Fatigue level estimation system, vehicle-mounted device, server, fatigue level estimation method, and computer program

Abstract

A fatigue level estimation system according to the present invention comprises: a sensor data acquisition unit that acquires sensor data from a seating sensor; a state information acquisition unit that acquires state information which indicates the state of a vehicle in which the seating sensor is provided; and a fatigue level estimation unit that estimates, on the basis of the sensor data and the state information, the fatigue level of an occupant of the vehicle who is seated on the seat in which the seating sensor is provided. The fatigue level estimation unit includes a state detection unit that detects, on the basis of the state information, the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is substantially stopped and an estimation unit that compares, with a threshold value, a fatigue level index of the occupant based on the sensor data in the first state or the second state, so as to estimate the fatigue level of the occupant.

Description

Fatigue level estimation system, in-vehicle device, server, fatigue level estimation method, and computer program

[0001] The present disclosure relates to a fatigue level estimation system, an in-vehicle device, a server, a fatigue level estimation method, and a computer program. This application claims priority to Japanese Patent Application No. 2023-135516 filed on August 23, 2023, and incorporates by reference all of the contents of that Japanese application.

[0002] One of the main causes of traffic accidents is distracted driving due to fatigue. Distracted driving due to fatigue accounts for approximately one-quarter of all traffic accidents. In order to prevent such traffic accidents, it is necessary to accurately detect the driver's fatigue state and allow them to take appropriate rest or vacation, or reduce their workload.

[0003] The degree of fatigue a driver feels may differ from what the driver feels. In other words, even if the driver does not feel tired, the driver may actually be physically fatigued. Therefore, whether the driver is fatigued or not should not be left to the driver's judgment, but rather an external, objective standard for determining this is necessary.

[0004] In relation to these problems, Patent Document 1 (hereinafter referred to as "Patent Document 1") describes a technology in which a biosensor is provided on the steering wheel or seat of a vehicle and a driver's state is determined based on a biosignal from the biosensor. The technology described in Patent Document 1 acquires the driver's heart rate or pulse rate as a biosignal using the biosensor, and determines the driver's biostatus (driver's state) while driving based on the acquired biostatus. In Patent Document 1, the driver's biostatus while driving, i.e., whether or not the driver is drowsy (drowsy state) or overly excited (excited state), is determined based on the degree of change between biostatus information based on the biostatus signal while the vehicle is running and biostatus information based on the biostatus signal while the vehicle is stopped.

[0005] JP 2009-213768 A

[0006] A fatigue level estimation system according to an aspect of the present disclosure includes a sensor data acquisition unit that acquires sensor data from a seating sensor; a state information acquisition unit that acquires state information representing a state of a vehicle in which the seating sensor is provided; and a fatigue level estimation unit that estimates a fatigue level of an occupant of the vehicle who is seated in a seat in which the seating sensor is provided, based on the sensor data and the state information. The fatigue level estimation unit includes a state detection unit that detects, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped; and an estimation unit that estimates a fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data in the first state or the second state with a threshold value.

[0007] The present disclosure can be provided as a fatigue level estimation system, an in-vehicle device, a server, a fatigue level estimation method, and a computer program that include such characteristic configurations. Furthermore, the present disclosure can be provided as other systems, devices, methods, or computer programs that include the fatigue level estimation system, the in-vehicle device, the server, the fatigue level estimation method, or the computer program.

[0008] FIG. 1 is a diagram illustrating an example of the configuration of a fatigue level estimation system according to a first embodiment. FIG. 2 is a block diagram illustrating an example of the hardware configuration of an in-vehicle device illustrated in FIG. 1. FIG. 3 is a block diagram illustrating an example of the hardware configuration of a server illustrated in FIG. 1. FIG. 4 is a block diagram illustrating an example of the functional configuration of an in-vehicle system including the in-vehicle device illustrated in FIG. 1. FIG. 5 is a diagram illustrating the seating sensor illustrated in FIG. 4. FIG. 6 is a block diagram illustrating an example of the functional configuration of the server illustrated in FIG. 1. FIG. 7 is a diagram illustrating a method for determining whether a person has repositioned their seat. FIG. 8 is a diagram illustrating a determination of whether a notification is made to an administrator or a driver. FIG. 9 is a flowchart illustrating an example of the control structure of a program executed in the in-vehicle device according to the first embodiment. FIG. 10 is a flowchart illustrating an example of the control structure of a program executed in the server according to the first embodiment. FIG. 11 is a diagram illustrating an example of the configuration of a fatigue level estimation system according to a first modified example. FIG. 12 is a diagram illustrating an example of the configuration of a fatigue level estimation system according to a second modified example. FIG. 13 is a diagram illustrating an example of the determination of repositioning in a fatigue level estimation system according to the second embodiment. FIG. 14 is a diagram illustrating repositioning forward or backward in a seat. FIG. 15 is a diagram for explaining shifting one's seat to the left or right. FIG. 16 is a block diagram showing an example of the functional configuration of an in-vehicle system in a fatigue level estimation system according to a third embodiment. FIG. 17 is a block diagram showing an example of the functional configuration of a server in the fatigue level estimation system according to the third embodiment. FIG. 18 is a plan view for explaining a seating sensor. FIG. 19 is a diagram for explaining an example of determining shifting one's seat in the fatigue level estimation system according to the third embodiment. FIG. 20 is a diagram for explaining an example of the configuration of a fatigue level estimation system according to a fourth embodiment. FIG. 21 is a block diagram showing an example of the functional configuration of an in-vehicle system in a fatigue level estimation system according to the fourth embodiment. FIG. 22 is a flowchart showing an example of the control structure of a program executed in an in-vehicle device according to the fourth embodiment.

[0009] According to the technology described in Patent Document 1, since the degree of change in biological information is the subject of judgment, even if each piece of biological information is within a normal range, it is possible to capture a sudden change in the biological information within the normal range. Therefore, it is possible to accurately judge the driver's biological condition. In addition, since it is not necessary for the driver to wear a biological sensor, it is also possible to reduce the burden on the driver.

[0010] However, the technology described in Patent Document 1 determines the driver's subjective state of drowsiness or excitement. These biological conditions (driver state) are indicators different from the degree of fatigue. Therefore, the technology described in Patent Document 1 has a problem in that it cannot estimate the driver's (passenger's) fatigue level.

[0011] The present disclosure has been made to solve such problems, and one purpose of the present disclosure is to provide a fatigue level estimation system, an in-vehicle device, a server, a fatigue level estimation method, and a computer program that can estimate the fatigue level of a vehicle occupant without imposing a burden on the occupant.

[0012] According to the present disclosure, it is possible to provide a fatigue level estimation system, an in-vehicle device, a server, a fatigue level estimation method, and a computer program that can estimate the fatigue level of a vehicle occupant without imposing a burden on the occupant.

[0013] Preferred embodiments of the present disclosure will be described below. At least some of the embodiments described below may be combined in any combination.

[0014] (1) A fatigue level estimation system according to a first aspect of the present disclosure includes a sensor data acquisition unit that acquires sensor data from a seating sensor, a state information acquisition unit that acquires state information representing the state of a vehicle in which the seating sensor is provided, and a fatigue level estimation unit that estimates the fatigue level of a passenger of the vehicle who is seated in a seat in which the seating sensor is provided based on the sensor data and the state information. The fatigue level estimation unit includes a state detection unit that detects, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped, and an estimation unit that estimates the fatigue level of the passenger by comparing a fatigue level index of the passenger based on the sensor data in the first state or the second state with a threshold value.

[0015] Since the fatigue level of the occupant is estimated using sensor data from the seat sensor, the fatigue level of the occupant can be estimated without forcing the occupant to wear a sensor. In other words, the fatigue level of the occupant can be estimated without imposing a burden on the occupant of the vehicle. The fatigue level estimation unit estimates the fatigue level of the occupant by comparing the fatigue level index of the occupant when the vehicle is stopped or in a state equivalent to a stop with a threshold value. Since the fatigue level index is an index obtained based on sensor data from the seat sensor, it can also be said to be an index based on the occupant's behavior. Therefore, the fatigue level estimation unit estimates the fatigue level based on the occupant's behavior when the vehicle is stopped or in a state equivalent to a stop. When the vehicle is stopped or in a state equivalent to a stop, fluctuations due to external factors that occur when the vehicle is traveling (e.g., a shift in the occupant's center of gravity when turning a corner, a shift in the occupant's center of gravity due to vibrations during traveling) can be eliminated. Furthermore, it is considered that occupants are more likely to take actions to recover from fatigue when the vehicle is stopped or in a state equivalent to a stop compared to when the vehicle is traveling. Therefore, by estimating the fatigue level based on the behavior of the occupant when the vehicle is stopped or in a state similar to being stopped, the fatigue level of the occupant can be estimated with high accuracy.

[0016] (2) In the above (1), the fatigue level estimation unit may further include a re-sitting determination unit that determines whether the occupant has re-sat based on the sensor data, the fatigue level index may include a number of times the occupant has re-sat, which is the number of times the re-sitting determination unit has determined that the occupant has re-sat, and the estimation unit may estimate the fatigue level of the occupant by comparing the number of times the occupant has re-sat in the first state or the second state with the threshold value. This allows the fatigue level of the occupant to be estimated more accurately.

[0017] (3) In the above (2), the estimation unit may estimate the fatigue level of the occupant based on whether a state in which the number of times the occupant changes seats per unit time in the first state or the second state exceeds a first threshold value has occurred consecutively for a number of times equal to or greater than a second threshold value. This makes it possible to prevent a decrease in estimation accuracy due to variations in the number of times the occupant changes seats.

[0018] (4) In the above (2) or (3), the re-seating determination unit may determine whether the occupant has re-seated based on a moving speed of the center of gravity of the occupant's body pressure on the seating sensor. This allows for accurate determination of whether the occupant has re-seated.

[0019] (5) In the above (4), when an axis parallel to the traveling direction of the vehicle is defined as a first axis, the movement of the center of gravity position of the occupant based on the sensor data includes a movement of the center of gravity parallel to the first axis and a movement of the center of gravity parallel to a second axis perpendicular to the first axis, the re-seat determination unit may further determine whether the occupant has re-seat on the first axis by moving their center of gravity parallel to the first axis or on the second axis by moving their center of gravity parallel to the second axis, and the estimation unit may correct the number of times the occupant has re-seat on the first axis or on the second axis, thereby enabling the fatigue level of the occupant to be estimated with even greater accuracy.

[0020] (6) In any one of (2) to (4) above, the estimation unit may correct the number of times the occupant has shifted their seat in accordance with the amount of movement of the center of gravity of the occupant's body pressure on the seat sensor. This also makes it possible to estimate the occupant's fatigue level with even greater accuracy.

[0021] (7) In the above (2) or (3), the re-seating determination unit may determine whether the passenger has re-seated based on a change in the seat pressure of the seating sensor while the passenger is seated in the seat on which the seating sensor is provided. This also makes it possible to accurately determine whether the passenger has re-seated.

[0022] (8) In any of the above (1) to (7), the second state may include a state in which the vehicle is traveling at a speed equal to or lower than a speed defined as a traffic jam. In such a state, the fatigue level of the passenger can be estimated with high accuracy, just as in a state in which the vehicle is stopped.

[0023] (9) In any of the above (1) to (7), the second state may include a state in which the vehicle is traveling in a traffic jam area. Even in such a state, the fatigue level of the occupant can be estimated with high accuracy, just as in a state in which the vehicle is stopped.

[0024] (10) In any one of (1) to (9) above, the fatigue level estimation system may further include a notification unit that notifies a manager who manages the passenger of the passenger's fatigue level. This allows the manager to execute a predetermined process to reduce fatigue in the vehicle passenger, thereby reducing traffic accidents caused by distracted driving due to fatigue.

[0025] (11) In any one of (1) to (10) above, the fatigue level estimation system may further include an on-board device mounted on the vehicle and a server that communicates with the on-board device, the on-board device including a communication unit that acquires the sensor data and the status information and transmits them to the server, the server including the sensor data acquisition unit that acquires the sensor data by receiving the sensor data from the on-board device, the status information acquisition unit that acquires the status information by receiving the status information from the on-board device, and the fatigue level estimation unit that estimates the fatigue level of the occupant sitting in a seat provided with the seating sensor based on the sensor data and the status information. This allows the fatigue level of the occupant to be accurately estimated without imposing a burden on the occupant of the vehicle.

[0026] (12) According to a second aspect of the present disclosure, an in-vehicle device is provided in a vehicle equipped with a seating sensor, and includes: a sensor data acquisition unit that acquires sensor data from the seating sensor; a state information acquisition unit that acquires state information representing a state of the vehicle; and a fatigue level estimation unit that estimates a fatigue level of a vehicle occupant seated in the seat equipped with the seating sensor based on the sensor data and the state information, wherein the fatigue level estimation unit includes: a state detection unit that detects, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped; and an estimation unit that estimates a fatigue level of the vehicle occupant by comparing a fatigue level index of the vehicle occupant based on the sensor data with a threshold value in the first state or the second state. This configuration makes it possible to estimate the fatigue level of the vehicle occupant without imposing a burden on the vehicle occupant.

[0027] (13) A server according to a third aspect of the present disclosure is a server that communicates with an in-vehicle device mounted on a vehicle equipped with a seating sensor, and includes: a sensor data acquisition unit that acquires sensor data from the seating sensor via the in-vehicle device; a state information acquisition unit that acquires state information representing a state of the vehicle via the in-vehicle device; and a fatigue level estimation unit that estimates a fatigue level of a vehicle occupant seated in the seat equipped with the seating sensor based on the sensor data and the state information, wherein the fatigue level estimation unit includes: a state detection unit that detects, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped; and an estimation unit that estimates a fatigue level of the vehicle occupant by comparing a fatigue level index of the vehicle occupant based on the sensor data with a threshold value in the first state or the second state. This configuration makes it possible to estimate the fatigue level of the vehicle occupant without imposing a burden on the vehicle occupant.

[0028] (14) A fatigue level estimation method according to a fourth aspect of the present disclosure is a fatigue level estimation method for estimating a fatigue level of a vehicle occupant seated in a vehicle seat based on sensor data from a seating sensor provided in the seat, the fatigue level estimation method including the steps of: acquiring sensor data from the seating sensor; acquiring state information representing a state of the vehicle; and estimating a fatigue level of the occupant based on the sensor data and the state information, wherein the fatigue level estimating step includes the steps of detecting, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped; and estimating a fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data in the first state or the second state with a threshold value. This configuration makes it possible to estimate the fatigue level of the vehicle occupant without imposing a burden on the occupant.

[0029] (15) A fifth aspect of the present disclosure provides a computer program for causing a computer to estimate a fatigue level of a vehicle occupant seated in a vehicle seat based on sensor data from the seat sensor, the computer program causing the computer to execute the following steps: acquiring sensor data from the seat sensor, acquiring state information representing a state of the vehicle, detecting, based on the state information, whether the vehicle is in a first state in which the vehicle is stopped or a second state in which the vehicle is quasi-stopped, and estimating the fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data with a threshold value in the first state or the second state. With this configuration, the fatigue level of the occupant can be estimated without imposing a burden on the vehicle occupant.

[0030] [Details of Embodiments of the Present Disclosure] Specific examples of a fatigue level estimation system, an in-vehicle device, a server, a fatigue level estimation method, and a computer program according to embodiments of the present disclosure will be described below with reference to the drawings. Note that in the following embodiments, identical components are assigned the same reference numerals. Their functions and names are also identical. Therefore, detailed descriptions thereof will not be repeated.

[0031] (First Embodiment) [Overall Configuration] Referring to Fig. 1 , a fatigue level estimation system 50 according to this embodiment includes an in-vehicle device 100 mounted on a vehicle 60 and a server 200 that communicates with the in-vehicle device 100. When a fatigue level index for estimating the fatigue level of an occupant of the vehicle 60 exceeds a threshold value, the fatigue level estimation system 50 executes a predetermined process, for example, to prompt the occupant to take a rest. The occupant of the vehicle 60 may be a fellow passenger in the vehicle 60, but in this embodiment, the occupant is the driver who drives the vehicle 60. The fatigue level estimation system 50 reduces mindless driving by the driver due to fatigue.

[0032] In this embodiment, a delivery company that handles deliveries that require a relatively long driving time will be described as an example. Therefore, the vehicle 60 is a delivery vehicle such as a truck, and the driver of the vehicle 60 is, for example, an employee of the delivery company. However, the vehicle 60 is not limited to a delivery vehicle, and may be a vehicle other than a delivery vehicle.

[0033] The in-vehicle device 100 transmits biosensor data of the driver and status information of the vehicle 60 to the server 200. Specifically, the in-vehicle device 100 receives biosensor data of the driver (hereinafter sometimes referred to as "sensor data") and status information of the vehicle 60 from biosensors installed in the vehicle 60 and the vehicle 60, respectively, at a predetermined sampling period, and transmits the received information to the server 200. The biosensors include a seat occupancy sensor, which will be described later. The status information of the vehicle 60 includes information such as whether the vehicle 60 is moving or not.

[0034] The server 200 receives the sensor data and the vehicle 60 status information transmitted from the in-vehicle device 100, and calculates a fatigue level index of the driver of the vehicle 60 based on the received information set. The driver fatigue level index includes the number of times the driver shifts his / her seat while the vehicle 60 is stopped (also referred to as the first status) or in a status equivalent to a stop (also referred to as the second status). The server 200 estimates the driver's fatigue level by comparing the driver's fatigue level index with a threshold value. It is considered that accumulated physical fatigue is relatively noticeable while the vehicle is stopped. Therefore, the fatigue level estimation system 50 according to this embodiment estimates the driver's fatigue level from the driver's behavior while the vehicle is stopped or in a status equivalent to a stop.

[0035] A vehicle stop includes a stop with the driver seated in the seat. An example of such a stop is a temporary stop while the vehicle is traveling, such as when waiting for a traffic light at an intersection. A state equivalent to a stop refers to a state in which fatigue level estimation can be performed to the same extent as when the vehicle is stopped. When the vehicle is stopped, vehicle acceleration does not affect the detection of the driver's repositioning. Therefore, a state equivalent to a stop can also be said to be a state in which the vehicle is traveling at a speed that is hardly affected by vehicle acceleration in fatigue level estimation. An example of such a state is a state in which the vehicle is traveling at a speed below the speed defined as a traffic jam (10 km / h or less on a general road). In this case, traffic congestion may or may not actually be occurring. When the vehicle is traveling through a traffic congestion area as displayed on a car navigation device (in-vehicle navigation system), this state may be considered a state equivalent to a stop.

[0036] When the driver's fatigue level index exceeds a threshold value, the server 200 determines that the driver's fatigue level is high and notifies the vehicle 60 or an administrator who manages the driver of the vehicle 60. Specifically, the server 200 communicates with the terminal device 40 used by the administrator and transmits a fatigue level notification regarding the driver's fatigue level to the terminal device 40. The fatigue level notification may include, for example, a notification that the driver's fatigue level is high and that measures to alleviate the fatigue are necessary.

[0037] The manager receives a fatigue level notification regarding the driver of the vehicle 60 from the server 200 via the terminal device 40. Upon receiving the fatigue level notification, the manager takes predetermined measures to alleviate the fatigue of the driver of the vehicle 60. The predetermined measures include, for example, instructing the driver to take a break or rearranging the work route. For example, the manager contacts the driver of the vehicle 60 by mobile phone or business radio and instructs the driver to take a break. If the work route is rearranged, the manager notifies the driver that the work route has been changed.

[0038] The server 200 may notify the driver's fatigue level to the in-vehicle device 100 of the vehicle 60 driven by the driver, thereby enabling the driver to know his or her own fatigue level.

[0039] 2 , the in-vehicle device 100 includes a computer 102. The computer 102 includes a control unit 110 that controls the entire in-vehicle device 100, a memory 120 that stores various data, an in-vehicle communication unit 130 that communicates with the in-vehicle network, and a communication unit 140 that communicates with the external wireless device 62. The control unit 110, the memory 120, the in-vehicle communication unit 130, and the communication unit 140 are all connected to a communication bus 150, and data exchange between them is performed via the communication bus 150.

[0040] The control unit 110 includes an arithmetic unit 112, a read-only memory (ROM) 114 that stores a boot-up program for the computer 102, and a randomly writable and readable random access memory (RAM) 116. The arithmetic unit 112 includes, as a computing element (processor), a central processing unit (CPU) or a micro processing unit (MPU). The memory 120 includes, for example, a non-volatile memory such as a flash memory. The ROM 114 or the memory 120 stores software (computer programs) executed by the arithmetic unit 112 and various information sets (data).

[0041] The in-vehicle communication unit 130 provides an interface (IF) for communicating with the in-vehicle network, and communicates with the in-vehicle network in accordance with a predetermined communication protocol. The in-vehicle network may be, for example, a Controller Area Network (CAN), a Local Interconnect Network (LIN), a Media Oriented Systems Transport (MOST), a FlexRay, 10BASE-T1S, 100BASE-T1, 1000BASE-T1, a Clock Extension Peripheral Interface (CXPI), an Automotive Safety Restrictions Bus (ASRB), or a CAN XL. In this embodiment, a CAN is used as the in-vehicle network.

[0042] Under the control of the control unit 110, the in-vehicle device 100 (computer 102) receives data for estimating the driver's fatigue level via the in-vehicle network and transmits the received data to an external server 200 (see FIG. 1 ). The communication unit 140 provides an IF for communicating with an exterior wireless device 62. The exterior wireless device 62 is a wireless device for communicating with devices external to the vehicle 60. The communication unit 140 communicates with the server 200 via the exterior wireless device 62.

[0043] 3 , the server 200 includes a computer 202. The computer 202 includes a control unit 210, a storage device 220, and a communication unit 230. The control unit 210 includes a CPU 212, a GPU (Graphics Processing Unit) 214, a ROM 216, and a RAM 218. The control unit 210, the storage device 220, and the communication unit 230 are all connected to a communication bus 240, and data exchange between them is performed via the communication bus 240.

[0044] The storage device 220 includes a non-volatile storage device such as a flash memory or a hard disk drive. The storage device 220 stores computer programs to be executed by the CPU 212 and various information sets. The communication unit 230 provides a connection to the network 64 that enables communication with other devices including the in-vehicle device 100.

[0045] The server 200 communicates with the in-vehicle device 100 (see FIG. 1 ) via the network 64 and the communication unit 230. The server 200 acquires data from the in-vehicle device 100 for estimating the fatigue level of the driver of the vehicle 60 in which the in-vehicle device 100 is installed. The server 200 estimates the fatigue level of the driver of the vehicle 60 based on the acquired data, and notifies the manager of the driver's fatigue level when the estimated fatigue level exceeds a threshold value. Note that the server 200 may be configured to notify the in-vehicle device 100 of the vehicle 60 driven by the driver of the driver's fatigue level.

[0046] A computer program for causing server 200 to function as each functional unit of server 200 according to this embodiment is stored and distributed on a predetermined storage medium such as a DVD (Digital Versatile Disc) or a USB (Universal Serial Bus) memory, and is then transferred from this medium to storage device 220. Alternatively, the computer program may be transmitted to computer 202 from an external device via network 64 and stored in storage device 220.

[0047] [Functional Configuration] (In-Vehicle System 70) Referring to Fig. 4, the vehicle 60 includes an in-vehicle system 70. The in-vehicle system 70 includes a seating sensor 300 as a biosensor, the above-described in-vehicle device 100, and an in-vehicle navigation system 320. The seating sensor 300, the in-vehicle device 100, and the in-vehicle navigation system 320 are connected to each other so as to be able to communicate with each other via an in-vehicle network 330. The in-vehicle device 100 is further connected to various ECUs (Electronic Control Units) so as to be able to communicate with each other via the in-vehicle network 330.

[0048] The seating sensor 300 is a body pressure (pressure) sensor provided in the driver's seat 66 inside the vehicle. The seating sensor 300 periodically measures the body pressure distribution of the driver seated in the seat 66 and outputs the measured value as sensor data. The sensor data output by the seating sensor 300 includes seat pressure data.

[0049] 5, seating sensor 300 is disposed on the seating surface of driver's seat 66. Seat sensor 300 measures the seat pressure distribution when the driver is seated on seat 66. Note that seating sensor 300 is not limited to being disposed on the seating surface of seat 66, and may be provided, for example, inside the driver's seat.

[0050] Referring again to FIG. 4 , the in-vehicle device 100 includes, as functional units, a sensor data receiving unit 160, a status information receiving unit 162, and a warning notification unit 164 in addition to the communication unit 140. The sensor data receiving unit 160 receives sensor data from the seat occupancy sensor 300. The status information receiving unit 162 receives status information indicating the status (e.g., whether the vehicle 60 is moving or not moving) of the vehicle 60 equipped with the in-vehicle system 70 from a vehicle control unit (not shown) such as an ECU. When receiving a fatigue level notification from the server 200 (see FIG. 1 ), the warning notification unit 164 notifies the driver of the vehicle 60 of the received fatigue level. The status information receiving unit 162 receives, for example, CAN information as status information of the vehicle 60. The received CAN information includes information such as vehicle speed that can be used to determine whether the vehicle 60 is moving.

[0051] The sensor data receiving unit 160, the status information receiving unit 162, and the warning notification unit 164 are each connected to the in-vehicle network 330. The sensor data receiving unit 160, the status information receiving unit 162, and the warning notification unit 164 are also connected to the communication unit 140 and communicate with the server 200 (see FIG. 1 ) via the communication unit 140. The sensor data receiving unit 160 receives sensor data from the seating sensor 300 via the in-vehicle network 330 and transmits the received sensor data to the server 200 via the communication unit 140. More specifically, the sensor data receiving unit 160 receives seating pressure data of the driver from the seating sensor 300 and calculates the driver's center of gravity position based on the received seating pressure data. That is, the sensor data receiving unit 160 extracts data on the driver's center of gravity position from the received seating pressure data. The sensor data receiving unit 160 transmits the extracted center of gravity position data to the server 200 as sensor data. The status information receiving unit 162 receives status information of the vehicle 60 via the in-vehicle network 330, and transmits the received status information to the server 200 via the communication unit 140. The warning notification unit 164 receives a fatigue level notification from the server 200 (see FIG. 1 ) via the communication unit 140, and transmits the received fatigue level notification to, for example, the in-vehicle navigation system 320 via the in-vehicle network 330.

[0052] The in-vehicle navigation system 320 includes a route guidance unit 322, a display unit 324, and an audio output unit 326. The route guidance unit 322 searches for a route to a destination and displays it on the display unit 324, and receives traffic congestion information and displays the status on the display unit 324. The display unit 324 displays various information sets including map information. The audio output unit 326 notifies the driver of various information sets such as route guidance and traffic congestion information by audio. When the in-vehicle navigation system 320 receives a fatigue level notification from the warning notification unit 164, it issues a warning to the driver to take a break.

[0053] 6 , the server 200 includes, as functional units, a sensor data acquisition unit 250, a status information acquisition unit 260, a fatigue level estimation unit 270, a timer 280, and a warning notification unit 290 in addition to the communication unit 230. The sensor data acquisition unit 250 receives sensor data transmitted from the in-vehicle device 100 via the communication unit 230, thereby acquiring sensor data from the seat occupancy sensor 300. The status information acquisition unit 260 receives status information transmitted from the in-vehicle device 100 via the communication unit 230, thereby acquiring status information of the vehicle 60 in which the in-vehicle device 100 is installed.

[0054] The fatigue level estimation unit 270 periodically executes a process of estimating the driver's fatigue level under the control of the timer 280. The fatigue level estimation unit 270 includes: a seating repositioning determination unit 272 that determines whether the driver has repositioned his / her seat based on the sensor data (center of gravity position data) acquired by the sensor data acquisition unit 250; a state detection unit 274 that detects whether the vehicle 60 is in a stopped state or a state quasi-stopped based on the state information acquired by the state information acquisition unit 260; and an estimation unit 276 that estimates the driver's fatigue level by comparing a driver fatigue level index based on the sensor data when the vehicle 60 is in a stopped state or a state quasi-stopped with a threshold value.

[0055] When the estimated fatigue level exceeds a threshold value, the warning notification unit 290 transmits a fatigue level notification regarding the driver's fatigue level to the manager via the communication unit 230.

[0056] As described above, the fatigue level estimation system 50 according to this embodiment estimates the driver's fatigue level by using the number of times the driver shifts in his / her seat while the vehicle 60 is stopped or in a state equivalent to being stopped as a fatigue level index. The fatigue level estimation system 50 detects whether the driver has shifted in his / her seat based on sensor data from the seating sensor 300.

[0057] A determination method (determination process) for determining whether the driver has repositioned himself / herself will be described with reference to Fig. 7. This determination process is executed by the fatigue level estimation unit 270 (repositioning determination unit 272) of the server 200 shown in Fig. 6. The repositioning determination unit 272 determines that the driver has repositioned himself / herself when the speed of movement of the center of gravity per unit time based on the position of the center of gravity of the driver is equal to or greater than a certain value.

[0058] Figure 7A shows center-of-gravity position 400 at time T1. As time passes, at time T2, the driver's center-of-gravity position moves from center-of-gravity position 400 to center-of-gravity position 402 as shown in Figure 7B. If the distance the center-of-gravity position moves at this time is distance L1, the center-of-gravity movement speed is L1 / T2. As time passes further, at time T3, the state shown in Figure 7C is reached. If the driver's center-of-gravity position moves from center-of-gravity position 402 to center-of-gravity position 404 and the distance the center-of-gravity position moves at this time is distance L2, the center-of-gravity movement speed is L2 / T3.

[0059] If the calculated center-of-gravity shift speed is equal to or greater than a certain threshold, the re-seating determination unit 272 determines that the driver has re-seated. For example, if a center-of-gravity shift of 10 cm or more per second is determined to be a re-seating, the threshold value of the center-of-gravity shift speed for determining whether the driver has re-seated is set to 0.1 m / s.

[0060] The above-described seat-rest reassembly determination process is executed when the vehicle is stopped or in a state equivalent to being stopped.

[0061] The estimation unit 276 of the server 200 (see FIG. 6 ) counts and records the number of times the driver changes his / her seat per unit time (e.g., 30 minutes) and determines whether the number of times the driver changes his / her seat exceeds a threshold value (α). The estimation unit 276 further counts and records the number of times the driver changes his / her seat exceed the threshold value (α), and determines that the driver is fatigued if the number of times the threshold value (α) is exceeded consecutively is equal to or exceeds a threshold value (β). More specifically, the estimation unit 276 determines that the driver's fatigue level is at a level that requires notification to the manager or the driver.

[0062] The above-mentioned determination of notification to the administrator or driver will be explained with reference to Fig. 8. The horizontal axis of Fig. 8 represents time, and the vertical axis represents the number of times the occupant repositioned their seat while the vehicle was stopped per unit time. In Fig. 8, the number of times the occupant repositioned their seat while the vehicle was stopped is shown, but it may also be the sum of the number of times the occupant repositioned their seat while the vehicle was stopped and the number of times the occupant repositioned their seat while the vehicle was stopped.

[0063] The number of times a driver changes his / her seat per unit time increases as driving time increases. As driving time increases, fatigue gradually accumulates. For example, if a driver's lower back becomes stiff from sitting for extended periods, he / she may change his / her seat when stopped to relieve the stiffness. Therefore, as fatigue accumulates due to long-term driving, the number of times a driver changes his / her seat gradually increases, and the number of times a driver changes his / her seat per unit time exceeds the threshold value (α). If the number of times a driver changes his / her seat per unit time exceeds the threshold value (α), it can be said that the driver is changing his / her seat frequently. If this situation occurs continuously, it is estimated that the driver's level of fatigue is high. Therefore, if the number of times a driver changes his / her seat that exceeds the threshold value (α) occurs consecutively for a threshold value (β) (here, two times) or more, it is determined that a notification to the administrator or the driver is necessary. In other words, a fatigue level notification is sent to the administrator or the driver when the number of times a driver changes his / her seat that exceeds the threshold value (α) occurs twice in a row.

[0064] 9, a control structure of a computer program executed in the on-vehicle device 100 (see FIG. 1) for transmitting sensor data from the seat occupancy sensor 300 (see FIG. 4) and status information of the vehicle 60 (see FIG. 1) to the server 200 (see FIG. 1) will be described. This program starts, for example, in response to turning on the ignition of the vehicle 60 (engine).

[0065] This program includes step S1000, which repeats steps S1010 and S1020, which will be described below, until the ignition is turned off. In step S1000, the process repeated until the ignition is turned off includes step S1010, which receives sensor data from seat sensor 300 and receives status information of vehicle 60, and step S1020, which is executed after step S1010 and transmits the received sensor data and status information to server 200. In step S1020, the driver's center of gravity position is extracted based on the seat pressure data received from seat sensor 300, and the extracted center of gravity position data is transmitted to server 200 as sensor data. Transmitting the center of gravity position data reduces the amount of data to be transmitted.

[0066] 10, a control structure of a computer program executed by server 200 (see FIG. 1) to estimate the fatigue level of the driver of vehicle 60 (see FIG. 1) will be described. This program starts in response to communication with in-vehicle device 100, for example.

[0067] This program includes steps S2000, S2010, S2020, and S2040. In step S2000, the sensor data and status information transmitted from the in-vehicle device 100 are received to acquire sensor data from the seating sensor 300 and status information of the vehicle 60. Step S2010 is executed after step S2000. Based on the acquired status information, it is determined whether the vehicle 60 is stopped or in a state equivalent to a stop, and the control flow branches depending on the determination result. Step S2020 is executed when it is determined in step S2010 that the vehicle 60 is stopped or in a state equivalent to a stop. Based on the acquired sensor data, it is determined whether the driver has repositioned himself / herself, and the control flow branches depending on the determination result. Step S2030 is executed when it is determined in step S2020 that the driver has repositioned himself / herself, and the number of times the driver has repositioned himself / herself is counted (the number of times the driver has repositioned himself / herself is incremented). Step S2040 is executed after step S2030 or when it is determined in step S2020 that the driver has not shifted positions. It determines whether the number of shifts per unit time has been obtained (whether the unit time has elapsed) and branches the flow of control depending on the determination result.

[0068] This program further includes steps S2050, S2060, S2062, S2070, and S2080. Step S2050 is executed when it is determined in step S2040 that the number of times the person changes seats per unit time has been acquired, and determines whether the number of times the person changes seats per unit time exceeds a threshold value (α), and branches the flow of control according to the determination result. Step S2060 is executed when it is determined in step S2050 that the number of times the person changes seats per unit time exceeds the threshold value (α), and increments the number of times (N) that the threshold value (α) is exceeded. Step S2062 is executed when it is determined in step S2050 that the number of times the person changes seats per unit time does not exceed the threshold value (α), and resets the number of times (N) that the threshold value (α) is exceeded. Step S2070 is executed after step S2060, and determines whether the number of times (N) that the threshold value (α) is exceeded has continued for a certain number of times (threshold value (β)) or more, and branches the flow of control depending on the determination result. Step S2080 is executed if it is determined in step S2070 that the number of times (N) that the threshold value (α) has been exceeded for a certain number of times (threshold value (β)) or more, and transmits a fatigue level notification to the manager (or driver).

[0069] This program further includes steps S2090 and S2092. Step S2090 is executed when it is determined in step S2010 that vehicle 60 is neither stopped nor in a state equivalent to being stopped, after step S2062, when it is determined in step S2070 that the number of times (N) exceeding threshold value (α) has not consecutively exceeded a certain number of times (threshold value (β)), or after step S2080. Step S2090 determines whether a predetermined termination condition is met and branches the flow of control depending on the determination result. Step S2092 is executed when it is determined in step S2090 that the predetermined termination condition is not met, and resets the number of times the seat has been repositioned.

[0070] For example, if the fatigue level measurement period is the working hours of the driver of vehicle 60 in one day, the specified termination condition can be that the working hours of the driver of vehicle 60 have ended (the end of work time has passed).

[0071] If it is determined in step S2090 that a predetermined termination condition is met, the program ends. After step S2092, or if it is determined in step S2040 that the number of times the person has changed seats per unit time has not been obtained, control returns to step S2000.

[0072] [Operation] The fatigue level estimation system 50 according to this embodiment operates as follows. Referring to Fig. 5, the driver of the vehicle 60 gets into the vehicle 60, for example, when starting work. The driver sits in the seat 66 provided with the seating sensor 300 and turns on the ignition. Referring to Fig. 1, in response to the ignition being turned on, the in-vehicle device 100 of the vehicle 60 starts up, and the in-vehicle device 100 starts communicating with the server 200.

[0073] 4, the in-vehicle device 100 receives sensor data from the seating sensor 300 and also receives status information of the vehicle 60 from the vehicle control unit of the vehicle 60 (step S1010 in FIG. 9). The in-vehicle device 100 extracts the center of gravity position of the driver based on the received sensor data (seat pressure data). The in-vehicle device 100 transmits the center of gravity position data (sensor data) together with the status information to the server 200 (step S1020 in FIG. 9).

[0074] Referring to FIG. 6 , server 200 acquires sensor data and status information transmitted from in-vehicle device 100 by receiving these data (step S2000 in FIG. 10 ). Status detection unit 274 determines whether vehicle 60 is stopped or moving based on the acquired status information. More specifically, when vehicle 60 is stopped or in a state equivalent to a stop, status detection unit 274 detects the state based on the acquired status information (YES in step S2010). When vehicle 60 is stopped or in a state equivalent to a stop, seat repositioning determination unit 272 detects and counts whether the driver has repositioned his or her seat based on the acquired sensor data (YES in step S2020, step S2030). Estimation unit 276 acquires the number of times the driver has repositioned his or her seat per unit time based on the counting result (YES in step S2040), and then determines whether the number of times the driver has repositioned his or her seat per unit time exceeds a threshold value (α). If the number of times the driver has changed his / her seat per unit time exceeds the threshold value (α) (YES in step S2050), this is counted as the number of times (N) that the threshold value (α) has been exceeded (step S2060).If the number of times the driver has changed his / her seat that exceeds the threshold value (α) continues for a threshold value (β) or more (YES in step S2070), estimation unit 276 causes warning notification unit 290 to notify the manager or the driver of the driver's fatigue level.

[0075] 1, the manager who receives the notification from server 200 contacts the driver and takes measures to reduce fatigue, such as instructing the driver to take a break or changing the work route. When the fatigue level notification is notified to the driver, a warning is issued to the driver via, for example, in-vehicle navigation system 320 (see FIG. 4).

[0076] In this embodiment, as described above, the driver's fatigue level is estimated using sensor data from the seat sensor 300, so that the driver's fatigue level can be estimated without forcing the driver to wear a sensor. In other words, the driver's fatigue level can be estimated without imposing a burden on the driver of the vehicle 60. The fatigue level estimation unit 270 estimates the driver's fatigue level by comparing the driver's fatigue level index when the vehicle 60 is stopped or in a state equivalent to a stop with a threshold value. The fatigue level index is an index obtained based on the sensor data from the seat sensor 300, and is therefore also an index based on the driver's behavior. Therefore, the fatigue level estimation unit 270 is configured to estimate the driver's fatigue level based on the driver's behavior when the vehicle 60 is stopped or in a state equivalent to a stop. When the vehicle 60 is stopped or in a state equivalent to a stop, fluctuations due to external factors while the vehicle is traveling (e.g., shifts in the driver's center of gravity when turning a corner, shifts in the driver's center of gravity due to vibrations while traveling) can be eliminated. Furthermore, compared to when the vehicle is moving, the driver is more likely to take actions to recover from fatigue when the vehicle is stopped or in a state similar to a stop. Therefore, by estimating the fatigue level based on the driver's behavior when the vehicle 60 is stopped or in a state similar to a stop, the driver's fatigue level can be estimated with high accuracy.

[0077] The fatigue level estimation unit 270 further includes a re-sitting determination unit 272 that determines whether the driver has re-sat in their seat based on the sensor data. The fatigue level index includes the number of times the occupant has re-sat in their seat, which is the number of times the re-sitting determination unit 272 has determined that the occupant has re-sat in their seat. The estimation unit 276 estimates the driver's fatigue level by comparing the number of times the occupant has re-sat in their seat while the vehicle 60 is stopped or in a state equivalent to being stopped with a threshold value. This allows the driver's fatigue level to be estimated more accurately.

[0078] The estimation unit 276 estimates the driver's fatigue level based on whether the number of times the driver shifts his / her seat per unit time while the vehicle 60 is stopped or in a state quasi-stopped, exceeds a first threshold value (α), and the number of times this occurs consecutively is equal to or greater than a second threshold value (β). This makes it difficult for the estimation accuracy to decrease due to variations in the number of times the driver shifts his / her seat.

[0079] The re-seating determination unit 272 determines whether the driver has re-seated based on the moving speed of the center of gravity position of the driver's body pressure on the seating sensor 300. This makes it possible to accurately determine whether the driver has re-seated.

[0080] The fatigue level estimation system 50 includes a warning notification unit 290 that notifies a manager who manages the driver of the driver's fatigue level. This allows the manager to execute a predetermined process to reduce the fatigue of the driver of the vehicle 60, thereby reducing traffic accidents caused by mindless driving due to fatigue.

[0081] (First Modification) In the first embodiment, an example is shown in which the manager directly contacts the driver and instructs the driver to take a break. However, the present disclosure is not limited to such an embodiment. For example, the manager may instruct the vehicle driver to take a break via a server.

[0082] 11 , fatigue level estimation system 50A according to the first modification has a similar configuration to that of the first embodiment. However, it differs from the first embodiment in that a manager who receives a fatigue level notification from server 200 operates terminal device 40 to respond to the received fatigue level notification. In the first modification, for example, the manager instructs the driver to take a break via terminal device 40 and server 200, or, if the manager has rearranged a work route, notifies the driver of the rearranged work route via terminal device 40 and server 200.

[0083] The server 200 transmits a response instruction from the administrator (terminal device 40) to the in-vehicle device 100 of the vehicle 60. The in-vehicle device 100 receives the response instruction from the administrator via the server 200. The in-vehicle device 100 further notifies the driver of the vehicle 60 of the content of the response instruction, for example, by using the in-vehicle navigation system 320 (see FIG. 4 ).

[0084] (Second Modification) In the above-described first embodiment, an example was shown in which a delivery vehicle such as a truck was the target. However, the present disclosure is not limited to such an embodiment. The vehicle targeted by the fatigue level estimation system may be a vehicle other than a delivery vehicle. In the second modification, such a configuration example will be described.

[0085] 12 , a fatigue level estimation system 50B according to the second modification includes an in-vehicle device 100 mounted on a vehicle 60A and a server 200 that communicates with the in-vehicle device 100. The in-vehicle device 100 and the server 200 have configurations similar to those of the first embodiment. The vehicle 60A in which the in-vehicle device 100 is mounted is different from the vehicle 60 of the first embodiment and is, for example, a privately owned vehicle. In this case, there is no administrator who manages the driver of the vehicle 60A. Therefore, the server 200 notifies the in-vehicle device 100 of the vehicle 60A driven by the driver of the driver of the fatigue level notification.

[0086] Second Embodiment The fatigue level estimation system according to this embodiment differs from the first embodiment in that it determines the level of fatigue when a person resits, and corrects the number of times the person has resitted in accordance with the result of this determination. The correction of the number of times the person has resitted is performed by weighting the number of times the person has resitted in accordance with the level of fatigue. For example, a resit that is determined to have a low level of fatigue is counted as one time, and a resit that is determined to have a high level of fatigue is counted as two times. The level of fatigue is determined based on whether the person has resitted forward or backward or to the left or right. As in the first embodiment, these processes are executed by the server.

[0087] When the axis parallel to the vehicle's traveling direction is defined as the first axis, the movement of the driver's center of gravity position includes a front-to-rear component and a left-to-right component. Referring to FIG. 13 , assume that the driver's center of gravity position moves from center of gravity position 410 to center of gravity position 412. The movement of the center of gravity position (rear-to-rear shift) in this case includes a center of gravity shift parallel to the first axis (front-to-rear component) and a center of gravity shift parallel to a second axis perpendicular to the first axis (left-to-right component). Depending on which component has a larger absolute value, it is determined whether the shift is on the first axis (a shift in which the front-to-rear component is larger than the left-to-right component) or on the second axis (a shift in which the left-to-right component is larger than the front-to-rear component). The shift in the first axis and the shift in the second axis are also referred to as a shift in the front-to-rear direction and a shift in the left-to-right direction, respectively.

[0088] Referring to Figure 14, shifting forward or backward will be described. Figure 14(A) shows center of gravity position 420 at time T1. As time passes, at time T2, as shown in Figure 14(B), the driver's center of gravity moves from center of gravity position 420 to center of gravity position 422. The front-to-back component of this movement is larger than the left-to-right component. As time passes further, at time T3, as shown in Figure 14(C), the driver's center of gravity moves from center of gravity position 422 to center of gravity position 424. The front-to-back component of this movement is also larger than the left-to-right component. Therefore, if the speed of these movements is equal to or greater than a certain threshold, it is determined that the driver has shifted forward or backward.

[0089] Next, referring to Figure 15, we will explain repositioning to the left or right. Figure 15(A) shows center of gravity position 430 at time T1. As time passes, at time T2, as shown in Figure 15(B), the driver's center of gravity moves from center of gravity position 430 to center of gravity position 432. The left-right component of this movement is larger than the front-rear component. As time passes further, at time T3, as shown in Figure 15(C), the driver's center of gravity moves from center of gravity position 432 to center of gravity position 434. The left-right component of this movement is also larger than the front-rear component. Therefore, if the movement speed of these movements is equal to or greater than a certain threshold, it is determined that the driver has repositioned to the left or right.

[0090] Repositioning forward or backward is often performed when, for example, the driver leans back in the seat or returns to a driving position. In contrast, repositioning left or right is often performed when, for example, the driver stretches out a stiff lower back. Therefore, repositioning left or right is considered to be performed when more fatigue has accumulated than repositioning forward or backward. Therefore, in this embodiment, the fatigue level estimation unit of the server determines that the fatigue level is low when the driver repositions forward or backward, and that the fatigue level is high when the driver repositions left or right.

[0091] In this embodiment, as described above, the server further determines whether the driver has shifted his / her seat back and forth by shifting his / her center of gravity parallel to the first axis or shifted his / her seat back and forth by shifting his / her center of gravity parallel to the second axis, and corrects the number of times the driver has shifted his / her seat back and forth depending on the determination result, thereby enabling the driver's fatigue level to be estimated with even greater accuracy.

[0092] The other configurations are the same as those in the first embodiment.

[0093] (Third embodiment) The fatigue level estimation system of this embodiment differs from the above-described embodiment in that it detects the driver re-sitting based on the center of gravity movement speed in that it detects the driver re-sitting based on the change in seat pressure (change in the total value) measured by the seating sensor.

[0094] 16 , the fatigue level estimation system according to the present embodiment includes an in-vehicle device 100A instead of the in-vehicle device 100 (see FIG. 4 ). The in-vehicle device 100A includes a sensor data receiving unit 160a instead of the sensor data receiving unit 160 (see FIG. 4 ). The sensor data receiving unit 160a transmits the sensor data received from the seating sensor 300 to the server via the communication unit 140. The sensor data receiving unit 160a may be configured to transmit a total value of the seating pressure based on the sensor data received from the seating sensor 300 to the server as sensor data.

[0095] 17 , the fatigue level estimation system according to the present embodiment further includes a server 200A instead of server 200 (see FIG. 6 ). Server 200A includes a fatigue level estimation unit 270a instead of fatigue level estimation unit 270 (see FIG. 6 ). Fatigue level estimation unit 270a includes a re-sitting determination unit 272a instead of re-sitting determination unit 272 (see FIG. 6 ). Re-sitting determination unit 272a determines whether the driver has re-sitting based on the total seating pressure.

[0096] Referring to FIG. 18 , the seating surface of the seating sensor 300 is composed of a plurality of squares 302, each of which is provided with a sensor (not shown). The fatigue level estimation system calculates the sum of the measurement values ​​of each square 302 (total seating pressure) based on the sensor data transmitted from the seating sensor 300. If the sensor of each square 302 is set to a maximum measurable value, the maximum value will not be exceeded even if the driver's weight is applied to some of the squares 302. Therefore, the total seating pressure decreases when the driver reseats (e.g., when the driver lifts his / her body). The fatigue level estimation system monitors changes in the total seating pressure and compares the total seating pressure with a threshold value to determine whether the driver has reseat. More specifically, the reseat determination unit 272a determines that the driver has reseat when the total seating pressure falls below the threshold value.

[0097] 19, let us assume that the total seat pressure shown in (A) changes from P1 (e.g., 9900 mm / Hg) to P2 (e.g., 6500 mm / Hg) as shown in (B). If the threshold for re-seating is, for example, 7000 mm / Hg, the state in which the total seat pressure is P2 (6500 mm / Hg) is below the threshold. Therefore, for example, when the state shown in (A) changes to the state shown in (B), the re-seating determination unit 272a (see FIG. 17) determines that the driver has re-seated.

[0098] As described above, according to the fatigue level estimation system of this embodiment, the re-sitting determination unit 272a determines whether the driver has re-sitting based on a change in the seating pressure of the seating sensor 300. This also makes it possible to accurately determine whether the driver has re-sitting.

[0099] The other configurations are the same as those in the first embodiment.

[0100] 20 , a fatigue level estimation system 50C according to the present embodiment includes an in-vehicle device 500 mounted on a vehicle 60B. That is, the fatigue level estimation system 50C according to the present embodiment differs from the above-described embodiment in that the driver's fatigue level is estimated by the in-vehicle device 500, in that the driver's fatigue level is estimated by the server.

[0101] 21 , vehicle 60B includes in-vehicle system 70A. In-vehicle system 70A includes in-vehicle device 500 instead of in-vehicle device 100 (see FIG. 4 ). In-vehicle device 500 includes, as functional units, a sensor data acquisition unit 510, a status information acquisition unit 520, a fatigue level estimation unit 530, a timer 540, and a warning notification unit 550. Sensor data acquisition unit 510 receives sensor data from seat occupancy sensor 300. Status information acquisition unit 520 receives status information indicating a status (e.g., whether the vehicle 60B in which in-vehicle device 500 is installed is moving or not moving) from a vehicle control unit (not shown) such as an ECU.

[0102] The fatigue level estimation unit 530 periodically executes a process of estimating the driver's fatigue level under the control of the timer 540. The fatigue level estimation unit 530 includes a sitting-back determination unit 532, a state detection unit 534, and an estimation unit 536. The sitting-back determination unit 532 determines whether the driver has sat back down based on the sensor data received by the sensor data acquisition unit 510. The state detection unit 534 detects whether the vehicle 60B is stopped or in a state equivalent to being stopped based on the state information received by the state information acquisition unit 520. The estimation unit 536 estimates the driver's fatigue level by comparing a driver fatigue level index based on the sensor data when the vehicle 60B is stopped or in a state equivalent to being stopped with a threshold value.

[0103] When the fatigue level estimated by the fatigue level estimation unit 530 exceeds a threshold value, the warning notification unit 550 transmits a notification regarding the driver's fatigue level to, for example, the in-vehicle navigation system 320 via the in-vehicle network 330 .

[0104] 22, a control structure of a computer program executed in the on-vehicle device 500 (see FIG. 20) to estimate the fatigue level of the driver of the vehicle 60B (see FIG. 20) will be described. This program starts, for example, in response to turning on the ignition of the vehicle 60B.

[0105] This program includes steps S3000, S3010, S3030, and S3040. In step S3000, sensor data transmitted from seating sensor 300 and status information of vehicle 60B are acquired. Step S3010 is executed after step S3000, and determines whether vehicle 60B is stopped or in a state equivalent to being stopped based on the acquired status information, and branches the control flow according to the determination result. Step S3020 is executed when it is determined in step S3010 that vehicle 60B is stopped or in a state equivalent to being stopped, and determines whether the driver has repositioned himself / herself based on the acquired sensor data, and branches the control flow according to the determination result. Step S3030 is executed when it is determined in step S3020 that the driver has repositioned himself / herself, and counts the number of times the driver has repositioned himself / herself (increments the number of times the driver has repositioned himself / herself). Step S3040 is executed after step S3030 or when it is determined in step S3020 that the driver has not shifted his / her seat. It determines whether the number of shifts per unit time has been obtained (whether the unit time has elapsed) and branches the flow of control depending on the determination result.

[0106] This program further includes steps S3050, S3060, S3062, S3070, and S3080. Step S3050 is executed when it is determined in step S3040 that the number of times the user changes seats per unit time has been acquired, and determines whether the number of times the user changes seats per unit time exceeds a threshold value (α), branching the flow of control depending on the determination result. Step S3060 is executed when it is determined in step S3050 that the number of times the user changes seats per unit time exceeds the threshold value (α), and increments the number of times (N) the threshold value (α) is exceeded. Step S3062 is executed when it is determined in step S3050 that the number of times the user changes seats per unit time does not exceed the threshold value (α), and resets the number of times (N) the threshold value (α) is exceeded. Step S3070 is executed after step S3060, and determines whether the number of times (N) that the threshold value (α) is exceeded has continued for a certain number of times (threshold value (β)) or more, and branches the flow of control depending on the determination result. Step S3080 is executed when it is determined in step S3070 that the number of times (N) that the threshold value (α) has been exceeded for a certain number of times (threshold value (β)) or more, and notifies the driver of the degree of fatigue.

[0107] This program further includes steps S3090 and S3092. Step S3090 is executed after step S3062 when it is determined in step S3010 that vehicle 60B is neither stopped nor in a state equivalent to being stopped; after step S3062; when it is determined in step S3070 that the number of times (N) exceeding threshold value (α) has not consecutively exceeded a certain number of times (threshold value (β)); or after step S3080. Step S3090 determines whether a predetermined termination condition is met, and the flow of control branches depending on the determination result. Step S3092 is executed when it is determined in step S3090 that the predetermined termination condition is not met, and resets the number of times the seat has been repositioned.

[0108] For example, if one drive is used as the fatigue measurement period, the specified termination condition can be turning off the ignition of vehicle 60B or arriving at the destination guided by in-vehicle navigation 320 (see Figure 21).

[0109] If it is determined in step S3090 that a predetermined termination condition is met, the program ends. After step S3092, or if it is determined in step S3040 that the number of times the person has changed seats per unit time has not been obtained, control returns to step S3000.

[0110] According to the fatigue level estimation system 50C of this embodiment, the fatigue level of the driver can be estimated in the in-vehicle device 500. Therefore, even with this configuration, the fatigue level of the driver of the vehicle 60B can be estimated without imposing a burden on the driver.

[0111] The other configurations are the same as those of the first, second or third embodiment.

[0112] (Modification) In the above embodiment, an example has been described in which the in-vehicle device receives sensor data from the seat occupancy sensor via an in-vehicle network. However, the present disclosure is not limited to such an embodiment. The in-vehicle device may be configured to receive sensor data from the seat occupancy sensor via a path other than the in-vehicle network. For example, the in-vehicle device may be configured to communicate directly with the seat occupancy sensor via a wired or wireless connection to receive sensor data.

[0113] In the above embodiment, an example has been described in which the in-vehicle device transmits sensor data from the seat sensor to the server. However, the present disclosure is not limited to such an embodiment. When the seat sensor communicates with a terminal device such as a smartphone, the terminal device may be configured to transmit the sensor data from the seat sensor to the server. In this case, the terminal device may also be configured to transmit the sensor data from the seat sensor to the in-vehicle device as needed.

[0114] In the above embodiment, an example has been described in which CAN information is used as vehicle status information. However, the present disclosure is not limited to such an embodiment. The vehicle status information may be information other than CAN information. For example, vehicle position information may be used as status information.

[0115] In the above embodiment, an example has been described in which the in-vehicle device calculates (extracts) center-of-gravity position data and transmits it to the server. However, the present disclosure is not limited to such an embodiment. The calculation (extraction) of center-of-gravity position data may be performed by a device other than the in-vehicle device. For example, the server may calculate (extract) the center-of-gravity position data from sensor data. In this case, the in-vehicle device transmits the sensor data received from the seating sensor to the server as is.

[0116] When a car navigation device (in-vehicle navigation system) or the like displays a state in which the vehicle is traveling through a traffic congestion area as being equivalent to a stopped state, the fatigue level estimation system can use vehicle position information as vehicle status information. When fatigue level estimation is performed in a server, the in-vehicle device may transmit to the server, together with the vehicle position information, information indicating that the vehicle is traveling through a traffic congestion area. Furthermore, the in-vehicle device may be configured to transmit the vehicle position information to the server as status information, and the server may acquire traffic congestion information and determine whether the vehicle is traveling through a traffic congestion area based on the acquired traffic congestion information and the received position information.

[0117] In the above-described embodiment, the fatigue level estimation system may be configured to determine whether the occupant has shifted their seat only when the vehicle is stopped, or may be configured to determine whether the occupant has shifted their seat only when the vehicle is in a state similar to a stop. The fatigue level estimation system may further be configured to determine whether the occupant has shifted their seat both when the vehicle is stopped and in a state similar to a stop.

[0118] In the above embodiment, an example has been shown in which it is determined that the driver is fatigued when the number of times the driver has repositioned his / her seat exceeds the threshold value (α) for a number of consecutive times equal to or greater than the threshold value (β). However, the present disclosure is not limited to such an embodiment. For example, it may be determined that the driver is fatigued when the number of times the driver has repositioned his / her seat exceeds the threshold value (α).

[0119] In the above embodiment, an example has been shown in which the number of times the driver changes his / her seat per unit time is used as the fatigue level index of the occupant (driver). However, the present disclosure is not limited to such an embodiment. The fatigue level index of the occupant (driver) may be an index other than the number of times the driver changes his / her seat. For example, the total value (accumulated value) of the amount of center of gravity movement per unit time may be used as the fatigue level index of the occupant (driver).

[0120] In the above embodiment, an example has been shown in which the level of fatigue is determined based on whether the person has repositioned their seat to the left or right or forward or backward, and the number of times the person has repositioned their seat is corrected based on the determination result. However, the present disclosure is not limited to such an embodiment. The determination of the level of fatigue may be made by a method other than repositioning their seat to the left or right or forward or backward. For example, the number of times the person has repositioned their seat may be corrected based on the amount of movement of the center of gravity of the passenger's (driver's) body pressure on the seat sensor. More specifically, the level of fatigue may be determined based on whether the amount of movement of the center of gravity when it is determined that the person has repositioned their seat is greater than a threshold, and the number of times the person has repositioned their seat may be corrected based on the determination result.

[0121] In the above embodiment, an example is shown in which the level of fatigue is determined depending on whether the person has repositioned themselves to the left or right or forward or backward, and the number of times they have repositioned themselves is corrected depending on the determination result. However, the present disclosure is not limited to such an embodiment. For example, the number of times they have repositioned themselves may be counted only when it is determined that they have repositioned themselves to the left or right.

[0122] If the vehicle is an electrically powered vehicle such as an electric car, the electrically powered vehicle is equipped with a power switch instead of an ignition. Therefore, the processing executed in response to the on / off of the ignition, as shown in the above embodiment, may be configured to be executed in response to the on / off of the power switch if the vehicle is an electrically powered vehicle.

[0123] Embodiments obtained by appropriately combining the techniques disclosed above are also included within the technical scope of the present disclosure.

[0124] The processes (functions) performed by the sensor data receiving unit, the status information receiving unit, the warning notification unit, the sensor data acquiring unit, the status information acquiring unit, the fatigue level estimating unit, the status detecting unit, the estimating unit, and the re-sitting determining unit are executed by a processing circuit including one or more processors. The processing circuit may be configured as an integrated circuit or the like that combines one or more memories, various analog circuits, and various digital circuits in addition to the one or more processors.

[0125] The embodiments disclosed herein are merely examples, and the present disclosure is not limited to the above-described embodiments. The scope of the present disclosure is defined by the claims in the scope of the claims, taking into consideration the description of the detailed description of the invention, and includes all modifications within the meaning and scope equivalent to the wordings described therein.

[0126] 40 Terminal device 50, 50A, 50B, 50C Fatigue level estimation system 60, 60A, 60B Vehicle 62 Exterior wireless device 64 Network 66 Seat 70, 70A In-vehicle system 100, 100A, 500 In-vehicle device 102, 202 Computer 110, 210 Control unit 112 Calculation unit 114, 216 ROM 116, 218 RAM 120 Memory 130 In-vehicle communication unit 140, 230 Communication unit 150, 240 Communication bus 160, 160a Sensor data receiving unit 162 Status information receiving unit 164, 290, 550 Warning notification unit 200, 200A Server 212 CPU 214 GPU 220 Storage device 250, 510 Sensor data acquisition unit 260, 520 Status information acquisition unit 270, 270a, 530 Fatigue level estimation unit 272, 272a, 532 Sitting-back determination unit 274, 534 Status detection unit 276, 536 Estimation unit 280, 540 Timer 300 Seat sensor 302 Grid 320 In-vehicle navigation 322 Route guidance unit 324 Display unit 326 Audio output unit 330 In-vehicle network 400, 402, 404, 410, 412, 420, 422, 424, 430, 432, 434 Center of gravity position L1, L2 Distance T1, T2, T3 Time

Claims

1. A fatigue estimation system comprising: a sensor data acquisition unit that acquires sensor data from a seating sensor; a status information acquisition unit that acquires status information representing a status of a vehicle in which the seating sensor is provided; and a fatigue level estimation unit that estimates a fatigue level of an occupant of the vehicle who is seated in a seat in which the seating sensor is provided based on the sensor data and the status information, wherein the fatigue level estimation unit includes: a status detection unit that detects, based on the status information, whether the vehicle is in a first state in which the vehicle is stopped, or a second state in which the vehicle is in a state equivalent to being stopped; and an estimation unit that estimates the fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data in the first state or the second state with a threshold value.

2. The fatigue level estimation system of claim 1, wherein the fatigue level estimation unit further includes a seating repositioning determination unit that determines whether the occupant has repositioned their seat based on the sensor data, the fatigue level index includes the number of times the occupant has repositioned their seat, which is the number of times determined by the seating repositioning determination unit to be the occupant having repositioned their seat, and the estimation unit estimates the fatigue level of the occupant by comparing the number of times the occupant has repositioned their seat in the first state or the second state with the threshold value.

3. A fatigue level estimation system as described in claim 2, wherein the estimation unit estimates the fatigue level of the occupant based on whether a state in which the number of times the occupant shifts in their seat per unit time in the first state or the second state exceeds a first threshold value has occurred consecutively a number of times equal to or greater than a second threshold value.

4. A fatigue level estimation system as described in claim 2 or claim 3, wherein the re-seating determination unit determines whether the occupant has re-seated based on the speed at which the center of gravity of the occupant's body pressure on the seat sensor moves.

5. The fatigue level estimation system of claim 4, wherein, when an axis parallel to the vehicle's direction of travel is defined as a first axis, the movement of the occupant's center of gravity position based on the sensor data includes a movement of the center of gravity parallel to the first axis and a movement of the center of gravity parallel to a second axis perpendicular to the first axis, the seating adjustment determination unit further determines whether the occupant has adjusted his / her seat on the first axis by moving his / her center of gravity parallel to the first axis, or has adjusted his / her seat on the second axis by moving his / her center of gravity parallel to the second axis, and the estimation unit corrects the number of times the occupant has adjusted his / her seat depending on whether the occupant has adjusted his / her seat on the first axis or the second axis.

6. A fatigue level estimation system as described in any one of claims 2 to 4, wherein the estimation unit corrects the number of times the occupant has shifted in their seat depending on the amount of movement of the center of gravity of the occupant's body pressure on the seat sensor.

7. A fatigue level estimation system as described in claim 2 or claim 3, wherein the re-seating determination unit determines whether the occupant has re-seated based on a change in the seat pressure of the seating sensor when the occupant is seated in the seat on which the seating sensor is provided.

8. A fatigue level estimation system according to any one of claims 1 to 7, wherein the second state includes a state in which the vehicle is traveling at a speed below a speed defined as a traffic jam.

9. A fatigue level estimation system according to any one of claims 1 to 7, wherein the second state includes a state in which the vehicle is traveling in a traffic congestion area.

10. A fatigue level estimation system as described in any one of claims 1 to 9, further comprising a notification unit that notifies an administrator who manages the passenger of the passenger's fatigue level.

11. The fatigue level estimation system according to any one of claims 1 to 10, further comprising an in-vehicle device mounted on the vehicle and a server that communicates with the in-vehicle device, the in-vehicle device including a communication unit that acquires the sensor data and the status information and transmits them to the server, the server including: a sensor data acquisition unit that acquires the sensor data by receiving the sensor data from the in-vehicle device; a status information acquisition unit that acquires the status information by receiving the status information from the in-vehicle device; and a fatigue level estimation unit that estimates the fatigue level of the occupant seated in a seat on which the seating sensor is provided based on the sensor data and the status information.

12. An on-board device mounted on a vehicle equipped with a seating sensor, comprising: a sensor data acquisition unit that acquires sensor data from the seating sensor; a status information acquisition unit that acquires status information representing a status of the vehicle; and a fatigue level estimation unit that estimates a fatigue level of an occupant of the vehicle who is seated in the seat on which the seating sensor is provided based on the sensor data and the status information, wherein the fatigue level estimation unit includes: a status detection unit that detects, based on the status information, that the vehicle is in a first state in which the vehicle is stopped, or a second state in which the vehicle is in a state equivalent to being stopped; and an estimation unit that estimates the fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data in the first state or the second state with a threshold value.

13. A server that communicates with an in-vehicle device mounted on a vehicle equipped with a seating sensor, comprising: a sensor data acquisition unit that acquires sensor data from the seating sensor via the in-vehicle device; a status information acquisition unit that acquires status information representing the status of the vehicle via the in-vehicle device; and a fatigue level estimation unit that estimates a fatigue level of an occupant of the vehicle who is seated in a seat equipped with the seating sensor based on the sensor data and the status information, wherein the fatigue level estimation unit includes: a status detection unit that detects, based on the status information, that the vehicle is in a first state in which the vehicle is stopped, or a second state in which the vehicle is in a state equivalent to being stopped; and an estimation unit that estimates the fatigue level of the occupant by comparing a fatigue level index of the occupant based on the sensor data in the first state or the second state with a threshold value.

14. A fatigue level estimation method for estimating a fatigue level of a passenger seated in a vehicle seat based on sensor data from a seating sensor provided in the seat, comprising the steps of: acquiring sensor data from the seating sensor; acquiring status information representing a status of the vehicle; and estimating a fatigue level of the passenger based on the sensor data and the status information, wherein the step of estimating a fatigue level includes the steps of: detecting, based on the status information, that the vehicle is in a first state in which the vehicle is stopped, or a second state in which the vehicle is in a state equivalent to being stopped; and estimating the fatigue level of the passenger by comparing a fatigue level index of the passenger based on the sensor data in the first state or the second state with a threshold value.

15. A computer program for causing a computer to estimate the fatigue level of a passenger seated in a vehicle seat based on sensor data from a seating sensor provided in the seat, the computer program executing the following steps: acquiring sensor data from the seating sensor; acquiring status information representing the status of the vehicle; detecting, based on the status information, that the vehicle is in a first status in which the vehicle is stopped, or a second status in which the vehicle is equivalent to being stopped; and estimating the fatigue level of the passenger by comparing a fatigue level index of the passenger based on the sensor data in the first status or the second status with a threshold value.

Images