Papers
7
Total Citations
511
H-Index
7
About
Huaguang Zhang is a leading figure in intelligent control and reinforcement learning (RL), whose work bridges the gap between theoretical optimal control and real-world industrial resilience. His primary research focuses on adaptive dynamic programming (ADP) for complex, uncertain systems, including Markov jump systems and multi-agent networks. A cornerstone of his contribution is pioneering the use of RL to solve optimal control problems for systems with *unknown* dynamics, as evidenced by his highly cited 2014 paper (152 citations) on discrete-time nonlinear Markov jump systems. He has further extended this framework to address critical practical challenges, such as fault-tolerant tracking control for actuator faults (128 citations) and resilient control against cyber-attacks (66 citations). Beyond control theory, Zhang demonstrates remarkable versatility by applying advanced AI to industrial inspection, developing a cascade attention network for defect detection in pipeline magnetic flux leakage signals (65 citations). His work on fully distributed formation control using novel event-triggered strategies (61 citations) showcases his ability to solve complex coordination problems in multi-agent systems. With a career spanning foundational theory, fault tolerance, and practical deployment, Zhang’s research provides essential tools for building safer, smarter, and more autonomous engineering systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7