This exoskeleton uses machine learning to put a custom spring in your step

Exoskeletons have been largely confined to the realm of fantasy, appearing in science fiction or superhero films to make characters stronger, taller, or more destructive (in the James Cameron movie). symbol picturesomewhat terrifying AMP suit as a “A human operator amplifier”, but in fact it is more like a human war machine with a real human inside). In terms of actual uses, exoskeleton Tested or developed in industries such as automobile manufacturingAnd the air travelThe armyAnd the Health Care; These are mostly to help people lift heavy objects and materials.

The new exoskeleton serves a different purpose: to help people walk. Developed by engineers at the Stanford Biomechanics Laboratory, the device is described in a research paper published this week in temper nature. In short, it’s a motorized shoe that gives the wearer a forward boost in every step they take. What sets it apart, however, is that its functionality is designed for everyone who uses it rather than being standard across different heights, weights, and speeds.

“This exoskeleton personalizes the assistance as people walk normally in the real world,” he said. Steve Collinsan assistant professor of mechanical engineering who leads the Stanford Biomechatronics Laboratory, at press release. “This has resulted in exceptional improvements in walking speed and energy economy.”

The customization is enabled by a machine learning algorithm, which the team trained using simulators — machines that collected data on movement and energy expenditures from volunteers they were hooked up to. Volunteers walked at varying speeds under imagined scenarios, such as trying to get on a bus or taking a walk in a park.

The algorithm mapped links between these scenarios and people’s energy expenditures, and applied the links to learn in real time how to help the wearer walk in a way that is actually beneficial to them. When a new person puts on the shoe, the algorithm experiences a different pattern of assist each time they walk, and measures how their movements change in response. There is a short learning curve, but on average, the algorithm was able to effectively adapt itself to new users in just an hour.

The exoskeleton works by applying torque to the ankle, replacing some of the functions of the calf muscle. When users take a step, the device helps them push before their toes are about to leave the ground. It worked fine. On average, people walked 9 percent faster than usual while expending 17 percent less energy. In direct comparisons on a treadmill, the exoskeleton presented twice as much effort as comparable devices.

Reducing the effort it takes to walk is generally not a goal most of us should strive for; If anything, Americans need the opposite. But the team that developed the exoskeleton sees it being used to help people with mobility impairments, including the elderly or disabled.

“I think over the next decade we will see these ideas of personalizing help and portable effective exoskeleton Study author and bioengineering researcher Patrick Slade said: press release.

Since the exoskeleton is currently in the prototype stage, it will not reach a wider user base soon. In addition, it has only been tested in healthy adults in their mid-20s so far, so new tests and adjustments are needed for people who really need help walking.

The team also plans to design repetitions that will help improve the wearer’s balance and even reduce joint pain. They are optimistic about the capabilities of their devices. “I really think this technology will help a lot of people,” He said Collins.

image rights: Stanford University / Kurt Heckman

Leave a Comment