|
|
#1
03-09-2018, 01:16 AM
|
|||
|
|||
Learning Method for Tuning Exoskeletons
 Body-worn robots that assist people with disabilities are becoming more common, thanks to research and development over the last decade or so. While there’s been a great deal of progress in perfecting powered exoskeletons, there’s still a lot of work left to be able to coordinate their movements with the individuals that are wearing them. Researchers at Harvard’s Wyss Institute have been investigating how their soft exosuit, created to help people walk, can be tuned to work with the body of the wearer to achieve high efficiency walking that feels natural and pleasant. Tuning of such devices is usually a manual task, requiring the wearer to repeat the same movements over and over, but an automated system would help to speed up the Tuning process while leading to better results. The team used*human-in-the-loop optimization, a technique that adjusts various parameters while monitoring what effects it has on the individual being affected. This involved volunteers wearing the exosuit along with stress test-like equipment to measure the metabolic cost of walking. Using their methodology, the researchers were able to reduce that cost by an average of over 17%, achieving considerably better walking gaits. “This new Method is an effective and fast way to optimize control parameter settings for assistive wearable devices,” said Ye Ding, a researcher that worked on the technology. “Using this method, we achieved a huge improvement in metabolic performance for the wearers of a hip extension assistive device.” Here’s a Wyss Institute video about the new system: Study in Science Robotics: Human-in-the-loop optimization of hip assistance with a soft exosuit during walking… Via: Wyss Institute… 
|
 |
|
|
العرض العادي
