Connect with us
  • Elysium

Neuro rehab technology

This lower limb exoskeleton could revolutionise stroke rehabilitation

Published

on

A team of researchers have developed a new method for controlling lower limb exoskeletons using deep reinforcement learning.

This method allows for more robust and natural walking control for sets of lower limb exoskeletons.

Advances in wearable robotics are paving the way in helping to restore mobility for those who have difficulties with movement.

However, current control methods for exoskeletons are limited in their ability to provide natural and intuitive movements for users. Thus, meaning balance is compromised and contributions to user fatigue and discomfort are made.

The researchers behind this exoskeleton hope they can add to the few studies that have focused on the development of robust controllers that can optimise the user’s experience in terms of safety and independence.

Existing exoskeletons for lower limb rehabilitation employ a bundle of technologies to help the user maintain balance, including such items such as special crutches and sensors, according to co-author, Dr Ghaith Androwis, senior research scientist in the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation and director of the Center’s Rehabilitation Robotics and Research Laboratory.

Exoskeletons that operate without such helpers allow more independent walking, but at the cost of added weight and slow walking speed.

Dr Androwis, says: “Advanced control systems are essential to developing a lower limb exoskeleton that enables autonomous, independent walking under a range of conditions.

(Left) The developed prototype of the lower extremity robotic exoskeleton (LE-RE). (Right) The integrated musculoskeletal and exoskeleton model. The yellow coordination frames show the bushing frames coincidentally fixed on the LE-RE and the human model.

The method developed by the research team uses deep reinforcement learning to improve exoskeleton control. Reinforcement learning is a type of artificial intelligence that enables machines to learn from their own experiences through trial and error.

Corresponding author Xianlian Zhou, says: “Using a musculoskeletal model coupled with an exoskeleton, we simulated the movements of the lower limb and trained the exoskeleton control system to achieve natural walking patterns using reinforcement learning.

“We are testing the system in real-world conditions with a lower limb exoskeleton being developed by our team and the results show the potential for improved walking stability and reduced user fatigue.”

The team are determined that their proposed model generates a universal robust walking controller which is capable of handling multiple levels of human-exoskeleton interactions without the need for tuning parameters.

This new system has the potential to benefit a wide range of conditions which cause movement impairments such as stroke.

The researchers plan to continue with testing on the system with users and further refine the control algorithms to improve walking performance.

Dr Androwis, concludes: “We are excited about the potential of this new system to improve the quality of life for people with lower limb impairments.

“By enabling more natural and intuitive walking patterns, we hope to help users of exoskeletons to move with greater ease and confidence.”

HIWIN

Trending