A generalizable knowledge framework for semantic indoor mapping based on Markov logic networks and data driven MCMC

• This work proposes a generalizable knowledge framework for data abstraction.
• This work combines knowledge reasoning in Markov logic networks (MLNs) and data driven MCMC sampling.
• This work shows in detail how to adapt the proposed framework to do semantic robot mapping.
• MLNs are used to formulate task-specific context knowledge as descriptive rules.
• Experiments on real world data and simulated data show the usefulness of this framework.

In this paper, we propose a generalizable knowledge framework for data abstraction, i.e., finding a compact abstract model for input data using predefined abstract terms. Based on these abstract terms, intelligent autonomous systems, such as a robot, should be able to make inferences according to a specific knowledge base, so that they can better handle the complexity and uncertainty of the real world. We propose to realize this framework by combining Markov logic networks (MLNs) and data driven MCMC sampling, because the former are a powerful tool for modeling uncertain knowledge and the latter provides an efficient way to draw samples from unknown complex distributions. Furthermore, we show in detail how to adapt this framework to a certain task, in particular, semantic robot mapping. Based on MLNs, we formulate task-specific context knowledge as descriptive soft rules. Experiments on real world data and simulated data confirm the usefulness of our framework.