A Markov semi-supervised clustering approach and its application in topological map extraction

Ming Liu (1) , Francis Colas (1) , François Pomerleau (1) , Roland Siegwart (1)

1 ASL - Autonomous Systems Lab

In this paper, we present a novel semi-supervised clustering approach based on Markov process. It deals with data which include abundant local constraints. We apply the designed model to a topological region extraction problem, where topological segmentation is constructed based on sparse human inputs (potentially provided by human experts). The model considers human indications as seeds for topological regions, i.e. the partially labeled data. It results in a regional topological segmentation of connected free space.

Domaines: Robotique [cs.RO]

Ming Liu, Francis Colas, François Pomerleau, Roland Siegwart. A Markov semi-supervised clustering approach and its application in topological map extraction. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2012, Vilamoura, Portugal. ⟨10.1109/IROS.2012.6385683⟩. ⟨hal-01142738⟩