Patent Application
20210355663
The present invention relates to a fitting, in particular an outlet fitting, for a sanitary installation, a fitting arrangement having a fitting according to the invention, and a method for controlling a fitting according to the invention.
In sanitary engineering, components used to change and control material flows (e.g. fluids, i.e. liquids or gases) are referred to as fittings. They are used in particular on pipelines and boilers. So-called outlet fittings are also known in the household as faucets, shower or bathtub inlet fittings, depending on the application. Combined hot and cold water outlet valves are often called mixer taps. Depending on where they are used, fittings are more specifically referred to as kitchen faucets or bathroom faucets, for example. A fitting typically includes an operating unit and/or a control unit and a sanitary element controllable by the control unit, such as a pipe with a valve that is used to regulate the flow of a fluid.
It is known to operate sanitary systems by means of electronic control units. It is desirable that the respective user can trigger predetermined functions without contact. Infrared sensors or capacitive sensors are often used for this purpose, which react to the user's approach to the sensor. Recently, however, voice-controlled faucets have also become available, which can be controlled by voice command using voice assistants such as Amazon Alexa, Apple Siri or Google Assistant. This means that the user always has two hands free and does not have to touch any controls, which has practical and hygienic advantages. However, in noisy environments (such as public restrooms), voice recognition is often impaired, making voice control unreliable. There is also a need for improved automatic support in the use of fittings in very different applications. In particular, it would be desirable if the fitting could automatically recognize and trigger or execute a variety of different actions desired by the user.
It is therefore an object of the present invention to provide a fitting for a sanitary installation which automatically assists a user in using the fitting, so that the fitting can be controlled in particular without contact. Moreover, such a fitting should be able to be used in many different fields of application. According to the invention, this object is solved by the fitting defined in claim 1.
It is a further object of the present invention to disclose a fitting arrangement comprising a sanitary installation and a fitting. Such a fitting arrangement is disclosed in claim 13.
It is a further object of the present invention to propose a method which automatically assists a user in the use of a fitting, so that the fitting can be controlled in particular without contact. According to the invention, this object is solved by the method proposed in claim 15.
Specific embodiment variants of the present invention are given in the dependent claims.
A fitting for a sanitary installation according to the invention comprises a control unit and a sanitary element controllable with the control unit. In addition, the fitting has at least one imaging sensor. The control unit is adapted to trigger an action of the sanitary element depending on an object recognition based on at least one output signal from the at least one imaging sensor. The imaging sensor is used to detect a scene in a spatial area of the fitting, for example in an outlet region of the fitting.
For example, the fitting may be a faucet, a shower or bathtub inlet fitting, but it may also be a part (e.g., a spout) of a soap, lotion, or disinfectant dispenser, or a part (e.g., an air nozzle) of a hand or hair dryer.
In one embodiment variant of the fitting, the at least one imaging sensor is a 2D or 3D/stereo (optical) camera (for the visible light range), a thermal imaging camera (for the infrared/IR light range), an ultrasonic sensor, a radar sensor, or a laser distance measurement sensor, in particular a LIDAR (=light detection and ranging) or ToF (=time of flight) sensor or a laser scanner, or a combination of said sensor types. If only one sensor (element) is used to detect a scene in a spatial region of the fitting, it is particularly adapted to successively (and periodically) scan (i.e., spatially scan) the spatial region, e.g., by changing the direction in which a sensor signal is picked up over time, thereby capturing a two-dimensional (or three-dimensional) image of the spatial region (consisting of multiple pixels or voxels). For example, a combination of a 2D optical camera and a ToF sensor (which can be oriented in different spatial directions) can also be used for additional distance measurement. In particular, a plurality of ToF sensors can also be used to determine multiple distances in different directions simultaneously.
In a further embodiment variant, the fitting additionally comprises an illumination unit for illuminating objects, wherein the illumination unit comprises in particular one or more LEDs (light emitting diodes) or laser diodes or an ultraviolet/UV or infrared/IR light source.
In a further embodiment variant, the fitting additionally comprises an image processing unit to perform the object recognition. The image processing unit may comprise, for example, a microprocessor/controller (MPU/MCU) or signal processor (DSP), wherein these are programmable. Alternatively (or additionally), the image processing unit may comprise application-specific hardware, such as an ASIC or FGPA (field-programmable gate array). The image processing unit may also be implemented as part of the control unit. The image processing unit and/or the control unit may be commonly referred to as the processor(s) of the fitting.
In a further embodiment variant, the fitting additionally comprises a communication unit for sending the at least one output signal from the at least one imaging sensor to a remote image processing unit, e.g. a server, in particular in the cloud, for object recognition and for receiving a result of the object recognition.
In a further embodiment variant of the fitting, the image processing unit is adapted to perform object recognition by means of a neural net/network, in particular by means of a neural net/network trained before commissioning (e.g. by the manufacturer) of the fitting.
In a further embodiment variant of the fitting, the neural net/network is a self-learning neural net/network, wherein in particular so-called “reinforced learning” can be executed. In this case, the user provides feedback to the control unit or the image processing unit or the unit performing the object recognition, with which the user indicates whether the action triggered by the control unit was correct or not. The feedback from the user can be picked up by the imaging sensor, for example, in that the user covers the imaging sensor with his hand for a short time if the triggered action was incorrect.
In a further embodiment variant, the fitting additionally comprises a microphone with which the user can, in particular provide feedback to the control unit, wherein the control unit is adapted, in particular to detect clapping and/or whistling noises based on an output signal from the microphone.
In a further embodiment variant of the fitting, the image processing unit is adapted to perform an object classification as part of the object recognition in order to assign an object to a specific class from a plurality of predefined classes. In this context, each object class comprises a specific type of object.
In a further embodiment variant of the fitting, the object classification can be used to recognize different classes of kitchen utensils, such as plates, glasses, cups, cutlery, cooking pots, pans, etc., or of limbs, such as hands (including individual fingers), arms, feet or legs, of a user of the fitting, or of cleaning utensils, such as a cleaning brush, a cleaning sponge, steel wool or a cleaning cloth.
In a further embodiment variant of the fitting, the image processing unit is adapted to determine at least one property of an object, such as transparency, color, size, or degree of contamination.
In a further embodiment variant of the fitting, the image processing unit is adapted to determine a position, in particular relative to a reference position, and/or a movement of an object.
In a further embodiment variant of the fitting, the control unit is adapted to trigger a specific action of the sanitary element depending on the object classification and/or the property of the object and/or the position of the object and/or the movement of the object.
In a further embodiment variant of the fitting, one or more of the following actions can be triggered:
Fluids are understood to be gases (e.g. air or ozone), liquids (e.g. water or disinfectant) and/or gas/liquid mixtures (sparkling water). Instead of fluids, the fitting may be adapted to dispense fine-grained solids (such as powder or sand). However, in the context of the present invention, fluids may also include viscous substances such as soaps, lotions, creams and pastes.
According to a further aspect of the present invention, a fitting arrangement comprises a sanitary installation and a fitting according to one of the embodiments listed above, wherein the (at least one) imaging sensor is arranged in such a way that an inlet region, in particular for dispensing a fluid, and/or an outlet region, in particular for leading away the dispensed fluid, of the fitting is/are detectable by the (at least one) imaging sensor.
In one embodiment variant of the fixture arrangement, the sanitary installation is a sink or washtub, bidet, shower, bathtub, soap dispenser, lotion dispenser, disinfectant dispenser, hand dryer, hair dryer, toilet, shower toilet, urinal, or washing facility.
According to another aspect of the present invention, a method for triggering an action of a sanitary element of a fitting according to any of the above embodiments comprises the following steps:
In one embodiment variant of the method, the scene is illuminated by means of an illumination unit, in particular one or more LEDs or laser diodes or a UV or IR light source.
In a further embodiment variant of the method, the scene recorded by the at least one imaging sensor is sent as an output of the at least one imaging sensor to a remote image processing unit, e.g., a server, in particular in the cloud (i.e., IT infrastructure made available, for example, over the Internet), for object recognition, and a result of the object recognition is received by the remote image processing unit.
In a further embodiment variant of the method, the object recognition is performed by means of a neural net/network, in particular by means of a neural net/network trained before the fitting is put into operation (e.g. by the manufacturer).
In another embodiment of the method, an object classification is performed as part of the object recognition process to assign an object to a particular class from a plurality of predefined classes.
In a further embodiment variant of the method, different classes of kitchen utensils, such as plates, glasses, cups, cutlery, cooking pots, pans, etc., or of limbs, such as hands (including individual fingers), arm, feet and legs, of a user of the fitting or of cleaning utensils, such as a cleaning brush, a cleaning sponge, steel wool or a cleaning cloth, are recognized by means of the object classification.
In a further embodiment variant of the method, at least one property of an object, such as transparency, color, size or degree of soiling, is determined.
In a further embodiment variant of the method, a position, in particular relative to a reference position, and/or a movement of an object is determined.
In a further embodiment variant of the method, a specific action of the sanitary element is triggered depending on the object classification and/or the property of the object and/or the position of the object and/or the movement of the object.
In a further embodiment variant of the method, the action comprises at least one of the following:
In a further embodiment variant, the method additionally comprises at least one of the following steps:
It should be noted that combinations of the above embodiment variants are possible, which in turn lead to more specific embodiments of the present invention.
Non-limiting exemplary embodiments of the present invention are explained in further detail below with reference to figures, wherein:
In the figures, the same reference numerals stand for the same elements.
In order to explain the basic principle of the present invention,
The advantage of object recognition is now that different actions can be performed depending on the detected object and its movement(s). For example, the flow rate of water can be controlled by the imaging sensor 5 depending on the distance of the object 7 (e.g., the hands)—e.g., the further away the hands are from the camera 5, the more water is dispensed per unit time. In addition, for example, in the case of a mixing faucet, i.e., a combined hot- and cold-water outlet valve, the water temperature can be adjusted depending on a movement of the object 7, for example—e.g., a movement/shift of the hands 7 to the right leads to colder water and a movement/shift of the hands 7 to the left leads to warmer water.
For example, as part of object recognition, object classification is performed to assign an object to a particular class from a variety of predefined classes. Each object class comprises a certain type of object, such as kitchen utensils (e.g. plates, glasses, cups, cutlery, cooking pots, pans, etc.) or limbs (e.g. hands, fingers, arms, feet or legs) of a user of the fitting or cleaning utensils (e.g. cleaning brush, cleaning sponge, steel wool or cleaning cloth). Depending on the detected object, various actions of the sanitary element can then be triggered, i.e., each object (or each type of object) is assigned a specific action.
Object recognition can be carried out in particular by means of a neural net or network. The neural network was trained for this purpose before the fitting was put into operation (e.g. by the manufacturer of the fitting). This means that the settings of the neural network were determined e.g. with the help of training data. The training data for training the neural network consist of output signals/data of the imaging sensor 5 as well as an assignment to a specified (known) object (called “data labeling” in the field of machine learning). The training of the neural network is performed offline as mentioned above and is typically carried out using powerful computers (e.g. in the cloud) and specialized software tools. Local object recognition (e.g., by “inference” using the neural network) at the fitting has the advantage that the recorded images do not have to be transmitted to an external server, which is preferred especially for data protection reasons as well as to preserve privacy. It is conceivable that the user records training data for new objects to be recognized by means of the imaging sensor and transmits these to an (automatic) service, which sends back to the user new settings (e.g. in the form of a “TensorFlow Lite” model) for the neural network or new firmware for object recognition or classification.
In
In
In
In
Analogous to the embodiments for the application for a shower, the fitting according to the invention can also be used for a hand or hair dryer mounted on a wall, wherein the air flow can be switched on and off and the temperature and strength (as well as direction) can be regulated depending on the object recognition.
If a certain (new, previously unknown) object is to be recognized, corresponding images (or film or videos) can be taken by the user as training data with the camera of the fitting (or with another camera, e.g. of a smartphone). This data can be transmitted to a server, as mentioned above, which then returns an appropriately trained neural network to the fitting (e.g., in the form of a “TensorFlow Lite” model). The assignment of a certain object (or a gesture concerning this object) to a certain action can be done or changed by the user himself, for example by means of a web app or an app on his smartphone.
Further areas of application of the fitting according to the invention are conceivable, for example, in beverage dispensers or automatic washing systems. Depending on the detected container (large, small, transparent, of a certain color), different beverages are dispensed in the beverage vending machines, e.g. pure water, sparkling water, tea, coffee, soup, etc.
The proposed fitting can be used both in the private sector and in public sanitary facilities, although for the private sector application a much higher degree of personalization is possible, as well as a greater variety of different actions. For the public sector, however, the proposed fitting also has the advantage that an installer, plumber or service technician can configure the system without a control element simply by using the built-in imaging sensor (e.g. camera), and does not need a special configuration/programming device to do so.
| Number | Date | Country | Kind |
|---|---|---|---|
| 00602/20 | May 2020 | CH | national |
