Qie Sima
Papers
3
Total Citations
15
H-Index
3
About
Qie Sima is a rising researcher at the intersection of robot learning and model predictive control, whose work is shaping how robots perceive and manipulate their environments. Her research spans visual pre-training for manipulation, robust control theory, and dexterous robot planning. In her highly cited 2023 work, "Exploring Visual Pre-training for Robot Manipulation," Sima systematically investigated how large-scale real-world visual data can be leveraged to improve robot learning from pixel observations—a foundational contribution that has already garnered 7 citations. She further advanced the field with her 2024 papers on robust tube-based Model Predictive Control (MPC), where she addressed the critical challenge of computational delay in real-time robot manipulation. By developing methods for smooth computation without input delay, Sima's work enables more reliable and responsive control for dexterous tasks. Her contributions are particularly notable for bridging the gap between data-driven visual pre-training and theoretically grounded control, offering practical recipes for building more capable robotic systems. With her innovative approach to combining learning and control, Sima is establishing herself as a key voice in next-generation robot manipulation research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3