November 24, 2021

Stanford's Smart Cane Helps Visually Impaired Individuals Navigate Better

from hackster.io

Stanford University researchers developed a smart cane made of tools from autonomous vehicles that helps visually impaired individuals safely navigate through their environment. It allows users to detect and identify obstacles, move around objects, and follow indoor and outdoor routes. The affordable robotic cane only costs $400, weighs three pounds, can be built from home, and runs on open source software.

Other research sensor canes are generally more expensive and heavy, weighing up to 50 pounds while costing $6,000. Sensor canes on the market, however, can only detect objects in front of the user. The team hopes their device can become a useful solution for 250 million people worldwide suffering from visual impairment.

Overall, the augmented cane features a LIDAR sensor, GPS, accelerometers, magnetometers, and gyroscopes to track the user’s speed, position, direction, etc. It also uses AI-based finding and robotics algorithms, such as simultaneous localization and mapping (SLAM) and visual servoing, moving the user toward an object in an image.

Meanwhile, a motorized, omnidirectional wheel sits atop the cane to ensure it constantly touches the ground. The wheel tugs and nudges left and right around obstacles to efficiently guide a user. With a built-in GPS, the cane enables the user to navigate to a specific location, like a store in the mall or coffee shop.

Sighted and visually impaired volunteers tested the augmented cane in real-world environments. They completed everyday navigational challenges, including hallways, avoiding obstacles, and traversing outdoor waypoints. “We want the humans to be in control but provide them with the right level of gentle guidance to get them where they want to go as safely and efficiently as possible,” says Mykel Kochenderfer, the study’s senior author.

Participants with visual impairments walked 20% faster with this device compared to the white cane. Sighted people who were blindfolded increased their speed by more than a third. As a result, this device could significantly improve a user’s quality of life.

The team says the project is completely open-source. “We wanted to optimize this project for ease of replication and cost. Anyone can go and download all the code, bill of materials, and electronic schematics, all for free,” Kochenderfer adds.

The researchers plan to refine the device and develop a model that uses a smartphone as the processor. Doing so could make it more affordable, improve functionality, and broaden access to the technology.