Yang Xueke

National University of Defense Technology

Papers

Total Citations

H-Index

About

Yang Xueke is a researcher advancing the frontiers of multi-agent systems and human-robot interaction, with a particular focus on enabling service robots to understand and execute complex tasks through natural language. Her work bridges the gap between visual perception, semantic planning, and autonomous coordination, addressing fundamental challenges in embodied AI. Notably, her 2021 study on "Visual Semantic Planning for Service Robot via Natural Language Instructions" tackles the ALFRED benchmark—a rigorous test of interactive instruction following—where robots must perceive their environment, parse language commands, and perform sequential manipulations. This contribution, along with her 2022 paper on "Multi-agent Task Coordination Method Based on RCRS," which explores decentralized coordination frameworks, has garnered early citations from peers working in robotics and AI planning. While her citation counts are modest, reflecting the recency of her publications, Xueke’s research is positioned at the intersection of language grounding, task planning, and multi-robot collaboration—critical areas for developing intelligent, responsive service robots. Her work offers a foundation for students and researchers interested in how robots can seamlessly interpret human instructions and collaborate in dynamic, real-world settings.