Papers

5

Total Citations

28

H-Index

3

About

Tomoki Nishi is a robotics and artificial intelligence researcher whose work spans rehabilitation engineering, reinforcement learning, and multi-agent systems. His research focuses on developing intelligent robotic systems that can learn and adapt through observation, interaction, and partial knowledge of their environment. Nishi's most cited work investigates robotic therapy for gait rehabilitation, specifically examining how partial body-weight support combined with functional electrical stimulation affects treadmill locomotion—a study that has garnered 12 citations and contributes to the early-stage development of end-effector gait-training devices. He has made significant contributions to behavior acquisition in robotics, proposing novel approaches for incremental learning through observation in multi-agent environments, and developing Actor-Critic methods for linearly-solvable continuous Markov decision processes with partially known dynamics. His work on modular learning systems and self-task decomposition through coach instruction has advanced understanding of how robots can efficiently learn complex behaviors without exhaustive exploration. With a career spanning over a decade, Nishi's research addresses fundamental challenges in making robots more adaptable and capable of learning from limited information, with applications ranging from rehabilitation to autonomous systems.

Research Focus

Key Achievements

3
H-Index
5
Papers
28
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Effects of partial body-weight support and functional electrical stimulation on gait characteristics during treadmill locomotion: Pros and cons of saddle-seat-type body-weight support
12 citations · 2017
📈 Most Prolific Year: 2017 (2 Papers)
🤝 Key Collaborators: 18
🏛 Institutions: Toyonaka Municipal Hospital, The University of Osaka, Machine Science

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
    Incremental Purposive Behavior Acquisition based on Modular Learning System.
    2 citations · 2006

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago