Extraction of candidate points for a destination estimation method based on behavior dynamics

For effective trajectory formation of robots, we propose a method to extract candidate points of the destination of walking people from their walking trajectories. The method is useful for setting the candidate points of the destination automatically which is necessary to estimate the pedestrians´ destination. We assume that potential fields influence pedestrians. After estimating parameters of the potential fields and evaluating their minimum points, we extracted candidate points of the respective destinations of pedestrians. To estimate the parameters of the potential fields accurately, we classified data of pedestrian´ walking trajectories into groups. Thereby, the trajectories leading to the same destination are gathered in one group. We designed an evaluation function that indicates the conformity between the trajectory and the destination to classify the data correctly. Results obtained from experiments in an actual environment to verify the availability of the proposed method show that appropriate candidate points of the destination are extracted.