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