Ankh - Navigation and Obstacle Avoidance for the Visually Impaired

CSEF · 2023 Computational Systems & Analysis Honorable_mention Award

Overview

The existing navigational systems for severely visually-impaired individuals are highly inadequate and under-equipped for an urban environment. At present, the only mainstream tool available for this purpose is the white cane, which has limited range and ability to pass on important information about the user's immediate environment back to the user. These risks can be completely eliminated with use of machine-learning, paired with computer vision and SONAR (Sound Navigation and Ranging) for path creation and navigation. Ankh is a portable and stand-alone device for the visually impaired, allowing safe navigation of an individual in an urban environment. Ultrasonic sensors and a camera, positioned in front of the user, pass real time data to a Raspberry Pi microprocessor worn by the user. This data is parsed through a series of machine-learning algorithms that detect paths, obstacles, pedestrian crossings and changes in elevation. Information from these algorithms is then provided to the user through bone conduction headphones. Ankh was trained on over 59,000 images, of which over 43,000 were captured by hand. Testing algorithmically, Ankh has an accuracy of over 99%, with 58,880 of the images predicted correctly by the models. Additionally, real-world testing showed that Ankh was able to safely guide users 100% of the time using ultrasonic sensors alongside machine-learning. This data suggests that Ankh is not only a viable tool for visually impaired individuals, but one that is much better equipped for navigation in a rapidly changing environment. This has far-fetching practical applicability in society globally.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

  • Category Award: HM

Competition history

  • CSEF 2023 Computational Systems & Analysis · Entry S0851

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google