Papers
84
Total Citations
965
H-Index
17
About
Yunjiang Lou is a prolific robotics researcher whose work spans parallel manipulator design, robot sensing, human-robot interaction, and advanced control systems. He is perhaps best known for his foundational contributions to the optimal kinematic synthesis of parallel manipulators, introducing the concept of "effective regular workspace" and developing robust numerical optimization algorithms to solve the inherently complex, nonlinear design problems these systems present — work that has collectively garnered over 135 citations. His research extends into precision sensing, notably with a highly cited joint torque sensor for real-time robot collision detection (62 citations) and rigorous methods for force/torque sensor bias estimation and gravity compensation, both critical to safe human-robot cooperation. Lou has also made notable contributions to robot calibration through an improved product-of-exponentials kinematic formulation, and to emerging domains including optical tweezers-based microparticle manipulation and crowd-aware robot navigation using interactive model predictive control (51 citations). More recently, his development of a generalized multikernel maximum correntropy Kalman filter demonstrates growing engagement with robust state estimation theory. Across his career, Lou has consistently bridged theoretical rigor with practical implementation, making his work highly relevant to researchers and engineers advancing intelligent, safe, and precise robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Randomized Optimal Design of Parallel Manipulators73 citations · 2008
- 2
- 3
- 4
- 5Interactive Model Predictive Control for Robot Navigation in Dense Crowds51 citations · 2021
- 6
- 7
- 8
- 9
- 10