Resume: A new study describes how AI and computer simulations train robotic exoskeletons to help users conserve energy while walking, running and climbing stairs. This method eliminates the need for lengthy experiments involving humans and can be applied to a variety of devices.
The breakthrough offers significant potential for helping people with mobility problems, improving accessibility in everyday life. Researchers found that participants used up to 24.3% less energy with the exoskeleton.
Key Facts:
- AI and simulations train exoskeletons without experiments involving humans.
- Exoskeletons allowed users to save up to 24.3% energy during movement tests.
- The method can be applied to various devices, including prostheses.
Source: Institute of Technology of New Jersey
A team of researchers has demonstrated a new method that uses AI and computer simulations to train robotic exoskeletons that allow users to save energy while walking, running and climbing stairs.
Described in a study published in Natureis rapidly developing the new method of exoskeleton controllers to support locomotion without relying on long-term experiments involving humans.
Furthermore, the method can be applied to a wide variety of devices beyond the hip exoskeleton as demonstrated in this study.
“It could also apply to knee or ankle exoskeletons, or other multi-joint exoskeletons,” said Xianlian Zhou, associate professor and director of NJIT’s BioDynamics Lab.
In addition, it can be applied similarly to above-the-knee or below-knee prosthetics, providing immediate benefits to millions of able-bodied and mobility-impaired individuals, he said.
“Our approach marks a significant advancement in the field of wearable robotics, as our exoskeleton controller was developed exclusively through AI-driven simulations,” explains Zhou. “Additionally, this controller transitions seamlessly to hardware without the need for further human testing, making it experimental-free.”
This breakthrough holds promise for helping individuals with mobility issues, including the elderly or stroke survivors, without requiring their presence in a laboratory or clinical setting for extensive testing. Ultimately, it paves the way for restoring mobility and improving accessibility for daily life at home or in the community.
“This work proposes and demonstrates a new method using physics-informed and data-driven reinforcement learning to control wearable robots so that people can directly benefit from it,” said Hao Su, corresponding author of an article on the work and associate professor of mechanical research. and aerospace engineering from North Carolina State University.
Exoskeletons have the potential to improve human locomotion performance in a wide range of users, from injury rehabilitation to permanent assistance for people with disabilities. However, lengthy human testing and control laws have limited its widespread acceptance.
The researchers focused on improving the autonomous control of embodied AI systems – systems where an AI program is integrated into a physical technology.
This work focused on teaching robotic exoskeletons how to assist able-bodied people with a variety of movements, and builds on previous reinforcement learning-based research on exoskeletons for lower extremity rehabilitation, also a collaboration between Zhou, Su and several others .
“Previous achievements in reinforcement learning have tended to focus on simulation and board games. Our method provides a basis for turnkey solutions in the development of controllers for wearable robots,” said Shuzhen Luo, assistant professor at Embry-Riddle Aeronautical University and first author of both works. Luo previously worked as a postdoc in both Zhou and Su’s laboratories.
Typically, users must “train” an exoskeleton for hours so the technology knows how much force is needed – and when to apply that force – to help users walk, run or climb stairs.
The new method allows users to use the exoskeletons immediately, because the closed-loop simulation includes both exoskeleton controller and physics models of musculoskeletal dynamics, human-robot interaction and muscle responses, generating efficient and realistic data and iteratively developing better control policies in the simulation is learned. .
The device is pre-programmed to be ready to use straight away, and it is also possible to update the controller on the hardware as researchers make improvements in the laboratory through extensive simulations. Future prospects for this project include the development of individualized, customized controllers that assist users in various activities of daily life.
“This work actually turns science fiction into reality – allowing people to burn less energy while performing different tasks,” says Su.
For example, when tested with human subjects, the researchers found that study participants used 24.3% less metabolic energy while walking in the robotic exoskeleton, compared to walking without the exoskeleton. Participants used 13.1% less energy when running in the exoskeleton and 15.4% less energy when climbing stairs.
While this study focused on the researchers’ work with able-bodied people, the new method aims to help people with mobility issues using assistive devices.
“Our framework can provide 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 said.
“We are in the early stages of testing the performance of the new method in robotic exoskeletons used by older adults and people with neurological conditions, such as cerebral palsy. And we are also interested in exploring how the method can be used to improve the performance of robotic prosthetics.”
Financing: This research was conducted with support from the National Science Foundation under awards 1944655 and 2026622; the National Institute on Disability, Independent Living, and Rehabilitation Research, award DRRP 90DPGE0019; the Administration for Community Living’s Switzer Research Fellowship Program; and the National Institutes of Health, award 1R01EB035404.
About this AI and neurotech research news
Author: Derik Raymond
Source: Institute of Technology of New Jersey
Contact: Deric Raymond – New Jersey Institute of Technology
Image: The image is credited to the New Jersey Institute of Technology
Original research: Closed access.
“Experiment-free exoskeleton assistance via simulation learning” by Xianlian Zhou et al. Nature
Abstract
Experiment-free assistance with the exoskeleton via learning in simulation
Exoskeletons have enormous potential to improve the performance of human locomotives. However, their development and wide distribution are limited by the need for long-term human testing and hand-crafted control laws. Here we demonstrate an experiment-free method to learn versatile control policies in simulation.
Our learning-in-simulation framework uses dynamically aware models of the musculoskeletal system and exoskeleton and data-driven reinforcement learning to bridge the gap between simulation and reality without human experimentation.
The learned controller is deployed on a modified hip exoskeleton that automatically generates support during various activities with a reduced metabolic rate of 24.3%, 13.1% and 15.4% for walking, running and climbing stairs, respectively.
Our framework can provide a generalizable and scalable strategy for the rapid development and widespread adoption of a variety of assistive robots for both able-bodied and impaired individuals.