A groundbreaking new method leveraging artificial intelligence (AI) and computer simulations is revolutionizing the development of robotic exoskeletons designed to assist human movement.
Researchers have demonstrated how these advanced exoskeletons can help users save energy while walking, running, and climbing stairs. This innovation, described in a study published in Nature, marks a significant advancement in wearable robotics.
Rapid Development Without Human Experiments
The novel method developed by the researchers rapidly creates exoskeleton controllers using AI-driven simulations, eliminating the need for lengthy human-involved experiments.
Xianlian Zhou, associate professor and director of NJIT’s BioDynamics Lab, explained that this approach can apply to various assistive devices, including knee or ankle exoskeletons and above-the-knee or below-the-knee prostheses.
“Our approach marks a significant advancement in wearable robotics, as our exoskeleton controller is exclusively developed through AI-driven simulations,” Zhou stated. “Moreover, this controller seamlessly transitions to hardware without requiring further human subject testing, rendering it experiment-free.”
Enhancing Mobility for All
The breakthrough holds promise for aiding individuals with mobility challenges, such as the elderly or stroke survivors, without necessitating their presence in a laboratory or clinical setting for extensive testing.
This technology paves the way for restoring mobility and enhancing accessibility for everyday in-home or community living.
“This work proposes and demonstrates a new method that uses physics-informed and data-driven reinforcement learning to control wearable robots in order to benefit humans directly,” says Hao Su, corresponding author of the study and associate professor of mechanical and aerospace engineering at North Carolina State University.
Broad Applications and Benefits
Exoskeletons have the potential to improve human locomotive performance across a wide variety of users, from injury rehabilitation to permanent assistance for people with disabilities. However, their broad adoption has been limited by the need for extensive human testing and complex control laws.
This new method focuses on improving autonomous control of embodied AI systems—AI programs integrated into physical technology—by teaching robotic exoskeletons to assist able-bodied people with various movements.
“Previous achievements in reinforcement learning have tended to focus primarily on simulation and board games.
Our method provides a foundation for turnkey solutions in controller development for wearable robots,” says Shuzhen Luo, assistant professor at Embry-Riddle Aeronautical University and the first author of both studies. Luo previously worked as a postdoc at both Zhou’s and Su’s labs.
Immediate Usability
Typically, users must spend hours training an exoskeleton to understand the necessary force and timing to assist in walking, running, or climbing stairs.
The new method allows users to utilize the exoskeletons immediately. The closed-loop simulation incorporates both the exoskeleton controller and physics models of musculoskeletal dynamics, human-robot interaction, and muscle reactions, generating efficient and realistic data and iteratively learning better control policies in simulation.
The unit is pre-programmed to be ready to use right away, and it is also possible to update the controller on the hardware if researchers make improvements in the lab through expanded simulations.
Future prospects for this project include developing individualized, custom-tailored controllers that assist users with various activities of daily living. “This work is essentially making science fiction reality—allowing people to burn less energy while conducting a variety of tasks,” says Su.
Energy Savings and Efficiency
Testing with human subjects showed that study participants used 24.3% less metabolic energy when walking in the robotic exoskeleton compared to walking without it.
Participants used 13.1% less energy when running and 15.4% less energy when climbing stairs. While this study focused on able-bodied individuals, the new method aims to help people with mobility impairments using assistive devices.
“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 notes.
Future Directions
The researchers are in the early stages of testing the new method’s performance in robotic exoskeletons used by older adults and people with neurological conditions, such as cerebral palsy. They are also exploring how the technique could improve the performance of robotic prosthetic devices.
This research was supported by the National Science Foundation under awards 1944655 and 2026622; the National Institute on Disability, Independent Living, and Rehabilitation Research under award DRRP 90DPGE0019;
The Administration for Community Living’s Switzer Research Fellowship Program and the National Institutes of Health under award 1R01EB035404.
The team’s work has the potential to transform the landscape of assistive technology, providing immediate and substantial benefits to millions of individuals worldwide.