Papers
4
Total Citations
90
H-Index
4
About
Abdullah Yusefi is a robotics and artificial intelligence researcher whose work centers on autonomous navigation, visual-inertial odometry (VIO), and multi-robot systems for real-world applications. His most influential contribution, "HVIOnet: A deep learning based hybrid visual–inertial odometry approach for unmanned aerial system position estimation" (2022, 51 citations), introduces a novel hybrid deep learning architecture that fuses visual and inertial data to improve position estimation accuracy for UAVs—a critical challenge in GPS-denied environments. Building on this, his earlier work "The YTU dataset and recurrent neural network based visual-inertial odometry" (2021, 20 citations) provides a benchmark dataset and RNN-based framework that advances the field of state estimation. Yusefi also contributes to educational resources, as seen in his tutorial on SLAM and ROS applications (2021, 13 citations), which helps bridge theory and practice for students and practitioners. Demonstrating the societal impact of robotics, his 2022 study on COVID-19 isolation control proposes using UAVs and UGVs in crowded indoor spaces to enforce social distancing, offering a proactive, non-diagnostic approach to pandemic mitigation. With over 90 total citations, Yusefi’s work is shaping the future of autonomous systems, from robust navigation algorithms to socially beneficial robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2The YTU dataset and recurrent neural network based visual-inertial odometry20 citations · 2021
- 3
- 4