[2L2-OS-6a] [Organized Session] OS-6

[2L2-OS-6a-02] Spatial Concept Formation-based Semantic Mapping

〇Yuki Katsumata¹, Akira Taniguchi¹, Yoshinobu Hagiwara¹, Tadahiro Taniguchi¹ (1. Ritsumeikan University)

Keywords:symbol emergence in robotics, Semantic Mapping

This paper propose a new statistical semantic mapping method called SpCoMapping, which integrates probabilistic spatial concept acquisition and simultaneous localization and mapping via Markov random field to yield semantic information. Using a simulation environment, we compared in an experiment SpCoMapping with other previously proposed methods. We show that our method can generate better semantic maps than CNN-based semantic mapping and spatial concept formation.