Mingrui Yu
Papers
7
Total Citations
132
H-Index
5
About
Mingrui Yu is a robotics researcher whose work centers on deformable object manipulation, dexterous in-hand manipulation, and adaptive robotic control. His most significant contributions address one of robotics' persistent challenges: enabling robots to handle deformable linear objects (DLOs) such as wires, cables, and ropes with human-like dexterity. His 2022 paper on global model learning for DLO manipulation has garnered 82 citations, establishing him as a leading voice in this specialized domain. Yu's research develops data-driven and adaptive approaches that allow robots to learn and update deformation models on the fly, circumventing the difficulty of deriving these models theoretically. His work extends into increasingly complex scenarios, including dual-arm manipulation in constrained 3D environments and tactile-sensing-enabled in-hand following of DLOs — skills that closely mirror how humans naturally interact with flexible objects. Beyond deformable objects, Yu has contributed to dexterous finger-based in-hand manipulation, winning the RGMC championship, and has explored robotic ultrasound scanning with human-intention-aware compliance. With a growing citation record across multiple robotic manipulation frontiers, Yu represents an emerging researcher making meaningful strides toward genuinely dexterous, adaptable robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7A Lightweight sequence-based Unsupervised Loop Closure Detection5 citations · 2021