Taijing Chen

Papers

Total Citations

H-Index

About

Taijing Chen is pioneering robust, long-term localization and mapping for robots operating in dynamic, real-world environments. Her research lies at the critical intersection of visual SLAM (Simultaneous Localization and Mapping) and probabilistic object modeling, addressing the fundamental challenge of robots maintaining consistent spatial awareness over days, months, or years despite drastic changes in lighting, geometry, and appearance. Chen’s most impactful work, "ObVi-SLAM: Long-Term Object-Visual SLAM" (2024, 28 citations), introduces a novel framework that replaces fragile low-level feature descriptors with persistent object-level landmarks, enabling scalable and resilient localization while dramatically reducing map size. This builds directly on her earlier foundational contribution, "Probabilistic Object Maps for Long-Term Robot Localization" (2022, 6 citations), which formalized how robots can identify and prioritize stable, long-term features in highly changeable settings like warehouses and parking lots. By shifting the paradigm from point features to probabilistic object representations, Chen’s work provides a practical pathway for robots to operate autonomously over extended periods without human intervention. Her research is essential reading for anyone working on long-duration robot deployment, infrastructure inspection, or autonomous navigation in non-static environments.