Jianchao Song

Papers

Total Citations

H-Index

About

Jianchao Song is a robotics researcher specializing in mobile robot localization, with a particular focus on global localization and mapping in indoor environments. His work addresses fundamental challenges in autonomous navigation, including the "kidnapped robot problem" and robust pose estimation in dynamic settings. Song's most influential contribution is his 2019 paper on a novel global localization approach that introduces a structural unit encoding scheme (SUES) combined with multiple hypothesis tracking (MHT). This work, which has garnered 30 citations, presents an elegant solution for 2D laser-based global localization by encoding geometric relationships between structural units, enabling robots to determine their position without prior pose knowledge. His earlier research advanced Monte-Carlo Localization (MCL) by integrating motion detection and scan matching to improve robustness in dynamic environments, while also developing grid submap-based approaches using depth-first search for efficient scan-to-submap matching. Though his citation counts remain modest, Song's contributions represent meaningful steps toward more reliable and computationally efficient localization systems for indoor mobile robots, with potential applications in service robotics and warehouse automation.