Toshio Tsuji

About

Toshio Tsuji is a pioneering researcher whose work sits at the intersection of human-robot interaction, biomedical engineering, and intelligent control systems. His career has been defined by two interconnected themes: harnessing electromyographic (EMG) signals to create intuitive human-robot interfaces, and developing sophisticated impedance and trajectory control methods for robotic systems. Tsuji's foundational contributions to EMG-based interfaces—spanning from early neural network motion discrimination (1993) to a landmark Bayesian-neural hybrid classification framework (2009, 161 citations)—have significantly advanced the reliability of prosthetic device control and rehabilitation robotics. His 2002 rehabilitation interface prototype demonstrated the practical potential of adaptive, patient-responsive robotic aids, earning 94 citations. Complementing this, his impedance control research, including neural network learning of robot arm impedance (1996) and noncontact visual impedance control (1999), has shaped how robots interact safely and dynamically with their environments. Tsuji also made notable strides in bio-mimetic trajectory generation and robotic food handling—demonstrating unusual breadth. With over 680 cumulative citations across his most recognized works, his research has meaningfully influenced rehabilitation engineering, prosthetics, and intelligent robotics, making his publications essential reading for anyone entering human-robot systems research.

Research Focus

Key Achievements

Top Papers

1. 1
   A Hybrid Motion Classification Approach for EMG-Based Human–Robot Interfaces Using Bayesian and Neural Networks

   161 citations · 2009
2. 2
   Tracking Control Properties of Human–Robotic Systems Based on Impedance Control

   107 citations · 2005
3. 3
   EMG-based human-robot interface for rehabilitation aid

   94 citations · 2002
4. 4
   Bio-mimetic trajectory generation of robots via artificial potential field with time base generator

   77 citations · 2002
5. 5
   Neural network learning of robot arm impedance in operational space

   50 citations · 1996
6. 6
   An Optimum Design of Robotic Hand for Handling a Visco-elastic Object Based on Maxwell Model

   44 citations · 2007
7. 7
   Discrimination of Forearm Motions from EMG Signals by Error Back Propagation Typed Neural Network Using Entropy

   42 citations · 1993
8. 8
   Noncontact impedance control for redundant manipulators

   37 citations · 1999
9. 9
   On-line learning of robot arm impedance using neural networks

   35 citations · 2005
10. 10
    An EMG controlled robotic manipulator using neural networks

    34 citations · 2002

Key Collaborators

Contact & Links