Xiang Wu

Papers

Total Citations

H-Index

About

Xiang Wu is a rising researcher at the intersection of robotics, artificial intelligence, and natural language processing, with a primary focus on instruction-driven robotic task planning. His most significant contribution is the development of **GRID (Scene-Graph-based Instruction-driven Robotic Task Planning)**, a novel framework that leverages scene graphs to bridge the gap between high-level human commands and low-level robot actions. Unlike conventional methods that rely on raw images, GRID uses structured scene graphs to help Large Language Models (LLMs) more effectively understand and ground environmental information, enabling robots to perform complex, multi-step tasks with greater accuracy and efficiency. This work has garnered 19 citations since its 2024 publication, reflecting its immediate impact on the field. Wu’s research addresses a critical bottleneck in embodied AI: how to make robots truly understand and execute natural language instructions in dynamic, real-world settings. By moving beyond pixel-level reasoning to structured semantic representations, he is helping to build more intelligent, adaptable robotic systems. His work is particularly relevant for students and researchers interested in LLM-based robotics, human-robot interaction, and scene understanding.