Access-H20: Sensor-driven Smart Faucet

Conventionally, a bathroom faucet includes a hot and cold-water knob used to control flow of water through the faucet, which is utilized for hand washing, face washing, rinsing after brushing, etc. However, existing faucets are inconvenient to use for purposes other than conventional hand washing, unhygienic, and result in wasting large amounts of water. Existing faucets make it difficult for individuals with cervical spinal cord injury (SCI) to carry out basic activities of daily living (ADLs), such as drinking, rinsing their mouths, and washing their faces.

To address these challenges, Nasoni Inc. develop the new faucet, Access H2OTM faucet, to address these challenges. During the Phase I study from 2022-2023, we achieved the following objectives: 1) Successfully designing and producing a prototype of the Access H2O faucet that met input specifications in bench testing, and 2) Developing control algorithms using sensor-based inputs successfully allowed both control and SCI subjects to accurately access desired water. The clinical feasibility study showed that the faucet could improve water access for SCI subjects and improve their ADLs. SCI subjects showed a strong preference for Access-H2O faucets compared to traditional methods.

Before proceeding with commercialization, it is necessary to optimize the operational functions of the prototype. In the Phase II study, the engineering team has planned to enhance the prototype's faucet form factor design and sensors based on the findings from the Phase I study. These enhancements include: 1) optimizing the form factor and nozzle water delivery, 2) refining the sensor \& display components, and 3) expanding sensor integration capabilities. Also, the team has improved the water control mechanisms established in Phase I by integrating Access-H2O faucet intelligent algorithms and developing a supporting digital platform with a mobile app to support product efficacy, usability, and field maintenance.

Specifically, Phase II evaluates improvements in faucet form factor, sensor placement, manufacturing-ready hardware, and interaction modalities, all informed by Phase I user feedback and clinical observations. Accordingly, the objective of this Phase II study is to assess system refinements that impact real-world independence and usability beyond initial feasibility. The Phase II study comprises two sets of studies conducted in Year 1 and Year 2 separately. They were labelled as the Year 1 testing study and the Year 2 testing study.

The Year 1 testing was conducted in a clinical setting. The specific aims of the feasibility assessment were to evaluate the feasibility and usability of the refined Access-H2O™ faucet system-controlled via voice commands, hand motion, and a wireless remote-to drink water (drinking), rinse the face (grooming), or wash hair (washing; optional).

The Year 2 testing was conducted in each participant's home. The specific aims of the feasibility assessment were to evaluate whether participants could use the refined Access-H2O™ faucet system-controlled via voice commands, hand motion, and a wireless remote-to drink water (drinking), rinse their face (grooming), or wash their hair (optional) in a home setting.

Besides the unique water floor technology, the Access-H2O™ faucet system equips hand-free methods for water access and water temperature control:

• Voice control via keyword recognition using Alexa integration
• Motion control using a time-of-flight (ToF) proximity sensor
• Wireless remote control with tactile buttons (newly introduced in Phase II)
• Raised spout (+5 cm) and re-angled water stream for seated face washing and hair rinsing
• Temperature control system using PID logic and a 40°C thermal safety cap

There are three control sensors: voice, motion, and remote controls. Voice recognition is enabled through integration with a pre-existing Amazon Alexa device using a custom Alexa Skill. Users activate the system by saying "Alexa" followed by predefined commands (e.g., "Faucet on" or "Turn on Grooming Mode") to control faucet operation, mode selection, and temperature hands-free. Motion detection is implemented using ToF proximity sensors mounted at the base of the faucet to detect hand motion to activate the faucet for water dispensing. A handheld wireless remote control that provides an alternative input method for operating the faucet with maximal flexibility in placement and use. The remote communicates with the faucet via Bluetooth and allows users to activate or deactivate water flow and select among predefined water delivery modes. The remote may be positioned on a nearby surface or affixed using hook-and-loop fasteners, allowing users to locate the control within comfortable reach. On the front of the control, three buttons labeled "F," "W," and "G" correspond to fountain, washing, and grooming, respectively.

In the Year 1 testing, a total of 18 subjects living with SCI, called SCI subjects, and 5 control subjects were recruited in an outpatient rehabilitation clinic. Controls without limitations in head, trunk, or arm movement were used to verify that all faucet functions operated correctly and that water was accessible for drinking, rinsing, and grooming. This preliminary assessment by the controls was conducted after installing the Access-H2OTM faucet in the rehabilitation clinic and before SCI subjects' participation.

The feasibility testing was conducted to test the faucet's voice, motion, and remote control sensors for SCI subjects' ADLs - drinking, grooming, or washing (optional). We sought answers to the following questions: 1) Can the test participants use voice, motion, and remote controls to activate the faucet to get their mouth to drink/hydrate? 2) Can the test participants use the three controls to rinse a quarter-sized area of soap partially or fully from their left or right cheek or 3) can the test participants use the three controls to wash a quarter soap in hairs.

In the Year 1 testing, all SCI subjects who relied on wheelchairs were seated in their own manual or power wheelchairs. The wheelchairs were positioned in front of a sink equipped with the Access-H2OTM faucet. Sufficient space was provided to accommodate the subjects' legs under the sink, ensuring standardized data collection. Then, the physical therapist who provided scripted instructions to each participant on how to turn on the faucet, and then turn off the faucet. During setup, the system was tested and calibrated to ensure proper operation. If any function did not meet the standard, manual adjustments were made as needed. For example, during setup, flow and spray angles for fountain mode and grooming mode can be customized by adjusting valve angles or water pressure to achieve the preferred water flow trajectory.

Once the system was ready, each SCI subject was asked to place his or her hand by the motion sensor (motion control), use a speech speaker (voice control), and push the remote control to activate water output modes for drinking, grooming, or washing. For example, to test eye gaze control, a subject looked at the right side of the eye gaze sensor to activate fountain mode for drinking and looked at the left side of the sensor to activate grooming mode for spray pattern flow to wash a quarter-sized area of soap from the left or right cheek. Each participant performed the same activity (drinking, grooming, or washing) and sensor controls (voice, motion, and remote) three times. For example, a subject used the voice control to activate fountain mode for drinking and repeated the procedure three times. A total of 27 tests were conducted (3 sensors x 3 modes x 3 repetitions). Each activity was recorded "complete," "partially complete," or "unable to complete." The investigators also recorded the time it took for each subject to complete each activity.

In the Year 2 study, the feasibility of the smart faucet was evaluated in each participant's residential bathroom. The goal was for participants to incorporate the faucet into their daily routines in a real-world setting. A total of 10 control participants without SCI and 7 individuals with SCI met the recruitment criteria, were enrolled, and completed the testing procedures. We conducted home visits for participants who met the recruitment criteria to assess whether the sink was suitable for faucet installation. If the sink was deemed suitable, written informed consent was obtained, and the faucet installation was scheduled. On the day of installation in each participant's bathroom, a licensed plumber installed the faucet. Following installation, a trained research associate performed testing and calibration of the device and provided instructions for trial preparation, including mobile app setup, usage, and operation of the faucet. The mobile app was used to automatically record user interactions and water flow settings. Each SCI participant then used the faucet for activities of daily living (ADLs) over a 14-day period, including drinking water (at least five times per day), face washing (morning and night), hand washing (morning and night), and hair washing (no set frequency). Participants were provided with a log sheet to record whether each activity was "complete" or "not complete." If an activity was skipped, participants were required to document the reason (e.g., "too difficult," "forgot," or "no need today"). On the 15th day of the trial, the plumber uninstalled the faucet, and the research associate collected the log sheet and a user-reported satisfaction survey.