Mahmood Fathy

Institute for Research in Fundamental Sciences, Iran University of Science and Technology

Papers

Total Citations

H-Index

About

Mahmood Fathy is a leading researcher in human-robot interaction and artificial intelligence, with a primary focus on human activity recognition and bipedal robotics. His most impactful work centers on advancing structured prediction models for recognizing complex human activities from depth skeleton data, addressing the critical challenge of variability in how individuals perform actions. In his highly cited 2020 paper (46 citations), Fathy introduced a switching structured prediction framework that significantly improves both simple and complex activity recognition, enabling more natural human-robot communication. His earlier 2017 work (10 citations) established foundational methods for modeling short- and long-range dependencies in skeleton-based activity recognition. Fathy has also made notable contributions to robotics through a novel online gait optimization approach for biped robots with point-feet, solving constrained nonlinear optimization problems to achieve stable walking despite modeling errors or environmental changes. His research, which bridges computer vision, machine learning, and robotics, has accumulated over 60 citations, demonstrating its influence on developing more adaptive and intelligent interactive systems. Fathy's work is essential reading for researchers interested in structured prediction, human activity analysis, and autonomous robot locomotion.