Papers
40
Total Citations
1,755
H-Index
19
About
Leonel Rozo is a leading robotics researcher whose work sits at the intersection of machine learning, human-robot collaboration, and robot skill acquisition. His research focuses primarily on learning from demonstration, physical human-robot interaction, and adaptive robot control — areas where he has made substantial and lasting contributions to the field. Rozo's most celebrated work centers on enabling robots to learn collaborative behaviors directly from human demonstrations. His 2016 paper on learning physical collaborative robot behaviors has garnered over 310 citations, reflecting its broad influence on how robots are programmed to work safely and naturally alongside people in real-world environments. Complementing this, his foundational research on impedance-based learning (2013, 151 citations) addressed a critical challenge: teaching robots not merely to replicate movements, but to interact with humans safely through compliant, force-aware control. His development of Kernelized Movement Primitives (2019, 258 citations) represents a significant methodological advance in imitation learning, offering flexible frameworks for generalizing motion patterns across varying contexts. Throughout his career, Rozo has consistently bridged theory and application, tackling tasks ranging from liquid pouring to bimanual manipulation. With over 1,300 cumulative citations, his body of work has profoundly shaped modern collaborative robotics research.
Research Focus
Key Achievements
Top Papers
- 1Learning Physical Collaborative Robot Behaviors From Human Demonstrations311 citations · 2016
- 2Kernelized movement primitives258 citations · 2019
- 3Learning Collaborative Impedance-Based Robot Behaviors151 citations · 2013
- 4
- 5Force-based variable impedance learning for robotic manipulation118 citations · 2018
- 6
- 7
- 8
- 9
- 10Generalized Task-Parameterized Skill Learning45 citations · 2018