Project Info
Inspiration
We noticed that some people are either unable to navigate or move around their spaces easily. We wanted to empower these people by giving them the tools to embody a robot using brain control.
What it does
It allows users to control a robot like spot using their brain signals.
How we built it
eeg part wrote a visual entrainment script on psychopy (using python) wrote a real-time eeg processing script that takes in continuous voltage data from 8 channels, cleans/filters it with butterworth and independent component analysis, complete fast fourier transform, and wrote an algorithm to classify which frequency had the largest increase in power within the past five seconds.
Challenges we ran into
visual entrainment script is supposed to have four images flashing at different frequencies but both psychopy and react cannot achieve this. should've tried matlab. real-time eeg processing is difficult to debug as it requires constant streaming of data and using multiple functions at the same time.
Accomplishments we're proud of
debugging nonstop for several hours + finally understanding most of lsl
What we learned
need to conduct a full literature review for eeg projects in a short amount of time + understood more in depth about real-time processing
BrainRobotConnect
Robot control using a brain computer interface
Folder Directory
EEG: contains files for the brain-computer interfaceclient-controller: contains sample code to control Spot using a BCIhackathon-spot-control-fork: contains the forked repository (with our modifications) that allow us to control Spot using HTTPraspberry-pi: some code that we wrote for a Raspberry Pi while evaluating different optionsserver: NextJS server used to connect the client controller to the Spot receiver code
Analysis
View
Metric
- 16
- 3
- 3
- 2
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
- CSSIn code
- JavaScriptIn code
- Next.jsIn code
- PythonIn code
- ReactIn code
- SupabaseIn code
- Tailwind CSSIn code
7 of 7 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
23 KB
Source files
15
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
LukeKulm/BrainRobotConnect
32 files · 2.3 MB · @ 8ed3188
Structure
API & routing
12 files · 38%Request entry points: routes, handlers and controllers.
Application logic
9 files · 28%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
- Python52%
- JavaScript30%
- Markdown10%
- YAML5%
- CSS3%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
server/package.json
npm · 7- @supabase/supabase-js
- next
- react
- react-dom
- +3 more
hackathon-spot-control-fork/requirements.txt
pypi · 1- supabase
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
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.