Ali Etemad
Papers
6
Total Citations
76
H-Index
6
About
Ali Etemad is a leading researcher at the intersection of human-machine interaction, biomechanics, and applied deep learning. His work focuses on developing intelligent systems that can accurately sense, model, and predict human physical intent, with direct applications in powered exoskeletons, rehabilitation robotics, and assistive devices. A central theme of his research is the multimodal estimation of force and torque during both quasi-dynamic and dynamic muscle contractions, a notoriously difficult problem due to changing joint angles and movement speeds. His most cited work (2022, 17 citations) introduces a novel deep learning framework for this task, while subsequent studies (2022, 14 citations; 2024, 13 citations) advance the field through bagged tree ensemble modeling and transfer learning, enabling models to generalize across new users and conditions. Beyond force estimation, Etemad has made notable contributions to in-bed pressure-based pose estimation using image space representation learning (2021, 14 citations) and to touchless control of heavy equipment via low-cost hand gesture recognition (2022, 11 citations). His work is characterized by a practical, application-driven approach that bridges the gap between cutting-edge machine learning and real-world engineering challenges, making him a key figure in the development of next-generation human-centered robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Touchless Control of Heavy Equipment Using Low-Cost Hand Gesture Recognition11 citations · 2022
- 6