Google's frontier research organization spanning machine learning, health, and sensing.
Google researchers introduce SensorWM, a machine learning framework that converts passive smartwatch biometrics into a modifiable coachable health age and uses an action-conditioned world model to simulate personalized 12-week what-if habit trajectories. The framework extends to routine blood biomarkers for early cardiovascular-kidney-metabolic (CKM) risk tracking, grounding personalized coaching in validated clinical prognostics.
Google Research and the Stanford Accelerator for Learning launched Polar Peaks, an interactive quest for students aged 11-14 that teaches AI literacy through mapping neurons, practicing data cleaning and model testing while stressing human oversight. Companion teacher training modules are available via the Google AI Educator Series.
Google Research expanded its building-level rooftop reflectivity dataset to more than 50 global cities, released through a new high-resolution Heat Resilience Earth Engine App to help urban planners deploy cool-roof solutions against extreme heat. The work is backed by a Nature Communications paper and an interactive data portal.
Google researchers establish a positive association between hard-braking events (HBEs) collected via Android Auto and actual road segment crash rates, showing that segments with more HBEs carry significantly higher crash risk. The work proposes HBEs as leading indicators for road safety assessment, addressing the lagging and statistically sparse nature of police-reported crash data.