Abstract: Disclosed are systems and techniques for determining biometrics of a user of a bed system based on force data. A bed system can include a support element having at least one leg, at least one force sensor of the at least one leg, the force sensor being configured to sense a force applied to the bed system or the leg, and a controller. The controller can receive at least one force data-stream from the at least one force sensor, the at least one force data-stream representing a force sensed by the force sensor, determine a biometric parameter of a user on the bed system at predetermined time intervals based on processing the at least one force data-stream, generate an aggregate biometric parameter of the user based on aggregating the biometric parameters for the predetermined time intervals, and return the aggregate biometric parameter of the user.

Abstract: Disclosed herein are systems, methods, and techniques for detecting presence of leaks and/or holes in bed systems. An example system can include a bed system having a mattress to support a user laying on the bed system, at least one sensor that can be configured to collect pressure data on the bed system, and a computer system having a processor and memory. The computer system can be configured to: receive the pressure data that is collected by the at least one sensor, provide, as input, the pressure data to a model to detect presence of a leak in the mattress of the bed system based at least in part on the pressure data, receive, as output from the model, data indicating the detected presence of a leak in the mattress, and return a message indicating the detected presence of a leak in the mattress.

Abstract: The disclosed technology provides a bed system for detecting bed presence of a user, having a bed with at least one temperature sensor and a computer system that performs operations including: receiving, from the at least one temperature sensor, temperature signals collected at the bed, providing the temperature signals as input to a bed presence classifier, receiving, from the bed presence classifier, output of a bed presence indication, and returning the bed presence indication. The computer system can also receive, from at least one motion sensor of the bed, pressure signals, and the bed presence classifier can generate the bed presence indication based on the pressure signals and the temperature signals. The bed presence indication can be provided, to a data pipeline, which can include at least one classifier that was trained to determine at least one of user sleep metrics or user health metrics.

Abstract: A bed system detects and prevents user sleepwalking events. The system includes a sensor and computer system to receive data from the sensor during the user's sleep session, provide, as input to a sleep state classifier, a first portion of the data, the sleep state classifier using a machine learning model to determine the user's sleep states, receive, as output, a sleep state classification for the user, provide, as input to a bed exit detection classifier, a second portion of the sensor data, the bed exit detection classifier using a machine learning model to determine when the user exits the bed, receive, as output, a bed exit detection classification for the user, determine whether (i) the sleep state classification satisfies a first threshold condition and (ii) the bed exit detection classification satisfies a second threshold condition, generate, based on the determination, a probability of a sleepwalking event for the user.