Applying Rule-Based Context Knowledge to Build Abstract Semantic Maps of Indoor Environments
This work addresses the challenge of creating detailed semantic maps for robotics in indoor settings, representing an incremental improvement by integrating existing methods with context knowledge.
The paper tackles the problem of building abstract semantic maps for indoor environments by combining data-driven MCMC sampling with rule-based context knowledge, resulting in a parametric model that accurately represents geometry and provides abstract information beneficial for high-level robotic applications, with experiments on real-world data showing promising results.
In this paper, we propose a generalizable method that systematically combines data driven MCMC samplingand inference using rule-based context knowledge for data abstraction. In particular, we demonstrate the usefulness of our method in the scenario of building abstract semantic maps for indoor environments. The product of our system is a parametric abstract model of the perceived environment that not only accurately represents the geometry of the environment but also provides valuable abstract information which benefits high-level robotic applications. Based on predefined abstract terms,such as type and relation, we define task-specific context knowledge as descriptive rules in Markov Logic Networks. The corresponding inference results are used to construct a priordistribution that aims to add reasonable constraints to the solution space of semantic maps. In addition, by applying a semantically annotated sensor model, we explicitly use context information to interpret the sensor data. Experiments on real world data show promising results and thus confirm the usefulness of our system.