Igor Slinko

Papers

Total Citations

H-Index

About

Igor Slinko is a researcher specializing in robotics, computer vision, and semantic SLAM (Simultaneous Localization and Mapping), with a particular focus on indoor scene understanding and autonomous navigation. His most notable contribution is the creation of the DISCOMAN dataset, a comprehensive resource designed to train and benchmark semantic SLAM methods. This dataset, comprising 200 long sequences with 3,000–5,000 frames each, is generated from realistic home layouts and simulates the motion of a home robot, providing a critical tool for advancing robotic perception in domestic environments. Although his work has garnered 3 citations to date, the DISCOMAN dataset represents a foundational effort in bridging the gap between simulated and real-world robotic navigation, offering a standardized platform for evaluating odometry, mapping, and semantic understanding. Slinko’s research is instrumental for students and researchers aiming to develop more robust, context-aware robots capable of operating in complex indoor spaces, highlighting his role in shaping future benchmarks in the field.