Seat device

Abstract

[Task] To provide a seat device capable of accurately estimating the position of a sole. [Solution] A seat device (1) is provided with: a seat body (2) provided behind an operation pedal (3); a sensor 10 mounted on the seat surface 7 of the seat body 2 and configured to detect a body pressure distribution of the seated person; and a controller configured to estimate a position of a sole of a right foot of the seated person based on the body pressure distribution. The controller is configured to estimate the position of the sole of the right foot based on a body pressure distribution in each of a plurality of monitoring areas provided in different positions on the seat surface 7.

Description

Technical Field

[0001] This invention relates to a seating device. Background Technology

[0002] Patent Document 1 discloses a vehicle control system that detects preparatory actions or movements unconsciously performed by the driver and controls the vehicle based on these actions or movements. The vehicle control system detects posture changes that occur immediately before the driver operates the brake or accelerator pedal, based on pressure distribution and center of gravity shift vectors obtained from pressure sensors located in the seat cushion, and performs vehicle control actions such as acceleration or deceleration when the posture change corresponds to a preparatory action or movement. As a result, the delay in response to driving operations in the vehicle is reduced, thereby improving safety and comfort.

[0003] Existing technical documents Patent documents

[0004] Patent Document 1: Japanese Patent No. 4740399 Summary of the Invention

[0005] The task to be accomplished by the invention

[0006] In the invention described in Patent Document 1, posture is estimated based on the pressure distribution over an entire area of ​​the seat cushion, specifically the area including the ischium position of the seated person. Therefore, the pressure exerted by the ischium of the hips becomes dominant, and changes in leg pressure are relatively small and tend to be masked. Consequently, it is difficult to accurately detect and estimate the position and movement of the feet, and there are limitations in the accuracy of predicting driving operations performed via the legs, such as braking or accelerator operation.

[0007] In view of the above background, the object of the present invention is to provide a seat device that can accurately estimate the position of the soles of the feet.

[0008] means of completing the task

[0009] To achieve this objective, one aspect of the present invention provides a seating device comprising: a seat body disposed behind an operating pedal; a sensor mounted on a seat surface of the seat body and configured to detect a body pressure distribution of a seated person; and a controller that estimates the position of the sole of the right foot of the seated person based on the body pressure distribution, the controller being configured to estimate the position of the sole of the right foot based on the body pressure distribution in each of a plurality of monitoring areas disposed at different locations on the seat surface.

[0010] The effects of the invention

[0011] Based on this, it is possible to provide a seat device that can accurately estimate the position of the feet. Attached Figure Description

[0012] Figure 1 is a perspective view of the seating device according to an embodiment. Figure 2 is an explanatory diagram showing the structure of the seating device. Figure 3 is an explanatory diagram showing the position of the sole of the right foot of a seated person. Figure 4 is an explanatory diagram showing the pressure distribution obtained by a first sensor installed in the seat cushion. Figure 5 is an illustration of the feature quantities obtained based on pressure distribution. Figure 6 is a flowchart illustrating the process for estimating the position of the sole of a seated person's right foot. Figure 7 is an illustrative diagram showing the body pressure distribution obtained by the first and second sensors. Figure 8 is an explanatory diagram showing an example of the monitoring area according to a modified embodiment. Figure 9 is an explanatory diagram showing an example of the monitoring area according to a modified embodiment. Figure 10 is an explanatory diagram showing an example of the monitoring area according to a modified embodiment. Detailed Implementation

[0013] Hereinafter, embodiments of the seat device of the present invention applied to a driver's seat of an automobile will be described with reference to the accompanying drawings.

[0014] As shown in Figure 1, the seat assembly 1 includes a seat body 2 mounted on the floor of the vehicle. The seat body 2 constitutes the driver's seat of the vehicle. The seat body 2 is located behind the vehicle's operating pedals 3. The operating pedals 3 include an accelerator pedal 3A and a brake pedal 3B.

[0015] The seat body 2 includes: a seat cushion 5 that supports the buttocks of a seated person from below; and a seat back 6 that extends upward from the rear of the seat cushion 5 and supports the back of the seated person from behind. Each of the seat cushion 5 and seat back 6 includes a frame, a padding supported by the frame, and an outer material covering the padding. The seat cushion 5 is disposed on the floor of the vehicle. A sliding device or a lifting device may be provided between the floor and the seat cushion 5.

[0016] The seat body 2 includes a seat surface 7 that supports a seated person. The seat surface 7 includes the upper surface of the seat cushion 5 and the front surface of the seat back 6. The seat surface 7 is equipped with sensors 10 capable of detecting the body pressure distribution of the seated person.

[0017] Sensor 10 is preferably a sheet-like pressure distribution sensor capable of measuring the body pressure distribution of a seated person. The pressure distribution sensor can be configured to have multiple pressure sensing elements arranged in a grid or matrix pattern to acquire the pressure distribution on a two-dimensional plane in a regional manner. The pressure sensing elements are incorporated into a layered sensor sheet comprising a pressure-sensitive material or structure.

[0018] Pressure sensing elements can be, for example, resistive sensors made of conductive polymers or conductive rubber whose resistance changes with pressure. Pressure sensing elements can also be capacitive sensors that detect changes in capacitance between electrodes, piezoelectric sensors that generate charge in response to pressure, or arrays of force sensors.

[0019] The substrate constituting the sensor sheet can be flexible PET film, silicon-based materials, etc. The sensor sheet can flexibly adapt to the curved shape of the seat surface 7 and the bending deformation during use.

[0020] Sensor 10 includes a first sensor 10A disposed on the upper surface of the seat cushion 5 constituting the seat surface 7, and a second sensor 10B disposed on the front surface of the seat back 6. The first sensor 10A is preferably disposed between the upper surface of the cushion constituting the seat cushion 5 and the cover material. The second sensor 10B is preferably disposed between the upper surface of the cushion constituting the seat back 6 and the cover material.

[0021] As shown in Figure 4, each of the first sensor 10A and the second sensor 10B includes a plurality of detection units 11 arranged in a grid pattern along the surface. The plurality of detection units 11 are arranged in the X and Y directions. In this embodiment, each of the first sensor 10A and the second sensor 10B has 16×16 detection units 11. The position of each detection unit 11 is represented by its position in the X direction and its position in the Y direction. The first sensor 10A is arranged such that the X direction corresponds to the left-right direction and the Y direction corresponds to the front-back direction. The X direction value increases from right to left (X01 to X16), and the Y direction value increases from front to back (Y01 to Y16). The second sensor 10B is arranged such that the X direction corresponds to the left-right direction and the Y direction corresponds to the up-down direction. In the second sensor 10B, the X direction value increases from right to left (X01 to X16), and the Y direction value increases from bottom to top (Y01 to Y16).

[0022] As shown in Figure 2, a first sensor 10A and a second sensor 10B are connected to a seat controller 20. The seat controller 20 is an electronic control device including a processor 21 and a memory 22 communicatively connected to the processor 21. The processor 21 may include at least one of a central processing unit (CPU), a graphics processing unit (GPU), and a reduced instruction set computer (RISC) as its core. The memory 22 may include at least one of volatile memory and non-volatile memory. Volatile memory may be, for example, dynamic random access memory (DRAM) or static random access memory (SRAM). Non-volatile memory may be a solid-state drive (SSD), flash memory, disk storage, or optical disk storage. At least a portion of the seat controller 20 may be implemented by hardware such as an LSI, ASIC, or FPGA, or by a combination of software and hardware. The processor 21 executes programs stored in the memory 22 to implement various applications. The seat controller 20 may consist of a single piece of hardware or multiple pieces of hardware capable of communicating with each other.

[0023] The processor 21 of the seat controller 20 executes the program stored in the memory 22 to function as the foot position estimation unit 25, the hazard prediction level estimation unit 26, the cause estimation unit 27, and the notification unit 28.

[0024] The foot position estimation unit 25 estimates the position of the sole of the seated person's right foot based on the body pressure distribution of the seated person. The position of the sole of the seated person's right foot includes at least the position facing the accelerator pedal 3A (see Figure 3A), the position facing the brake pedal 3B (see Figure 3B), and the position on the floor. The foot position estimation unit 25 acquires the body pressure distribution of the seated person based on signals from the first sensor 10A and the second sensor 10B. Here, the body pressure distribution includes the pressure at the plurality of detection units 11 of the first sensor 10A and the second sensor 10B. The foot position estimation unit 25 estimates the position of the sole of the seated person's right foot based on the body pressure distribution in each of the plurality of monitoring areas set at different positions on the seat surface 7.

[0025] The plurality of monitoring areas includes a first monitoring area. The first monitoring area includes at least the central portion of the right side of the seat surface 7 of the seat cushion 5 in the fore-aft direction. The first monitoring area is the area facing the right thigh of the seated person and is intended to detect the pressure distribution received from the right thigh of the seated person. The first monitoring area may be a central area obtained by dividing the right half of the seat surface 7 of the seat cushion 5 into three parts in the fore-aft direction.

[0026] As shown in Figure 4, preferably, the plurality of monitoring areas are located on the right half of the seat surface 7 of the seat cushion 5. Some of the plurality of monitoring areas may include left and right ischial support portions 31 arranged on the seat surface 7 of the seat cushion 5. The left and right ischial support portions 31 are portions corresponding to the left and right ischial bones of the seated person and may be preset based on the typical ischial position of the seated person. Alternatively, the ischial support portions 31 may be located at the position of the highest pressure in the left and right halves obtained by dividing the pressure distribution acquired by the first sensor 10A into left and right halves. The ischial support portions 31 may correspond to the area associated with the single detection unit 11 with the highest pressure, or correspond to the area including the single detection unit 11 with the highest pressure and the surrounding detection units 11.

[0027] The plurality of monitoring areas consists of four monitoring areas A1 to A4. Monitoring area A1 is located in the center of the right half of the seat surface 7 of the seat cushion 5 in the front-rear direction. The rear part of monitoring area A1 may overlap with the right ischial support 31. Monitoring areas A2 and A3 may be areas obtained by dividing monitoring area A1 into left and right halves. Monitoring area A2 may correspond to the left half of monitoring area A1, and monitoring area A3 may correspond to the right half of monitoring area A1. The rear part of monitoring area A2 may overlap with the right ischial support 31. The rear part of monitoring area A3 may be configured not to overlap with the right ischial support 31. Monitoring area A4 is located at the front right part of the seat surface 7 of the seat cushion 5. Monitoring area A4 may be configured not to overlap with the right ischial support 31. In this example, monitoring areas A1 and A2 correspond to the first monitoring area.

[0028] In this embodiment, the first sensor 10A includes 16 detection units 11 named X01 to X16 in the X direction (lateral direction) and 16 detection units 11 named Y01 to Y16 in the Y direction (front-back direction), thereby forming a 16×16 array of detection units 11. Monitoring area A1 is an 8×8 square area defined by (X1, Y7) and (X8, Y14). Monitoring area A2 is a 4×8 square area defined by (X5, Y7) and (X8, Y14). Monitoring area A3 is a 4×8 square area defined by (X1, Y7) and (X4, Y14). Monitoring area A4 is an 8×8 square area defined by (X1, Y1) and (X8, Y8).

[0029] The foot position estimation unit 25 calculates a feature quantity related to the body pressure distribution in each of the plurality of monitoring areas A1 to A4, based on the body pressure distribution in each of the plurality of monitoring areas A1 to A4, and estimates the position of the right foot's sole based on the feature quantity. The feature quantity is calculated for each monitoring area. The feature quantity may, for example, include at least one of the first to seventh feature quantities.

[0030] The first characteristic is the position of the centroid G of the body pressure distribution in each monitoring area A1 to A4 in the lateral direction (X direction) (see Figure 5). Here, the centroid G of the body pressure distribution in each monitoring area A1 to A4 is calculated based on the body pressure distribution limited to the corresponding monitoring area. The centroid G can be calculated, for example, by multiplying the pressure value at each detection point 11 of the body pressure distribution by its position in the X direction and dividing the sum by the total pressure value.

[0031] The second characteristic is the position of the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 in the front-back direction (Y direction).

[0032] The third characteristic is the proportion of areas in each monitoring zone A1 to A4 where the pressure is equal to or higher than a predetermined value. For example, in an 8×8 monitoring zone, when the number of detection units 11 where the pressure is equal to or higher than the predetermined value is 32, the proportion of areas where the pressure is equal to or higher than the predetermined value is 0.5 (=32 / 64). Instead of the proportion of areas where the pressure is equal to or higher than the predetermined value, the third characteristic can be the number of detection units 11 where the pressure is equal to or higher than the predetermined value.

[0033] The fourth and fifth characteristic quantities can be the angles centered on a reference point set on the seat surface 7 of the center of gravity G of the body pressure distribution in each monitoring area A1 to A4. In the fourth characteristic quantity, the reference point is the center point C of the seat surface 7 of the seat cushion 5 (see Figure 5). In the fifth characteristic quantity, the reference point is the ischial support 31 on the right side (see Figure 5). The center point C of the seat surface 7 of the seat cushion 5 and the right ischial support 31 can be at preset positions. Furthermore, the right ischial support 31 can be located at the position of the detection unit 11 with the maximum pressure in the right half of the pressure distribution. The angle centered on the reference point set on the seat surface 7 of the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 can be the angle relative to a reference line extending laterally through the reference point. The angle can be calculated based on the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 and the position of the reference point.

[0034] The sixth and seventh characteristics include the distance between the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 and a reference point set on the seat surface 7. In the sixth characteristic, the reference point is the center point C (center of the seat surface) of the seat surface 7 of the seat cushion 5. In the seventh characteristic, the reference point is the right ischial support 31. The distance between the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 and the reference point set on the seat surface 7 can be calculated based on the center of gravity G of the body pressure distribution in each monitoring area A1 to A4 and the position of the reference point.

[0035] In this embodiment, since the first to seventh feature values ​​are obtained for each of the four monitoring areas A1 to A4, a total of 28 feature values ​​are obtained.

[0036] The foot position estimation unit 25 uses a machine learning model to estimate the position of the right foot's sole based on feature quantities. The machine learning model receives the feature quantities as input and outputs the position of the right foot's sole. The machine learning model can be composed of known neural network models, deep learning models, etc. The machine learning model can be a trained model trained using training data. Each record of the training data includes multiple feature quantities and the position of the right foot's sole stored in association with each feature quantity. The sole position preferably includes at least three positions: "on the brake pedal," "on the accelerator pedal," and "on the floor." In this embodiment, 28 feature quantities are input into the machine learning model, and the machine learning model outputs one of the positions "on the brake pedal," "on the accelerator pedal," and "on the floor" as the position of the right foot's sole.

[0037] The foot position can be "in transition". "In transition" means the foot position does not correspond to any of "on the brake pedal", "on the accelerator pedal", or "on the floor" and the foot position is changing. In response to the input of the feature quantity, the machine learning model outputs one of "on the brake pedal", "on the accelerator pedal", "on the floor", and "in transition" as the position of the right foot.

[0038] In this context, the location of the foot in the training data used to create the machine learning model could include "on the brake pedal", "on the accelerator pedal", "on the floor", and "in the transition".

[0039] As shown in Figure 2, the seat controller 20 is connected to the vehicle control system 40. The vehicle control system 40 is an electronic control device that controls the movement of the vehicle and includes a processor 41 and a memory 42 communicatively connected to the processor 41. The configuration of the processor 41 and the memory 42 can be the same as the configuration of the processor 21 and the memory 22.

[0040] The processor 41 of the vehicle control system 40 functions as the driving control unit 44, obstacle recognition unit 45, and hazard prediction unit 46 by executing programs stored in the memory 42.

[0041] The vehicle control system 40 is connected to the accelerator pedal 3A and the brake pedal 3B. Each of the accelerator pedal 3A and the brake pedal 3B includes a sensor that detects its position and outputs a signal corresponding to the position to the vehicle control system 40. The driving control unit 44 of the vehicle control system 40 controls a propulsion device such as an internal combustion engine or an electric motor based on the position of the accelerator pedal 3A, and controls the brake based on the position of the brake pedal 3B.

[0042] The vehicle control system 40 is connected to an external environment detector 51 that detects obstacles present around the vehicle. The external environment detector 51 is a sensor that captures electromagnetic waves and light from the vehicle's surrounding environment to detect objects outside the vehicle. The external environment detector 51 includes at least one of radar, lidar, and a camera.

[0043] The obstacle recognition unit 45 of the vehicle control system 40 identifies obstacles present around the vehicle based on the detection results of the external environment recognizer 51. The obstacle recognition unit 45 identifies the surrounding environment (external environment), including obstacles around the vehicle, road shape, the presence or absence of sidewalks, road markings, etc., based on the detection results of the external environment recognizer 51. Obstacles include, for example, guardrails, utility poles, surrounding vehicles, and people such as pedestrians. The obstacle recognition unit 45 can obtain the state of obstacles from the detection results of the external environment recognizer 51, such as the position, speed, and acceleration of surrounding vehicles and pedestrians.

[0044] The hazard prediction unit 46 of the vehicle control system 40 determines whether the vehicle is in a hazardous state. Here, a hazardous state refers to a state in which the vehicle may collide with obstacles such as other vehicles, buildings, or pedestrians. The hazard prediction unit 46, for example, determines the probability of a collision between the obstacle and the vehicle, and determines the hazardous state based on the probability of a collision. For example, when the time to collision (TTC) between the obstacle and the vehicle is equal to or less than a collision threshold, the hazard prediction unit 46 determines that there is a probability of a collision between the obstacle and the vehicle. The hazard prediction unit 46 can determine the probability of colliding with an obstacle among those detected by the obstacle recognition unit 45 whose distance from the vehicle is within a specified value. The collision time can be calculated by dividing the distance between the obstacle and the vehicle by the relative speed between the obstacle and the vehicle. Furthermore, the hazard prediction unit 46 can determine the hazardous state based on blind spot information obtained through communication with other vehicles. The blind spot information may include information about pedestrians, etc., present around another vehicle and located in a position not visible from the vehicle. The hazard prediction unit 46 can determine the hazardous state based on the probability of colliding with obstacles included in the blind spot information.

[0045] The vehicle control system 40 outputs information to the seat controller 20 relating to the respective positions of the accelerator pedal 3A and the brake pedal 3B. This information may indicate whether each of the accelerator pedal 3A and the brake pedal 3B is depressed, or it may indicate the respective positions of the accelerator pedal 3A and the brake pedal 3B. The vehicle control system 40 also outputs information to the seat controller 20 relating to hazardous conditions determined by the hazard prediction unit 46. This information may indicate the presence or absence of a hazardous condition, or it may be a value obtained by quantifying the hazardous condition.

[0046] The foot position estimation unit 25 can estimate the position of the seated person's right foot based on information received from the vehicle control system 40 related to the respective positions of the accelerator pedal 3A and the brake pedal 3B. For example, when the brake pedal 3B is depressed, the foot position estimation unit 25 can determine that the seated person's right foot is operating the brake pedal 3B.

[0047] Figure 6 illustrates an example of the process for estimating the position of the feet performed by the foot position estimation unit 25 of the seat controller 20. First, the seat controller 20 acquires the body pressure distribution of the seat cushion 5 based on a signal from the first sensor 10A (ST1). Next, the seat controller 20 corrects the acquired body pressure distribution (ST2). Correction can be performed to reduce noise in the body pressure distribution. For example, the pressure value of the detection unit (unit) 11, whose pressure is equal to or lower than a predetermined lower limit, can be set to 0. Furthermore, the pressure value of the detection unit (unit) 11, whose pressure is equal to or higher than a predetermined upper limit, can be set to the upper limit. The correction process in step ST2 can be omitted.

[0048] Next, the seat controller 20 acquires the body pressure distribution (ST3) in each monitoring area of ​​monitoring areas A1 to A4. Next, the seat controller 20 calculates the first to seventh characteristic quantities (ST4) for each monitoring area of ​​monitoring areas A1 to A4.

[0049] Next, the seat controller 20 inputs the first to seventh feature values ​​acquired for each monitoring area A1 to A4 into the machine learning model, and outputs the position of the seated person's right foot (ST5). The position of the foot is one of "on the brake pedal", "on the accelerator pedal", "on the floor", and "in transition".

[0050] Next, the seat controller 20 determines whether the foot position is "in transition" (ST6). When the foot position is "in transition" (ST6: Yes), the seat controller 20 determines the foot position as "in transition" (ST7).

[0051] When the foot position is not in the "in transition" state (ST6: No), the seat controller 20 determines whether the accelerator pedal 3A or brake pedal 3B is depressed based on information received from the vehicle control system 40 related to the respective positions of the accelerator pedal 3A and brake pedal 3B (ST8). When the accelerator pedal 3A or brake pedal 3B is depressed (ST8: Yes), the seat controller 20 determines the foot position as "pedal depressed" (ST9).

[0052] When neither the accelerator pedal 3A nor the brake pedal 3B is pressed (ST8: No), the seat controller 20 determines the position of the foot as one of "on the brake pedal", "on the accelerator pedal", and "on the floor" based on the estimated foot position derived from the output of the machine learning model in step ST5 (ST10).

[0053] The hazard prediction level estimation unit 26 determines the hazard prediction level of the occupant who is the driver based on the foot position determined by the foot position estimation unit 25 and information related to the hazardous situation received from the hazard prediction unit 46. The hazard prediction level is expressed as high or low. When the hazard prediction level is "high", the occupant is highly aware of the surrounding environment of the monitoring vehicle and is able to respond immediately to unexpected situations.

[0054] When the vehicle is determined to be in a hazardous state based on information related to the hazardous state received from the hazard prediction unit 46, the hazard prediction level estimation unit 26 determines the hazard prediction level of the seated occupant based on the position of the sole of the occupant's right foot. A hazardous state can be, for example, a state where the probability of a collision between the vehicle and an obstacle is equal to or higher than a predetermined value. More specifically, a hazardous state can be a state where the time to collision (TTC) is equal to or lower than a predetermined value.

[0055] When the vehicle is in a dangerous state and the seated occupant's right foot is positioned "on the brake pedal," the hazard prediction level estimation unit 26 estimates the hazard prediction level as "high." That is, because the seated occupant's right foot is positioned "on the brake pedal," and the seated occupant is in a state where they can immediately depress the brake pedal 3B, the hazard prediction level is estimated as "high."

[0056] On the other hand, when the vehicle is in a dangerous state and the occupant's right foot is not "on the brake pedal," the hazard prediction level estimation unit 26 estimates the hazard prediction level as "low." When the occupant's right foot is not "on the brake pedal," the occupant needs time to depress the brake pedal 3B, therefore the hazard prediction level is estimated as "low."

[0057] The notification unit 28 of the seat controller 20 controls the notification device 53. The notification device 53 includes, for example, a display and a speaker, and provides notifications to the seated occupants via images or sounds. When the hazard prediction level estimation unit 26 estimates the hazard prediction level as "low," the notification unit 28 notifies the seated occupants via images or sounds that the hazard prediction level has decreased. The notification unit 28 can also prompt the seated occupants to rest.

[0058] When the hazard prediction level is equal to or lower than a predetermined value, the cause estimation unit 27 estimates the cause of the hazard prediction level being equal to or lower than the predetermined value based on the body pressure distribution. As shown in Figure 7, the body pressure distribution of the seat cushion 5 obtained by the first sensor 10A and the body pressure distribution of the seat back 6 obtained by the second sensor 10B vary depending on the seated person's seating position (correct, forward, or backward). As fatigue accumulates among the seated person, the seating position tends to shift forward. Therefore, the fatigue state of the seated person can be estimated based on the body pressure distribution. When the cause estimation unit 27 identifies fatigue as the cause of the hazard prediction level being equal to or lower than the predetermined value, the notification unit 28 can notify the seated person that they are fatigued and can issue a message prompting the seated person to rest.

[0059] This concludes the description of the specific embodiments, but the invention is not limited to the above embodiments and can be widely modified and implemented. In another embodiment, the number of monitoring areas can be appropriately changed. For example, as shown in Figures 8 to 10, six monitoring areas B1 to B6 can be set. In this case, first to seventh feature values ​​can also be obtained for each of the monitoring areas B1 to B6. Therefore, the number of feature values ​​input into the machine learning model for estimating the position of the foot is 42 (6 × 7).

[0060] Some of the multiple monitoring areas can be configured to exclude the ischial support 31. This prevents pressure from the ischium from becoming dominant and allows for accurate detection of changes in pressure exerted from the seated person's right thigh. For example, monitoring areas B2 to B6 shown in Figures 9 and 10 are examples of monitoring areas excluding the ischial support 31. On the other hand, monitoring areas A1 to A3 shown in Figure 4 and monitoring area B1 shown in Figure 8 are examples of monitoring areas including the ischial support 31. The number of monitoring areas and the number of feature quantities can be appropriately varied.

[0061] Multiple ventilation holes penetrating along the thickness direction can be formed at appropriate locations on the first sensor 10A and the second sensor 10B. These ventilation holes can be arranged to avoid the detection section 11. For example, each ventilation hole can be arranged at the boundary between adjacent detection sections 11. Alternatively, some of the detection sections 11 in the first sensor 10A and the second sensor 10B can be removed, and ventilation holes can be provided in the removed portions. The multiple ventilation holes can be arranged not to overlap with the monitoring area. The ventilation holes can be arranged opposite to ventilation channels formed in the liner. The ventilation channels can be connected to a blower. For example, the detection section 11 to be removed can be a rectangular area defined by (X01, Y01) and (X04, Y12), or a rectangular area defined by (X01, Y01) and (X04, Y16). Ventilation holes can be provided in these areas. These areas are the areas on the right half of the seat surface 7 of the seat cushion 5 that are closer to the accelerator pedal 3A than the brake pedal 3B. Therefore, these areas have a minimal impact on the accuracy of determining whether the sole of the foot is resting on the brake pedal 3B. Thus, ventilation holes can be installed without significantly reducing the accuracy of determining whether the sole of the foot is resting on the brake pedal 3B, and further, in determining the hazard prediction level.

[0062] The above embodiments can also be described as follows:

[0063] One embodiment provides a seating device 1, comprising: a seat body 2 disposed behind an operating pedal 3; a sensor 10 mounted on a seat surface 7 of the seat body 2 and configured to detect body pressure distribution of a seated person; and a controller configured to estimate the position of the sole of the right foot of the seated person based on the body pressure distribution, the controller being configured to estimate the position of the sole of the right foot based on body pressure distribution in each of a plurality of monitoring areas disposed at different locations on the seat surface 7.

[0064] Based on this aspect, since the controller estimates the position of the right foot's sole based on the body pressure distribution in each of the multiple monitoring areas on the seat surface 7, it is possible to accurately estimate the foot's position while suppressing the effects of pressure exerted from the hip. Therefore, it is possible to provide a seat device 1 capable of accurately estimating the position of the sole of the foot.

[0065] In the above embodiments, preferably, the seat body 2 includes: a seat cushion 5 configured to support the buttocks of the seated person from below; and a seat back 6 extending upward from the rear of the seat cushion 5 and configured to support the back of the seated person from behind, the plurality of monitoring areas including a first monitoring area, and the first monitoring area including at least the central portion in the front-rear direction on the right side of the seat surface 7 of the seat cushion 5.

[0066] In this respect, since the first monitoring area is located at the position corresponding to the right thigh of the seated person, it is possible to accurately capture pressure changes related to the position of the right foot, thereby further improving the accuracy of estimating the position of the foot.

[0067] In the above embodiment, preferably, the controller is configured to: calculate a feature quantity related to the body pressure distribution in each of the plurality of monitoring areas based on the body pressure distribution in each of the plurality of monitoring areas; and estimate the position of the sole of the right foot based on the feature quantity.

[0068] In the above embodiments, preferably, the feature quantity includes the centroid position G in each of the plurality of monitoring areas.

[0069] Based on this, it is possible to concisely and accurately capture changes in body pressure distribution and improve the accuracy of estimating the position of the sole of the foot by using the center of gravity position G in each monitoring area as a characteristic quantity.

[0070] In the above embodiments, preferably, the feature quantity includes the distance between the center of gravity position G in each of the plurality of monitoring areas and a reference point set on the seat surface 7.

[0071] Based on this, by including the distance between the centroid position G and the reference point as a characteristic quantity, the spatial relative relationship of the foot position can be clearly reflected, thereby achieving a more accurate estimate.

[0072] In the above embodiments, preferably, the feature quantity includes the angle of the center of gravity position G in each of the plurality of monitoring areas on the seat surface 7, the angle being centered on a reference point set on the seat surface 7.

[0073] Based on this aspect, by including the angle of the center of gravity position G centered on the reference point as a characteristic quantity, it is possible to estimate the position of the foot while reflecting the orientation and movement trend of the foot, thereby improving the reliability of the estimation.

[0074] In the above embodiments, preferably, the characteristic quantity includes the proportion of areas in each of the plurality of monitoring areas where the pressure is equal to or higher than a predetermined value.

[0075] Based on this aspect, it becomes possible to quantitatively assess the intensity and range of pressure distribution by including the proportion of regions whose pressure is equal to or higher than a certain value, thereby improving the accuracy of estimating foot location.

[0076] In the above embodiments, preferably, the controller is configured to use a machine learning model to estimate the position of the sole of the right foot based on the feature quantity, wherein the machine learning model receives the feature quantity as input and outputs the position of the sole of the right foot.

[0077] Based on this, it becomes possible to perform a highly accurate determination that comprehensively considers multiple feature quantities by using machine learning models to determine whether the sole of the foot is positioned facing the pedal.

[0078] In the above embodiment, preferably, the seat body 2 is installed in the vehicle, the operating pedal 3 is the vehicle's brake pedal 3B, and the controller is configured to determine the hazard prediction level of the seated person based on the position of the sole of the right foot when the controller determines the collision risk between the vehicle and an obstacle.

[0079] Based on this, when a collision risk exists, it is possible to determine the hazard prediction level of the seated occupant based on the position of their feet. Therefore, it is possible to provide a seat device 1 that accurately assesses the driver's reaction readiness and contributes to safe driving support.

[0080] In the above embodiments, preferably, the controller is configured to estimate the reason why the hazard prediction level is equal to or lower than the predetermined value based on the body pressure distribution when the hazard prediction level is equal to or lower than the predetermined value.

[0081] Based on this, when the hazard prediction level is low, the cause can be estimated from the distribution of body stress, making it possible to identify driver inattention or inappropriate posture and provide more appropriate driving assistance and warning controls.

[0082] List of reference numerals 1: Seating assembly 2: Seat body 3: Operation pedal 3A: Accelerator pedal 3B: Brake pedal 5: Seat cushion 6: Seat backrest 7: Seat surface 10: Sensors 10A: First sensor 10B: Second sensor 11: Testing Department 20: Seat controller 25: Foot position estimation unit 26: Hazard Prediction Level Estimation Unit 27: Cause Estimation Unit 28: Notification Unit 31: Ischial support 40: Vehicle Control System 44: Driving control unit 45: Obstacle Recognition Unit 46: Hazard Prediction Unit 51: External Environment Recognition 53: Notifier.

Claims

1. A seating device, comprising: The main body of the seat is located behind the operating pedal; A sensor is mounted on the seat surface of the seat body and configured to detect the body pressure distribution of the seated person; as well as A controller configured to estimate the position of the sole of the seated person's right foot based on the body pressure distribution, wherein, The controller is configured to estimate the position of the sole of the right foot based on the body pressure distribution in each of a plurality of monitoring areas set at different locations on the seat surface.

2. The seating device according to claim 1, wherein, The seat body includes: a seat cushion configured to support the buttocks of the seated person from below; and a seat back extending upward from the rear of the seat cushion and configured to support the back of the seated person from behind. The plurality of monitoring areas includes a first monitoring area, and The first monitoring area includes at least the central portion of the right side of the seat surface of the seat cushion in the front-to-back direction.

3. The seating device according to claim 2, wherein, The controller is configured as follows: Based on the body pressure distribution in each of the multiple monitoring areas, calculate the characteristic quantity related to the body pressure distribution in each of the multiple monitoring areas; and The position of the sole of the right foot is estimated based on the aforementioned feature quantity.

4. The seating device according to claim 3, wherein, The feature quantity includes the centroid position in each of the plurality of monitoring areas.

5. The seating device according to claim 3, wherein, The characteristic quantity includes the distance between the center of gravity position in each of the plurality of monitoring areas and a reference point set on the seat surface.

6. The seating device according to claim 3, wherein, The characteristic quantity includes the angle of the center of gravity position in each of the plurality of monitoring areas on the seat surface, the angle being centered on a reference point set on the seat surface.

7. The seating device according to claim 3, wherein, The characteristic quantity includes the proportion of areas in each of the plurality of monitoring areas where the pressure is equal to or higher than a predetermined value.

8. The seating device according to claim 3, wherein, The controller is configured to use a machine learning model to estimate the position of the sole of the right foot based on the feature quantity, wherein the machine learning model receives the feature quantity as input and outputs the position of the sole of the right foot.

9. The seating device according to claim 1, wherein, The seat body is installed in the vehicle. The operating pedal is the vehicle's brake pedal, and The controller is configured to determine the hazard prediction level of the seated person based on the position of the sole of the right foot when the controller determines a collision risk between the vehicle and an obstacle.

10. The seating device according to claim 9, wherein, The controller is configured to estimate the reason why the hazard prediction level is equal to or lower than the predetermined value based on the body pressure distribution when the hazard prediction level is equal to or lower than the predetermined value.

Images