Irena Markievicz

Papers

Total Citations

H-Index

About

Irena Markievicz is a leading researcher in human-robot interaction and natural language processing for robotics, specializing in bridging the gap between human communication and robot action execution. Her work centers on enabling robots to understand, generalize, and reuse actions from simple language instructions, addressing a fundamental challenge in robotics: the inability of machines to transfer knowledge between similar tasks as humans do. Her most influential paper, "Cut & Recombine: Reuse of Robot Action Components Based on Simple Language Instructions" (2019, 9 citations), introduces a system that performs action generalization across different manipulation scenarios, allowing robots to decompose and recombine action components from natural language commands. Earlier foundational work, "Action Classification in Action Ontology Building Using Robot-Specific Texts" (2015, 7 citations), tackles the complex translation of human instructions into robot-executable formats by developing ontologies that capture implicit information. Her research on "Reading Comprehension of Natural Language Instructions by Robots" (2017, 4 citations) further advances how robots interpret and complete incomplete instructions. Markievicz’s contributions are critical for developing more adaptable, intuitive robotic systems that can learn from minimal human guidance, with implications for manufacturing, assistive robotics, and autonomous systems.