Teng‐Yok Lee
Papers
2
Total Citations
25
H-Index
2
About
Teng-Yok Lee is a researcher at the forefront of visual analytics and robotic manipulation, bridging the gap between complex AI systems and practical, real-world control. His work primarily focuses on two challenging domains: making deep reinforcement learning (RL) interpretable for physical tasks, and enabling robots to perform semantically-aware object manipulation. In his highly cited 2020 work, "DynamicsExplorer," Lee tackled the "black box" problem of deep RL, creating a visual analytics system that allows engineers to understand and debug the control policies of robots trained for dynamic tasks. This contribution is critical for deploying RL in safety-critical environments, earning 22 citations for its novel approach to human-in-the-loop analysis. Lee also advanced the field of robotic placement with his 2019 study on "Pose-Aware Placement," which integrated semantic labels—like brand names—to guide a dual-arm robot in placing objects with proper orientation and context. This work moves beyond simple pick-and-place toward more intelligent, context-driven manipulation. Through these efforts, Lee is helping to build the foundational tools and interfaces needed for the next generation of autonomous, explainable robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2