
Exoskeleton Robot and our control approach. (a) Developed carbon frame exoskeleton robot. (b) Proposed selective assist strategy. In our approach, assistive policy is selected among candidate daily motions by using an EMG-based movement classification method constructed in a positive-unlabeled (PU)-learning framework and assists user’s motion with a newly developed lightweight exoskeleton robot. Credit: IEEE Robotics and Automation Letters (2022). DOI: 10.1109/LRA.2022.3148799
Researchers from the RIKEN Guardian Robot Project and collaborators have used a combination of lightweight material engineering and artificial intelligence to create an exoskeleton robot that could help people with mobility impairments. An important element of the new device is technology that allows the skeleton to effectively guess the intentions of the user.
Robotic exoskeletons promise to play an important role in supporting an aging population. Essentially, they are suits that people can wear, allowing them to exert strength when their old bodies are not capable of exerting strength themselves. However, developing exoskeletons has been hampered by the fact that they are generally heavy, and if not properly controlled can act as hindrances rather than assistance. Thus, it is important to develop exoskeletons that are both lightweight and can assist the efforts of the user without hindering their efforts.
The current research involved two main elements. First, the researchers developed a lightweight, carbon fiber-based exoskeleton for the lower body that was attached to the thighs and lower legs of users. The exoskeleton was built with highly backdrivable actuators, so that it did not impede the movements of users even when the actuators were not activated. And importantly, the research team turned to artificial intelligence to see if they could use it to predict how the user wanted to move. They used a method known as PU-learning, or positive and unlabeled, to have the exoskeleton learn to correctly read the intentions of the user, based on measurements of the muscle activities of the user. The PU-classification method allows the use of ambiguous data, by combining positively labeled data, which the machine knows is correct, with other unlabeled data that might either be positive or negative, allowing the artificial intelligence to learn from data that is not all labeled.
For the experiment, participants performed various movements that can begin in the same way—standing up, crossing their legs, leaning forward, and repositioning themselves in a chair. The exoskeleton used machine learning to guess when they were actually trying to stand up and then provided assistance for the movement.
The experiment was successful. According to Jun-ichiro Furukawa of the Guardian Robot Project, the first author of the paper, the results were better than conventional systems that use fully labeled data in situations where user’s behavior other than the target sit-to-stand motion can occur, indicating that the method could be expanded to other movements as well.
According to Jun Morimoto, who led the research team, “The key element of our research is that when controlling a robot to assist human movement, it is important to develop it based on the assumption that humans will behave in ways that are not in the learning data.”
The research was led by researchers from the RIKEN Guardian Robot Project, a project dedicated to creating robotic devices that can assist people who require assistance, in collaboration with researchers from the RIKEN Center for Brain Science, ATR Computational Neuroscience Labs, Kyushu University, and Kyoto University.
Original Article: Robotic exoskeleton uses machine learning to help users stand up
More from: RIKEN | Kyushu University | Kyoto University
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Exoskeleton robot
- ReWalk Robotics Presents on Personal Exoskeleton Pricing at Medicare Public Meeting
ReWalk supports “gap-filling” pricing method proposed by CMS with use of up-to-date pricing information.MARLBOROUGH, Mass. and BERLIN and YOKNEAM ILLIT, Israel, Nov. 30, 2023 (GLOBE NEWSWIRE) -- ...
- ExoAtlet Unveils Groundbreaking ExoAtlet 2 and Industry-First Pediatric Exoskeleton
Enhancing Lives with Advanced Robotics: The Introduction of ExoAtlet 2 and Pediatric Exoskeleton Los Angeles, CA USA - November 30, 2023 — In a landmark move, ExoAtlet is proud to announce the launch ...
- ReWalk Robotics to use AI to help people walk
Marlborough-based ReWalk Robotics, a firm that develops assistive walking devices, has added artificial intelligence capabilities to its next prototype.
- ReWalk Robotics Ltd.: ReWalk Robotics Demonstrates AI Autonomous Decision Making in Next Generation Exoskeleton Prototype
MARLBOROUGH, Mass. and BERLIN and YOKNEAM ILLIT, Israel, Nov. 28, 2023 (GLOBE NEWSWIRE) -- ReWalk Robotics, Ltd. (Nasdaq: RWLK) ("ReWalk" or the "Company"), a leading provider of innovative technologi ...
- ReWalk Robotics demonstrates proof-of-concept with next-gen, AI-powered exoskeleton
ReWalk Robotics (Nasdaq:RWLK) announced today that it successfully demonstrated proof-of-concept with its next-generation exoskeleton.
Go deeper with Google Headlines on:
Exoskeleton robot
[google_news title=”” keyword=”exoskeleton robot” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
PU-learning
- Mangaluru: Expert PU College organizes Annual Sports Meet
The Expert College, Kodialbail organized ‘Annual Sports Meet 2023’ on November 30, at Mangala Stadium. Mukund Kamath, proprietor of Ideal Ice Cream, Mangaluru was the chief guest for the inaugural ...
- Get This Personalized, Handmade Toiletry Bag for Everyone on Your List
Us Weekly has affiliate partnerships so we may receive compensation for some links to products and services. It’s gifting season. For some, this evokes joy and festive humming about in the holiday ...
- The Learning Network
What’s using all the water? By The Learning Network Soccer fans are tuning into watchalongs — streaming parties where they can hear and see everything except the game. Does that sound appealing?
- No distance learning in state as centres fail to meet UGC criteria
Thousands of youth living in remote areas of the state are being denied the opportunity for distance learning due to universities failing to meet UGC criteria. Nalanda Open University (NOU) and other ...
- What’s Going On in This Picture?
By The Learning Network A new slide show of some of our favorite “What’s Going On in This Picture?” posts, culled from the last four years of images. By The Learning Network Want to use ...
Go deeper with Google Headlines on:
PU-learning
[google_news title=”” keyword=”PU-learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]