Papers
12
Total Citations
123
H-Index
5
About
Yingjie Yin is a robotics and control systems researcher whose work spans autonomous aerial systems, dexterous robotic manipulation, and hybrid dynamical modeling. His most influential contribution — a position measurement system for autonomous aerial refueling of UAVs using monocular vision — introduced a multitask parallel deep convolutional neural network (MPDCNN) for robust landmark detection, earning 54 citations and establishing him as a notable voice in vision-guided autonomous systems. Building on this theme, his 2017 work on position and orientation measurement for aerial refueling further refined monocular vision techniques for real-world aerospace applications. Yin has made equally significant contributions to robotic manipulation and locomotion. His research on hybrid control of multi-fingered robot hands addresses the complex mechanics of dexterous manipulation, while his mixed logic dynamical (MLD) modeling framework provided a unified approach for optimizing both biped robot walking and multi-contact hand interactions across varying environments. His earlier work on gain-scheduling H∞ vibration control and nonlinear adaptive robust control for manipulators reflects a strong theoretical foundation in advanced control design. Collectively, his publications demonstrate a career dedicated to bridging rigorous mathematical control theory with practical robotics applications, from humanoid locomotion to cutting-edge autonomous aerial systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Hybrid control of multi-fingered robot hand for dexterous manipulation19 citations · 2004
- 3
- 4
- 5
- 6
- 7
- 8
- 9Hybrid System Modeling and Control of Multi-contact Hand Manipulation3 citations · 2005
- 10