This paper presents motion prediction model of cyclist based on potential field for a hazard-anticipatory collision avoidance braking system to enhance the collision avoidance performance and secure the smoothness of driving. The target situation is chosen as the scene that a cyclist overtakes a pedestrian or another slow cyclist based on the traffic survey. The 1st order motion prediction method reaches its limit under the situation that a cyclist runs towards a pedestrian or another cyclist as the prediction is conducted based on the current position and velocity of cyclist within a finite time horizon. If the overtake action of cyclist can be predicted before the cyclist changes moving direction, the vehicle maneuver to avoid collision with cyclist can be executed in advance without activating harsh braking. The trajectories of cyclists overtakes a pedestrian and a slower cyclist is measured to find the characteristics in overtake action. Motion prediction model of cyclist based on potential field is constructed by considering the trajectory analysis. The effectiveness of the proposed prediction model in the target scenario is verified by comparing the measured trajectory with the calculated data based on 1st order prediction and the proposed method.
<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270006/05.jpg"" width=""300"" /> The focused scenario</div>This paper discusses 2-dimensional (2-D) pedestrian motion prediction and autonomous braking control for enhancing the collision avoidance performance of an active safety system. The paper targets a typical scenario involving a pedestrian walking toward a parked vehicle on a crowded urban road. The pedestrian is not expected to continue walking in a straight line. Conventional first-order motion prediction accuracy alone is not enough to predict the pedestrian motion because prediction is based on the pedestrian’s current position and velocity within a finite time. We formulated a 2-D pedestrian motion model of the parked vehicle based on learning the measured trajectory of pedestrians in the same scenario. We then designed an autonomous braking control system based on whether the vehicle will overtake a pedestrian. We evaluated the validity of the proposed autonomous braking control system in simulation experiments.
This thesis focuses on collision avoidance automatic braking control system based on pedestrian motion prediction in order to enhance the effectiveness of automatic emergency braking. In the situation that a pedestrian suddenly change his moving direction, current active safety systems cannot avoid collisions in the critical situations due to physical limits in braking capability. Therefore, in order to develop high-performance advanced driver assistance systems, it is important to predict pedestrian motion. This research focuses on the situation that there is the parked vehicle in front of pedestrian who will avoid the parked vehicle and change his moving direction to the center of road. In order to predict pedestrian motion correctly, pedestrian motion model is formulated based on experimental result by using LAIDAR. In addition, an automatic braking control method is constructed based on pedestrian motion prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.