Explanation of the Sense of Visual Perception in Cornering Based on Gaze Position and Optical Flows

In the recently developed self-driving technologies, users often experience strangeness when performing cornering control such as in lane-keeping assist. To realize human-centered cornering control, we had proposed a human perception model that considers optical flow and gaze position for cornering. In this paper, we propose a divergence point detection method for identifying the target position on the spherical image corresponding to the gaze position. We first discuss the relationship between optical flow and gaze movement in cornering, and we identify optical flows radiating outward from the gaze position. Next, we explain a divergence point detection method that uses optical flow vectors based on particle swarm optimization. For verifying the proposed method, we perform an experiment using an actual vehicle; the results show that the divergence detection method can detect a divergence point.