Papers
6
Total Citations
122
H-Index
4
About
Mohamed El-Shamouty is a leading researcher at the intersection of robotics, artificial intelligence, and industrial automation. His work focuses on enabling safe, efficient human-robot collaboration (HRC) and accelerating the deployment of robotic systems in manufacturing. A central theme of his research is using deep reinforcement learning (DRL) to overcome critical bottlenecks. His most cited work (62 citations) introduces a DRL framework for safe HRC, directly addressing the costly, over-emphasized safety measures that limit productivity. He further advances this by developing skill-based programming for force-controlled assembly (13 citations) and proposing uncertainty-guided active learning with Bayesian neural networks to improve RL efficiency and safety. El-Shamouty also contributes to simulation-driven machine learning for robotics (37 citations), enabling fast adaptation to mass personalization. His practical impact is exemplified by CARA (Computer-Aided Risk Assessment), an engineering tool that simplifies and automates risk assessment for HRC, making industrial collaboration easier to implement. With a portfolio spanning from human motion prediction (PredNet) to functional safety automation, El-Shamouty’s work is pivotal in bridging the gap between cutting-edge AI and real-world industrial applications.
Research Focus
Key Achievements
Top Papers
- 1Towards Safe Human-Robot Collaboration Using Deep Reinforcement Learning62 citations · 2020
- 2Simulation-driven machine learning for robotics and automation37 citations · 2019
- 3
- 4
- 5
- 6