Xuyun Yang
Papers
6
Total Citations
131
H-Index
5
About
Xuyun Yang is a leading researcher at the intersection of robotics, optimization, and artificial intelligence, with a primary focus on multi-robot navigation, imitation learning, and neurodynamic optimization. Yang’s most impactful work introduces a Taylor–Zhang discretization formula for zeroing neurodynamics applied to future equality-constrained quadratic programming (67 citations), providing a rigorous framework for real-time optimization in dynamic systems. In multi-robot systems, Yang pioneered a decentralized deep reinforcement learning method that enables robot teams to navigate unknown complex environments while maintaining connectivity and avoiding collisions (42 citations), a critical contribution to swarm robotics. Yang further advanced robot learning with a dual-domain meta-learning approach that allows robots to generalize skills from demonstrations across different domains, and a vision-based one-shot imitation learning method supplemented with target recognition via meta-learning. Additional work includes connectivity-guaranteed multi-robot navigation and 6D hybrid pose estimation for robotic grasping in cluttered industrial scenes. With over 130 total citations and a growing portfolio of high-impact publications, Yang’s research bridges theoretical optimization and practical robot autonomy, offering scalable solutions for real-world applications in manufacturing, search-and-rescue, and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6