Wanyu Lin
Papers
2
Total Citations
14
H-Index
2
About
Wanyu Lin’s research lies at the intersection of robotic manipulation, multi-agent systems, and deep reinforcement learning, with a focus on enabling robots to operate intelligently in complex, real-world environments. Her work addresses two critical challenges: learning soft object manipulation skills and fostering multi-robot cooperation under partial observability. In her 2023 paper “SoftGPT,” Lin introduces a generative pre-trained heterogeneous graph transformer that allows robots to learn goal-oriented soft object manipulation from human demonstrations—a task notoriously difficult due to objects’ variable shapes and dynamics. This work, garnering 8 citations, offers a promising path for domestic robotics. Earlier, her 2021 study on hierarchical deep reinforcement learning for multi-robot cooperation tackles the problem of limited information in domains like package delivery and search-and-rescue. By designing dedicated communication protocols, her approach enables robots to share observations effectively, achieving coordinated behavior despite partial observability. With 6 citations, this contribution is foundational for scalable multi-robot systems. Lin’s research not only advances theoretical frameworks but also provides practical solutions for autonomous systems, making her a rising figure in robotics and AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2