Xinghang Li

Papers

Total Citations

H-Index

About

Xinghang Li is an emerging researcher in the field of embodied artificial intelligence and human-robot interaction, with a particular focus on multi-agent task planning and natural language understanding for robotic systems. His most notable work addresses one of the fundamental challenges in human-robot collaboration: bridging the communication gap between intuitive human instructions and robotic comprehension. His 2022 paper, "Embodied Multi-Agent Task Planning from Ambiguous Instruction," tackles the critical problem of ambiguity in human-to-robot communication, where implicit contextual information embedded in natural language instructions can confuse autonomous systems. This research has garnered 24 citations, reflecting growing interest in making robotic agents more adept at interpreting real-world, imprecise human directives. Li's contributions sit at the intersection of embodied AI, multi-agent systems, and natural language processing — an increasingly vital research frontier as collaborative robots become more prevalent in everyday environments. His work lays important groundwork for developing robots that can reason more intelligently about incomplete or underspecified instructions, ultimately advancing the practical deployment of autonomous agents in complex, human-centered settings.