Papers

5

Total Citations

46

H-Index

3

About

Ran Dong is a pioneering researcher at the intersection of robotics, traditional Japanese performing arts, and human-robot interaction. Her work centers on solving the "uncanny valley" problem—the discomfort humans feel when robots appear almost, but not quite, human—by drawing inspiration from Bunraku, a UNESCO-recognized puppet theater known for producing some of the world's most emotionally expressive motions. Dong’s most influential paper, "A deep learning framework for realistic robot motion generation" (2021, 20 citations), establishes a foundational approach for creating lifelike robot movements. Her groundbreaking contributions include characterizing and implementing 3D "squash and stretch" motions from Bunraku into real life-size humanoid robots, and applying the Japanese aesthetic principle of *Jo-Ha-Kyū*—a rhythmic structure of beginning, breaking, and rapid conclusion—to robot sounds and movements. This work enables robots to convey emotion without triggering the uncanny valley. Dong has also developed a keyframeless motion-transfer method using multivariate empirical mode decomposition, allowing more nuanced robotic imitation. Her research, with over 46 total citations, is vital for designing emotionally resonant, socially acceptable robots, particularly for post-pandemic IoT applications requiring non-physical human connection.

Research Focus

Key Achievements

3
H-Index
5
Papers
46
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
A deep learning framework for realistic robot motion generation
20 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 16
🏛 Institutions: Tokyo University of Technology, University of Tsukuba, Chukyo University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago