Please ensure that JavaScript is enabled in your browser to view this page.
Body mobility is not something that most of us think too much about. But as people grow older, or have to learn to deal with a disability, mobility becomes a big concern. The simple, everyday activities that normally fill our lives become too difficult, and those with limited mobility can find themselves socially isolated and unable to take care of their own basic needs. Traditional mobility aids, like walkers and wheelchairs can be of assistance, but these tools can also be very cumbersome, and can restrict the types of activities one can participate in. What most people would like is a little bit of a boost when they need it, without having to lug around large, heavy equipment.
Exoskeletons offer the promise of giving this extra boost when needed, but they have typically been very expensive and completely impractical for use outside of a laboratory setting. A recent paper published by a research group at Stanford University has described a boot-like exoskeleton that can offer assistance to the wearer while walking, but it is also made from relatively inexpensive components, and has been validated to work under real world conditions. By making use of machine learning and off-the-shelf hardware components, this exoskeleton eschews the tethers and complicated setup that is typically required of such devices, and can provide real help to real people.
The boot consists of a Raspberry Pi 4 single board computer, some inexpensive sensors that monitor the walking motions of the wearer, a motor driver, and a motor. A rechargeable battery pack is worn around the waist like a belt, which makes the exoskeleton completely self-sufficient — all power and processing units are worn on-body. The system applies torque at the ankle to partially replace the work normally done by the calf muscle. When taking a step, just before the toes leave the ground, the motor gives assistance in pushing off of the ground. This has an effect similar to removing a 30 pound backpack, according to the team.
As you might imagine, everyone has a somewhat different way of walking, and the assistance that each person needs is unique. Simply applying the same boost to each step for every user would make for an odd experience that would be more likely to cause problems than it would be to give help. The exoskeleton deals with this by employing a machine learning model that learns over time how best to assist the wearer. When a new user first wears the boot, it takes about an hour of monitoring their patterns of walking for the device to adjust the model and customize it to provide an optimal level of assistance.
In real world trials of the boot, it was found that people could walk 9% faster while expending 17% less energy for a given distance traveled as compared to using normal shoes. This is a huge improvement over existing exoskeletons — it is about twice the reduction in walking effort seen with the current state of the art devices. Also of importance, this new exoskeleton can actually be used outside of the lab, and without a team of researchers to manually tune it. There is a lot of potential in this work to help people in real world situations.
The team’s next step is to clinically validate their device with older users, and those with disabilities. They are also planning to build variants of the device that are designed to reduce joint pain or help with balance. When this work is complete, they hope to team up with commercial partners to bring the exoskeleton to market.
Hackster.io, an Avnet Community © 2022