A personal care device with improved location tracking using distance sensor data fusion and related methods

Abstract

Disclosed are devices and methods for determining a location of a personal care device relative to a target region of the user's body using fused sensor data. The disclosed devices employ an inertial measurement unit (IMU) configured to detect an acceleration and rotation of the personal care device as the personal care device is moved proximal to a target region of the user's body. The devices and methods further include a distance sensor configured to detect a distance between the handheld personal care device and the target region. The devices and methods further include a processor configured to determine a location of the personal care device relative to the target region by classifying the location based, at least partially, on the acceleration, rotation, and distance.

Description

A PERSONAL CARE DEVICE WITH IMPROVED LOCATION TRACKING USING DISTANCE SENSOR DATA FUSION AND RELATED METHODSField of the Disclosure

[0001] The present disclosure generally relates to improved location tracking of a personal care device. More specifically, the present disclosure is directed to devices and methods for determining the location of a personal care device relative to a target region of the user’s body using fused sensor data.Background

[0002] Proper tooth brushing technique, including length and coverage of brushing, helps ensure long-term dental health. Many dental problems are experienced by individuals who either don't regularly brush their teeth or who do so inadequately. Among individuals who do regularly brush, improper brushing habits can result in poor coverage and thus surfaces that are not adequately cleaned.

[0003] To facilitate proper brushing technique, toothbrushes have been designed to provide a timer function such that a user knows to brush for a minimum recommended amount of time. The timer function can include an audible sound, haptic feedback, or other notification mechanism to let the user know when a predetermined amount of time has elapsed for each segment of the mouth. This provides the user with an indication that they have brushed their teeth for an adequate amount of time.

[0004] Another mechanism to facilitate proper brushing technique is to ensure that there is adequate cleaning of all dental surfaces, including areas of the mouth that are hard to reach or that tend to be improperly cleaned during an average brushing session. One way to ensure adequate coverage is to track the location of the toothbrush in the mouth during a brushing session and compare that to a map of the dental surfaces. For example, a system with sensors positioned in fixed relationship to the teeth of the user could track the movement of a toothbrush over the user's teeth.

[0005] Machine learning (ML) models have previously been used for tracking the location of a brush head of a toothbrush inside of a user’s mouth. ML location tracking is traditionally performed using one or more sensors, such as accelerometers, that provide data relevant to the location of the toothbrush. An ML model is trained by annotating (or tagging) a large set of brushing session data with the true location of the brush head in the user’s mouth. The truelocation may be determined, for example, by infrared camera-based systems that track fiducial targets added to the toothbrush. These previously known techniques can work fairly well for guided brushing, where the user is required to brush according to a predetermined pattern. The accuracy of guided brushing methods depends on the user moving to each segment, as prompted. Guided brushing significantly simplifies the location tracking process by eliminating the ambiguity of IMU data associated with locations that have similar accelerometer data. During training, the ML model learns the relationship between sensor outputs and the location of the brush head in each predefined segment of the user’s mouth. During deployment, the ML model uses this learned relationship to classify the location of the toothbrush as being upon one of the predefined segments.

[0006] Current ML-enabled techniques are less accurate for unguided location sensing, due at least to the fact that these ML models are typically trained on data obtained from users instructed to keep their heads still while brushing. However, users in their own homes are likely to move around while brushing, for example, by turning around or bending over the sink. This additional movement leads to motion sensor outputs that deviate from the data that the ML model was trained on, resulting in less accurate motion tracking.

[0007] Accordingly, there still exists a need in the art for devices and methods capable of determining the location of a handheld personal care device relative to a user’s body in a manner that allows for unguided tracking of the personal care device and where the user is free to move the orientation of their head.Summary of the Disclosure

[0008] The present disclosure is generally directed to devices and methods for determining a location of a handheld personal care device relative to a user’s body using fused sensor data. This is achieved partially based on the realization and appreciation by the Applicant that a distance sensor, coupled to a handheld personal care device, can be used to supplement inertial sensor data with additional data indicative of the distance traveled by the personal care device relative to the user. In this way, the distance sensor helps resolve ambiguities in inertial sensor data classification, introduced from user movement, by supplying the ML model with data reflecting the relative distance between the personal care device and target area of a user.

[0009] The embodiments and implementations disclosed or otherwise envisioned herein can be utilized with any user-operated personal care device. Examples of suitable personal caredevices include a power toothbrush such as a Philips Sonicare® toothbrush or a flossing device such as a Philips Sonicare® Power Flosser, both manufactured by and available from Koninklijke Philips Electronics, N. V., an oral irrigator, or a tongue cleaner. While the approach disclosed herein is particularly applicable for oral care devices and applications, such as brushing teeth, where it can accurately identify a tooth or region of the mouth being targeted by the toothbrush and enable feedback and brushing guidance, the disclosure is not limited to these enumerated devices, and thus the disclosure and embodiments disclosed herein can encompass any other personal care device, such as a shaver, or a skin care device.

[0010] Generally, one aspect of this disclosure relates to a handheld personal care device. The personal care device includes an inertial measurement unit (IMU) configured to detect an acceleration and rotation of the personal care device as the personal care device is moved proximal to a target region of the user’s body. The personal care device further includes a distance sensor configured to detect a distance between the handheld personal care device and the target region. The personal care device further includes a processor configured to determine a location of the personal care device relative to the target region by classifying the location based, at least partially, on the acceleration, rotation and distance.

[0011] In various embodiments, the IMU includes three accelerometers and three gyroscopes, and, in particular embodiments, the IMU may further include three magnetometers.

[0012] In some embodiments, the at least one distance sensor is a time-of-flight (ToF) sensor, and, in particular embodiments, the distance sensor is integrated with or mounted to the handheld personal care device. According to some examples, the at least one distance sensor is configured to detect the distance using modulated light emitted by the distance sensor at an angle offset from a longitudinal axis of the personal care device.

[0013] In some embodiments, the handheld personal care device is an oral care device including a handle portion and a working portion having an operating end, and, in particular variants of these embodiments, the pair of distance sensors are positioned with a substantially 180° offset from each other over the surface of the working portion offset from the operating end. In further variants, the working portion includes four distance sensors positioned equidistantly from each other around the surface thereof.

[0014] Another aspect of the present disclosure generally relates to a method for determining a location of a handheld personal care device relative to a user’s body. The methodincludes receiving, from an IMU, an acceleration and rotation of the personal care device as the personal care device is moved proximal to a target region of the user’s body. The method further includes receiving, from at least one distance sensor, a distance between the handheld personal care device and the target region. The method further includes determining a location of the personal care device relative to the target region by classifying the location based, at least partially, on the acceleration, rotation, and distance.

[0015] The handheld personal device may be tracked by continuously or periodically determining its location.

[0016] In some embodiments, the at least one distance sensor is a time-of-f light (ToF) sensor. According to some examples, the at least one distance sensor detects the distance using modulated light emitted by the distance sensor at an angle offset from a longitudinal axis of the personal care device.

[0017] In various embodiments, the personal care device is an oral care device and the target region is a user’s mouth. In some examples, the location is classified based, at least partially, on a plurality of regions of the user’s mouth.

[0018] Yet another aspect of the present disclosure generally relates to a toothbrush. The toothbrush includes a handle portion and a working portion having an operating end. An IMU and processor are contained within the handle portion. The IMU is configured to detect an acceleration and rotation of the toothbrush as the toothbrush is moved proximal to a target region of a user’s body. The IMU includes at least three accelerometers, at least three gyroscopes, and at least three magnetometers. The toothbrush further includes at least one ToF distance sensors integrated with or mounted to a position along the working portion offset from the operating end. The ToF distance sensor is configured to continuously or periodically detect a distance between the toothbrush and the target region using modulated light emitted by the distance sensor at an angle offset from a longitudinal axis of the toothbrush. The processor is configured to determine a location of the personal care device relative to the target region by classifying the location based, at least partially, on the acceleration, rotation, and distance.

[0019] In various implementations, a processor or controller can be associated with one or more storage media (generically referred to herein as "memory,” e.g., volatile and non-volatile computer memory such as ROM, RAM, PROM, EPROM, and EEPROM, floppy disks, compact disks, optical disks, magnetic tape, Flash, OTP-ROM, SSD, HDD, etc.). In some implementations,the storage media can be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform at least some of the functions discussed herein. Various storage media can be fixed within a processor or controller or can be transportable, such that the one or more programs stored thereon can be loaded into a processor or controller so as to implement various aspects as discussed herein. The terms "program” or "computer program” are used herein in a generic sense to refer to any type of computer code (e.g., software, firmware, or microcode) that can be employed to program one or more processors or controllers.

[0020] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0021] These and other aspects of the various embodiments will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.Brief Description of the Drawings

[0022] FIG. 1 is an illustration of a personal care device according to some aspects of the present disclosure.

[0023] FIG. 2 is an illustration of an acceleration and rotation of a personal care device according to some aspects of the present disclosure.

[0024] FIG. 3 is a schematic of an IMU according to some aspects of the present disclosure.

[0025] FIG. 4 is an illustration of a personal care device located on a left buccal portion and a right lingual portion of a user’s mouth according to some aspects of the present disclosure.

[0026] FIG. 5 is an illustration of a distance sensor that uses a modulated light pulse to measure a distance between a personal care device and target region of a user’s body according to some aspects of the present disclosure.

[0027] FIG. 6 is a graph of ToF sensor values over various distances according to some aspects of the present disclosure.

[0028] FIG. 7A shows a pair of distance sensors positioned with a substantially 180° offset from each other along a working portion of the personal care device, according to some embodiments.

[0029] FIG. 7B shows four distance sensors positioned with a substantially 90° offset from each other along the working portion of the personal care device, according to some embodiments.

[0030] FIG. 70 shows a pair of distance sensors mounted to a housing using optical cement, according to some embodiments.

[0031] FIG. 8 is an illustration of a distance sensor emitting a modulated light pulse at an angle offset from a longitudinal axis of a personal care device according to some aspects of the present disclosure.

[0032] FIG. 9 is a flow chart illustrating a method for determining a location of a handheld personal care device relative to a user’s body according to some aspects of the present disclosure.

[0033] FIG. 10 illustrates a plurality of regions of a user’s mouth that may be used to characterize a location of a personal care device according to some aspects of the present disclosure.

[0034] FIG. 11 is a pair of graphs illustrating the output of a distance sensor versus a triaxial accelerometer when a personal care device is moved from a left buccal portion to a right lingual portion of a user’s mouth according to some aspects of the present disclosure.Detailed Description of Embodiments

[0035] The present disclosure is generally directed to devices and methods for determining a location of a handheld personal care device relative to a target region of user’s body using fused distance sensor data. These devices and systems include an inertial measurement unit (IMU) configured to detect an acceleration and rotation of the personal care device as the personal care device is moved proximal to the target region. The devices and systems additionally include a distance sensor, which may be integrated with or mounted to the handheld personal care device.

[0036] FIG. 1 illustrates a personal care device 2 according to some aspects of the present disclosure. Personal care device 2 is illustrated as a toothbrush in FIG. 1 , however embodiments and implementations disclosed or otherwise envisioned herein can be utilized with any user-operated personal care device. Personal care device 2 includes a handle portion 5 and a working portion 6. Handle portion 5 may be grasped by the hand of a user and is further configured to contain various components of personal care device 2. Working portion 6 may be removably or nonremovably coupled to handle portion 5 at an end offset from an operating end 7. Operating end 7 includes operating features for applying personal care device 2 to a body of a user. For example, FIG. 1 shows operating end 7 as including bristles of a toothbrush. Depending on the implemented form of personal care device 2, operating end 7 may alternatively include the nozzle of a flossing device, the blade of a shaver, the brush head of a face cleansing device, etc. An inertial measurement unit (IMU) 3 and a processor 4 are contained within handle portion 5. Personal care device 2 further includes one or more distance sensors 8 integrated with or mounted to the personal care device. In FIG. 1 , distance sensor 8 is shown at a position along working portion 6 that is offset from operating end 7. This allows a clear path between distance sensor 8 and a target region 25 of the user’s body (described in more detail below with reference to Fig. 5). Proceeding to FIG. 2, IMU 3 is configured to detect an acceleration 10 and rotation 12 of personal care device 2 as personal care device 2 is moved proximal to the target region 25. FIG. 3 illustrates a schematic of exemplary components for IMU 3. IMU 3 can take the form of a six-degree of freedom IMU with three accelerometers 14 and three gyroscopes 16. In this case, each of the three accelerometers 14 and gyroscopes 16 would be associated with a particular coordinate direction, for example, an X, Y, and Z direction. The accelerometers 14 are configured to detect a linear acceleration in each of the X, Y, and Z directions, while the gyroscopes 16 are configured to detect rotation of personal care device 2 along each axis respectively formed from the X, Y, and Z directions. The three accelerometers 14 and three gyroscopes 16 may be integrated into a single MEMS IMU chip and soldered onto a printed circuit board. IMU 3 may further include a set of three magnetometers 18, making it a nine-degree of freedom IMU. This would have the advantage of improving the classification model of personal care device 2 within three-dimensional space, as the magnetic field vector indicated by magnetometers 18 is not sensitive to motion in the same manner as accelerometers 14.

[0037] FIG. 1 shows processor 4 integrated within personal care device 2, however processor 4 may also be remote from personal care device 2 and receive data from IMU 3 and distance sensor 8 via a wireless protocol. Processor 4 may be implemented as a machine learning (ML) model that logs the output of IMU 3 either after each personal care session or inreal time to provide locational feedback to a user. Processor 4 receives data from IMU 3 and uses this data to determine a location of personal care device 2 relative to the user.

[0038] The general problem of location tracking using inertial navigation, as opposed to ML classification models, is that the location prediction accuracy depends on the accuracy of the inertial sensors (i.e. accelerometers 14 and gyroscopes 16). Data from gyroscopes 16 may be used to determine how the direction of movement changes, while data from accelerometers 14 may be used to calculate how far personal care device 2 has moved in this direction by converting data for acceleration over time into distance traveled. In the case where the detected velocity and acceleration are constant, the position of personal care device 2 may be calculated according to the following equation:where x(t) is the position as a function of time, x0is the initial position, v0is the initial velocity, a is acceleration, and t is time. Notice that because position, x(t), increases with time squared for acceleration, even small errors in the acceleration can cause large errors in distance calculation. For nonconstant values of velocity and acceleration, the equation for position would be found by double integration of the acceleration, however, this static equation suffices to illustrate the general relationship between the distance and acceleration detected by IMU 3 as it relates to the teachings of this disclosure.

[0039] As an example of this possibility of error, if IMU 3 was stationary but one of the accelerometers 14 was pointing straight up, then the indicated distance traveled will quickly increase because the accelerometer pointing up will have 1 g of acceleration due to Earth’s gravity (1 g = 9.8 m / sec2). For example, with 1 g of acceleration, the distance traveled in 1 sec would be 4.9 meters. In 10 seconds, the distance traveled would be 490 meters! This result shows why gyroscopes 16 are needed in addition to accelerometers 14. If the changes in direction are tracked by gyroscopes 16, then the acceleration due to gravity can be removed from the outputs of the accelerometers 14 so the calculated distance travelled will be correct (assuming there are no other acceleration errors).

[0040] This also illustrates why navigation grade accelerometers must have very low offset errors (or bias errors) for accurate location tracking. To emphasize this point, consider an IMUon an airplane flying for two hours. If there was a small offset of 0.001 g (or 1 mg), from one of the accelerometers, then after two hours, the error in distance traveled would be a 254,000- meter error which is about 158 miles! Considering that the distance between mouth segments is on the order of 2 to 3 cm, then for a two-minute brushing session, the accelerometer bias errors would have to be less than 2.8 m / sec2or about 0.3 pg to avoid segment location sensing errors. Typical offsets for a commercial grade accelerometer and gyroscope, significantly exceed these values, as shown in Table 1 below.

[0041] Due to these intricacies in calculating and tracking position directly from inertial sensor data, an alternative approach of feeding the inertial data into an ML location sensing model is preferred. The ML is typically trained using annotated position data from a large sample of users. The users are encouraged to keep their heads still during the training to ensure that the ML model is trained on high quality and properly labeled position data. In this way, the ML model learns relationships between the received inertial sensor data and the position of personal care device 2. However, an issue with ML location sensing models trained only on data from IMU 3 is that such ML models only "know” the spatial position of personal care device 2; they do not "know” the relative position of personal care device 2 to the user’s mouth. For example, with reference to FIG. 4, the rotation 12 of personal care device 2 on a left buccal area 20 of the user’s mouth would be the same as the rotation 12 of personal care device 2 on a right lingual area 22 of the user’s mouth if only data from IMU 3 is used. Accordingly, when the ML model is implemented to track the oral care device during personal care sessions, for example in a user’s home, additional user movement can make it hard for the ML model to accurately determine the position of the personal care device based on inertial sensor data alone. Additional data is required for the ML model to learn how this additional movement affects the inertial data and position relationship.

[0042] To address these challenges, personal care device 2 further includes one or more distance sensors 8 configured to detect a distance between handheld personal care device 2 and a target region 25 of user’s body. The target region would vary depending on the part of the user’s body that personal care device 2 is used to treat. For example, in the case that personal care device 2 is a toothbrush, the target region would be one or more teeth to be brushed inside the user’s mouth. While in the case that personal care device 2 is a hairbrush, the target region could be the user’s hair. Distance sensor 8 can continuously or periodically detect the distance between personal care device 2 and target region 25. The distance detected by distance sensor 8 can be detected at the same range of time points that acceleration 10 and rotation 12 are detected. In this way, for example, distance sensor 8 would record a change in distance when personal care device 2 is moved from left buccal area 20 to right lingual area 22 because the distance to the user’s face changes. Data from both IMU 3 and distance sensor 8 is received by processor 4.

[0043] With reference to FIG. 5, distance sensor 8 may be implemented as a time-of-flight (ToF) sensor that measures distances by emitting a short pulse of light 26 or sound towards the user’s body 24. When light 26 or sound contacts the skin of the user, it reflects back towards distance sensor 8. Distance sensor 8 records the time it takes for the pulse of light 26 or sound to travel to the object and return via a detector and signal processing system. Using the known speed of light 26 or sound, the sensor calculates the distance to the object based on the time it took for the light 26 or sound to travel. The calculated distance is then provided as sensor output. Sensor 8 may utilize continuous wave modulation. In this way, instead of directly measuring the time it takes for the light to reflect off target region 25 and return to personal care device 2, distance sensor 8 is configured to measure the phase difference between the modulation of outgoing signals emitted from distance sensor 8 and incoming signals reflected from target region 25. This phase difference can be used to calculate the distance traveled given a known modulation frequency. Such modulation can be achieved using a ramp or chirp, for example, a continuously increasing or decreasing sine wave. Continuous wave modulation is particularly useful when the distances traveled by emitted light 26 or sound are short, such as the distance between a toothbrush and a user’s face.

[0044] Thus, the ToF sensor receives the reflected light 26 or sound and determines the distance between personal care device 2 and target region 25 based on the time it takes for thereflected light 26 or sound to arrive back at the ToF sensor. Distance sensor 8 may be manufactured within a chip-scale sized package and include integrated signal conditioning and digital outputs. Examples of such a distance sensor includes the VL6180X sensor available from STMicroelectronics and a multizone version, VL53L5Cx, also available from STMicroelectronics. In examples where distance sensor 8 is configured to detect reflected light, multizone implementations of distance sensor 8 use one or more diffractive optical elements to spread a light beam from a single cavity surface emitting laser into a square field of view. The reflected light in each of a plurality of zones of the field of view is received by an array of single photon avalanche diodes. A multizone implementation of distance sensor 8 may, for example, output distance measurements for a 4x4 or 8x8 array of zones. Depending on the particular application, light 26 can be pulsed light, amplitude modulated light, or frequency modulated light, depending on the particular sensor used. As shown in FIG. 6, another benefit of this type of sensor is that distance data is fairly consistent over a wide range of reflectivity.

[0045] When implemented as a ToF sensor, it is important that distance sensor 8 is configured to be insensitive to the amount of light reflected from the user’s face as shown in Figure 6. In this way, light reflected off of features such as facial hair, for example, still results in a valid distance measurement. FIGS. 7A and 7B illustrate sectional views of working portion 6 having one or more distance sensor 8 mounted thereon. FIG. 7A shows a pair of distance sensors 8, diametrically opposed from each other, i.e. positioned with a substantially 180° offset from each other along the surface of the working portion 6, for example, along its circumference, in embodiments where the working portion is substantially cylindrical. In other embodiments, such as those shown in FIG. 7B, there are four distance sensors 8 positioned with a substantially 90° offset from each other along the surface of the working portion 6. Including additional distance sensors 8 will help to provide more distance data from each of the different sides of personal care device 2. In some embodiments, a housing 28 may be molded around personal care device 2, for example around a position along working portion 6 that is offset from operating end 7, to form a mounting surface for one or more distance sensors 8. Housing 28 is preferably made of a material that is transparent at the wavelength of light emitted by distance sensor 8 (for example 840 nm). This helps to avoid housing 28 interfering with operation of distance sensor 8. For example, housing 28 can be made of a methylmethacrylate acrylonitrile butadiene styrene (MABS) material that is transparent while still exhibiting sturdy structuralproperties. FIG. 70 illustrates distance sensors 8 being positioned within housing 28. Distance sensors 8 are mounted to housing 28 with index matching optical cement 30. Optical cement 30 helps prevent internal reflections within housing 30 disrupting the path of light 26 by matching the index of refraction of house 28. Depending on the application, configuration, and relative dimensions of the handle and the working portion of the personal care device, housing 28 may be implemented in a variety of different shapes.

[0046] In the case that distance sensor 8 is implemented as a ToF sensor, then the connection between distance sensor 8 and personal care device 2 can be done with a four- conductor flex print, since this sensor implementation is an I2C bus enabled device. Only power, ground, SDA and SCL pins are needed. Once the flex print is connected to the main board of the personal care device 2, processor 4 can pull data from distance sensor 8. Since the I2C address can be reprogrammed, this distance sensor implementation is compatible with any existing I2C bus on the main board.

[0047] FIG. 8 shows distance sensor 8 emitting light 26 at an angle offset from a longitudinal axis 32 of personal care device 2. Offset angle 36 makes it easier for distance sensor 8 to detect changes in distance due to tilting of personal care device 2. For example, if distance sensor 8 were to emit light pulse 26 parallel to longitudinal axis 32 (as shown by 34), then the detected distance to the user’s face would vary during certain movements, such as brushing back molars when personal care device 2 is implemented as a toothbrush, but would not vary as much when the change of distance is due to tilting of personal care device 2. However, emitting light 16 at offset angle 36 will make distance sensor 8 more sensitive to changes in distance due to tilting of personal care device 2. This will help reduce location sensing errors for movements such as brushing frontal teeth, where longitudinal axis 32 is typically not normal to the user’s face.

[0048] FIG. 9 illustrates a method 100 for determining a location of a handheld personal care device relative to a user’s body. Step 102 of method 100 includes receiving, from an IMU, an acceleration and rotation of the personal care device as the personal care device is moved proximal to a target region of the user’s body. This step, for example, could be performed by processor 4 receiving data from IMU 3 as previously discussed. Step 104 of method 100 includes receiving, from a distance sensor, a distance between the handheld personal care device and the target region. This step, for example, could be performed by processor 4 receivingdata from distance sensor 8 as previously discussed. Step 106 of method 100 includes determining a location of the personal care device relative to the target region by classifying the location, based at least partially, on the acceleration, rotation, and distance. This step may include inputting data from both IMU 3 and distance sensor 8 into an ML model, for example an ML classifier trained on annotated data from the inertial and distance sensors. In some embodiments, previously discussed processor 4 can be implemented as such an ML classifier. The ML model may be trained by inputting inertial and distance sensor data from a large group of users using an oral care device, such as oral care device 2. With reference back to FIG. 5, data from a plurality of infrared cameras 38 that can track fiducial elements that were added to the oral care device used to calculate the actual location of personal care device 2 relative to the target region 25. The calculations can then be added to annotate the training data for the ML model. The classification model learns the relationship between the data received from IMU 3 and distance sensor 8, and the location of personal care device during training that includes the annotated data. This learning can be achieved using any ML classification method known in the art. Such methods include, but are not limited to, techniques such as: logistic regression, naive Bayes models, k-nearest neighbor, decision trees, support vector machines, and / or artificial neural networks.

[0049] According to an example embodiment illustrated in FIG. 10, in the case where the target region is a user’s mouth 40, classifying the location of personal care device 2 may include classifying the location based, at least partially, on a plurality of regions of the user’s mouth 40. For example, the location can be characterized as being on an upper jaw 42 or lower jaw 44 of user’s mouth 40. FIG. 10 illustrates how the location can be further classified according to increasingly specific regions of the user’s mouth 40. A 6-segment classification can include classifying the location as being at one of a top left location 46, a top right location 48, a top front location 50, a bottom left location 52, a bottom right location 54, or a bottom front location 56. The classification can be further expanded to encompass 12-segments by further classifying the segments as being on either the buccal 58 or lingual 60 side of the user’s mouth 40. The classification can be even further expanded to encompass 24-segments by further classifying the segments as being on one of a buccal 58, lingual 60, or occlusal side 62 of the user’s mouth 40.

[0050] Fusing acceleration 10 and rotation 12 data obtained from IMU 3 with distance data obtained from distance sensor 8 into an ML model allows the model to continuously track personal care device 2 throughout a personal care session by continuously or periodically determining the location of personal care device 2 relative to the target region 25. This data fusion is so effective that, with reference back to FIG. 4, in the cases where personal care device 2 is an oral care device, the devices and methods disclosed herein can be used to classify the location based on a particular tooth 64 that personal care device 2 is positioned upon. This can be used to provide various feedback to the user, such as automatically adapting an intensity of personal care device 2 based on its determined location or altering motor frequency modulation modes for a particular tooth 64 based on user preferences.

[0051] FIG. 11 demonstrates an exemplary triaxial accelerometer output 66 versus an exemplary distance sensor output 68 during a personal care session, according to some aspects of the present disclosure. Triaxial accelerometer output 66 shows output from the three accelerometers configured to detect acceleration in and X, Y, and Z direction respectively. As brushing is moved from a left buccal to a right lingual area of the user’s mouth, accelerometer output 66 stays substantially constant in all three directions. However, distance sensor output 68 demonstrates much greater variation as brushing is moved from the left buccal to right lingual area. FIG. 11 demonstrates just one of many cases where distance sensor 8 can be used to disambiguate data from IMU 3 to improve location tracking of personal care device 2.

[0052] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0053] The indefinite articles "a” and "an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean "at least one.”

[0054] The phrase "and / or,” as used herein in the specification and in the claims, should be understood to mean "either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with "and / or” should be construed in the same fashion, i.e., "one or more” of the elements so conjoined. Other elements can optionally be present other than the elements specifically identified by the "and / or” clause, whether related or unrelated to those elements specifically identified.

[0055] As used herein in the specification and in the claims, "or” should be understood to have the same meaning as "and / or” as defined above. For example, when separating items in a list, "or” or "and / or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one, of a number or list of elements, and, optionally, additional unlisted items. Only terms clearly indicated to the contrary, such as "only one of” or "exactly one of,” or, when used in the claims, "consisting of,” will refer to the inclusion of exactly one element of a number or list of elements. In general, the term "or” as used herein shall only be interpreted as indicating exclusive alternatives (i.e. "one or the other but not both”) when preceded by terms of exclusivity, such as "either,” "one of,” "only one of,” or "exactly one of.”

[0056] As used herein in the specification and in the claims, the phrase "at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements can optionally be present other than the elements specifically identified within the list of elements to which the phrase "at least one” refers, whether related or unrelated to those elements specifically identified.

[0057] It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0058] In the claims, as well as in the specification above, all transitional phrases such as "comprising,” "including,” "carrying,” "having,” "containing,” "involving,” "holding,” "composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases "consisting of” and "consisting essentially of” shall be closed or semi-closed transitional phrases, respectively.

[0059] The above-described examples of the described subject matter can be implemented in any of numerous ways. For example, some aspects can be implemented using hardware, software, or a combination thereof. When any aspect is implemented at least in part in software, the software code can be executed on any suitable processor or collection of processors,whether provided in a single device or computer or distributed among multiple devices / computers.

[0060] The present disclosure can be implemented as a system, a method, and / or a computer program product at any possible technical detail level of integration. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0061] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0062] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions fromthe network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0063] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, statesetting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the "C” programming language or similar programming languages. The computer readable program instructions can execute entirely on the user’s computer, partly on the user's computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some examples, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0064] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to examples of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0065] The computer readable program instructions can be provided to a processor of a, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readableprogram instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram or blocks.

[0066] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0067] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various examples of the present disclosure. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the Figures. For example, two blocks shown in succession can, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0068] Other implementations are within the scope of the following claims and other claims to which the applicant can be entitled.

[0069] While various examples have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the examples described herein. More generally, those skilled in the art will readilyappreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the teachings is / are used. Those skilled in the art will recognize or be able to ascertain using no more than routine experimentation, many equivalents to the specific examples described herein. It is, therefore, to be understood that the foregoing examples are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, examples can be practiced otherwise than as specifically described and claimed. Examples of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the scope of the present disclosure.

[0070] Although various embodiments have been depicted and described in detail herein, it will be apparent to those skilled in the relevant art that various modifications, additions, substitutions, and the like can be made without departing from the spirit of the disclosure and these are therefore considered to be within the scope of the disclosure as defined in the claims which follow.

Claims

ClaimsWhat is claimed is:1 . A handheld personal care device (2), comprising: an inertial measurement unit (IMU) (3) configured to detect an acceleration (10) and rotation (12) of the personal care device (2) as the personal care device (2) is moved proximal to a target region (25) of a user’s body (24); one or more distance sensors (8) configured to detect a distance between the handheld personal care device (2) and the target region (25); a processor (4) configured to determine a location of the personal care device (2) relative to the target region (25) by classifying the location based, at least partially, on the acceleration (10), rotation (12), and distance.

2. The handheld personal care device (2) of claim 1, wherein the one or more distance sensors (8) is a time-of-flight (ToF) sensor, integrated with or mounted to the handheld personal care device (2).

3. The handheld personal care device (2) of claim 2 comprising an oral care device including a handle portion (5) and a working portion (6) having an operating end (7), and further comprising a pair of distance sensors (8) positioned with a substantially 180° offset from each other at a position along the working portion (6) offset from the operating end (7).

4. The handheld personal care device (2) of claim 1 , wherein the IMU (3) comprises at least three accelerometers (14) and at least three gyroscopes (16).

5. The handheld personal care device (2) of claim 4, wherein the IMU (3) further comprises at least three magnetometers (18).

6. The handheld personal care device (2) of claim 1, wherein the distance sensor (8) is configured to detect the distance using a pulse of modulated light (26) emitted by the distance sensor (8) at an angle (36) offset from a longitudinal axis (32) of the personal care device (2).

7. The handheld personal care device (2) of claim 1, wherein the distance between the handheld personal care device (2) and the target region (25) is measured by the at least one distance sensor (8) continuously or periodically.

8. A method (100) for determining a location of a handheld personal care device (2) relative to a user’s body (24), the method comprising: receiving (102), from an IMU (3), an acceleration (10) and rotation (12) of the personal care device (2) as the personal care device (2) is moved proximal to a target region (25) of the user’s body (24); receiving (104), from a distance sensor (8), a distance between the handheld personal care device (2) and the target region (25); determining (106) a location of the personal care device (2) relative to the target region (25) by classifying the location based, at least partially, on the acceleration (10), rotation (20), and distance.

9. The method (100) of claim 8, further comprising tracking the handheld personal care device (2) by continuously or periodically determining the location of the personal care device.

10. The method (100) of claim 8, wherein the distance sensor (8) is a time-of-flight sensor.11 . The method (100) of claim 8 , further comprising detecting the distance using a pulse of modulated light (26) emitted by the distance sensor (8) at an angle (36) offset from a longitudinal axis (32) of the personal care device (2).

12. The method (100) of claim 8, wherein the personal care device (2) is an oral care device and the target region (25) is a user’s mouth (40), and wherein classifying the location comprises classifying the location based, at least partially, on a plurality of regions of the user’s mouth (40).

13. The method (100) of claim 12, wherein classifying the location comprises classifying the location based, at least partially, on a tooth (64) within the user’s mouth (40) which the oral care device (2) is positioned upon.

14. A toothbrush, comprising: a handle portion (5) and a working portion (6) having an operating end (7); an IMU (3) contained within the handle portion (5) and configured to detect an acceleration (10) and rotation (12) of the toothbrush as the toothbrush is moved proximal to a target region (25) of a user’s body (24), the IMU further comprising: at least three accelerometers (14); at least three gyroscopes (16); and at least three magnetometers (18); at least one ToF distance sensor (8) integrated with or mounted to a position along the working portion (6) offset from the operating end (7) and configured to continuously or periodically detect a distance between the toothbrush and the target region (25) using a pulse of modulated light emitted by the distance sensor (8) at an angle (36) offset from a longitudinal axis (32) of the toothbrush; and a processor (4) contained within the handle portion (5) and configured to determine a location of the personal care device (2) relative to the target region (25) by classifying the location based, at least partially, on the acceleration (10), rotation (12), and distance.

Images