MSGID: 1:317/3 649fabe6   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Robotic glove that 'feels' lends a 'hand' to relearn playing piano after   
   a stroke    
      
     Date:   
         June 30, 2023   
     Source:   
         Florida Atlantic University   
     Summary:   
         A new soft robotic glove is lending a 'hand' and providing hope   
         to piano players who have suffered a disabling stroke or other   
         neurotrauma.   
      
         Combining flexible tactile sensors, soft actuators and AI, this   
         robotic glove is the first to 'feel' the difference between   
         correct and incorrect versions of the same song and to combine   
         these features into a single hand exoskeleton. Unlike prior   
         exoskeletons, this new technology provides precise force and   
         guidance in recovering the fine finger movements required for   
         piano playing and other complex tasks.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   For people who have suffered neurotrauma such as a stroke, everyday   
   tasks can be extremely challenging because of decreased coordination   
   and strength in one or both upper limbs. These problems have spurred the   
   development of robotic devices to help enhance their abilities. However,   
   the rigid nature of these assistive devices can be problematic, especially   
   for more complex tasks like playing a musical instrument.   
      
   A first-of-its-kind robotic glove is lending a "hand" and providing   
   hope to piano players who have suffered a disabling stroke. Developed   
   by researchers from Florida Atlantic University's College of Engineering   
   and Computer Science, the soft robotic hand exoskeleton uses artificial   
   intelligence to improve hand dexterity.   
      
   Combining flexible tactile sensors, soft actuators and AI, this robotic   
   glove is the first to "feel" the difference between correct and incorrect   
   versions of the same song and to combine these features into a single   
   hand exoskeleton.   
      
   "Playing the piano requires complex and highly skilled movements, and   
   relearning tasks involves the restoration and retraining of specific   
   movements or skills," said Erik Engeberg, Ph.D., senior author,   
   a professor in FAU's Department of Ocean and Mechanical Engineering   
   within the College of Engineering and Computer Science, and a member   
   of the FAU Center for Complex Systems and Brain Sciences and the FAU   
   Stiles-Nicholson Brain Institute. "Our robotic glove is composed of   
   soft, flexible materials and sensors that provide gentle support and   
   assistance to individuals to relearn and regain their motor abilities."   
   Researchers integrated special sensor arrays into each fingertip of the   
   robotic glove. Unlike prior exoskeletons, this new technology provides   
   precise force and guidance in recovering the fine finger movements   
   required for piano playing. By monitoring and responding to users'   
   movements, the robotic glove offers real-time feedback and adjustments,   
   making it easier for them to grasp the correct movement techniques.   
      
   To demonstrate the robotic glove's capabilities, researchers programmed   
   it to feel the difference between correct and incorrect versions of   
   the well-known tune, "Mary Had a Little Lamb," played on the piano. To   
   introduce variations in the performance, they created a pool of 12   
   different types of errors that could occur at the beginning or end of   
   a note, or due to timing errors that were either premature or delayed,   
   and that persisted for 0.1, 0.2 or 0.3 seconds.   
      
   Ten different song variations consisted of three groups of three   
   variations each, plus the correct song played with no errors.   
      
   To classify the song variations, Random Forest (RF), K-Nearest Neighbor   
   (KNN) and Artificial Neural Network (ANN) algorithms were trained with   
   data from the tactile sensors in the fingertips. Feeling the differences   
   between correct and incorrect versions of the song was done with the   
   robotic glove independently and while worn by a person. The accuracy of   
   these algorithms was compared to classify the correct and incorrect song   
   variations with and without the human subject.   
      
   Results of the study, published in the journal Frontiers in Robotics and   
   AI,demonstrated that the ANN algorithm had the highest classification   
   accuracy of 97.13 percent with the human subject and 94.60 percent without   
   the human subject. The algorithm successfully determined the percentage   
   error of a certain song as well as identified key presses that were out   
   of time. These findings highlight the potential of the smart robotic   
   glove to aid individuals who are disabled to relearn dexterous tasks   
   like playing musical instruments.   
      
   Researchers designed the robotic glove using 3D printed polyvinyl acid   
   stents and hydrogel casting to integrate five actuators into a single   
   wearable device that conforms to the user's hand. The fabrication process   
   is new, and the form factor could be customized to the unique anatomy   
   of individual patients with the use of 3D scanning technology or CT scans.   
      
   "Our design is significantly simpler than most designs as all the   
   actuators and sensors are combined into a single molding process,"   
   said Engeberg.   
      
   "Importantly, although this study's application was for playing a song,   
   the approach could be applied to myriad tasks of daily life and the   
   device could facilitate intricate rehabilitation programs customized for   
   each patient."  Clinicians could use the data to develop personalized   
   action plans to pinpoint patient weaknesses, which may present themselves   
   as sections of the song that are consistently played erroneously and   
   can be used to determine which motor functions require improvement. As   
   patients progress, more challenging songs could be prescribed by the   
   rehabilitation team in a game-like progression to provide a customizable   
   path to improvement.   
      
   "The technology developed by professor Engeberg and the research team   
   is truly a gamechanger for individuals with neuromuscular disorders   
   and reduced limb functionality," said Stella Batalama, Ph.D., dean of   
   the FAU College of Engineering and Computer Science. "Although other   
   soft robotic actuators have been used to play the piano; our robotic   
   glove is the only one that has demonstrated the capability to 'feel'   
   the difference between correct and incorrect versions of the same song."   
   Study co-authors are Maohua Lin, first author and a Ph.D. student; Rudy   
   Paul, a graduate student; and Moaed Abd, Ph.D., a recent graduate; all   
   from the FAU College of Engineering and Computer Science; James Jones,   
   Boise State University; Darryl Dieujuste, a graduate research assistant,   
   FAU College of Engineering and Computer Science; and Harvey Chim, M.D.,   
   a professor in the Division of Plastic and Reconstructive Surgery at   
   the University of Florida.   
      
   This research was supported by the National Institute of Biomedical   
   Imaging and Bioengineering of the National Institutes of Health (NIH),   
   the National Institute of Aging of the NIH and the National Science   
   Foundation. This research was supported in part by a seed grant from the   
   FAU College of Engineering and Computer Science and the FAU Institute   
   for Sensing and Embedded Network Systems Engineering (I-SENSE).   
      
       * RELATED_TOPICS   
             o Health_&_Medicine   
                   # Disability # Bladder_Disorders # Today's_Healthcare   
             o Mind_&_Brain   
                   # Brain-Computer_Interfaces # Music # Stroke   
             o Matter_&_Energy   
                   # Acoustics # Wearable_Technology # Engineering   
             o Computers_&_Math   
                   # Robotics # Neural_Interfaces # Artificial_Intelligence   
       * RELATED_TERMS   
             o Left-handed o Virtual_reality o Robot o   
             Robotic_surgery o Muscle o Soft_drink o Rett_syndrome o   
             Obsessive-compulsive_personality_disorder   
      
   ==========================================================================   
   Story Source: Materials provided by Florida_Atlantic_University. Original   
   written by Gisele Galoustian. Note: Content may be edited for style   
   and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Maohua Lin, Rudy Paul, Moaed Abd, James Jones, Darryl Dieujuste,   
      Harvey   
         Chim, Erik D. Engeberg. Feeling the beat: a smart hand exoskeleton   
         for learning to play musical instruments. Frontiers in Robotics   
         and AI, 2023; 10 DOI: 10.3389/frobt.2023.1212768   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/06/230630130152.htm   
      
   --- up 1 year, 17 weeks, 4 days, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45 5075/35   
   PATH: 317/3 229/426