Hair and Dust Recognition for Robot Vacuum Cleaners

Apr. 2024 – Dec. 2024  ·  Project Member / AI & Software Developer

LG Electronics, South Korea

TL;DR: On-device segmentation of hair and dust for a domestic robot vacuum, constrained to ≤5M parameters — ≥85% pixel accuracy at ≤10% false-positive rate, trained on a purpose-built 10K-image dataset.