Skip to content
Bridging the Gap: AI Facilitates Autonomous Training of Robotic Exoskeletons

Bridging the Gap: AI Facilitates Autonomous Training of Robotic Exoskeletons

In an unprecedented step forward, researchers at North Carolina State University have harnessed artificial intelligence (AI) and computer simulations to autonomously train robotic exoskeletons. This breakthrough technology allows exoskeletons to help users conserve energy during various activities such as walking, running, or stair climbing. Promising a seamless enhancement of human locomotion, this development creates a significant impact on the future of robotic exoskeleton technology.

The team leveraged a novel machine-learning framework, connecting virtual simulations and real-world application to autonomously control wearable robots. The primary intent is to significantly enhance human mobility and health. Hao Su, associate professor of mechanical and aerospace engineering at NC State and the corresponding author of the related paper, stressed the vast potential of exoskeletons in ameliorating human locomotive performance. However, he also emphasized the current limitations, which include the necessity for extensive human tests and intricate control laws.

The newly-implemented machine-learning framework enables the AI within portable exoskeletons to learn optimal assistance techniques within a computer simulation. This method negates the need for tedious real-world experiments, hence expediting and simplifying the process. Traditionally, users had to spend hours training an exoskeleton to gauge necessary force and timing for assistance. The innovative method allows instant utilization.

The aim is to make what once appeared as science-fiction a reality by helping users conserve energy while performing a variety of tasks. In a significant breakthrough, the researchers discovered that study participants conserved 24.3% more energy when walking, 13.1% when running, and 15.4% when climbing stairs with the assistance of the robotic exoskeleton compared to performing the same tasks unaided. These reductions in energy usage emphasize the impactful energy-saving capability of this exoskeleton technology.

While this study primarily focused on able-bodied individuals, the same technique has potential applications in aiding individuals with mobility impairments. Current stages of testing involve exploring the efficacy of this method in improving robotic prosthetic devices' performance for amputee populations and in robotic exoskeletons used by older adults and those with neurological conditions. The researchers also project that this framework can pave the way for rapid development and widespread adoption of various assistive robots that can greatly benefit both able-bodied and mobility-impaired individuals.

The research stemmed from collaboration and support from various institutes, including the National Science Foundation, the National Institute on Disability, Independent Living, and Rehabilitation Research, and the National Institutes of Health.

Disclaimer: The above article was written with the assistance of an AI tool. The original sources can be found on ScienceDaily.