Papers
29
Total Citations
926
H-Index
14
About
Yongduan Song is a prominent researcher specializing in adaptive control systems, multi-agent coordination, fault-tolerant control, and intelligent robotics. His work sits at the intersection of control theory and artificial intelligence, with particular emphasis on developing robust, neuroadaptive frameworks for complex, uncertain dynamical systems. Song's most influential contributions address critical challenges in robotic and networked systems control. His 2018 paper on neuroadaptive control under time-varying asymmetric motion constraints (132 citations) pioneered a feasibility-condition-free approach, eliminating restrictive assumptions that had long limited practical implementation. His research on distributed fault-tolerant control of Euler–Lagrange systems (99 citations) and cooperative tracking using self-structuring neural networks (93 citations) established foundational methodologies for resilient multi-agent coordination under real-world uncertainties, including actuator failures and communication faults. Song has consistently advanced the field through terminal sliding-mode consensus control, backstepping neural adaptive design, and observer-based cooperative control for humanoid robots, demonstrating both theoretical depth and practical applicability. His more recent exploration of reinforcement learning for long-horizon manipulation tasks reflects a forward-looking integration of modern machine learning into robotics. With multiple papers exceeding 70 citations and a body of work spanning nearly a decade of high-impact publications, Song's research has meaningfully shaped modern intelligent control and autonomous systems engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10