Ramana Vinjamuri leads the UMBC lab that studies brain control of complex hand movements. The group draws on kinematic synergies, where the brain coordinates multiple joints to simplify motions. Vinjamuri developed the dance-inspired approach during a 2023 conference at the Indian Institute of Technology Mandi.
Dancers maintain flexibility through lifelong training, notes Vinjamuri. "We noticed dancers tend to age super gracefully: They remain flexible and agile because they have been training. That was a huge inspiration for us when we started looking for richer alphabets of movement. With dance, we are looking not just at healthy movement, but super healthy. And so the question became, could we find a 'superhuman' alphabet from the dance gestures?"
The team analyzed 30 natural hand grasps for objects from water bottles to beads and identified six synergies that account for nearly 99 percent of variations. They applied the same method to 30 single-hand mudras and found six synergies covering 94 percent of variations. Mudra-derived synergies better reconstructed 15 American Sign Language letters than grasp-derived ones.
"When we started this type of research more than 15 years ago, we wondered: Can we find a golden alphabet that can be used to reconstruct anything?" says Vinjamuri. "Now I highly doubt that there is such a thing. But the mudras-derived alphabet is definitely better than the natural grasp alphabet because there is more dexterity and more flexibility." The researchers aim to create task-specific movement libraries for activities like cooking or playing instruments.
Vinjamuri's team teaches robotic hands these synergies and combinations for new gestures, differing from mimicry methods. They test on a standalone robotic hand and a humanoid robot, adapting mathematical models to each. A camera and software system captures and analyzes movements cost-effectively for home applications like physical therapy.
"Once I learned about synergies, I became so curious to see if we could use them to make a robotic hand respond and perform the same way as a human hand," says Parthan Olikkal, a Ph.D. candidate in computer science at UMBC. "Adding my own work to the research efforts, and seeing the results has been gratifying."
Research Report:Reconstructing hand gestures with synergies extracted from dance movements
Related Links
University of Maryland Baltimore County
All about the robots on Earth and beyond!
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
