Tianyu Li
Papers
1
Total Citations
5
H-Index
1
About
Tianyu Li is an emerging researcher specializing in robot learning, motion planning, and dynamical systems, with a particular focus on developing efficient and stable control policies for robotic systems. His work centers on advancing Linear Parameter Varying Dynamical Systems (LPV-DS), a powerful framework that combines statistical modeling with semi-definite optimization to encode complex, reactive robot motion policies that remain stable and time-invariant across varying conditions. Li's most notable contribution to date addresses a fundamental challenge in LPV-DS learning: improving the efficiency and directionality-awareness of the underlying mixture model sampling process. His 2024 paper introduces a parallel sampling approach that enhances the scalability and practical applicability of LPV-DS for real-world robotic control, already garnering 5 citations within its first year — a promising indicator of the work's relevance to the robotics and machine learning communities. His research sits at the intersection of probabilistic modeling, optimization, and autonomous systems, making it highly relevant to researchers working on imitation learning, motion generation, and human-robot interaction. As a developing voice in the field, Li's contributions are helping to make learned motion policies more computationally tractable and deployable in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1