This Exoskeleton Uses AI to Help People Walk Faster With Less Energy

Largely limited to the realm of fiction, exoskeletons appear in science fiction or superhero films to make characters stronger, bigger, or more destructive (in James Cameron’s avatar, the slightly terrifying AMP suit serves as “a human operator’s amp” but is really more like a humanoid war machine with a real human inside). In terms of real-world use, exoskeletons have been tested or developed in industries such as automotive manufacturing, aerospace, military, and healthcare; These are mainly designed to help people lift heavy objects and materials.

A new exoskeleton serves a different purpose: helping people walk. The device, developed by engineers at Stanford Biomechatronics Laboratory, is described in an article published in this week Nature. In short, it’s a motorized boot that gives the wearer a push forward with every step. However, what sets it apart is that its function is tailored to each person using it, rather than standardizing on different heights, weights, and walking speeds.

“This exoskeleton personalizes support when humans walk normally through the real world,” said Steve Collins, associate professor of mechanical engineering who heads the Stanford Biomechatronics Laboratory, in a press release. “And it resulted in exceptional improvements in walking speed and energy savings.”

The personalization is made possible by a machine-learning algorithm that the team trained using emulators — machines that collected data about movement and energy use from volunteers connected to them. The volunteers walked at different speeds under imagined scenarios, such as trying to catch a bus or taking a walk through a park.

The algorithm made connections between these scenarios and people’s energy use and applied the connections to learn in real time how to help the wearers walk, so that it is actually useful for them. When a new person puts the boot on, the algorithm tests a different support pattern 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 to new users in just an hour.

READ :  People assess mobile home damage in North Fort Myers

The exoskeleton works by applying torque to the ankle, replacing some of the function of the wearer’s calf muscle. When users take a step just before their toes leave the ground, the device helps them push off. It worked pretty well; On average, people walked 9 percent faster than usual while using 17 percent less energy. In a direct comparison on a treadmill, the exoskeleton required about twice as much effort as comparable devices.

Reducing the effort of walking is generally not a goal that most of us should aim for; If anything, Americans need the opposite. But the team that developed the exoskeleton believes it will help people with mobility impairments, including the elderly or disabled.

“I believe that over the next decade we will see these ideas for personalizing assistance and effective wearable exoskeletons that will help many people overcome mobility problems or maintain their ability to lead active, independent, and meaningful lives,” said study author and bioengineering researcher Patrick Slade in the press release.

Since the exoskeleton is currently in the prototype stage, it will not reach a broader user base anytime soon. Additionally, it has only been tested on healthy adults in their mid-20s, so new testing would need to be done and adjustments made for people who actually need walking assistance.

The team also plans to develop iterations that will help improve wearer balance and even reduce joint pain. They are optimistic about the potential of their device. “I really think this technology will help a lot of people,” Collins said.

Credit: Stanford University/Kurt Hickman