Shaohang Han
Papers
1
Total Citations
12
H-Index
1
About
Shaohang Han is a rising researcher at the forefront of safe autonomous systems, specializing in the intersection of reinforcement learning, control theory, and robotics. His work directly tackles one of the most critical barriers to deploying AI-driven robots in the real world: the lack of verifiable safety guarantees. In his highly cited 2023 paper, "Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions," Han introduces a novel framework that integrates control Lyapunov and barrier functions directly into the RL training loop. This approach ensures that learned policies not only achieve high performance but also provably maintain system stability and avoid unsafe states—a breakthrough for applications in autonomous driving, drone navigation, and human-robot interaction. With 12 citations in its first year, this work is rapidly shaping the field of safe learning-based control. Han’s contributions are particularly notable for bridging the gap between rigorous control-theoretic methods and the flexibility of deep reinforcement learning, offering a practical pathway toward certifiably safe autonomy. His research is essential reading for anyone working on trustworthy AI in physical systems.
Research Focus
Key Achievements
Top Papers
- 1