A Generalizable Knowledge Framework for Semantic Indoor Mapping Based on Markov Logic Networks and Data Driven MCMC

TL;DR

This paper introduces a generalizable framework combining Markov Logic Networks and data-driven MCMC sampling to enable semantic indoor mapping, improving autonomous systems' ability to handle complex, uncertain environments.

Contribution

It presents a novel integration of MLNs and MCMC for data abstraction and applies it specifically to semantic robot mapping, demonstrating its effectiveness.

Findings

Framework effectively models uncertain knowledge.

Successful application to semantic robot mapping.

Validated on real and simulated data.

Abstract

In this paper, we propose a generalizable knowledge framework for data abstraction, i.e. finding 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 inference according to 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 modelling 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.