Related Experiment Video
Updated: May 16, 2026

06:58
A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
Published on: November 6, 2015
Dynamic Manipulation Skill Learning for Tactile Myoelectric Prosthetic Hands in Tool Handling
Boao Li1,2, Shuhui Wu2, Ting You3
1Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China.
Cyborg and Bionic Systems (Washington, D.C.)
|May 15, 2026
Summary
This study introduces a novel bionic gripping controller (TKE-BGC) that integrates tactile, kinesthetic, and electromyography (EMG) data for advanced prosthetic hand control. The TKE-BGC enhances stability and reduces user workload during continuous tool use.
Area of Science:
- Biomedical Engineering
- Robotics
- Human-Computer Interaction
Background:
- Continuous tool operation with myoelectric prosthetic hands is challenging due to the need for stable, adaptive control under varying loads.
- Human motor control achieves stability via a biological sensorimotor closed loop, using tactile feedback to adapt to environmental changes.
- Existing prosthetic control strategies struggle with dynamic impacts and tracking delays, limiting functionality.
Purpose of the Study:
- To design and evaluate a multimodal controller, the tactile, kinesthetic, and electromyography (EMG) bionic gripping controller (TKE-BGC), for enhanced prosthetic hand control.
- To develop a prosthetic control framework using human skill transfer that enables robust, end-to-end adaptive control.
- To improve stability, reduce tool drops, shorten task completion times, and lower physical workload for prosthetic users during tool manipulation.
Main Methods:
- Collected multimodal data (tactile, kinematic, EMG) from able-bodied users during tool manipulation using a data glove.
- Trained a TKE-BGC model using a Transformer encoder for feature extraction and a multilayer perceptron for real-time joint angle prediction.
- Developed a prosthetic control framework based on the TKE-BGC, enabling adaptive control through human skill transfer.
Main Results:
- The TKE-BGC framework demonstrated precise performance in 4 tool operation tasks, including unseen ones.
- Significantly reduced tool drops and task completion times compared to baseline methods.
- Achieved human-like average contact forces and substantially lowered user physical workload (e.g., reduced average EMG amplitude).
Conclusions:
- The TKE-BGC enables robust, adaptive control for myoelectric prosthetic hands, mimicking human sensorimotor feedback.
- This approach significantly improves performance in continuous tool use tasks, enhancing daily independence for amputees.
- The research has practical value for vocational rehabilitation and reemployment of individuals with limb loss.

