Sleep Robotics
Sleep plays a fundamental role in health and well-being. Bad sleep hygiene, sleep deprivation, and sleep disorders increase risk of cardiovascular diseases and have a negative impact on mood, cognitive performance, and motor function. The vision of the Somnomat project is to develop autonomous robotic platforms that are able to monitor the users during sleep and to interact with them to improve their sleep and overall quality of life.
Contact
Poor sleep quality affects approximately 30% of the global population. In our lab, we develop novel, non-pharmaceutical interventions aimed at improving sleep quality and treating specific sleep disorders.
One example is vestibular stimulation, which modulates brain regions involved in sleep regulation – such as the thalamus and brainstem – to promote relaxation and improve overall sleep quality.
Sleep apnea is another main research focus. Traditional treatments like CPAP often suffer from low adherence. To address this, we are developing user-friendly interventions, such as controlled position adjustments that shift users from supine to lateral positions to help keep their airways open.
Across all our projects, we integrate non-obtrusive real-time sensors to monitor sleep, detect events during the night and deliver closed-loop interventions.
Interested in joining our team and working on future sleep tech? Get in touch with Alex Breuss.
Subprojects:
Effects of Vestibular Stimulation on Sleep
Within this project we aim to gain a deeper scientific knowledge about the impact of vestibular stimulation on sleep onset and sleep quality. Our findings build the base for developing new treatment methods to improve sleep quality and may offer new non-pharmacological therapeutic approaches for various patient populations.
More about:
Treatment of Rhythmic Movement Disorders (Past research project)
Effects of Vestibular Stimulation on Sleep in Elderly (Past research project)
Controlled Positional Therapy
Roughly one third of the general population is affected by an intermittent partial or complete obstruction of the upper airways during the night. This is most often caused by the physiological reduced muscle tone during sleep and mainly present in supine position. We have developed two specialized robotic beds for the treatment of habitual snoring and positional obstructive sleep apnea that detect airway obstructions and trigger position changes.
More about:
Controlled positional therapy for the treatment of sleep-related breathing disorders
Controlled positional therapy to reduce snoring (Past research project)
Unobtrusive Sensing for Monitoring Sleep and Health Parameters
Using unobtrusive sensors directly integrated into the bed, we monitor physiological signals like body position, breathing, and heart rate. The goal is to use sensors that do not influence the comfort of the user negatively or cause any privacy concerns – while still allowing us to estimate the sleep efficiency of the users as well as to monitor the overall health. We experiment with sensorized textiles, bioradar sensors, and wearable sensors.
More about:
Unobtrusive Sensing for Monitoring Sleep and Health Parameters
AI-based Real-Time Sleep Decoding and Closed-Loop Intervention from Sparse Wearable EEG
Sleep is essential for physical health, cognitive function, and overall well-being. Yet most advanced sleep foundation models are still designed for retrospective, offline analysis in data-rich clinical settings. We build SleepLoopFM, a real-time sleep staging AI model to bring this level of analysis into the home.Traditional sleep analysis often depends on multichannel polysomnography. Home devices do not have that luxury. Consumer-grade headbands typically provide only sparse EEG, creating a major gap between clinical sleep models and real-world deployment. SleepLoopFM is designed specifically for this sparse-signal setting.
More about:
AI-based Real-Time SleepDecodingand Closed-Loop Intervention from Sparse Wearable EEG