System for monitoring the posture of vehicle occupants

Abstract

A system for a vehicle (100), the system comprising: a camera (218); and a computing system (220) including instructions stored in a non-transitory memory that, when executed, cause the computing system (220) to: Receiving images taken of an occupant in the vehicle by the camera (218); Determining the occupant’s body measurements based on the received images; Determining the current posture of the occupant based on the received images; Determining a recommended posture for the occupant based on the determined body measurements; and Issuing a first command in response to a difference between the current posture and the recommended posture exceeding a threshold difference, the first command being configured to cause one or more actuators to provide force feedback to the occupant.

Description

FIELD OF TECHNOLOGY

[0001] The present disclosure relates to a camera-based system for monitoring the posture of vehicle occupants. BACKGROUND

[0002] Driving posture can affect the health and comfort of a vehicle's driver. However, it may be difficult for the driver to monitor their own posture while concentrating on vehicle operation. As another example, different vehicle occupants, including different drivers during different trips, may have different heights, weights, and proportions. Therefore, seat adjustments for one occupant may not ensure the optimal seating posture for another occupant, and it may be difficult for the occupant to find a comfortable and ergonomic seating position through manual adjustment (e.g., controlled by the occupant). Furthermore, occupants may sometimes adopt an unfavorable seating position despite having an optimal seating position, particularly on long trips. SUMMARY

[0003] In various embodiments, the problems described above may be addressed by a system for a vehicle, the system including a camera and a computing system having instructions stored in non-transitory memory that, when executed, cause the computing system to receive images of an occupant in the vehicle captured by the camera, determine body measurements of the occupant based on the received images, determine a current posture of the occupant based on the received images, determine a recommended posture for the occupant based on the determined body measurements, and issue a first command in response to a difference between the current posture and the recommended posture exceeding a threshold difference, the first command configured to cause one or more actuators to provide force feedback to the occupant.

[0004] It should be understood that the foregoing brief description is provided to introduce, in a simplified form, a selection of concepts further described in the detailed description. It is not intended to identify important or essential features of the claimed subject matter, the scope of which is defined solely by the claims following the detailed description. Furthermore, the claimed subject matter is not limited to implementations that overcome any disadvantages noted above or in any part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The disclosure will be better understood from the following description of non-limiting embodiments with reference to the accompanying drawings, in which: Fig. 1 systematically illustrates a vehicle system according to one or more embodiments of the present disclosure; Fig. 2 shows a block diagram of a data flow during the detection of the posture of an occupant according to one or more embodiments of the present disclosure; and Fig. 3 shows a flowchart of a method for determining the posture of the occupant. Fig. 4 shows an example of a recommended driving posture according to one or more embodiments of the present disclosure; Fig. 5 shows a first example of an incorrect driving posture according to one or more embodiments of the present disclosure; Fig. 6 shows a block diagram of a vehicle system according to one or more embodiments of the present disclosure. Fig. 7 shows a flowchart of a method for increasing the comfort of vehicle occupants using a vehicle system according to one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0006] The following description relates to systems and methods for increasing the comfort of vehicle occupants via an occupant monitoring system. The occupant monitoring system may include a camera mounted in a vehicle, such as in the Fig. 1. A computing system may process and analyze images received from the camera to determine a posture of the occupant, such as a driver (e.g., a vehicle operator) or a passenger of the vehicle, and to make posture corrections, such as in accordance with the method described in Fig. 2. For example, the computing system may receive images captured by the camera as well as body measurement data of the occupant. The computing system may use image and data processing resources included in an in-vehicle processing system, a mobile processing system, or a networked processing system (e.g., cloud computing) to identify appropriate posture options, determine whether a current posture deviates significantly from the appropriate posture options, and encourage the occupant to change their posture, such as according to the method in Fig. 3. Fig. 4 and Fig. 5 show various measurements and relationships between the occupant, a seat, and a steering wheel that the computing system can analyze when determining the occupant's posture. Fig. 4 shows an example of a recommended posture, while Fig. 5 provides an example of incorrect driver posture that may cause driver discomfort or fatigue. A block diagram of a vehicle system according to one or more embodiments of the present disclosure is shown in Fig. 6. A flowchart of a method for increasing the comfort of vehicle occupants by means of a vehicle system is shown in Fig. 7, which can use the images and body measurement data used in the method of Fig. 3. In this way, comfort for the driver and front passenger can be increased from the moment they enter the vehicle to the moment they exit it, with minimal or no input from the occupants.

[0007] Now, with reference to the figures Fig. 1 schematically illustrates an exemplary vehicle 100. The vehicle 100 includes an instrument panel 102, a driver seat 104, a first passenger seat 106, a second passenger seat 108, and a third passenger seat 110. In other examples, the vehicle 100 may have more or fewer passenger seats. The driver seat 104 and the first passenger seat 106 are located in the front of the vehicle, near the instrument panel 102, and may therefore be referred to as front seats. The second passenger seat 108 and the third passenger seat 110 are located in the rear of the vehicle and may also be referred to as rear seats.

[0008] The vehicle 100 further includes a steering wheel 112 and a steering column 122 via which the driver can input steering commands for the vehicle 100. The steering column 122 may be adjustable so that the driver can change a height and / or tilt of the steering wheel 112 by adjusting the steering column 122. In some examples, the steering column 122 may be adjusted by the driver releasing a lever or lock on the steering column 122 and manually moving the steering column 122 and / or the steering wheel 112 to adjust the height and / or tilt of the steering wheel 112. In other examples, the position of the steering column 122 and the steering wheel 112 may be adjusted via an electric motor integrated into the steering column 122. The driver may input settings to the electric motor, such as via an interface (e.g.,a button or switch) on the steering column 122, or the computing system 120 may actuate the electric motor to adjust the position of the steering column 122 and the steering wheel 112 based on a stored setting for the driver.

[0009] The vehicle 100 further includes a camera 118. The camera 118 may be integrated into a driver monitoring system (e.g., a driver attention monitor). Fig. 1, the camera 118 is located to the side of the driver's seat 104, which may facilitate monitoring the driver in profile. However, in other examples, the camera 118 may be positioned in other locations within the vehicle 100, such as on the steering column 122 and directly in front of the driver's seat 104. The camera 118 may include one or more optical cameras (e.g., visible light), one or more infrared (IR) cameras, or a combination of optical and IR cameras with one or more viewing angles. In some examples, the camera 118 may have both interior and exterior perspectives. In some examples, the camera 118 may include more than one lens and more than one image sensor. For example, the camera 118 may have a first lens that directs light onto a first visible light image sensor (e.g.,a charge-coupled device or a metal-oxide-semiconductor), and a second lens that directs light onto a second thermal imaging sensor (e.g., a focal plane array) so that the camera 118 can collect light of different wavelength ranges to produce both visible and thermal images. In some examples, the camera 118 can further include a depth camera and / or a sensor, such as a time-of-flight camera or a LiDAR sensor. In some examples, the camera 118 can be configured to capture suitable images even in low-light conditions without the need for visible illumination. For example, the camera 118 can capture suitable images even during nighttime driving without the need for visible illumination (e.g.,a flashing light) is required, since visible lighting in such situations can startle and distract the occupants of the vehicle 100, which can lead to dangerous situations and accidents.

[0010] In some examples, camera 118 may be a digital camera configured to capture a series of images (e.g., single images) at a programmable frequency (e.g., frame rate) and may be electronically and / or communicatively coupled to computing system 120. Furthermore, camera 118 may output captured images to computing system 120 in real time so that they may be processed in real time by computing system 120 and / or a computing network, as described herein with particular reference to Fig. 2 and Fig. 6. As used herein, the term "real-time" refers to an operation that occurs instantaneously and without intentional delay. For example, "real-time" may refer to a response time of less than or equal to about 1 second. In some examples, "real-time" may refer to simultaneous or near-simultaneous processing, detection, or identification. In some examples, the camera 118 may be further calibrated with respect to a world coordinate system (e.g., World Space x, y, z).

[0011] The vehicle 100 may further include a driver seat sensor 124 coupled to or located within the driver seat 104, and a passenger seat sensor 126 coupled to or located within the first passenger seat 106. The rear seats may also include seat sensors, such as a passenger seat sensor 128 coupled to the second passenger seat 108 and a passenger seat sensor 130 coupled to the third passenger seat 110. The driver seat sensor 124 and the passenger seat sensor 126 may each include one or more sensors, such as a weight sensor, a pressure sensor, and one or more seat position sensors, that output a measurement signal to the computing system 120. For example, the output of the weight sensor or the pressure sensor may be used by the computer system 120 to determine whether or not the respective seat is occupied, and if occupied, the weight of a person occupying the seat.As another example, the output of the one or more seat position sensors may be used by the computing system 120 to determine one or more seat heights, a longitudinal position relative to the instrument panel 102 and the rear seats, and an angle (e.g., tilt) of a seatback of the corresponding seat. In other examples, the seat position may additionally or alternatively be determined based on images captured by the camera 118, as explained in more detail herein. According to some examples, it is alternatively or additionally possible to determine the weight of an occupant based on the images captured by the camera 118.

[0012] In some embodiments, the vehicle 100 further includes a driver seat motor 134 coupled to or positioned within the driver seat 104, and a passenger seat motor 138 coupled to or positioned within the first passenger seat 106. Although not shown, in some embodiments, the rear seats may also include seat motors. The driver seat motor 134 may be used to adjust the seat position, including the seat height, the fore-and-aft position of the seat, and the angle of the backrest of the driver seat 104, and may include an adjustment input 136. The adjustment input 136 may include, for example, one or more toggles, buttons, and switches. The driver can input the desired driver seat position settings to the driver seat motor 134 via the adjustment input 136, and the driver seat motor 134 may move the driver seat 104 accordingly in near real time.In other examples, the driver seat motor 134 may adjust the driver seat position based on inputs received from the computing system 120. The passenger seat motor 138 may similarly adjust a seat position of the passenger seat 106 based on inputs received from an adjustment input 140 and / or based on inputs received from the computing system 120. Further, in some examples, the computing system 120 may determine the seat position of the respective passenger seat based on feedback from the driver seat motor 134 and the passenger seat motor 138. Although not shown, the rear seats may be adjustable in a similar manner in some embodiments.

[0013] In some embodiments, the vehicle 100 further includes an in-cabin radar unit (not specifically illustrated). The in-cabin radar unit may, for example, be a 60 GHz radar unit. The in-cabin radar unit may be integrated into the driver monitoring system (e.g., a driver attention monitor). For example, the in-cabin radar unit may be positioned to the side of the driver seat 104, which may facilitate monitoring the driver in profile. However, in other embodiments, the in-cabin radar unit may be positioned in other locations within the vehicle 100, such as on the steering column 122 and directly in front of the driver seat 104. For example, the output of the in-cabin radar unit may be used by the computing system 120 to determine whether the respective seat is occupied or unoccupied.Some high-resolution in-cabin radar units may even allow the computing system 120 to determine the posture of the occupants based on the data received from the in-cabin radar unit.

[0014] Computing system 120 can both receive input via user interface 116 and output information to user interface 116. User interface 116 can be included, for example, in a digital cockpit or advanced driver assistance system (ADAS) and can include a display and one or more input devices. The one or more input devices can include one or more touchscreens, buttons, dials, hard keys, and soft keys for receiving user input from a vehicle occupant.

[0015] Computing system 120 includes a processor 142 configured to execute machine-readable instructions stored in memory 144. Processor 142 may consist of one or more cores, and the programs executed by processor 142 may be configured for parallel or distributed processing. In some embodiments, processor 142 is a microcontroller. Processor 142 may optionally include individual components distributed across two or more devices that may be located at remote locations and / or configured for coordinated processing. In some embodiments, one or more aspects of processor 142 may be virtualized and executed by networked, remotely accessible computing devices configured in a cloud computing configuration.For example, computing system 120 may be coupled to a wireless network 132 via a transceiver 146, and computing system 120 may communicate with the networked computing devices via the wireless network 132. Additionally or alternatively, computing system 120 may communicate directly with the networked computing devices via short-range communication protocols, such as Bluetooth®. In some embodiments, computing system 120 may include other electronic components capable of performing processing functions, such as a digital signal processor, a field-programmable gate array (FPGA), or a graphics card. In some embodiments, processor 142 may include multiple electronic components capable of performing processing functions.For example, processor 142 may include two or more electronic components selected from a variety of possible electronic components, including a central processor, a digital signal processor, a field-programmable gate array, and a graphics card. In still other embodiments, processor 142 may be configured as a graphics processing unit (GPU) having a parallel computing architecture and parallel processing capabilities.

[0016] Furthermore, memory 144 may include any non-transitory, tangible, computer-readable medium in which programming instructions are stored. As used herein, the term "tangible computer-readable medium" expressly includes any type of computer-readable memory. The example methods described herein may be implemented using encoded instructions (e.g., computer-readable instructions) stored on a non-transitory, computer-readable medium, such as flash memory, read-only memory (ROM), random access memory (RAM), a cache, or other storage medium on which information is stored for any period of time (e.g., for extended periods of time, permanently, for a short time, for temporarily buffering, and / or caching the information).Computer memory or computer-readable storage media referred to herein may include volatile and non-volatile or removable and non-removable media for storing electronically formatted information, such as computer-readable program instructions or modules of computer-readable program instructions, data, etc., which may be stand-alone or part of a computing device. Examples of computer memory may be any other medium that can be used to store the desired electronic information format and that can be accessed by the processor(s) or at least a portion of a computing device. In various embodiments, memory 144 may be an SD memory card, an internal and / or external hard drive, a USB storage device, or similar modular memory.

[0017] Furthermore, in some examples, computing system 120 may include a plurality of subsystems or modules that perform specific functions related to image acquisition and analysis. As used herein, the term "system," "unit," or "module" may include a hardware and / or software system operable to perform one or more functions. For example, a module, unit, or system may include a computer processor, controller, or other logic-based device that performs operations based on instructions stored on a tangible and non-transitory, computer-readable storage medium, such as computer memory. Alternatively, a module, unit, or system may include a hard-wired device that performs operations based on hard-wired logic of the device.Various modules or units shown in the attached figures may represent hardware that executes operations based on software or hardware instructions, software that instructs hardware to perform operations, or combinations thereof.

[0018] “Systems,” “units,” or “modules” may include, or represent hardware and associated instructions (e.g., software stored on a tangible and non-transitory, computer-readable storage medium) that perform, include, or embody one or more of the operations described herein. The hardware may include electronic circuitry that includes and / or is coupled to one or more logic-based devices, such as microprocessors, processors, controllers, or the like. These devices may be commercially available devices that are appropriately programmed or instructed to perform operations described herein based on the instructions described above. Additionally or alternatively, one or more of these devices may be hard-wired with logic circuitry to perform these operations. For example, the computing system 120, as described herein with respect to Fig. 3, determine a posture of an occupant based on the images received from the camera 118, determine a desired (e.g., recommended) posture of an occupant based on body measurements, determine a difference between the occupant's posture and the desired occupant's posture, and in response to a difference between the current posture and the recommended posture exceeding a threshold difference, issue a first command, the first command being configured to cause one or more actuators to provide force feedback to the occupant.

[0019] The following describes a data flow between various devices for determining the occupant's posture. With reference to Fig. 2, a block diagram of an exemplary data flow 200 is shown. A camera 218 provides image data to a computing system 220. The camera 218 may be similar or identical to the camera 118 of Fig. 1, and the computing system 220 may be similar or equal to the computing system 120 of Fig. 1. The computing system 220 includes an image acquisition module 232, an image analysis module 234, and (optionally) an advanced driver assistance system (ADAS) module 236. The image acquisition module 232 can send and receive data to and from the camera 218. For example, the image acquisition module 232 can control the acquisition settings of the camera 218, such as aperture, light sensitivity, depth of field, field of view, shutter speed, frame rate, etc. In some examples, the camera 218 can operate at a frame rate in a range between 4 to 24 frames per second to capture substantially continuous images of a vehicle interior. In other examples, the frame rate can be lower, such as one frame per second or every several seconds (e.g., 30-60 seconds), or higher (e.g., 30 frames per second).For example, the frame rate may be selected based on the processing speed of the image analysis module 234 so that each image can be completely analyzed before the image analysis module 234 receives a next image in the sequence.

[0020] Additionally, the image capture module 232 may update the capture settings of the camera 218 based on the feedback received from the image analysis module 234. For example, the image analysis module 234 may determine that the images captured by the camera 218 are too dark and update one or more of the settings, such as aperture, light sensitivity, and shutter speed, on the image capture module 232 accordingly.

[0021] The image analysis module 234 may access images / videos (e.g., an image library) stored in memory and analyze the images received from the camera 218 in real time to identify one or more features in each of the received images. For example, the image analysis module 234 may compare a real-time image received from the camera 218 with an image stored in memory to identify occupants inside the vehicle, including a driver and / or a non-driving occupant (e.g., a passenger). Additionally or alternatively, the image analysis module 234 may use a computer vision model or algorithm to identify the driver and / or the non-driving occupant. In some examples, the image analysis module 234 may further analyze the image, such as with a biometric algorithm that performs facial recognition, to uniquely identify the occupant(s).For example, to illustrate, the biometric algorithm may compare the driver's face with identification photos of all known drivers of the vehicle to uniquely identify the driver. Furthermore, the computing system 220 may store user-specific settings and information, including entry and exit seat settings, associated with each known / repeated vehicle occupant in memory.

[0022] In some examples, the image analysis module 234 may create a model of each occupant that includes skeletal tracking. The skeletal tracking may identify various skeletal joints of the occupant (e.g., the driver or the front passenger), which may correspond to actual joints of the occupant, midpoints of various anatomical structures, endpoints of the occupant's extremities, and / or points with no direct anatomical connection within the occupant (e.g., not associated with a specific anatomical structure), and map a simplified virtual skeleton to the occupant. Since each occupant joint has at least three degrees of freedom (e.g., world space x, y, z), each joint of the virtual skeleton used for skeletal tracking may be defined with a three-dimensional (3D) position, and changes in that 3D position may represent movement.In some examples, each joint of the virtual skeleton may also be defined with respect to the angle of rotation in 3D space and with respect to a centerline of the virtual skeleton. In some examples, the image analysis module 234 may use depth and / or visible light information acquired by the camera 218 to define an envelope of the occupant (e.g., the surface area and volume of the occupant), which in turn may be used to estimate a size of the occupant (e.g., a body mass index, height, etc.). As further explained herein and described with reference to FIG. Fig. 4 and Fig. 5, the virtual skeleton can be used to determine limb lengths and joint angles. The limb lengths and joint angles can be used by the image analysis module 234 alone or in combination with the envelope to determine a 3D posture estimate as well as a recommended (e.g., desired) posture for the respective occupant that, given the person's size and limb lengths, increases their comfort and / or health. Additional details are provided below with respect to Fig. 3 described.

[0023] In some examples, in addition to or alternatively to determining the envelope, the computing system 220 may receive body measurement inputs from the occupant(s). For example, the ADAS module 236 may prompt the occupant to enter height and weight via a user interface 216 similar to the one described in Fig. 1. In particular, the height and weight measurements may be received via an input device 240, and the ADAS module 236 may share the received information with the image analysis module 234. In some examples, the user interface 216 may be included in a smartphone (or tablet, smartwatch, etc.), and the smartphone may run a companion application (often referred to as a companion app) that interfaces with the ADAS module 236 of the vehicle-based computing system 220 to receive occupant inputs.

[0024] In some examples, computing system 220 may additionally or alternatively receive occupant weight measurements from seat sensors. For example, a driver seat sensor (e.g., driver seat sensor 124) may output a driver weight measurement to computing system 220, and the weight measurement may be used by image analysis module 234 alone or in combination with the images from camera 218 and / or the measurements received via input device 240 to determine the driver's body measurements.

[0025] Furthermore, in some examples, the image analysis module 234 may be integrated into the in-vehicle computing system 220, or it may be accessible via a user-provided mobile computing system, such as a smartphone, computer, or tablet. As another example, the image analysis module 234 may be integrated via a networked computing system, such as a cloud computer or similar computing environment, and may be accessible remotely (e.g., via a wireless network, such as the one described in Fig. 1 shown wireless network 132). Although the image analysis module 234 in the Fig. 2, in other embodiments, at least portions of the image analysis module 234 may be stored in computing devices and / or networks external to the computing system 220 that are communicatively coupled to the computing system 220.

[0026] Once the computing system 220 detects a significant difference between the estimated posture and the recommended posture, the computing system 220 issues a first command in response to a difference between the current posture and the recommended posture exceeding a threshold difference, the first command being configured to cause one or more actuators 214 to provide force feedback to the occupant. Each actuator 214 of the one or more actuators 214 may be implemented in the same or a different manner than the other actuators 214 of the one or more actuators. Each actuator 214 may be any type of actuator capable of providing any force feedback to the occupant. One or more actuators 214 may be disposed in or on a seating bottom of a vehicle seat in which the occupant sits.Additionally or alternatively, one or more actuators 214 may be arranged in or on a backrest and / or a headrest of the vehicle seat. Depending on where the one or more actuators 214 are arranged in or on the vehicle seat, the force feedback may be provided, for example, to the occupant's legs, the occupant's buttocks, the occupant's back, the occupant's shoulders, the occupant's neck, and / or the occupant's head.

[0027] The force feedback to the occupant may, for example, include generating vibrations that can be perceived by the occupant and / or exerting pressure on one or more parts of the occupant's body. That is, according to some embodiments, at least one of the one or more actuators 214 may be configured to provide vibration feedback to the occupant. Additionally or alternatively, at least one of the actuators may be configured to adjust the settings of a lumbar support integrated into the vehicle seat, thereby providing pressure feedback to the occupant. In this way, defined impulses that stimulate limb movement can be provided to the occupant.In particular, if the occupant perceives force feedback from one or more of the actuators 214, this can be understood as an indication that the occupant's current posture does not correspond to the recommended posture. Furthermore, any type of force feedback perceived by an occupant generally triggers at least unconscious movements of one or more body parts. In this way, the occupant is encouraged to adopt a slightly different, e.g., more upright, posture without startling them and with only little interaction from the occupant. This means that the occupants, and in particular the driver of a vehicle, are not distracted. By providing force feedback and / or by redistributing pressure to certain body parts, the occupant is encouraged to adopt an upright posture, which is generally considered desirable.In this way, the comfort of the occupant is significantly improved and fatigue can be reduced.

[0028] A method for performing the data flow of Fig. 2 will now be described. With reference to Fig. 3 illustrates an exemplary method 300 for determining the posture of a vehicle occupant and issuing a first command. The method 300 may be performed by a processor of a computing system (e.g., the computing system 120 of Fig. 1 or the computing system 220 of Fig. 2) be executed based on instructions stored in a memory of the computing system (e.g., the memory 144 of Fig. 1) are stored. The method 300 is described with regard to the systems and components of the Fig. 1 and Fig. 2. However, it is understood that the method may also be performed with other systems and components without exceeding the scope of the present disclosure. For clarity, method 300 is described with respect to an occupant, which may be a driver or a passenger of the vehicle, although method 300 may be used to determine the posture of more than one occupant simultaneously.

[0029] In some examples, method 300 may be performed in response to a new occupant being detected and / or in response to the occupant adjusting their seat. As another example, method 300 may additionally or alternatively be performed at a predetermined frequency during vehicle operation, such as every 10 minutes, every 30 minutes, every 60 minutes, etc. In some examples, a user may select or set the predetermined frequency. Furthermore, in some examples, method 300 may be temporarily disabled (e.g., automatically or by the occupant) and / or modified during low visibility (e.g., fog, heavy rain, snow) or poor road conditions (e.g., slippery, icy, or bumpy) while the vehicle is traveling at a non-zero speed, as explained in more detail below.

[0030] At 302, the method 300 includes receiving images from a camera. As described above with respect to Fig. As described in Figure 1, the camera may include one or more optical cameras, infrared cameras, and depth cameras, and may include one or more viewpoints for capturing images. Furthermore, the camera may capture a series of images at a preprogrammed frequency, such as a frequency in the range of 8 to 24 frames per second. Alternatively, the preprogrammed frequency may be greater than 24 frames per second or less than 8 frames per second. The computing system may receive the images captured by the camera via wired or wireless communication methods such as Ethernet, USB, Bluetooth®, and Wi-Fi.

[0031] At 304, the method 300 includes analyzing the images received from the camera to determine the posture of the occupant. As described above with respect to Fig. 2, the computing system may include an image analysis module (e.g., image analysis module 234) that analyzes the images received from the camera in real time to identify one or more features of the occupant in each of the received images. For example, the image analysis module may use one or any combination of an image library, a model, and an algorithm to recognize the vehicle occupant as well as interior features of the vehicle, such as a seat on which the occupant is sitting, a steering wheel, etc. For example, the computing system may distinguish the driver from one or more other vehicle occupants based on the position of each occupant relative to the steering wheel.

[0032] In some embodiments, the computing system may perform facial recognition (e.g., via a biometric algorithm) to determine the occupant's identity. The identity may include, for example, a name or a user identification number associated with previously received / measured / estimated body measurements, recommended postures, seating settings, or other preferences. If the occupant is unknown, such as if the occupant has not been previously identified, the computing system may create a new user identification number and store images of the occupant for future facial recognition.

[0033] Analyzing the images received from the camera to determine the occupant's posture includes determining the occupant's body measurements, as indicated at 306. The body measurements may include, but are not limited to, an arm length, a foot length or shoe size, a thigh length, a height, a neck length and waist circumference, a weight, and a body mass index (BMI). In some examples, the occupant inputs at least one of the body measurements via a user interface (e.g., the user interface 116 of Fig. 1 or the user interface 216 on Fig. 2). The user interface may be integrated into the vehicle or contained in a mobile device (e.g., a smartphone, tablet, or smartwatch) running a companion application that communicates with the computing system. For example, the user interface may prompt the occupant to enter and / or update their body measurements at a specific frequency (e.g., once a month) or upon detection of a new occupant. As another example, the computing system may additionally or alternatively receive information about at least one of the occupant's body measurements from an in-vehicle sensor, such as a weight sensor positioned in the seat (e.g., the driver seat sensor 124 in Fig. 1), received.

[0034] Additionally or alternatively, the computing system may estimate at least one of the body dimensions based on the received images. For example, the depth and / or visible light information captured by the camera may be used to determine the surface area and / or volume of the occupant, which in turn may be used to determine the various body dimensions. In addition, skeletal tracking may be used to identify joints (e.g., joint angles) and limb lengths. As discussed above with respect to Fig. 2 and in the Fig. 4 and Fig. 5, the computing system can model a virtual skeleton of the occupant to determine joint angles and limb lengths.

[0035] Analyzing the images received from the camera to determine the occupant's posture includes determining the occupant's body dimensions, as indicated at 308. The seat position may include, for example, a seat height, a seat angle (e.g., of the seatback relative to the seat cushion), a seat tilt (e.g., of the seat cushion), and a fore / aft position. For example, the computing system may identify the seat, including the seatback, the seat cushion, and a headrest, via a computer vision or image recognition algorithm and geometrically analyze the seatback relative to the seat cushion, the seat relative to the instrument panel, etc., to determine the seat position. Additionally or alternatively, the computing system may determine the seat position based on the output of a seat position sensor and / or based on the feedback of a seat motor (or its setting).

[0036] If the occupant is the driver, analyzing the images received from the camera to determine the occupant's posture may include determining a steering wheel position, as optionally indicated at 310. The steering wheel position may include, for example, a height and tilt angle of the steering wheel. The computing system may identify the steering wheel using a computer vision or image recognition algorithm and geometrically analyze the steering wheel relative to the instrument panel, vehicle ceiling, vehicle floor, etc., to determine the steering wheel position. Additionally or alternatively, the computing system may determine the position of the steering wheel based on feedback (or adjustment) from an electric motor in the steering column used to adjust the position of the steering wheel.

[0037] Analyzing the images received from the camera to determine the occupant's posture may include determining the occupant's body position relative to the seat, as indicated at 312. The occupant's body position relative to the seat may include, for example, a distance between the occupant's head and the headrest, a distance between the occupant's shoulders relative to the seatback, a distance between the occupant's hips relative to the seatback and the seat cushion, and a distance between the occupant's knees and the seat cushion. The distance for each of the above examples may be zero or non-zero. An example where the distance between the occupant's head and the headrest is zero is described with respect to Fig. 4, while an example where the distance between the occupant’s head and the headrest is not zero is described in relation to Fig. 5. Furthermore, the computing device may estimate the various distances described above using a real-world measurement scale (e.g., inches), a pixel-based scale, or another measurement scale that allows the computing device to compare distances from image to image. For example, the computing system may use an edge detection algorithm to determine a first boundary of the driver's head and a second boundary of the headrest, and then determine the number of pixels on a shortest path directly between the first and second boundaries.

[0038] If the occupant is the driver, analyzing the images received from the camera to determine the occupant's posture may further include determining the occupant's body position relative to the steering wheel, as optionally indicated at 314. For example, the occupant's body position relative to the steering wheel may include a distance between the steering wheel and the torso, a distance between the steering wheel and the thigh, etc. For example, the computing system may use an edge detection algorithm to determine a first boundary of the steering wheel and a second boundary of the driver's torso, and then determine a distance (e.g., in a real-world unit of measurement, a number of pixels, or other measurement scale) on a shortest path directly between the first boundary and the second boundary.

[0039] At 316, method 300 includes determining a recommended posture based on the user's body measurements. The computing system may use these body measurements to derive the recommended seating posture according to the posture recommendations stored in memory. The posture recommendations may, for example, apply a variety of body-part-specific rules for ergonomic and effective vehicle operation that can be adapted to a variety of body measurements. The posture recommendations may include, among other things, a threshold seat angle range, a threshold steering wheel-to-torso distance, a threshold steering wheel-to-thigh distance, a threshold head-to-headrest distance, a threshold knee angle range, a threshold hip angle range, a threshold elbow angle range, etc.For example, the computing system may input the occupant's body measurements into one or more lookup tables or algorithms that can output specific posture recommendations for the given body measurements. For example, the threshold distance between the steering wheel and the torso may be greater for individuals with longer limbs (e.g., longer arms and / or legs) than for individuals with shorter limbs. As another example, the threshold distance between the head and the head restraint may be the same regardless of body measurements. The lookup table(s) or algorithm(s) may further output a recommended seating position and a recommended steering wheel position that result in the recommended posture according to the posture recommendations for the given body measurements.In some examples, the posture recommendations may also be machine-learned, so that the multitude of body-part-specific rules can be updated or refined according to the data collected for the specific occupant or similarly sized occupants.

[0040] Additionally, in some examples, the occupant can enter physical limitations that may affect their posture. For example, the occupant may be unable to sit according to the standard body-part-specific rules due to a disability or degenerative condition. This allows the computing system to adapt the multitude of body-part-specific rules for the individual occupant based on the entered physical limitations. For example, the occupant may have a permanent spinal curvature that limits their ability to sit with their shoulders and head back. This allows the occupant to enable accessibility settings and enter information about the back's range of motion.

[0041] In some examples, the computing system may further consider driving conditions, including weather conditions, terrain conditions, the duration of a current vehicle trip, etc. For example, the plurality of body-part-specific rules may be adjusted or relaxed during poor driving conditions, allowing the occupant, particularly if the occupant is the driver, greater freedom of movement within the recommended body posture. For example, in poor visibility conditions, the driver may instinctively lean their body forward (e.g., toward the steering wheel). As another example, the plurality of body-part-specific rules may be less relaxed during a long trip to avoid fatigue.

[0042] At 318, method 300 includes determining a posture difference between the recommended posture and the determined occupant posture. For example, the computing system may compare the actual seating posture determined from the camera images and the recommended posture determined from the body measurements by comparing each specific posture recommendation to the determined posture. That is, the actual seating position may be compared to the recommended seating position, an actual elbow angle of the occupant may be compared to the threshold elbow angle range, etc. In some examples, the computing system may weight each posture component (e.g., seating position, steering wheel position, elbow angle, hip angle, various safety margins) differently according to its posture contribution.For example, because seat position can affect some or all of the various distances and joint angles, seat position may be given greater weight in the comparison, so that smaller differences in seat position (e.g., one or more seat angles, seat height, and fore / aft position) may have a greater impact in determining whether the postural difference is significant, as described below. Thus, the postural difference may, at least in some examples, include a weighted sum.

[0043] At 320, method 300 includes determining whether the posture difference is significant. A significance level of the posture difference may be derived using statistical analysis, such as standard rules of thumb. In some examples, the computing system may consider body mass index as an additional factor in the derivation. For example, an overweight body mass index may negatively impact postural dynamics, so even small posture differences in such individuals may be considered significant.

[0044] The method includes determining whether the posture difference is greater than or equal to a posture difference threshold, such as by summing or tabulating a magnitude difference or a percentage difference of all deviations between the user's posture and the recommended posture and comparing the sum to the posture difference threshold. The posture difference threshold may be a non-zero magnitude difference or a percentage difference stored in memory, corresponding to, for example, a significant posture difference. As mentioned above, some posture components may be given greater weight in the determination.

[0045] If the posture difference is significant (e.g., statistically significant) or greater than or equal to the threshold, method 300 proceeds to 322 and includes issuing a first command that causes one or more actuators to provide force feedback to the occupant. Method 300 may then end.

[0046] For example, if the posture difference is not significant or is below the threshold difference, method 300 may return to 302. Alternatively, method 300 may end if the posture difference is not significant or is below the threshold difference. According to some examples, if the posture difference is not significant (less than the threshold difference), the occupant may be encouraged to maintain their current posture because the occupant's posture substantially matches the recommended posture. In some examples, the user interface may output an icon or any type of feedback and / or message, e.g.,a green check mark next to a posture element on a display or a beep played through the speakers to inform the user that they are sitting in the recommended posture and to encourage them to maintain their current posture.

[0047] According to some examples, a posture score may be determined based on the difference between the current posture and the recommended posture, where the posture score is highest when the difference between the current posture and the recommended posture is zero and gradually decreases as the difference increases. For example, the posture score may be 100% when the difference between the current posture and the recommended posture is zero. The greater the difference between the current posture and the recommended posture, the lower the posture score.In response to a difference between the current posture and the recommended posture not exceeding the threshold difference, a second command may be issued, wherein the second command is configured to cause a user interface to provide feedback to the occupant. According to some examples, the feedback presented to the occupant includes a suitable representation of the posture assessment. This may include any type of visualization of the posture assessment.

[0048] In this way, the occupant can be provided with positive feedback if their current body position matches or does not deviate significantly from a recommended body position. This encourages the occupant to maintain their current body position. According to some examples, gamification elements, such as progress monitoring, can be provided to the occupant. It is also possible for occupants to receive rewards if they maintain a body position that is considered good. Alternatively or additionally, regular progress reports can be provided to the occupant. It is even possible for the results of the posture difference determination to be integrated with one or more of the occupant's smart devices for further motivation.Following further examples, the results of the posture difference assessment can be provided to insurance companies. Insurance premiums can be determined based on the results of the posture difference assessment. For example, insurance rates can be reduced if the insured person generally maintains good posture.

[0049] As one example, ADAS module 236 may be connected to user interface 216 to enable output via a display 238. Display 238 may be integrated into the vehicle or be a display on a smartphone running a companion app. Display 238 may, for example, output messages and / or icons.

[0050] Example parameters or components that are determined by a computing system (e.g., the computing system 120 of Fig. 1 or the computing system 220 Fig. 2) can be used in determining a driver’s posture will now be discussed with reference to the Fig. 4 and Fig. 5. Features from the Fig. 4 and Fig. 5, which are the same in the different rider postures, are numbered the same and are not reintroduced between the figures, while parameters (e.g. angles and distances) that change between the different rider postures are numbered differently, as explained in more detail below. For example, the Fig. 4 and Fig. 5 each show a side view of a driver 402 sitting on a driver seat 404, which may be, for example, the driver seat 104 of Fig. 1. The driver's seat 404 includes a headrest 404a, a backrest 404b, and a seat cushion 404c. The backrest 404b has a length 406, and the seat cushion 404c has a length 410. Furthermore, the driver's seat 404 is connected to the vehicle floor (not shown) via a seat base 440. The seat base 440 is fixedly connected to the floor of the vehicle (e.g., bolted) and does not move relative to the vehicle floor. However, the driver's seat 404 can move relative to the seat base. For example, a vertical position (e.g., the seat height) and a longitudinal position (e.g., how far forward or rearward the seat is relative to the front and rear of the vehicle) of the driver's seat 404 can be adjusted relative to the seat base 440. Each of the Fig. 4 and Fig. 5 further includes a steering wheel 412, which, for example, is the steering wheel 112 of Fig. 1, and a pedal 444, which may be an accelerator pedal, a brake pedal, or a clutch.

[0051] A virtual skeleton 408 may be mapped (e.g., overlaid) onto the driver 402 and may include nodes representing joints and dashed lines representing the general connectivity of the joints. In the example shown, the virtual skeleton 408 represents ankle, knee, hip, wrist, elbow, shoulder, and neck joints. The virtual skeleton 408 may be used by the computing system to determine the driver's posture, as described above with respect to Fig. 2 and Fig. 3. For example, the virtual skeleton 408 and thus the driver 402 has an upper body length 418 extending between the neck joint and a midpoint between the hip joints (e.g., at a pelvis), a thigh length 420 extending between the hip joint and the knee joint, a lower leg length (e.g., shin length) 424 extending between the ankle joint and the knee joint, an upper arm length 428 extending between the shoulder joint and the elbow joint, and a forearm length 430 extending between the elbow joint and the wrist. Although in the Fig. 4 and Fig. 5, other body measurements can also be estimated, such as an angle of the head 416 of the driver 402, a foot length and a foot angle, etc. The Fig. 4 and Fig. 5 are therefore intended to illustrate non-limiting examples of various body measurements that may be determined according to the systems and methods described herein and to illustrate an exemplary embodiment of body posture mapping using a virtual skeleton.

[0052] Now, with reference to Fig. 4 shows a first posture 400. The first posture 400 is an example of a recommended driving posture that corresponds to the posture recommendations for ergonomic and effective vehicle operation, as described with reference to Fig. 3. In the first posture 400, the driver's seat 404 is positioned at a seat angle 414, and the head 416 rests against the headrest 404a such that there is no distance (e.g., a gap) between the head 416 and the headrest 404a. For example, the seat angle 414 may be within a threshold range for the driver's comfort and visibility. The threshold range may help ensure that the driver 402 is not reclined so far that vehicle operation is impeded and is not inclined so far that comfort is compromised.

[0053] The first body posture 400 further includes a first clearance 434 between the steering wheel 412 and the upper body of the driver 402, a second clearance 436 between the steering wheel 412 and the thigh of the driver 402, and a longitudinal seating position represented by a distance 442 between a forwardmost upper corner of the seat base 440 (relative to the vehicle) and a forwardmost edge of the seat cushion 404c. However, the computing system may also use other reference values ​​to determine the longitudinal seating position. Although not shown in the present example, a seat height may also be determined.

[0054] The first body posture 400 further includes a knee angle 426, a hip angle 422, and an elbow angle 432. The knee angle 426 is formed at the knee joint between the lower leg length 424 and the thigh length 420, the hip angle is formed at the hip joint between the thigh length 420 and the torso length 418, and the elbow angle 432 is formed at the elbow joint between the forearm length 430 and the upper arm length 428. Although Fig. 4 is a two-dimensional representation of a 3D scene, the knee angle 426, the hip angle 422 and the elbow angle 432 can be defined in three dimensions (e.g., using x, y and z spatial coordinates).

[0055] Due to the longitudinal seating position represented by distance 442 and seat angle 414, first clearance 434 and second clearance 436 provide sufficient space for the driver to maneuver without contact with the steering wheel 412. Furthermore, knee angle 426 allows the driver to fully depress pedal 444 without fully bending the knee joint. Furthermore, because the driver's arms are bent at the obtuse elbow angle 432, the driver can easily reach the steering wheel 412.

[0056] Now, with reference to Fig. 5, a second posture 500 is shown. The second posture 500 is an example of an incorrect driving posture that can lead to overloading of the driver and / or impairing their ability to operate the vehicle. In the second posture 500, the driver's seat 404 is positioned at a seat angle 514 and has a longitudinal position with a distance 542 between the front upper corner of the seat base 440 and a front edge of the seat cushion 404c. The seat angle 514 is smaller than the seat angle 414 of the first posture 400 in Fig. 4 and lies outside the limit range for driver comfort and visibility. The seat angle 514 may, for example, be approximately 90 degrees, so that the backrest 404b is positioned vertically such that the driver 402 is bent forward toward the steering wheel 412. As a result, the hip angle 522 of the driver 402 in the second posture 500 is also smaller than the hip angle 422 of the first posture 400 of Fig. 4. The distance 542 in the second posture 500 is greater than the distance 442 in the first posture 400. Thus, the longitudinal position of the seat 404 in the second posture 500 is further forward than in the first posture 400 in Fig. 4. As a result of the longitudinal position being shifted further forward and the smaller seat angle 514, both a first distance 534 between the steering wheel 412 and the upper body of the driver 402 and the second distance 536 between the steering wheel 412 and the knee of the driver 402 are smaller than the first distance 434 and the second distance 436 in Fig. 4. As a result of the smaller second safety distance 536, the driver 402 is more likely to touch the steering wheel 412 with their knee. Furthermore, the head 416 is located a distance 538 from the headrest 404a. As a result, the driver 402 may expend additional energy and fatigue their muscles by leaning forward rather than resting their head 416 against the headrest 404a and being closer to the steering wheel 412 than would be desirable for vehicle operation.

[0057] The second posture 500 further includes a knee angle 526 and an elbow angle 532. Since the first clearance 534 in the second posture 500 is smaller than the first clearance 434 in the first posture 400, the elbow angle 532 is smaller (e.g., more acute) than the elbow angle 432 of the first posture 400 of Fig. 4. Similarly, the knee angle 526 is smaller (e.g. more acute) than the knee angle 426 of the first posture 400 in Fig. 4. Overall, the driver 402 is positioned inefficiently and in a manner that may result in strain and / or fatigue, making the second posture 500 undesirable. The computing system may accordingly provide feedback so that the occupant may transition from the second posture 500 to another posture, such as the first posture 400, such as according to the method of Fig. 3.

[0058] In Fig. 6 schematically illustrates a system for a vehicle 100. The system includes a camera 218 and a computing system 220 having instructions stored in non-transitory memory that, when executed, cause the computing system 220 to receive images of an occupant within the vehicle captured by the camera 218, determine body measurements of the occupant based on the received images, determine a current posture of the occupant based on the received images, determine a recommended posture for the occupant based on the determined body measurements, and, in response to a difference between the current posture and the recommended posture exceeding a threshold difference (poor posture), issue a first command, wherein the first command is configured to cause one or more actuators to provide force feedback 250 to the occupant.

[0059] According to some embodiments, the instructions stored in non-transitory memory, when executed, further cause the computing system 220 to determine a posture score based on the difference between the current posture and the recommended posture, where the posture score is highest when the difference between the current posture and the recommended posture is zero and gradually decreases as the difference increases.According to further embodiments, the instructions stored in non-volatile memory, when executed, further cause computing system 220 to issue a second command in response to a difference between the current posture and the recommended posture not exceeding the threshold difference (good posture), wherein the second command is configured to cause user interface 252 to provide feedback to the occupant. The feedback presented to the occupant may, for example, include a suitable representation of the posture assessment.

[0060] According to further embodiments of the disclosure, the occupant may be positioned in a seat of the vehicle 100, wherein, to determine the current posture of the occupant from the received images, the computing system 220 includes further instructions stored in the non-transitory memory that, when executed, cause the computing system 220 to determine a plurality of posture components of the occupant from the received images, wherein the plurality of posture components include an angle of each joint of the occupant, a position of the occupant relative to the seat of the vehicle, and seat position settings of the seat.To determine the recommended posture for the occupant based on the determined body measurements, the computing system 220 may further include further instructions stored in the non-transitory memory that, when executed, cause the computing system 220 to determine a plurality of recommended posture components for the occupant based on the body measurements and a plurality of body component-specific posture recommendations, wherein the plurality of recommended posture components include a recommended angle of each joint, a recommended position of the occupant relative to the seat, and recommended seat position settings.

[0061] According to some embodiments, the occupant may be positioned in a seat of the vehicle 100, the one or more actuators may be disposed in or on the seat of the vehicle 100, and the first command may include instructions for at least one of the one or more actuators to provide vibration feedback to the occupant. Alternatively or additionally, the first command may include instructions for at least one of the one or more actuators to adjust settings of a lumbar support integrated into the seat of the vehicle 100.

[0062] According to some embodiments, the system may be in communication with at least one sensor external to the system, and the instructions stored in the non-transitory memory, when executed, may further cause the computing system 220 to receive data collected by the at least one sensor external to the system and, based on the data received from the at least one sensor external to the system, make predictions about defined times at which the difference between the current posture and the recommended posture is most likely to exceed the threshold difference. The system may be in communication with at least one sensor, for example, located in or connected to a smart device worn by the occupant.

[0063] This means that the system can also aggregate data from sensors other than those located in the vehicle. In this way, the system can potentially predict when an occupant is most likely to assume an unfavorable posture. For example, it is possible that an occupant always assumes an unfavorable posture in the vehicle when returning from a sporting activity. If the system receives data from external sensors and devices, such as smartwatches or other smart devices worn by the occupant, the system can detect when the occupant is returning from a sporting activity (e.g., an elevated heart rate may have been detected over a defined period of time). In such cases (e.g., in response to a specific triggering event), the system can take action immediately at the start of a journey, even if no body position measurements have yet been taken.Alternatively or additionally, body position measurements can be performed more frequently within a specific time interval (e.g., during a journey, immediately after detecting that the occupant has completed a physical activity). This makes the system even more effective and allows for even more positive reinforcement to be provided to the occupant.

[0064] According to still further embodiments, the instructions stored in the non-transitory memory, when executed, may further cause the computing system 220 to store information about the difference between the current posture and the recommended posture in memory for later evaluation.

[0065] In Fig. 7, an exemplary method 700 is schematically illustrated. The method 700 may be performed by a processor of a computing system (e.g., the computing system 120 of Fig. 1 or the computing system 220 of Fig. 2) be executed based on instructions stored in a memory of the computing system (e.g., the memory 144 of Fig. 1) are stored. The method 700 is described with regard to the systems and components of the Fig. 1 and Fig.2. However, it should be understood that the method may also be performed with other systems and components without departing from the scope of the present disclosure. For clarity, the method 700 is described with respect to a vehicle seat, which may be a driver or passenger seat of the vehicle, but the method 700 may also be used to adjust multiple seats simultaneously. The method at 702 includes receiving images captured by the camera 218 of an occupant in the vehicle. At 704, the method includes performing body measurements of the occupant based on the received images and determining a current body posture of the occupant based on the received images. At 706, the method includes comparing the determined body posture of the occupant to a recommended body posture for the occupant.At 708, a difference between the occupant's posture and the recommended posture is determined. If a significant posture difference is determined, the method may continue to 710 and issue a first command, wherein the first command is configured to cause one or more actuators to provide force feedback to the occupant. The method may then terminate. If no significant difference in posture is determined, the method may continue to 712 and provide appropriate feedback to the occupant. For example, a representation of the determined posture rating may be presented to the occupant to provide positive feedback and encourage the occupant to maintain good posture. The method may then terminate.

[0066] The technical effect of monitoring the seating posture of a vehicle occupant and providing feedback in response to the seating posture deviating significantly from a recommended posture is that the comfort of the vehicle occupant can be increased.

[0067] The following claims particularly point out certain combinations and subcombinations that are considered novel and non-obvious. These claims may refer to "a" element or "a first" element, or the equivalent thereof. Such claims should be understood to include the inclusion of one or more such elements and neither require nor exclude two or more such elements. Other combinations and subcombinations of the disclosed features, functions, elements, and / or properties may be claimed by amending the present claims or by filing new claims in this or a related application.Such claims, whether broader, narrower, equal, or different in scope than the original claims, are also considered to be included within the subject matter of the present disclosure.

Claims

[1] A system for a vehicle (100), the system comprising: a camera (218); and a computing system (220) including instructions stored in a non-transitory memory that, when executed, cause the computing system (220) to: Receiving images taken of an occupant in the vehicle by the camera (218); Determining the occupant’s body measurements based on the received images; Determining the current posture of the occupant based on the received images; Determining a recommended posture for the occupant based on the determined body measurements; and Issuing a first command in response to a difference between the current posture and the recommended posture exceeding a threshold difference, the first command configured to cause one or more actuators to provide force feedback to the occupant. [2] The system of claim 1, wherein the instructions stored in the non-transitory memory, when executed, further cause the computing system (220) to: Determining a posture score based on the difference between the current posture and the recommended posture, where the posture score is highest when the difference between the current posture and the recommended posture is zero and gradually decreases as the difference increases. [3] The system of claim 2, wherein the instructions stored in the non-transitory memory, when executed, further cause the computing system (220) to: Issuing a second command in response to a difference between the current posture and the recommended posture not exceeding the threshold difference, the second command being configured to cause a user interface to present feedback to the occupant. [4] The system of claim 3, wherein the feedback presented to the occupant comprises a representation of the posture assessment. [5] A system according to any one of the preceding claims, wherein the occupant is positioned on a seat of the vehicle (100), and wherein the computing system (220), in order to determine the current posture of the occupant from the received images, includes further instructions stored in the non-transitory memory which, when executed, cause the computing system (220) to: Determining a plurality of posture components of the occupant from the received images, wherein the plurality of posture components include an angle of each joint of the occupant, a position of the occupant relative to the seat of the vehicle, and seat position settings of the seat. [6] The system of claim 5, wherein the computing system (220) for determining the recommended posture for the occupant based on the determined body measurements includes further instructions stored in the non-transitory memory that, when executed, cause the computing system (220) to: Determining a plurality of recommended posture components for the occupant based on the body measurements and a plurality of body component-specific posture recommendations, wherein the plurality of recommended posture components includes a recommended angle of each joint, a recommended position of the occupant relative to the seat, and recommended seat position settings. [7] The system of any preceding claim, wherein the occupant is positioned on a seat of the vehicle (100), the one or more actuators are disposed in or on the seat of the vehicle (100), and the first command includes instructions for at least one of the one or more actuators to provide vibration feedback to the occupant. [8] A system according to any one of the preceding claims, wherein the occupant is positioned on a seat of the vehicle (100), the one or more actuators may be arranged in or on the seat of the vehicle (100), and wherein the first command includes instructions for at least one of the one or more actuators to adjust settings of a lumbar support integrated into the seat of the vehicle (100). [9] The system of any preceding claim, wherein the system is in communication with at least one sensor external to the system, and the instructions stored in a non-transitory memory, when executed, further cause the computing system (220) to: Receiving data collected by the at least one sensor outside the system; and based on data received from the at least one sensor external to the system, making predictions about defined points in time at which a difference between the current posture and the recommended posture is most likely to exceed the threshold difference. [10] The system of claim 9, wherein the system is in communication with at least one sensor located in or connected to an occupant-worn smart device. [11] The system of any preceding claim, wherein the instructions stored in the non-transitory memory, when executed, further cause the computing system (220) to: Storing information about the difference between the current posture and the recommended posture in memory for later evaluation.

Images