Papers
17
Total Citations
243
H-Index
8
About
Norikazu Sugimoto is a leading researcher at the intersection of robotics, brain-machine interfaces (BMI), and reinforcement learning. His work focuses on enabling humanoid robots to learn complex, dynamically stable movements and on developing assistive technologies for rehabilitation. Sugimoto’s major contributions include pioneering the integration of EEG-based BMI with exoskeleton robots for rehabilitation, as demonstrated in his highly cited 2012 paper (64 citations), which laid the groundwork for non-invasive control of assistive devices. He also advanced humanoid motor learning through the eMOSAIC and MOSAIC models, which allow robots to adapt to multiple reward environments and complex dynamics. His research on motion capture and reinforcement learning (27 citations) enables the transfer of human movements to humanoids while maintaining dynamic stability, and his phase-dependent trajectory optimization for CPG-based biped walking (25 citations) has improved robotic locomotion. With over 200 total citations across his top papers, Sugimoto’s work has significantly impacted both rehabilitation robotics and autonomous humanoid control. His notable achievements include developing whole-body humanoid control via BMI (19 citations) and creating simulation-based learning frameworks that reduce real-world interactions, making his research highly relevant for students and researchers in robotics, AI, and neural engineering.
Research Focus
Key Achievements
Top Papers
- 1Brain-controlled exoskeleton robot for BMI rehabilitation64 citations · 2012
- 2MOSAIC for Multiple-Reward Environments29 citations · 2011
- 3The eMOSAIC model for humanoid robot control27 citations · 2012
- 4
- 5
- 6Brain-machine interfacing control of whole-body humanoid motion19 citations · 2014
- 7
- 8
- 9
- 10eMOSAIC Model for Humanoid Robot Control5 citations · 2010