While NASA is working to make drones quieter, one researcher at the University of Nevada, Reno, is using its noise to benefit blind athletes.
Eelke Folmer, an associate professor of computer science and the head of UNR’s Human Plus Lab, has built a prototype drone system that guides blind runners around a track, allowing them to exercise independently without a sighted guide. Equipped with two cameras—a downward-facing one that follows the lines on a track and a separate camera that focuses on a marker on the runner’s shirt—Folmer’s quadcopter flies at eye level, about 10 feet ahead of a runner, guiding them by sound. If the runner speeds up or slows down, the drone adjusts its own speed.
Folmer says he hasn’t been able to test it outdoors yet because the university is so close to the Reno airport it is subject to FAA regulations on drones. He is currently seeking permission from the airport’s radio tower to override this rule. “We’ve done some very simple trials inside just following a straight line and it seemed to work,” Folmer says. “I’m not sure how it’s going to be on a real oval where you also have to go through a turn.”
Assistive devices for navigation and communication abound, but relatively few technologies aim to help the visually impaired tackle fitness and obesity, the latter of which disproportionately impacts the disabled community. About one in three able-bodied adults in the U.S. are considered obese or extremely obese according to research published in the American Journal of Preventive Medicine, but among disabled adults, that rate rises to one in two. For those with mobility, navigation, or vision impairments, doing vigorous activities—the kind that actually burn calories and build muscle—can be tough.
Another of Folmer’s projects focuses specifically on increasing accessibility to moderate and vigorous exercise. VI Fit is a series of video-less video games created for blind children, though able-bodied users can play along. Developed for the PC platform, each of the three fitness games in the VI Fit series uses a Nintendo Wii controller to track motion, and guides players through bowling, tennis, or whack-a-mole style play using audio and tactile cues. The games are free and two use open-source code, allowing developers to tweak the games as they see fit or create new ones.
“Most of the accessibility research [for the blind] focuses more on things like screen readers and making the Web more accessible,” Folmer says. “The community of blind people still has major problems pertaining to health, socialization, and quality of life. It would be more helpful for this demographic if we research how technology can improve these issues.”
A few other projects also aim to make it easier for blind people to get fit. Kyle Rector, a graduate computer science and engineering student at the University of Washington, is the creator of Eyes-Free Yoga, a system that uses a Microsoft Kinect to guide visually impaired users through yoga workouts. For standing poses, users get step-by-step verbal instructions and real-time feedback on how they can adjust their bodies for proper form. For sitting or lying poses—positions that are more difficult for the Kinect’s computer vision system to follow—users rely on audio instructions only.
“My system isn’t necessarily intended to be used as the only exercise tool for the rest of their lives, but it is a way to kind of propel [blind users] to do more activity,” Rector says, adding that in testing, several users expressed interest in adding different exercise regimens since beginning Eyes-Free Yoga. “They use it as a starting point.”
The big new idea for making self-driving cars that can go anywhere
The mainstream approach to driverless cars is slow and difficult. These startups think going all-in on AI will get there faster.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.