Mike Franklin
Papers
1
Total Citations
76
H-Index
1
About
Mike Franklin is a leading researcher at the intersection of robotics, machine learning, and surgical automation. His work focuses on overcoming the fundamental challenge of precise control in systems with non-linear kinematics, particularly cable-driven mechanisms where joint elasticity and cable tensioning introduce significant inaccuracies. Franklin's major contribution lies in pioneering data-driven approaches to kinematic control, most notably through his highly cited 2014 paper on "Learning accurate kinematic control of cable-driven surgical robots using data cleaning and Gaussian Process Regression" (76 citations). This work demonstrated how combining rigorous data cleaning techniques with Gaussian Process Regression can dramatically improve control accuracy in systems that only have access to imprecise internal kinematic models—a common limitation in surgical robotics. His research has direct implications for enhancing the safety and precision of minimally invasive surgical procedures, where even millimeter-level errors can have serious consequences. Franklin's innovative fusion of robotics control theory with advanced statistical learning methods has established him as a key figure in the growing field of data-driven surgical automation, inspiring further work on adaptive control systems for medical and industrial applications.
Research Focus
Key Achievements
Top Papers
- 1