Dian Chen
Papers
1
Total Citations
51
H-Index
1
About
Dian Chen is a leading researcher in robot learning, with a focus on deformable object manipulation and vision-based control. Her work bridges self-supervised learning and imitation learning to tackle some of robotics’ most intricate challenges—particularly the manipulation of flexible materials like ropes and cloth. In her highly cited 2017 paper, “Combining self-supervised learning and imitation for vision-based rope manipulation” (51 citations), Chen introduced a system that learns from human demonstrations, using image sequences to map initial rope configurations to goal states and output precise action sequences. This approach significantly advanced the field by enabling robots to handle non-rigid objects without explicit modeling, a notoriously difficult problem. Her contributions have inspired further research in learning from demonstration and self-supervised robotics, with her work cited by studies in manipulation, computer vision, and human-robot interaction. Chen’s innovative methods continue to shape how robots perceive and interact with the physical world, making her a notable figure in the growing intersection of machine learning and robotics.
Research Focus
Key Achievements
Top Papers
- 1