{"id":9263,"date":"2024-06-12T19:18:12","date_gmt":"2024-06-12T23:18:12","guid":{"rendered":"https:\/\/spaceandplanetarynewswire.com\/?p=9263"},"modified":"2024-06-12T19:18:12","modified_gmt":"2024-06-12T23:18:12","slug":"artificial-intelligence-strategy-may-promise-more-widespread-use-of-portable-robotic-exoskeletons-on-earth-and-in-space","status":"publish","type":"post","link":"https:\/\/spaceandplanetarynewswire.com\/?p=9263","title":{"rendered":"Artificial Intelligence Strategy May Promise More Widespread Use of Portable, Robotic Exoskeletons \u2014 on Earth and in Space"},"content":{"rendered":"
Researchers developed a full-body musculoskeletal human model consisting of 208 muscles (upper left), as well as a custom hip exoskeleton (lower left), then leveraged artificial intelligence to simulate multiple activities (center) before deploying the learned controller on human subjects. (Graphic: \u201cNature,\u201d Luo et al., Figure 2.)<\/figcaption><\/figure>\n

Safer, more efficient movements for factory workers and astronauts, and improved mobility for people with disabilities could someday become a more widespread reality, thanks to new research published June 12 in the journal \u201cNature<\/em>.\u201d<\/p>\n

Called \u201cexoskeletons,\u201d wearable robotic frameworks for the human body promise easier movement, but technological hurdles have limited their broader application, explained Dr. Shuzhen Luo of Embry-Riddle Aeronautical University<\/a> \u2014 first author of the \u201cNature\u201d paper, with corresponding author Dr. Hao Su of North Carolina State University (NC State) and other colleagues.<\/p>\n

To date, exoskeletons must be pre-programmed for specific activities and individuals, based on lengthy, costly, labor-intensive tests with human subjects, Luo noted.<\/p>\n

Now, researchers have described a super smart or \u201clearned\u201d controller that leverages data-intensive artificial intelligence (AI) and computer simulations to train portable, robotic exoskeletons.<\/p>\n

\u201cThis new controller provides smooth, continuous torque assistance for walking, running, or climbing stairs without the need for any human-involved testing,\u201d Luo reported. \u201cWith only one run on a graphics processing unit, we can train a control law or `policy,\u2019 in simulation, so that the controller can effectively assist all three activities and various individuals.\u201d<\/p>\n

Driven by three interconnected, multi-layered neural networks, the controller learns as it goes \u2014 evolving through \u201cmillions of epochs of musculoskeletal simulation to improve human mobility,\u201d explained Dr. Luo, assistant professor of Mechanical Engineering<\/a> at Embry-Riddle\u2019s Daytona Beach, Florida, campus.<\/p>\n

The experiment-free, \u201clearning-in-simulation\u201d framework, deployed on a custom hip exoskeleton, generated what appears to be the highest metabolic rate reductions of portable hip exoskeletons to date \u2014 with an average of 24.3%, 13.1% and 15.4% reduced energy expenditure by wearers, for walking, running and stair-climbing, respectively.<\/p>\n

These energy reduction rates were calculated by comparing the performance of human subjects both with and without the robotic exoskeleton, Su of NC State explained. \u201cThat means it\u2019s a true measure of how much energy the exoskeleton is saving,\u201d said Su, associate professor of Mechanical and Aerospace Engineering. \u201cThis work is essentially making science fiction reality \u2014 allowing people to burn less energy while conducting a variety of tasks.\u201d<\/p>\n

Dr. Shuzhen Luo of Embry-Riddle Aeronautical University (at right), whose work appears in \u201cNature\u201d on June 12, 2024, discusses her research related to AI-powered robotic exoskeletons, during an internal poster presentation.<\/figcaption><\/figure>\n

Bridging the Simulation-to-Reality Gap<\/strong><\/p>\n

The approach is believed to be the first to demonstrate the feasibility of developing controllers, in simulation, that bridge the so-called simulation-to-reality, or \u201csim2real gap\u201d while significantly improving human performance.<\/p>\n

\u201cPrevious achievements in reinforcement learning have tended to focus primarily on simulation and board games,\u201d Luo said, \u201cwhereas we proposed a new method \u2014 namely, a dynamic-aware, data-driven reinforcement learning way to train and control wearable robots to directly benefit humans.\u201d<\/p>\n

The framework \u201cmay offer a generalizable and scalable strategy for the rapid, widespread deployment of a variety of assistive robots for both able-bodied and mobility-impaired individuals,\u201d added Su.<\/p>\n

Overcoming Technological Obstacles<\/strong><\/p>\n

As noted, exoskeletons have traditionally required handcrafted control laws based on time-consuming human tests to handle each activity and account for differences in individual gaits, researchers explained in the journal \u201cNature.\u201d A learning-in-simulation approach suggested a possible solution to those obstacles.<\/p>\n

The resulting \u201cdynamics-aware, data-driven reinforcement learning approach\u201d dramatically expedites the development of exoskeletons for real-world adoption, Luo said. The closed-loop simulation incorporates both exoskeleton controller and physics models of musculoskeletal dynamics, human-robot interaction and muscle reactions to generate efficient and realistic data. In this way, a control policy can evolve or learn in simulation.<\/p>\n

\u201cOur method provides a foundation for turnkey solutions in controller development for wearable robots,\u201d Luo said.<\/p>\n

Future research will focus on unique gaits, for walking, running or stair climbing, to help people who have disabilities such as stroke, osteoarthritis and cerebral palsy as well as those with amputations.<\/p>\n","protected":false},"excerpt":{"rendered":"

Safer, more efficient movements for factory workers and astronauts, and improved mobility for people with disabilities could someday become a more widespread reality, thanks to new research published June 12 in the journal \u201cNature.\u201d Called \u201cexoskeletons,\u201d wearable robotic frameworks for the human body promise easier movement, but technological hurdles have limited their broader application, explained…<\/p>\n","protected":false},"author":71,"featured_media":9264,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"fifu_image_url":"https:\/\/earimediaprodweb.azurewebsites.net\/Api\/v1\/Multimedia\/f2ef1e36-0099-4b5b-804c-4a058851cae4\/Rendition\/low-res\/Content\/Public","fifu_image_alt":"Artificial Intelligence Strategy May Promise More Widespread Use of Portable, Robotic Exoskeletons \u2014 on Earth and in Space","footnotes":""},"categories":[207],"tags":[],"class_list":["post-9263","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research"],"_links":{"self":[{"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/posts\/9263","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/users\/71"}],"replies":[{"embeddable":true,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=9263"}],"version-history":[{"count":1,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/posts\/9263\/revisions"}],"predecessor-version":[{"id":9265,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/posts\/9263\/revisions\/9265"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=\/wp\/v2\/media\/9264"}],"wp:attachment":[{"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/spaceandplanetarynewswire.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}