Supervised Learning of Topological Maps using Semantic Information Extracted from Range Data

This paper presents an approach to create topological maps from geometric maps obtained with a mobile robot in an indoor-environment using range data. Our approach utilizes AdaBoost, a supervised learning algorithm, to classify each point of the geometric map into semantic classes. We then apply a segmentation procedure based on probabilistic relaxation labeling on the resulting classifications to eliminate errors. The topological graph is then extracted from the individual different regions and their connections. In this way, we obtain a topological map in the form of a graph, in which each node indicates a region in the environment with its corresponding semantic class (e.g., corridor, or room) and the edges indicate the connections between them. Experimental results obtained with data from different real-world environments demonstrate the effectiveness of our approach