Collision risk assessment for possible collision vehicle in occluded area based on precise map

Abstract

Due to blockage by large obstacles, perception of detection sensors such as lidar, radar, and stereo vision can have visibility restrictions. The assessment of collision risk against moving vehicles in the occluded area is difficult because vehicle motion information for perception is not available. In order to overcome this difficulty, this paper presents a probabilistic approach of collision risk assessment for the potential collision of vehicles in the occluded area. The probabilistic assessment consists of three steps: a field of view (FoV) modeling of perception, a motion prediction of potential collision, and a probabilistic collision risk assessment. The first step is a FoV modeling of perception to classify the occluded region of perception visibility. The second step is motion predictions of the potential collision vehicles by applying the modeled FoV to the roadway geometry in the precise map. The final step is a probabilistic assessment of the collision risk for the occluded vehicles based on the motion predictions and probabilistic modeling of vehicle speed on the road. The proposed collision risk assessment was evaluated using various occlusion scenarios in real traffic situations, such as an alleyway.