TRAN Duc Liem
Papers
3
Total Citations
6
H-Index
2
About
Tran Duc Liem is a researcher advancing the frontiers of human-robot collaboration, with a focus on making physical interactions between humans and robots safer, more intuitive, and more efficient. His core research areas include variable impedance and admittance control, iterative learning, and Bayesian optimization for robotic systems. Liem’s major contributions lie in developing adaptive control frameworks that allow robots to dynamically adjust their stiffness and damping in real-time during collaborative tasks. Notably, he pioneered a method to learn damping field parameters using Bayesian optimization—borrowing concepts from potential field path planning—and introduced simplex gradient-based iterative learning to optimize impedance parameters modeled as Gaussian functions. His work on variable admittance control, enhanced by adaptive gradient methods, further improves the fluidity of human-robot cooperative manipulation. Though his most-cited papers (2022–2023) each hold 2 citations, they represent foundational steps in a rapidly growing field, demonstrating novel integrations of learning-based optimization with classical control theory. Liem’s research is particularly impactful for applications in manufacturing and assistive robotics, where reducing physical burden while maintaining precision is critical.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3