on-road lateral motion prediction. This methodology framework has the potential to be incorporated into current data-driven collision warning systems, to enable more practical on-road preprocessing in intelligent vehicles, and to be applied in autopilot-driving scenarios.
Highlights
According to the latest survey about causes of motor vehicle crashes in the United States [1], nearly 94 percent of crashes in 2015 were attributed to driver-related errors, including recognition, decision, performance, and non-performance errors
In addition to the basic safety concerns, the development of the advanced driver assistance systems (ADAS) in future intelligent driving systems requires this predicting scheme to resolve the uncertain behaviors of human drivers in order that they can co-exist within the foreseeable future
Since we aimed to predict the lateral motions of the vehicle ahead and assist the driver in making a correct judgment, there should be some reaction buffer time left for the driver or the autonomous driving system
Summary
According to the latest survey about causes of motor vehicle crashes in the United States [1], nearly 94 percent of crashes in 2015 were attributed to driver-related errors, including recognition, decision, performance, and non-performance errors. 33 percent of crashes caused by driver-related errors were due to the false prediction of actions by others, misjudgment of vehicle distance and speed, and other decision errors, while recognition errors caused by driver inattention and inadequate surveillance were responsible for 41 percent of these accidents alone. The false prediction of lateral motions by other vehicles is exceptionally dangerous for both the ego vehicle and the preceding ones. This maneuver is one of the riskiest movements during driving due to its changes in both the longitudinal and lateral velocity in the presence of the surrounding moving vehicles [2,3]. In addition to the basic safety concerns, the development of the advanced driver assistance systems (ADAS) in future intelligent driving systems requires this predicting scheme to resolve the uncertain behaviors of human drivers in order that they can co-exist within the foreseeable future
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
