Project Info
NVIDIA: Robo Prize (Jetson Dev kit per team member); TreeHacks Grand Prize | 3rd Place (iPhone 16 Pro per team member)
Portable Braille
Inspiration
Literacy level of Blind and Visually impaired community even in United States is lower than 10%. And the reason is simple - Braille (tactile text) is not affordable and not accessible today. I follow Haben Girma - the first deaf-blind person graduated Harvard Law school. She is a brilliant person, wrote books, influencer and advocates for people with disabilities rights. I saw how efficient she is in communications with people. However, she needs a special person who assists her by typing speech of her interlocutors, so it can be converted to Braille format and Haben can read it in tactile format. I believe that she could do even more if there is a device that could do handle it, keeping her communication private and without relying on assistance.
What it does
For visually impaired people the device allows users to read and write text on the phone privately, texting, surfing web, swiping Instagram, and of course learn and practice reading and writing. It is the first device that encourages blind users to improve their reading skills in most delightful ways - communication with loved ones and friends. Also device allows to "read" face expressions while talking to people, by face expression recognition using RayBan|Meta glasses and doing computing on the Jetson Orin Nano. It is the only solution today that doesn't require connection to internet and work even faster than BeMyEyes (powered by OpenAI). For deaf-blind users convert all speeches to text, and then converts it to tactile Braille and render in on the device, so user doesn't need an assistant.
How we built it
We 3d-printed an enclosure of the device on the 3d printer. Soldered Li-Po battery to battery-management-System module for correct charging/discharging and powered the microcontroller and Step-up boost DC-DC converter to power up braille module, which needs 200V for operating. Braille module gets data from microcontroller. There is a keypad of at least 6 buttons for typing braille combinations. Keypad also connected to the microcontroller. Microcontroller syncs with a phone over Bluetooth Low Energy. We hacked RayBan|Meta glasses in analog way to connect in to Jetson Orin Nano.
Challenges we ran into
Education Open
Accomplishments we're proud of
First really portable braille display that fits a pocket It encourages to practice reading Connected different platforms, even closed, to each other Allows blind and visually impaired individuals to receive and follow contemporary AI trends: not to listen but to read audio messages.
What we learned
how to power the hardware device with AI connect different platforms altogether still learning...
What's next
test the device with more users to collect more feedback explore if this project can transform to a Product
PortableBraille
Educational device that encourages young visually impaired people to learn and practice Braille in order to increase chances for future employment and expand general literacy level of the community.
Plan for designing and making the device:
- Collected data sheets of potential components
- Draw a schematics of the device
- Put all components on a breadboard and run the test firmware
- Choose electroni components to use
- Draw several sketches of the device itself, with Phone, in hands
- Make 3d-models of standard components
- Asseble all standard components in general assembly
- Model a boundry box of the device according to sketches
- Refine the 3d-model of the device
- Create a 3d-model of an enclosure of the divice in accordance with its 3d-Model
- Convert parts to STL or 3dmf format
- Slice parts and send to 3d-print
- Put all the components inside the enclosure and if somethind doesn't fit, andjust the model and reprint.
- Improve firmware
- Test with user.
Analysis
View
Metric
- 15
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CIn code
- C++In code
2 of 2 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
2.1 KB
Source files
3
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
Adil-Jussupov/PortableBraille
83 files · 186.4 MB · @ a40e790
Structure
Application logic
56 files · 67%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Markdown48%
- C++45%
- C8%
Share of indexed source by file size. Binary and vendored files are excluded.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.