Papers
14
Total Citations
135
H-Index
8
About
Nasser Rezzoug’s research sits at the intersection of robotics, biomechanics, and rehabilitation, where he applies robotic principles to understand and enhance human movement. His key contributions center on developing quantitative tools—like the manipulability index and force polytopes—to evaluate upper-limb movement capacities and force generation. In his highly cited 2011 work (25 citations), he introduced manipulability as a global performance index for the upper extremity, borrowing from robotics to quantify achievable wrist velocities. This approach has been extended to ergonomics and rehabilitation, including studies on spinal cord injury (2013, 8 citations) and elbow flexion effects (2015, 11 citations). Rezzoug also pioneered machine learning methods for robotic grasping, notably a modular neural network architecture for multifingered hand configuration under noisy sensing (2005, 17 citations), and a recurrent neural network for learning walking patterns (2013, 15 citations). His recent work on on-line feasible wrench polytope evaluation (2022, 14 citations) advances human-robot collaboration by enabling real-time adaptation of robotic assistance. With over 100 citations across his top papers, Rezzoug’s work has significant impact in rehabilitation robotics, ergonomics, and human-centered robot control, offering practical tools for assistive technologies and digital human modeling.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Learning to Walk Using a Recurrent Neural Network with Time Delay15 citations · 2013
- 4
- 5
- 6
- 7
- 8
- 9
- 10Robotic Grasping: A Generic Neural Network Architecture6 citations · 2006