First Look at Meta MyoSuite, an AI Platform That Applies Machine Learning to Musculoskeletal Models

Here’s a first look at Meta MyoSuite, an embodied artificial intelligence platform that applies machine learning (ML) to biomechanical control problems. Its musculoskeletal Models could have significant impact in developing prosthetics as well as post-injury rehabilitation since they are up to 4,000x faster than other simulators at meeting the data requirements of modern ML algorithms.

Mark Zuckerberg just announced MyoSuite, a new AI platform we developed to build realistic musculoskeletal simulations to help accelerate development of prosthetics. It could also help us build avatars that move more realistically in the metaverse. https://t.co/Q4gVboQGSa pic.twitter.com/T27CAbXBg5

— Meta Newsroom (@MetaNewsroom) May 23, 2022

The musculoskeletal models found in MyoSuite are far more computationally efficient and scalable than existing models, thus allowing one to simulate the large number of muscles the human body contains. It also solved a number of complex motor control behaviors that haven’t been done before, such as dexterous manipulation (twirling a pen, turning a key, etc.). These results will hopefully lead to progress in complex real-world problems like rehabilitation, prosthesis and ergonomics in the near future. Apply similar AI technology to facial recognition systems and even deepfakes won’t be fooling anybody.

Let’s consider a tendon-tear injury. MyoSuite can easily model tendon-transfer, a well-known technique for recovering functionality due to a torn tendon. MyoSuite also has the ability to simulate the outcome, in terms of mobility, achieved by a given surgical procedure and the impact it will have on the functional rehabilitation of the affected parts, following the surgical procedure,” said the company.