Wesley Yu-Shu Hsieh
Papers
2
Total Citations
132
H-Index
2
About
Wesley Yu-Shu Hsieh is a leading researcher in robot learning and manipulation, with a focus on enabling robots to operate effectively in cluttered, real-world environments. His work addresses a critical challenge in robotics: how to grasp specific objects when they are surrounded by obstacles, a problem central to applications like automated warehouse order fulfillment. Hsieh’s major contributions lie in developing efficient learning-from-demonstration algorithms that reduce the burden on human supervisors. His 2016 paper on using a hierarchy of supervisors for robot grasping in clutter has garnered 78 citations, establishing a foundation for robust manipulation in uncertain conditions. In another highly cited work (54 citations), Hsieh introduced SHIV, an algorithm that leverages support vectors to minimize supervisor queries in the DAgger framework, enabling scalable policy learning in high-dimensional state spaces. This innovation significantly cuts the time and effort required for human guidance, making robot training more practical. Hsieh’s research bridges the gap between theoretical learning algorithms and real-world robotic systems, offering impactful solutions for industries reliant on autonomous object handling. His work continues to inspire advances in robot autonomy and human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2