Currently, while using cartographer to generate a map, yolact can be used for object recognition to obtain the point cloud location and class name of the object from the camera. My goal is to navigate to the front of a given object using a map with the object's location and class name My thought is that it could be done with a method like semantic map. But I am not familiar with semantic map. Could you please elaborate on this? Also, are there any other simple methods? At this stage, I just need to be able to create a position diagram that shows the location of the object and the class name. Could someone please tell me what it is?