Online Semantic Exploration of Indoor Maps
This work addresses the need for semantic understanding in indoor mapping for robotics or AI systems, but appears incremental as it builds on existing grid map techniques.
The paper tackles the problem of extracting abstracted floor plans from grid maps using Bayesian reasoning, resulting in a probabilistic generative model suitable for higher-level reasoning and communication, with effectiveness demonstrated through real-world experiments.
In this paper we propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning. The result of this procedure is a probabilistic generative model of the environment defined over abstract concepts. It is well suited for higher-level reasoning and communication purposes. We demonstrate the effectiveness of the approach through real-world experiments.