Google Research

Sleep-wake Detection With a Contactless, Bedside Radar Sleep Sensing System

  • Michael Dixon
  • Logan Schneider
  • Jeffrey Yu
  • Jonathan Hsu
  • Anupam Pathak
  • D Shin
  • Reena Singhal Lee
  • Mark Rajan Malhotra
  • Ken Mixter
  • Mike McConnell
  • James Taylor
  • Shwetak Patel
Google (2021)


Sleep constitutes nearly ⅓ of the human lifespan, yet most individuals are unaware of precisely how much or how well they’re sleeping. With low-energy radar technology, integrated into the new second-generation Nest Hub device, users can access a contactless, bedside sleep-sensing system. Radar-based detection of sub-centimeter body movements enables the passive monitoring of sleep patterns with relative ease (e.g., no need to remember to charge the device or turn it on) and without the need for cameras, microphones, or physical contact with the user. Moreover, privacy-preserving, on-device processing of the raw sensor data is employed, so only the results of the algorithm (e.g., awake or asleep) are securely uploaded and provided to the user.

This paper provides a detailed understanding of the capabilities of the second-generation Nest Hub’s Sleep Sensing feature, including algorithm development and validation. In brief, the deep learning algorithm, when compared to gold-standard clinical sleep assessment, achieved overall epoch-by-epoch sleep-wake accuracy of 87% in healthy sleepers: correctly detecting 96% of sleep epochs and 55% of wake epochs. This accuracy is comparable to published results for other clinical- and consumer-grade devices.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work