Kennon Guglielmo
Georgia Institute of Technology, Southwest Research Institute
Papers
4
Total Citations
75
H-Index
4
About
Kennon Guglielmo is a pioneering figure in the field of robotic motion control, whose work has fundamentally advanced the theory and practical implementation of learning controllers for mechanical manipulators. His research centers on the development of adaptive and repetitive control algorithms that enable robots to learn from repetitive tasks, significantly improving precision and efficiency without requiring explicit dynamic models. Guglielmo’s most impactful contribution is the design and experimental validation of a repetitive learning controller that operates in Cartesian space, allowing robots to perform periodic tasks with remarkable accuracy. His seminal 1992 paper on adaptive and repetitive controllers, with 38 citations, laid the groundwork for this approach, while his 1996 work extended the theory to Cartesian trajectory description, earning 20 citations. Notably, his 2002 experimental evaluation on an IBM 7545 manipulator demonstrated that his algorithms exceeded simulation predictions, achieving superior performance through optical joint feedback. Guglielmo also explored hybrid learning force control, integrating position and force learning for tasks involving unknown surfaces. His work remains a cornerstone for researchers in robotics, offering a robust framework for autonomous learning in manufacturing and automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Experimental evaluation of a new robot learning controller12 citations · 2002
- 4Implementating a hybrid learning force control scheme5 citations · 1994