Ziyuan Liu

Papers

Total Citations

H-Index

About

Ziyuan Liu is a researcher specializing in semantic mapping, knowledge representation, and intelligent reasoning for indoor environments. His work sits at the intersection of robotics, artificial intelligence, and spatial understanding, with a particular focus on enabling machines to interpret and navigate complex indoor spaces with human-like contextual awareness. Liu's most notable contribution is his development of a generalizable knowledge framework for semantic indoor mapping, which combines Markov Logic Networks with data-driven Markov Chain Monte Carlo (MCMC) sampling to build abstract, meaningful representations of indoor environments. This work, which has garnered 20 citations, demonstrates how probabilistic logic and rule-based context knowledge can be systematically integrated to move beyond raw sensor data toward higher-level semantic understanding. Complementing this, his research on rule-based context knowledge for abstract semantic map construction further refines this methodology, showcasing its practical applicability in real-world indoor navigation scenarios. Together, these contributions address a fundamental challenge in autonomous systems: bridging the gap between low-level perceptual data and the rich, abstract understanding that intelligent navigation demands. Liu's work offers a principled, reusable framework with broad implications for robotics and smart environment research.