Papers
8
Total Citations
284
H-Index
7
About
Minghao Han is a robotics and control systems researcher whose work sits at the intersection of reinforcement learning, stability theory, and nonlinear control. His most influential contribution, "Actor-Critic Reinforcement Learning for Control With Stability Guarantee" (2020), has garnered over 145 citations and addresses one of the central challenges in applying model-free RL to real-world robotic systems: ensuring provable stability without relying on explicit mathematical models. This foundational work established Han as a leading voice in safety-aware learning-based control. Building on this, his 2021 paper on constrained dynamic systems introduced uniformly ultimate boundedness guarantees into the RL framework, further bridging the gap between theoretical rigor and practical deployment. His research also extends to robust control under uncertainty, demonstrated through validation on soft robots using a deep stochastic Koopman operator approach, and to aerial robotics, where he explored omnidirectional micro aerial vehicles equipped with compliant soft robotic arms. Han's broader contributions span H∞ robust RL, switched linear systems, and sim-to-real transfer challenges. With cumulative citations exceeding 280, his work provides essential tools for researchers seeking reliable, stable, and deployable learning-based controllers in complex robotic environments.
Research Focus
Key Achievements
Top Papers
- 1Actor-Critic Reinforcement Learning for Control With Stability Guarantee145 citations · 2020
- 2
- 3
- 4
- 5
- 6Actor-Critic Reinforcement Learning for Control with Stability Guarantee9 citations · 2020
- 7
- 8