obtaining a photographed image by photographing an object other than the cleaning robot and in proximity to the cleaning robot;

obtaining recognition information of the object included in the photographed image, by identifying a bounding box for the object and applying the photographed image to a trained artificial intelligence model;

setting a priority for at least one sensor of a plurality of sensors of the cleaning robot based on at least one characteristic of the object in the recognition information of the object;

selecting at least one sensor from the plurality of sensors of the cleaning robot based on the priority for the at least one sensor;

obtaining additional information of the object based on at least one detection result obtained by the at least one selected sensor, wherein the obtaining the additional information further comprises reducing a threshold value of the at least one sensor for an area in which an identification result of the bounding box and the at least one detection result do not match; and

performing a task of the cleaning robot based on the additional information of the object.