Papers
10
Total Citations
77
H-Index
5
About
Yansong Wu is an emerging robotics researcher whose work sits at the dynamic intersection of tactile sensing, robot manipulation, and AI-driven task planning. His research addresses some of the most pressing challenges in modern robotics: enabling machines to physically interact with the world through intelligent touch and autonomous decision-making. Wu's most impactful contribution to date is his development of multi-dimensional tactile perception systems using triboelectric sensors, which allow robots to classify and sort objects without visual input — a breakthrough with significant implications for intelligent manufacturing (32 citations). Complementing this, his work on TacDiffusion introduces diffusion model-based force-domain policies for high-precision robotic assembly, demonstrating strong transferability across insertion tasks (10 citations). A recurring theme in Wu's research is the use of large language models for behavior tree generation in robot task planning, a body of work that collectively represents one of the first systematic explorations of LLMs as task planners in assembly robotics (19+ combined citations). He has also made meaningful contributions to deformable object manipulation, contact-rich assembly strategies, and human-robot interaction via nanogenerator-based tactile interfaces. With a rapidly growing citation record, Wu represents a promising voice in next-generation autonomous robotics research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3TacDiffusion: Force-Domain Diffusion Policy for Precise Tactile Manipulation10 citations · 2025
- 4
- 51 kHz Behavior Tree for Self-adaptable Tactile Insertion5 citations · 2024
- 6
- 7
- 8
- 9
- 10