Papers
31
Total Citations
273
H-Index
8
About
Koji Ito is a multidisciplinary robotics and human-machine interface researcher whose work spans autonomous robot control, rehabilitation engineering, and intelligent systems. His research integrates machine learning, neural networks, and control theory to advance both robotic autonomy and human-assistive technologies. Ito's most influential contribution — a reinforcement learning framework employing an evolutionary state recruitment strategy for mobile robot control (2004, 69 citations) — demonstrated how adaptive learning architectures could dramatically improve autonomous navigation. His early and highly regarded work on EMG signal classification using backpropagation neural networks (1993, 42 citations) laid important groundwork for intuitive prosthetic control and human-machine interfacing, a thread he continued with EEG-driven stroke rehabilitation systems in 2012. His contributions to cooperative robotics are equally noteworthy, encompassing decentralized multi-manipulator control, adaptive hybrid control of flexible objects, and extended passive velocity field control — work that advanced the theoretical and practical foundations of coordinated robotic manipulation. Research into motor imagery and force field learning (2011, 27 citations) further reflects his commitment to bridging neuroscience and rehabilitation robotics. Across more than two decades, Ito has built a coherent and impactful body of work connecting intelligent control, human motor systems, and assistive technology.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Motor imagery facilitates force field learning27 citations · 2011
- 4On cooperative manipulation of dynamic objects13 citations · 1995
- 5
- 6Adaptive hybrid control of manipulators on uncertain flexible objects12 citations · 1995
- 7
- 8
- 9
- 10