Yanghua Xiao

Papers

Total Citations

H-Index

About

Yanghua Xiao is a leading researcher at the intersection of artificial intelligence, robotics, and knowledge engineering, with a primary focus on embodied AI and multimodal knowledge representation. His most impactful work centers on constructing scene-driven multimodal knowledge graphs that enable intelligent agents—particularly robots—to understand and interact with complex real-world environments. His 2024 paper on this topic has already garnered 38 citations, reflecting the field’s urgent need for structured, context-aware AI systems. Xiao’s contributions are notable for bridging natural language processing and robotics: his 2022 work introduced a human-in-the-loop robotic grasping framework that leverages BERT-based scene representations, allowing users to guide robot actions through intuitive language commands. This approach addresses a critical challenge in human-robot collaboration—making robotic systems more responsive and adaptable in cluttered, dynamic settings. By integrating scene knowledge, language understanding, and real-time decision-making, Xiao is advancing the frontier of embodied intelligence, where machines not only perceive but also reason and act in service of human needs.