Satoshi Funabashi
Papers
23
Total Citations
338
H-Index
11
About
Satoshi Funabashi is a robotics researcher whose work sits at the intersection of tactile sensing, dexterous manipulation, and machine learning for robotic hands. His research has made significant contributions to enabling robots to interact with objects in ways that more closely resemble human dexterity — a longstanding challenge in robotics. Funabashi's most influential work focuses on multi-fingered in-hand manipulation and tactile-based object recognition, with his top papers accumulating over 40 citations each. A recurring theme across his research is harnessing distributed tactile sensor arrays — such as the uSkin triaxial force sensor — combined with deep learning architectures including CNNs, Graph Convolutional Networks, and LSTM models to achieve robust grasping and manipulation across objects of varying shape, size, and material properties. His notable contributions include developing morphology-specific neural networks for tactile transfer learning, spatio-channel-temporal attention mechanisms for grasp stability prediction, and multi-modal slip detection integrating both vision and touch. Beyond manipulation, Funabashi has also extended sensing expertise into wearable robotics, proposing muscle deformation-based gait phase detection systems. With over 260 total citations across his most recognized works, his research is shaping how next-generation robots perceive and physically interact with the world around them.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Detection of Slip from Vision and Touch34 citations · 2022
- 4
- 5
- 6
- 7
- 8Robust in-hand manipulation of variously sized and shaped objects19 citations · 2015
- 9Variable In-Hand Manipulations for Tactile-Driven Robot Hand via CNN-LSTM14 citations · 2020
- 10