Related Experiment Video
Updated: Jun 2, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
Real-time upper limb motion estimation from surface electromyography and joint angular velocities using an artificial
1Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 305-701, Korea. sun.kwon@kaist.ac.kr
Summary
Estimating human upper limb motion using surface electromyography (SEMG) and joint angular velocities improves human-machine cooperation. This noncontact method enhances safety and natural interaction in cooperative systems.
Area of Science:
- Robotics
- Human-Computer Interaction
- Biomechanics
Background:
- Human-machine cooperation systems require accurate human motion estimation for safety and natural interaction.
- Estimating motion from its source, skeletal muscles via surface electromyography (SEMG), is a promising approach.
Purpose of the Study:
- To investigate an upper limb motion estimation method using SEMG and joint angular velocities for cooperative manipulation control.
- To evaluate the performance of this method in approximating limb flexion-extension in the 2-D sagittal plane.
Main Methods:
- Utilized SEMG signals from five upper limb muscles.
- Incorporated joint angular velocities of the limb.
- Developed a 2-D sagittal plane motion estimation model.
Main Results:
- Achieved acceptable motion estimation performance under noncontact conditions (NRMSE <0.15, CC >0.9).
- Identified the necessity of angular velocity input and estimation error feedback for physical contact scenarios.
Conclusions:
- The proposed SEMG-based motion estimation method is effective for natural human-machine cooperation.
- The findings suggest potential for enhanced safety and intuitive control in collaborative robotics.
