Engineers from Harvard University have developed a soft, wearable robotic device for movement assistance. The robot combines machine learning and a physics-based model to learn each user’s unique movements.
Developed by researchers from Harvard John A. Paulson School of Engineering and Applied Sciences, the robot provides personalized movement assistance for individuals with upper-limb impairment, such as stroke and ALS patients.
The robot also provides support for daily activities like eating and drinking. Researchers revealed that the robotic device — which was tested with stroke and ALS patients — could someday offer both assistive and rehabilitative benefits.
Wearable robot is responsive to individual user’s exact movements
Researchers with physician-scientists at Massachusetts General Hospital and Harvard Medical School upgraded the wearable robot to be responsive to an individual user’s exact movements, endowing the device with more personalized assistance that could give users better, more controlled support for daily tasks.
Published in Nature Communications, the work reveals personalized ML intention detection model to decode user’s motion intention from IMU and compression sensors.
The team leveraged a physics-based hysteresis model to enhance control transparency and adapt it for practical use in real-world tasks.
They combined and integrated these two models into a real-time controller to modulate the assistance level based on the user’s intention and kinematic state. Researchers also evaluated the effectiveness of our control strategy in improving arm function in a multi-day evaluation.
Robot improves movement quality
“For 5 individuals post-stroke and 4 living with ALS wearing a soft shoulder robot, we demonstrate that the controller identifies shoulder movement with 94.2% accuracy from minimal change in the shoulder angles (elevation: 3.4°, depression: 1.7°) and reduces arm-lowering force by 31.9% compared to a baseline controller,” said researchers in the study.
Engineers also revealed that the robot improves movement quality by increasing their shoulder elevation/depression (17.5°), elbow (10.6°), and wrist flexion/extension (7.6°) ROMs; reducing trunk compensation (up to 25.4%); and improving hand-path efficiency (up to 53.8%).
Distinguishes user’s shoulder movements with 94% accuracy
“For people living with ALS, the most important considerations include comfort, ease of use, and the ability of the device to adapt to their specific needs and movement patterns,” said ALS specialist Dr. Sabrina Paganoni, co-director of the Massachusetts General Hospital Neurological Clinical Research Institute.
“Personalization is crucial to enhance their functional independence and quality of life. This device holds the potential to significantly improve upper limb function, enhance daily living activities, and reduce compensatory movements.”
Results showed that a robot trained on an individual user’s movement data could distinguish the user’s shoulder movements with 94% accuracy.
The amount of force a person needed to lower their arm was reduced by about a third, compared to previous versions, according to a press release.
Prabhat Ranjan Mishra Prabhat, an alumnus of the Indian Institute of Mass Communication, is a tech and defense journalist. While he enjoys writing on modern weapons and emerging tech, he has also reported on global politics and business. He has been previously associated with well-known media houses, including the International Business Times (Singapore Edition) and ANI.
/w=3840,quality=90,fit=scale-down)
