Saeed Manaffam
Papers
1
Total Citations
4
H-Index
1
About
Saeed Manaffam is a researcher whose work sits at the intersection of robotics, machine learning, and human-robot interaction, with a particular focus on enabling robots to learn complex tasks from human demonstration. His key contributions center on developing algorithms that allow robots to not only imitate demonstrated motions but to intelligently generalize those skills to new situations. In his highly cited 2017 paper, "Learning from Demonstration: Generalization via Task Segmentation," Manaffam introduced a novel motion segmentation algorithm that breaks down a learned trajectory into locally distinct segments. This segmentation is then exploited to apply targeted transformations—such as scaling or rotation—to each segment independently, allowing the robot to adapt its learned behavior to novel environments or constraints. This work addresses a fundamental challenge in robotics: moving beyond simple mimicry to true skill generalization. With 4 citations, this paper has laid important groundwork for more flexible and robust robot learning systems. Manaffam's research is particularly relevant for students and engineers interested in creating robots that can learn from non-expert human teachers and adapt their skills to the messy, unpredictable real world.
Research Focus
Key Achievements
Top Papers
- 1Learning from Demonstration: Generalization via Task Segmentation4 citations · 2017