Tactile-enabled Prostetic Hands

Tactile-enable control for human-like and prostetic hands.

Tactile-enabled Control of Human-like and Prostetic Hands

The main goal of this project is to develop Machine Learning methods that enable the production of intelligent prostheses. Electric prosthesis rejection rates are 23% in adults and 32% in children, and in a recent study, 89% of users felt they were more efficient without the prosthesis, which is a frequent reason for avoiding prosthesis use. A significant limitation is that current devices require the user to pay extra attention when manipulating objects due to the missing sense of touch. Our research focuses on developing touch-enabled human-like hands and collected visual, tactile and muscle data from healthy individuals during tasks in laboratory environments. Some recent publications involve the study of tactile and visual response of individuals1, improving control2 and teleoperation3 of human-like hands.

  1. Wang, S., Zheng, J., Huang, Z., Zhang, X., Prado da Fonseca, V., Zheng, B., & Jiang, X. (2022). Integrating computer vision to prosthetic hand control with sEMG: Preliminary results in grasp classification. Frontiers in Robotics and AI, 9(September), 1–10. https://doi.org/10.3389/frobt.2022.948238 ↩

  2. Welyhorsky, M., Prado Da Fonseca, V., Zhu, Q., Rocha Lima, B. M., Alves De Oliveira, T. E., & Petriu, E. M. (2022). Neuro-Fuzzy Grasp Control for a Teleoperated Five Finger Anthropomorphic Robotic Hand. In 2022 IEEE International Systems Conference (SysCon) (pp. 1–5). IEEE. https://doi.org/10.1109/SysCon53536.2022.9773821 ↩

  3. Zhu, Q., da Fonseca, V. P., Lima, B. M. R., Welyhorsky, M., Goubran, M., de Oliveira, T. E. A., & Petriu, E. M. (2020). Teleoperated Grasping Using a Robotic Hand and a Haptic-Feedback Data Glove. In 2020 IEEE International Systems Conference (SysCon) (pp. 1–7). IEEE. https://doi.org/10.1109/SysCon47679.2020.9275927 ↩