Airat Gaskarov

Papers

Total Citations

H-Index

About

Airat Gaskarov is a researcher at the forefront of semantic SLAM (Simultaneous Localization and Mapping) and indoor robotics perception. His primary contributions center on developing high-quality, realistic datasets that bridge the gap between simulation and real-world robotic navigation. Gaskarov’s landmark work, "DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation" (2019), introduced a novel, large-scale synthetic dataset specifically designed for training and benchmarking semantic SLAM methods. Comprising 200 long sequences with 3,000–5,000 frames each, DISCOMAN leverages realistic home layouts and robot-like trajectories to provide a rigorous testbed for algorithms. Although a relatively recent contribution, the dataset has already garnered 3 citations, reflecting its growing importance in the field. Gaskarov’s work is notable for its emphasis on practical, reproducible benchmarks that accelerate progress in autonomous indoor navigation. By enabling researchers to train more robust, semantically aware mapping systems, his research directly supports the development of smarter home robots and autonomous systems. For students and researchers entering SLAM, Gaskarov’s dataset offers a foundational resource for understanding how perception, mapping, and semantics converge in real-world robotics.