Researchers at NC State University have harnessed AI and computer simulations to revolutionize robotic exoskeleton training, allowing users to save energy while walking, running and climbing stairs.
Imagine walking, running or climbing stairs using significantly less energy. This vision has become a reality thanks to innovative research at North Carolina State University (NC State). Using artificial intelligence (AI) and computer simulations, researchers have developed a new method to train robotic exoskeletons, assisting users in substantially reducing their metabolic energy usage.
“This work proposes and demonstrates a new machine-learning framework that bridges the gap between simulation and reality to autonomously control wearable robots to improve mobility and health of humans,” Hao Su, associate professor of mechanical and aerospace engineering at NC State and corresponding author of the study, said in a statement.
The AI-powered system leverages computer simulations, enabling robotic exoskeletons to autonomously adjust and help users move more efficiently without requiring lengthy human testing.
In tests with human subjects, participants wearing the robotic exoskeleton demonstrated a marked reduction in metabolic energy consumption. Specifically, subjects used 24.3% less energy while walking, 13.1% less when running and 15.4% less when climbing stairs.
“Exoskeletons have enormous potential to improve human locomotive performance,” Su added. “However, their development and broad dissemination are limited by the requirement for lengthy human tests and handcrafted control laws.”
This machine-learning framework’s embodiment AI learns how to assist users in a controlled simulation without requiring any experimental input. The framework holds promise not only for able-bodied individuals but also for those with mobility impairments.
“Our framework may offer a generalizable and scalable strategy for the rapid development and widespread adoption of a variety of assistive robots for both able-bodied and mobility-impaired individuals,” Su explained.
Future applications of this method are being explored to assist older adults and individuals with neurological conditions.
“We have developed a way to train and control wearable robots to directly benefit humans,” Shuzhen Luo, first author of the paper and a former postdoctoral researcher at NC State, said in the statement. Luo, currently an assistant professor at Embry-Riddle Aeronautical University, emphasizes the potential this research has in making science fiction a reality.
“This work is essentially making science fiction reality – allowing people to burn less energy while conducting a variety of tasks,” Su noted.
The study, titled “Experiment-free Exoskeleton Assistance Via Learning in Simulation,” was published in the journal Nature.