Papers
2
Total Citations
43
H-Index
2
About
Tingting Mi is a leading researcher in robotic tactile perception, with a focus on enabling robots to interpret physical properties of objects through touch. Her work centers on two critical challenges: object hardness classification and grasp stability prediction. In her highly cited 2022 paper, "TactONet," Mi introduced a novel ordinal network that leverages unimodal probability to classify object hardness—a task made difficult by the inherent ambiguity of tactile data. This work, with 23 citations, addresses the crucial gap of incorporating ordinal information between hardness levels, significantly improving classification accuracy. Her 2021 study on "Tactile Grasp Stability Classification Based on Graph Convolutional Networks" (20 citations) tackles the fundamental problem of predicting whether a grasped object will slip or fall. By fusing multi-sensory tactile data through graph convolutional networks, Mi developed a method that evaluates grasp state with high precision at the moment of initial contact. These contributions are foundational for advancing robotic manipulation in unstructured environments, making her work essential reading for researchers in tactile sensing and dexterous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2Tactile Grasp Stability Classification Based on Graph Convolutional Networks20 citations · 2021