Shusen Lin

Papers

Total Citations

H-Index

About

Shusen Lin is advancing the frontier of autonomous robotics by bridging natural language understanding with hierarchical metric-semantic mapping. His research focuses on task planning, scene graph optimization, and the integration of large language models (LLMs) into robotic decision-making. Lin’s most influential work, "Optimal Scene Graph Planning with Large Language Model Guidance" (2024), has already garnered 17 citations, demonstrating its immediate impact. In this study, he developed an efficient planning algorithm that leverages LLMs to interpret natural language tasks and optimize hierarchical metric-semantic models—enabling robots to reason about both spatial geometry and semantic concepts. A precursor to this work (2023) laid the foundational framework for grounding natural language commands in topological and semantic maps. Lin’s contributions are particularly notable for their practical implications in autonomous navigation and human-robot interaction, where robots must seamlessly translate high-level instructions into actionable, optimal paths. By fusing LLM guidance with scene graph planning, Shusen Lin is shaping a new paradigm for intelligent, context-aware robotic systems that can understand and execute complex tasks in dynamic environments.