Chong Ma
Papers
2
Total Citations
36
H-Index
2
About
Chong Ma is at the forefront of two transformative fields in robotics: integrating large language models (LLMs) into autonomous systems and advancing robust perception through multimodal sensor fusion. His highly cited work, "Large Language Models for Robotics" (2024, 20 citations), provides a seminal roadmap for leveraging LLMs' reasoning and language comprehension to generate precise, efficient action plans for robot task planning—a critical step toward more intuitive human-robot collaboration. Complementing this, his "Localization and Mapping Method Based on Multimodal Information Fusion and Deep Learning for Dynamic Object Removal" (2024, 16 citations) tackles a core challenge in SLAM: pose estimation drift in weak-texture or fast-moving environments. By fusing visual and inertial measurement unit (IMU) data with deep learning to remove dynamic objects, Ma’s method significantly enhances mapping robustness and localization accuracy. Together, these contributions demonstrate his dual impact on both high-level cognitive planning and low-level perceptual reliability in robotics. His work is already shaping how researchers approach autonomous navigation and intelligent interaction, marking him as a rising leader in the integration of language models and sensor-driven robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2