A significant challenge in service robots is the semantic understanding of their surrounding areas. Traditional approaches addressed this problem by segmenting the floor plan into regions corresponding to full rooms that are assigned labels consistent with human perception, e.g. office or kitchen. However, different areas inside the same room can be used in different ways: Could the table and the chair in my kitchen become my office? What is the category of that area now? office or kitchen? To adapt to these circumstances we propose a new paradigm where we intentionally relax the resulting labeling of semantic classifiers by allowing confusions inside rooms. Our hypothesis is that those confusions can be beneficial to a service robot. We present a proof of concept in the task of searching for objects.
Figures & tables
Fig. 1: Upper-left: the original indoor environment. Bottom-left: the semantic division based on full rooms. Right: example of our semantic division that keeps confusions based on appearance.
Fig. 2: Rows (1) and (2) show simulated environments while rows (3) and (4) depict real ones. Columns: (a) example scene image; (b) full 2D map; (c) appearance-based confusion map; (d) object-based confusion map; (e) merged confusion map.
Fig. 3: Results considering different initial locations for the lost object according to prior probabilities. X-axis values: 1=most probable place; 2=second most probable place, 3=third most probable place. Our approach (yellow) improves the search task by keeping the covered area and the viewpoints visited at a low level both in simulated and real-world scenarios.