Aifeng Wu
Papers
1
Total Citations
28
H-Index
1
About
Aifeng Wu has made foundational contributions to the theory and application of robust decision-making under uncertainty, with a particular focus on Markov decision processes (MDPs) and their role in cooperative multi-agent systems. Wu’s most cited work, “Robust Adaptive Markov Decision Processes: Planning with Model Uncertainty” (2012, 28 citations), addresses a critical challenge in autonomous systems: how to plan optimal behaviors when the underlying model of the environment is imperfect or unknown. By developing a framework that integrates robustness and adaptability, Wu provided a rigorous method for managing model uncertainty in real-time planning—an essential capability for teams of unmanned aerial vehicles (UAVs) and other cooperative robots operating in dynamic, unpredictable settings. This work has influenced subsequent research in safe reinforcement learning and risk-aware autonomy. Wu’s research bridges theoretical control and practical robotics, offering principled tools for ensuring reliability in high-stakes autonomous operations. With a career dedicated to advancing the mathematical foundations of adaptive and robust planning, Wu continues to shape how autonomous systems make complex decisions in the presence of uncertainty.
Research Focus
Key Achievements
Top Papers
- 1Robust Adaptive Markov Decision Processes: Planning with Model Uncertainty28 citations · 2012