Dimitris Margaritis

Papers

Total Citations

H-Index

About

Dimitris Margaritis is a researcher whose work lies at the intersection of robotics, human-robot interaction, and computer vision. His major contributions focus on making robots more accessible and trainable for everyday human environments. In his highly cited 1998 paper, "Template-based recognition of pose and motion gestures on a mobile robot" (29 citations), Margaritis pioneered a gesture-based interface that allows people to instruct robots using simple, intuitive arm gestures—both static poses and dynamic motions. This work addressed the critical need for easy-to-use robot instruction methods, enabling non-expert users to command robots without programming knowledge. His complementary research, "Learning to Locate an Object in 3D Space from a Sequence of Camera Images" (15 citations), tackled the challenge of enabling robots to autonomously recognize and locate objects in three-dimensional space from visual input. This approach allowed robots to be "trained" by example, learning to identify specific objects through visual demonstrations. Together, these contributions form an early foundation for intuitive, vision-based human-robot collaboration, demonstrating how robots can learn from natural human interaction rather than requiring explicit programming.