Qingshan Yin

Inspur (China), Institute of New Materials

Papers

Total Citations

H-Index

About

Qingshan Yin is a robotics researcher focused on bridging the gap between high-level semantic understanding and low-level spatial perception for intelligent robot navigation. His work centers on integrating Large Language Models (LLMs) and deep learning with augmented reality to create more holistic, task-oriented robotic systems. In his most notable contribution, Yin developed a novel system that harnesses LLMs to construct hierarchical 3D Scene Graphs (3DSGs) for indoor environments, enabling robots to achieve a richer, more contextual understanding of their surroundings beyond simple geometric mapping. This work, published in 2024, has already garnered early citations for its innovative approach to spatial intelligence. Additionally, his 2021 paper on combining augmented reality with deep learning for task-oriented robot navigation proposed a practical indoor system that integrates visual guidance with goal-driven planning. Though early in his career, Yin’s research is gaining traction for its forward-looking synthesis of natural language processing and embodied AI, positioning him as an emerging voice in the next generation of context-aware robotic systems.