Papers
3
Total Citations
37
H-Index
3
About
Ming Shi is a robotics researcher whose work focuses on enabling robots to learn and generalize complex human skills through advanced movement primitives. His primary research areas include robot learning from demonstration, dynamical movement primitives (DMPs), and human-robot skill transfer. Shi’s most significant contribution is his 2022 paper on “Generalization of orientation trajectories and force–torque profiles for learning human assembly skill,” which has garnered 30 citations—a strong indicator of its impact in the field. This work addresses a critical challenge in robotics: teaching machines to adapt not just position trajectories but also orientation and force profiles when learning assembly tasks from human demonstrations. His earlier research on Euclidean transformation DMPs (2021, 4 citations) tackles movement generalization across variable initial task states, while his work on geometric information-based obstacle avoidance under the DMPs framework (2021, 3 citations) integrates safety constraints into learned movements. Collectively, Shi’s research advances the frontier of dexterous robotic manipulation, moving beyond simple trajectory replication toward truly adaptive, human-like skill acquisition. His work is particularly relevant for applications in manufacturing, collaborative robotics, and autonomous assembly systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3