Related Experiment Video
Updated: Jan 10, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
1.2K
Reconstructing hand gestures with synergies extracted from dance movements.
Parthan Olikkal1, Chris Dollo1, Akshara Ajendla1
1Vinjamuri Lab, Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, 21250, USA.
Scientific Reports
|November 25, 2025
Summary
Indian classical dance hand gestures (mudras) offer a novel way to improve robot hand control. This dance-inspired approach enhances gesture recognition accuracy and precision for applications in robotics and rehabilitation.
Area of Science:
- Robotics and Human-Computer Interaction
- Biomechanics and Motor Control
- Cultural Heritage and Performing Arts
Background:
- Human hand gesture recognition is vital for robotics, sign language, and human-computer interaction.
- Existing research primarily focuses on gesture recognition, often overlooking the therapeutic potential of dance movements.
- Indian classical dance, specifically Bharatanatyam, utilizes intricate hand gestures called mudras with structured movement patterns.
Purpose of the Study:
- To introduce a novel method for understanding and reconstructing human hand gestures using movement primitives derived from Bharatanatyam mudras.
- To compare the effectiveness of mudra-derived movement synergies against those derived from natural hand grasps.
- To demonstrate the application of reconstructed gestures in controlling a humanoid robot.
Main Methods:
- Extracted hand gesture synergies using Gaussian-modeled joint angular velocities, representing them as fundamental motion syllables.
- Utilized these syllables to reconstruct 75 diverse hand gestures, including American Sign Language (ASL) postures, natural grasps, and traditional mudras.
- Mapped reconstructed gestures onto a humanoid robot (Mitra) using a continuous joint-mapping approach.
Main Results:
- Mudra-derived synergies achieved superior reconstruction accuracy: 95.78% for natural grasps and 92.99% for mudras, outperforming natural grasp-derived synergies (88.92% and 82.51%, respectively).
- The structured nature of Bharatanatyam mudras resulted in stronger movement syllables with enhanced generalizability and precision.
- Successfully mapped reconstructed gestures onto a five-degree-of-freedom robotic hand.
Conclusions:
- Bharatanatyam mudras provide a powerful, structured learning framework for hand gesture representation and reconstruction.
- Dance-inspired structured learning holds significant potential for improving dexterity, rehabilitation, and motor control.
- This approach paves the way for more efficient gesture-based interaction models in robotics, prosthetics, and rehabilitation.
Related Concept Videos
01:24Muscle Coordination and Action
3.0K
Muscle coordination is a complex and finely tuned process essential for smooth and purposeful movements like flexion, extension, adduction, abduction, and rotation. The human body orchestrates the actions of various muscles working in concert, each with a specific role. Four functional types describe how muscles work together: agonist, antagonist, synergist, and fixator.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement....
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement....
3.0K
01:29Relative Motion Analysis using Rotating Axes-Problem Solving
685
Consider a crane whose telescopic boom rotates with an angular velocity of 0.04 rad/s and angular acceleration of 0.02 rad/s2. Along with the rotation, the boom also extends linearly with a uniform speed of 5 m/s. The extension of the boom is measured at point D, which is measured with respect to the fixed point C on the other end of the boom. For the given instant, the distance between points C and D is 60 meters.
Here, in order to determine the magnitude of velocity and acceleration for point...
Here, in order to determine the magnitude of velocity and acceleration for point...
685