Harvard researchers are making robot exosuits that better support their users

We live in an age of personalized Amazon recommendations, Facebook news feeds, and Google search results. Why shouldn’t we have personalized robot exosuits as well? That’s the thinking driving a new project from the Wyss Institute for Biologically Inspired Engineering and Harvard University’s John A. Paulson School of Engineering and Applied Sciences. Researchers there have been working out how to personalize assistive soft robotic wearables so that they move in sync with the people they are intended to help.

“Previous fixed control strategies or parameter settings of many other wearable robotic devices can lead to high response variance between wearers,” postdoctoral researcher Ye Ding told Digital Trends. “Thus we developed a smart algorithm that can directly use wearer’s responses [in terms of] measured energy expenditure to quickly optimize for different individuals to improve walking economy.”

The idea of not just having a robot exosuit, but having a personalized robot exosuit may sound excessive. However, for people who require this technology, it could turn out to be a game-changer. Most of us take for granted the ability to easily walk around without having to think about the effort involved. But for people with physical impairments who need assistive technology to help them on a daily basis, an optimized exosuit can make a world of difference. The technology could also be useful in other scenarios, such as exosuits that are designed to help physically able people to increase their strength or walking abilities.

harvard robot exosuits harvardexosuit
Ye Ding/Harvard SEAS
Ye Ding/Harvard SEAS

“[Our] method aims to quickly establish the mapping between wearer’s energy expenditure with respect to the control parameters of soft exosuit by a using Bayesian optimization, which is an algorithm well suited to optimizing noisy performance signals with very limited data,” Ding continued. “In our study, we used this algorithm to configure peak and offset timings of the hip extension profile of our soft exosuit and achieved significant reduction.”

How significant? Enough that the technology reduced the amount of energy consumed as a result of performing actions by 17.4 percent in wearers, compared to that same person walking without an assistive wearable. In the future, the team wants to further optimize the technology so that it assists multiple joints — such as hip and ankle — at the same time.

Thanks to the researchers’ work, future robot exosuits should be a whole lot more efficient than current models.