AI wheelchair safety add-on
Help wheelchair users notice obstacles sooner.
CAREC clips onto an electric wheelchair, runs obstacle detection on-device, and warns the user with simple sound cues before nearby objects become a collision risk.
CAREC is an open-source prototype in validation. It is not a certified medical device and does not replace caregiver supervision or professional clinical judgment.
CAREC
Forward safety monitor
Latency
164 ms
Battery
87%
Mode
Offline
BLE
Connected
Caregiver event
Warning zone detected ahead. Slow audio cue active. No video uploaded.
Indoor mobility needs extra awareness without taking control away.
Powered wheelchairs are already safety-critical systems. CAREC focuses on adding obstacle awareness while preserving the original controls, user agency, and caregiver workflows.
Distance judgment
Young wheelchair users can struggle to judge how close furniture, walls, or people are while moving indoors.
Caregiver load
Parents, aides, and therapists need quick confidence that the safety layer is active without hovering over every movement.
Hardware limits
A practical add-on must avoid modifying the wheelchair, sending video to the cloud, or depending on WiFi for core alerts.
Clip on the module. Detect the path. Alert before contact.
The core loop is intentionally simple: watch the forward field of view, classify proximity, and turn that result into audio cues the user can understand quickly.
Step 1
Clip on CAREC
Step 2
Detect the path
Step 3
Warn the user
A practical edge-AI safety loop for real rooms.
CAREC combines local computer vision, deterministic alert zones, Bluetooth status, and open engineering documentation.
On-device AI
Three alert zones
Caregiver app
Privacy-first design
Open-source build
Smart-home ready
See the wheelchair safety concept in motion.
The demo shows the concept as a user-facing assistive layer: the system observes the path, classifies risk, and communicates with simple feedback.
Designed for homes, classrooms, therapy rooms, and clinics.
The goal is a non-invasive safety layer that can be explained quickly to users, families, therapists, doctors, and accessibility researchers.
Useful context for every person around the wheelchair user.
CAREC keeps the immediate alert simple while making technical status and history available to caregivers and reviewers.
Wheelchair users
Caregivers
Therapists
Researchers
Three distance states. One clear cue system.
The user does not need to read a dashboard while driving. Proximity is reduced to distinct audio and visual states.
Clear
100 cm+
No beep
Warning
60-100 cm
Slow beep
Critical
0-60 cm
Fast beep
It warns. It does not take over.
The project is intentionally scoped as a passive assistive layer. That boundary matters for user trust, caregiver review, and engineering validation.
CAREC warns but never drives, brakes, or overrides the wheelchair.
Original controls and caregiver supervision remain unchanged.
Core alerts work without internet access.
No cloud video is required for the safety loop.
The clip-on mount is designed to be removable.
Current status is prototype validation, not certified medical-device deployment.
Built as an inspectable embedded systems project.
The public project includes firmware architecture, validation goals, and implementation notes for contributors and reviewers.
Alert latency target
Under 200 ms
Runtime target
50+ hours
Core mode
Offline
Mounting
Non-invasive clip-on
Event data
Zone and timestamp
License
MIT open source
Common questions about CAREC.
Clear boundaries make the project easier to evaluate for caregivers, clinicians, and engineers.