Letian Chen

About

Letian Chen is a robotics and artificial intelligence researcher whose work sits at the intersection of human-robot interaction, learning from demonstration, and interpretable machine learning. His research is driven by a central mission: making robots more accessible and trustworthy for everyday users who lack specialized robotics expertise. Chen's most recognized contribution, "Human-Robot Teaming: Grand Challenges" (2023, 37 citations), maps the frontier of collaborative human-robot systems, helping shape the community's research agenda. His highly cited work on learning from suboptimal demonstrations (2020, 31 citations) represents a significant methodological advance — addressing a critical blind spot in inverse reinforcement learning by enabling robots to learn effectively even when human teachers provide imperfect examples, dramatically broadening who can usefully train a robot. Building on this foundation, Chen developed fast lifelong adaptive inverse reinforcement learning frameworks capable of accommodating diverse demonstration styles at scale, pushing toward real-world deployment. His work on interpretable reinforcement learning further reflects a commitment to safety and transparency in autonomous systems operating in high-stakes environments. Across his portfolio, Chen consistently bridges technical rigor with human-centered design, positioning him as a thoughtful contributor to the democratization of robotics and the responsible deployment of learning-based autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Human-Robot Teaming: Grand Challenges

   37 citations · 2023
2. 2
   Learning from Suboptimal Demonstration via Self-Supervised Reward Regression

   31 citations · 2020
3. 3
   Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations

   3 citations · 2022
4. 4
   Interpretable Reinforcement Learning for Robotics and Continuous Control

   2 citations · 2023

Key Collaborators

Contact & Links