Work vehicle

Abstract

To provide a work vehicle for improving work accuracy.SOLUTION: A work vehicle includes: an awakening degree estimation section for calculating an estimation value of an awakening degree which indicates the degree of awakening of an operator when photographing information of an operator photographing camera 42 is input; and attention calling means for calling attention in order to prevent a dose of the operator. The awakening degree estimation section performs: acquiring a drowsiness score from a learning model section when automatic driving is started; and calculating an estimation value of the awakening degree from information of the acquired drowsiness score, information related to a change of a body temperature of the operator acquired from a body temperature measurement camera 43, and information of a carbon dioxide concentration acquired from a carbon dioxide concentration measurement sensor 27. When the calculated estimation value of the awakening degree is equal to or less than a reference value, the attention calling means calls attention of the operator.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a work vehicle that performs agricultural work while automatically driving in a field. [Background technology]

[0002] Conventionally, as shown in, for example, Patent Document 1 and Patent Document 2 below, there are known work vehicles that use position information obtained from a satellite positioning system to perform agricultural work (hereinafter simply referred to as work) while driving automatically in a field. This type of automatically driven work vehicle can switch between manual driving and automatic driving, and when in automatic driving, it drives by alternating between going straight and turning in order to travel efficiently throughout the entire field.

[0003] Furthermore, as shown in Patent Document 3 below, for example, there are known work vehicles equipped with detection means such as ultrasonic sonar, laser scanners (lidars), and cameras on the body of the vehicle to detect obstacles around the vehicle while it is traveling. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-187351 [Patent Document 2] Patent Publication No. 2021-069291 [Patent Document 2] Japanese Patent Application Publication No. 2018-116611 Summary of the Invention [Problem to be solved by the invention]

[0005] While conventional self-driving work vehicles like these reduce the burden on workers and provide convenience, they can easily induce drowsiness if the worker remains seated for long periods of time without driving. However, if the worker (driver) falls asleep, problems arise, such as reduced safety, work accuracy, and work efficiency. Furthermore, as smart agriculture is currently being promoted, there is a demand for more multifunctional work vehicles that utilize detection means on the vehicle.

[0006] Therefore, the present invention solves such problems, prevents drowsiness during automatic driving, and The object is to provide a more multifunctional work vehicle by utilizing the detection means of the vehicle body. [Means for solving the problem]

[0007] In order to achieve the above object, the first invention is: A work vehicle equipped with a work implement and configured to be able to automatically drive in a field, and equipped with a control room in a cabin, a worker photographing camera that photographs the worker; A temperature measurement camera that measures the worker's temperature, a carbon dioxide concentration measurement sensor for measuring a carbon dioxide concentration in the cockpit; a learning model unit that is trained by machine learning to generate a drowsiness score indicating the degree of drowsiness of the worker using a machine learning algorithm having predetermined parameters when the photographing information of the worker photographing camera is input; The system includes an alertness estimation unit that calculates an estimated value of the alertness indicating the level of alertness of the worker, and an attention calling means that calls the attention of the worker to prevent the worker from falling asleep, When autonomous driving is started, the alertness estimation unit acquires the drowsiness score from the learning model unit, and calculates an estimated value of the alertness level from information on the acquired drowsiness score, information on changes in the worker's body temperature acquired from the body temperature measurement camera, and information on the carbon dioxide concentration acquired from the carbon dioxide concentration measurement sensor; The present invention provides a work vehicle characterized in that, when the calculated estimated value of the degree of wakefulness is equal to or less than a reference value, the warning means issues a warning to the worker.

[0008] According to the first aspect of the present invention, the wakefulness level estimation unit can accurately determine the wakefulness level of the worker, If the estimated level of alertness calculated by the alertness estimation unit is below a reference value, a warning means is used to warn the worker, preventing drowsiness during automated driving, and by utilizing detection means such as sensors and cameras, a more multifunctional work vehicle can be provided.

[0009] The second invention is the first invention, The front windshield and the left and right side windows in the cockpit are made of transparent screen glass that is translucent and can display projected images, A projection device disposed in the cockpit is configured to project and display images onto the front windshield and the left and right side windows, The attention-calling means is configured to display a warning message on the front windshield and the left and right side windows by the projection device.

[0010] According to the second invention, in addition to the effects of the first invention, The attention-attracting means displays a warning message on the front windshield and the left and right side windows using the projection device, thereby making an impact on the worker, urging them to wake up, and making the warning message more reliably visible.

[0011] The third invention is the first or second invention, After issuing a warning by the warning means, the photographic information from the worker photographing camera is acquired, and it is determined whether the worker responds to cancel the warning, and if there is no response from the worker to cancel the warning within a specified time, the vehicle is stopped from traveling.

[0012] According to the third invention, in addition to the effects of the first or second invention, This prevents the vehicle from operating automatically when the operator is dozing or in a state of drowsiness, thereby improving safety. [Effects of the Invention]

[0013] According to the present invention, drowsiness during automatic driving can be prevented, and by utilizing the vehicle's detection means, a more multifunctional work vehicle can be provided. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a left side view of a work vehicle according to an embodiment of the present invention. [Figure 2] FIG. 2 is a plan view of the same. [Figure 3] FIG. 3 is an external view of the cockpit interior as seen from the cockpit. [Figure 4] 4 is a schematic perspective view of the right side of the cockpit in FIG. [Figure 5] FIG. 5 is an enlarged view of part A in FIG. [Figure 6] FIG. 6 is a block diagram showing the configuration of a control system including a control device for a work vehicle. [Figure 7] FIG. 7 is an explanatory diagram showing an example of a procedure for creating teacher information. [Figure 8] FIG. 8 is a flowchart showing an example of the wakefulness level estimation process. [Figure 9] FIG. 9 is a flowchart showing an example of the drowsiness prevention process. [Figure 10] 10(a) and 10(b) are schematic left side views of a work vehicle according to another embodiment. [Figure 11] FIG. 11 is a schematic rear view of a work vehicle according to another embodiment. [Figure 12] 12(a) and 12(b) are explanatory diagrams relating to the design of a straight driving route. DETAILED DESCRIPTION OF THE INVENTION

[0015] A preferred embodiment of the present invention will be described below with reference to the accompanying drawings. In the following description, unless otherwise specified, the forward direction of the work vehicle 1 (the direction from the operator's seat 8 to the steering wheel 9, which will be described later) will be referred to as the front, the opposite direction will be referred to as the rear, and the right side when facing forward will be referred to as the right, and the left side will be referred to as the left. The work vehicle 1 as a whole will sometimes be referred to simply as the vehicle body.

[0016] <1. Basic configuration of work vehicle> First, the basic configuration of a work vehicle 1 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a left side view of the work vehicle 1 according to an embodiment, and Fig. 2 is a plan view. Note that the following description will be given using a tractor as an example of the work vehicle 1. Therefore, the work vehicle 1 will be mainly referred to as a tractor 1 below.

[0017] The tractor 1, which is a work vehicle, is an agricultural tractor that travels autonomously to perform work in fields, etc. The tractor 1 is operated by an operator (also called an operator) and travels within the field to perform predetermined tasks, and also performs predetermined tasks while automatically driving within the field through control of each part by a control system centered on a control device C (see Figure 3), which will be described later, that is disposed at an appropriate position on the vehicle body.

[0018] As shown in Fig. 1, the tractor 1 includes a traveling body 2 and a work implement W. The traveling body 2 includes a body frame 3, front wheels 4, rear wheels 5, a bonnet 6, an engine E, and a control unit 7. and a transmission case 10. The vehicle body frame 3 and the transmission case 10 form the main frame of the traveling vehicle body 2.

[0019] The front wheels 4 are a pair of left and right wheels, and are primarily used for steering (steered wheels). The rear wheels 5 are a pair of left and right wheels, and are primarily used for driving (drive wheels). The tractor 1 may be configured to be switchable between two-wheel drive (2WD) in which the rear wheels 5 are driven, and four-wheel drive (4WD) in which both the front wheels 4 and the rear wheels 5 are driven. In this case, both the front wheels 4 and the rear wheels 5 are drive wheels. The traveling body 2 may be equipped with a crawler device instead of wheels (front wheels 4 and rear wheels 5). In this case, the traveling crawler is the drive wheel.

[0020] The hood 6 is provided at the front of the traveling vehicle body 2 so as to be able to be opened and closed freely. The hood 6 can be rotated (opened and closed) in the vertical direction with the rear part as the rotation center. When closed, the hood 6 covers the engine E mounted on the vehicle body frame 3. The engine E is the driving source of the tractor 1 and is a heat engine such as a diesel engine or a gasoline engine.

[0021] The control unit 7 receives operations from the worker and functions to steer the work vehicle 1, and a control room 7r is defined by a cabin box 7a that covers the top of the traveling body 2. Inside the control room 7r, various operating members that receive operations from the worker are arranged, such as a driver's seat 8 where the worker sits and a steering wheel 9. The steering wheel 9 is a member that steers the front wheels 4, which are the steered wheels, and is steered manually by the worker during manual operation, and is automatically steered by a steering device 51 that is configured including a steering actuator and the like (not shown) during automatic operation. The configuration of the control room 7r will be described later.

[0022] The transmission case 10 houses a transmission (a speed change device 32). The power (rotational power) output from the engine E is appropriately reduced (shifted) by the transmission and transmitted to the front wheels 4 and rear wheels 5 via the front axle 4j and rear axle 5j, as well as to the PTO shaft 16. A PTO clutch, PTO speed change device, and braking device 33 (not shown) are also housed within the transmission case 10, making it possible to control the transmission (on / off, shifting) of power to the PTO shaft. This enables the work vehicle A to control the drive of the work implement W.

[0023] A work implement W that performs work in the field is connected to the rear of the traveling body 2, and a PTO shaft 16 that transmits power to drive the work implement W protrudes rearward from the transmission case 10. The PTO shaft 16 transmits rotational power that has been appropriately reduced by the transmission to the work implement W that is attached to at least the rear of the traveling body 2.

[0024] In addition, a lifting device 12 that raises and lowers the work implement W is provided at the rear of the traveling body 2. The lifting device 12 raises the work implement W to move it to a non-working position. The non-working position is a position where the work implement W is raised when, for example, the traveling body 2 moves backward or turns. In addition, the lifting device 12 lowers the work implement W to move it to a ground work position. The lifting device 12 includes a hydraulic lifting cylinder 121, a lift arm 122, a lift rod 123, a lower link 124, and a top link 125.

[0025] When hydraulic oil is supplied to the lift cylinder 121, the lift arm 122 rotates around the axis AX serving as the rotation fulcrum to raise the work implement W, and when hydraulic oil is discharged from the lift cylinder 121, the lift arm 122 rotates around the axis AX to lower the work implement W. A lift arm sensor 26 that detects the rotation angle of the lift arm 122 is provided at the base of the lift arm 122 (near the axis AX). The height of the work implement W is calculated based on the detection result of the lift arm sensor 26.

[0026] The positioning device 30 is, for example, a GNSS (Global Navigation Satellite System) antenna, and can perform positioning and timing by receiving radio waves from navigation satellites S orbiting the sky. It can also calculate the traveling speed from the history of positioning results and the Doppler effect of radio waves. During autonomous driving, a control device C (described later) acquires positioning information (in other words, vehicle position information) from the positioning device 30 to calculate the vehicle's position, and controls the steering device 51 to eliminate deviation from a predetermined target driving route, thereby enabling autonomous driving. The positioning device 30 also includes an IMU (Inertial Measurement Unit), which can simultaneously measure the tilt angle of the traveling vehicle body 2 (i.e., the tilt of the field).

[0027] The lift arm 122 is connected to the lower link 124 via the lift rod 123. In this way, the lifting device 12 connects the work machine W to the traveling body 2 via the lower link 124 and the top link 125 so that the work machine W can be raised and lowered. The lower link 124 is attached to the rear of the transmission case 10.

[0028] The work implement W is a machine that performs work in a farm field. In the example shown in Fig. 1, the work implement W is a rotary tiller that performs tilling work in a farm field. The rotary tiller tills the farmland (soil) by rotating the tiller tines 61 using power transmitted from the PTO shaft 16.

[0029] The tractor 1 also includes a control device C (see FIG. 3). The control device C controls the engine E and also controls the traveling speed of the traveling body 2. The control device C also controls the lifting and lowering of the work implement W.

[0030] The tractor 1 also allows the operator to set various tasks for a specific field by operating an information processing terminal (a mobile terminal such as a tablet terminal) 100. The information processing terminal 100 includes a storage unit configured with, for example, a hard disk, a ROM (Read Only Memory), a RAM (Random Access Memory), etc., and a display unit and operation unit configured with a touch panel. Note that various keys, buttons, etc. may also be provided separately as the operation unit.

[0031] <2. Work vehicle sensors> Next, the group of sensors N arranged on the tractor 1 will be described. The tractor 1 is configured to include, as a sensor group N, an obstacle sensor 20 that detects obstacles (people or objects) and a temperature sensor 40 that measures temperature.

[0032] The obstacle sensor 20 functions to detect obstacles (people or objects) around the aircraft. This obstacle sensor 20 is a medium-range sensor, preferably an infrared sensor, that can detect obstacles by emitting an infrared beam and detecting the light reflected from the obstacle. In addition, the distance to the obstacle can be measured by measuring the time between emitting the infrared beam and detecting the light reflected from the obstacle. The obstacle sensor 20, which is an infrared sensor, detects obstacles two-dimensionally, with a detection range of, for example, several meters to several tens of meters. Note that other medium-range sensors, such as sonar or millimeter-wave radar, can also be used as the obstacle sensor 20, or a combination of these can be used.

[0033] The obstacle sensor 20 includes a front sensor 21 and a rear sensor 22. The front sensor 21 has a detection area that extends forward of the vehicle body, and the rear sensor 22 has a detection area that extends rearward of the vehicle body. The front sensor 21 is disposed at the front of the traveling vehicle body 2, for example, by being attached to a sensor mounting stay 13 provided in front of the hood 6, and detects obstacles (people or objects) that exist in front of the traveling vehicle body 2. The rear sensor 22 is disposed at the upper rear of the traveling vehicle body 2, for example, by being attached to the top of the cabin 7a, and detects obstacles that exist behind the traveling vehicle body 2. The angle of the rear sensor 22 relative to the cabin 7a, i.e., the traveling vehicle body 2, can be changed by a motor (not shown).

[0034] The temperature sensor 40 is a sensor capable of detecting temperature using a resistance temperature detector. This temperature sensor 40 includes an indoor temperature sensor 40a that measures the temperature inside the cockpit 7r, and an outdoor air temperature sensor 40b that measures the air temperature outside (also referred to as outdoors) the cabin 7a. The indoor temperature sensor 40a is disposed, for example, near the cockpit 8. The outdoor air temperature sensor 40b is disposed, for example, at an appropriate position on the exterior side wall of the cabin 7a. The measurement information from the temperature sensor 40 is transmitted to a control device C, which will be described later.

[0035] The steering wheel 9 is provided with a fingerprint authentication sensor 9s that authenticates the fingerprint of the worker (see FIG. 3). The fingerprint authentication sensor 9s is, for example, a sheet-type image sensor that can measure not only fingerprints but also pulse rates, and when the worker places his / her finger on the sensor, fingerprint read data is created. The control device C, which will be described later, acquires the fingerprint read data created by the fingerprint authentication sensor 9s and compares it with fingerprint information of the worker (user U) that is pre-stored in the storage unit of the control device C, thereby authenticating the worker.

[0036] Although not described in detail, the tractor 1 is also equipped with an engine rotation sensor 23 that detects the engine rotation speed, a vehicle speed sensor 24 that detects the vehicle speed, a steering angle sensor 25 that detects the steering angle of the front wheels 4 that are the steered wheels, a lever sensor 35 that detects the operating positions of various operating levers such as the sub-transmission lever 14, and a carbon dioxide concentration detection sensor 27 that detects the carbon dioxide concentration in the operator's cabin 7r described later, each of which is arranged in an appropriate position.

[0037] <3. Work vehicle photography equipment> The work vehicle 1 is equipped with a monitoring camera 41 that captures images of the area around the vehicle. These monitoring cameras 41 are disposed at the front, rear, left and right positions on the roof portion (cabin roof) of the cabin 7a, and are capable of capturing images of all four sides of the work vehicle 1. The photographic information captured by the monitoring camera 41 is transmitted to a control device C, which will be described later.

[0038] A camera unit U for photographing workers is disposed in the cockpit 7r. This camera unit U is disposed in the ceiling of the cabin 7a and includes a worker photographing camera 42 for photographing the worker seated in the cockpit 8 and a body temperature measuring camera 43 for measuring the worker's body temperature, which are integrated into a single unit. The worker photographing camera 42 generates photographic information, which is image data obtained by photographing the worker at a predetermined time interval (e.g., one second). This photographic information is configured (the photographing angle of view, etc. is set) to include an image of at least the worker's entire face while working (when the worker is seated in the cockpit 8). The body temperature measuring camera 43 is a thermal camera that detects infrared energy radiated from the subject, converts it into temperature, and displays the temperature distribution. It measures the worker's body temperature and generates body temperature information. The photographic information from the worker photographing camera 42 and the body temperature information from the body temperature measuring camera 43 are transmitted to a control device C, which will be described later. The camera unit U is disposed in front of the cockpit 8 so that the worker photographing camera 42 can capture an image of the front of the worker.

[0039] <4. Configuration of the cockpit> Next, the configuration inside the cockpit 7r will be described. Fig. 3 is an external view of the interior of the cockpit 7r as viewed forward from the cockpit 8, Fig. 4 is a schematic perspective view of the right side of the cockpit 8 in Fig. 3, and Fig. 5 is an enlarged view of part A in Fig. 3. Note that the various operating devices shown in each figure are examples, and the types and arrangements of the operating devices are not limited to these.

[0040] As shown in FIG. 5, the steering wheel 9 is provided in front of the driver's seat 8 (see FIG. 1) as described above. A fingerprint authentication sensor 9s is provided on the spokes of the steering wheel 9. A clutch pedal 18 is provided on the lower left side of the handle post 350 to which the steering wheel 9 is attached, and a fingerprint authentication sensor 9s is provided under the handle post 350. An accelerator pedal 19 and a brake pedal 15 are provided on the right side of the handlebar post 350. The brake pedal 15 includes left and right brake pedals 15L and 15R. An engine key switch 36 for operating the engine E (on / off) is provided on the right side of the handlebar post 350.

[0041] The windshield 71 and the left and right side windows 72, 72 of the cabin box 7a are made of transparent screen glass that is translucent and can display projected images. For details about the configuration of the transparent screen glass, see, for example, Japanese Patent Application Laid-Open No. 2019-168621.

[0042] Furthermore, a projection device 44 that projects images is attached to the ceiling of the cockpit 7r, slightly forward of the cockpit seat 8. This projection device 44 is equipped with three-way image projection units 44x (so-called projectors) that can project images onto the front windshield 71 and the left and right side windows 72, 72, respectively, and is configured so that RGB laser light is projected from the projection light source of each image projection unit to display images on the front windshield 71 and the left and right side windows 72, 72. The operation of each image projection unit is controlled by a control unit C. That is, the projection operation and display content are instructed by the control unit C. The projection device 44 can also be configured so that the image projection units 44x can be rotated 360 degrees by a motor to project images onto the front windshield 71 and the left and right side windows 72, 72, respectively.

[0043] As described above, a camera unit U incorporating a worker photographing camera 72 and a body temperature measuring camera 73 is attached to the ceiling of the cockpit 7r in front of the cockpit 8. In this embodiment, the camera unit U is located slightly to the right of the front of the cockpit 8, but this is not limitative and the camera may be located in any position that allows it to capture images of the worker. The worker photographing camera 72 and the body temperature measuring camera 73 may also be located in different positions.

[0044] Furthermore, an audio output device 7p (a so-called speaker device) capable of outputting audio is provided at the front of the ceiling of the cockpit 7r, and an air conditioning device 7e (a so-called air conditioner device) that conditions the air inside the cockpit 7r is provided at the rear (Figure 1), enabling ventilation, heating, and cooling.

[0045] 4, the main transmission operation unit 17 (main transmission speed increase button 17a, main transmission speed decrease button 17b), the sub-transmission lever 14, the accelerator lever 151, the position lever 152, the lift position setting means (lift height dial) 90, the public road travel button 91, the operation panel storage section 62, etc. are provided on the right side of the operator's seat 8. Of these, the position lever 18 is operated when raising or lowering the lift arm 122.

[0046] Furthermore, various operation switches such as a PTO automatic / manual changeover switch, a PTO on / off switch, an engine rotation indicator, an RPM increase adjustment switch, and an RPM decrease adjustment switch are provided on the right side of the cockpit 8. The operation panel storage section 62 stores an operation panel on which operation switches other than those described above are provided.

[0047] The lifting position setting means (lifting height dial) 90 is a dial that adjusts the lifting cylinder 121, which is a hydraulic cylinder, to adjust the predetermined position H of the work implement W relative to the traveling vehicle body 2 when the public road driving button 91 is pressed or when the control device C determines that the vehicle is traveling on the road, or the angle value of the lift arm 122 detected by the lift arm sensor 26.

[0048] A forward / reverse lever 201 is provided on the upper left side of the handle post 350. Also, as shown in Figure 5, an accelerator lever 351, a turn signal lever 352, and a one-touch lift lever 353 are provided on the upper right side of the handle post 350. The one-touch lift lever 353 is used to operate, with one touch, the lift arm that connects the work machine to the machine body to the operating position of the position lever 152 or the uppermost position. Also, a PTO shift lever 354 is provided in the center of the handle post 350.

[0049] 5, a dashboard cover 355 is provided in front of the steering wheel 9. The dashboard cover 355 is also provided with a meter panel 11 so as to be visible to the operator in the cockpit 8. The meter panel 11 is also provided with a display unit (liquid crystal monitor) 356, an engine revolution meter (tachometer) 357, and the like. The liquid crystal monitor 356 displays various information such as a gear display that displays the current gear, a fuel consumption rate display, and a traveling speed display, and the fuel consumption rate display and the traveling speed display may be displayed so as to be switched at regular intervals.

[0050] Furthermore, a driving mode selection switch 223 and an engine mode selection switch 192 are provided on the right side of the dashboard cover 355. When the engine mode selection switch 192 is pressed, the engine E (see FIG. 1) is controlled according to an engine output curve that provides low fuel consumption.

[0051] In this embodiment, the tractor 1 is configured to be switchable, by operating the driving mode selection switch 223, among a manual driving mode in which the tractor travels in a field by manual steering (the operator operates the steering wheel 9, etc.), an automatic driving mode in which the tractor travels in a field by automatic steering, and a road driving mode in which the tractor travels on roads. The manual driving mode and the automatic driving mode are control modes selected when working in a field, and are controlled, for example, so that the vehicle travels only at low speeds (1 to 10 km / h). The road driving mode is a control mode selected, for example, when traveling on a road to a field, and is controlled so that the vehicle travels by manual steering as in the manual driving mode, but is controlled so that the vehicle travels at high speeds (15 km / h or higher).

[0052] <5. Control device configuration> FIG. 6 is a block diagram showing the configuration of a control system including a control device C of the work vehicle A. The control device C is an information processing device configured by combining multiple ECUs (Electronic Control Units). Each of the multiple ECUs is configured with a CPU that performs arithmetic processing and a memory that can read and write information required for the arithmetic processing. The CPU operates in accordance with various control programs stored in the memory, thereby realizing the configuration shown as functional blocks in Fig. 6.

[0053] As shown in FIG. 6, the control device C has on its input side a positioning device 30, a surveillance camera 41, a group of sensors N, a camera unit U, an engine key switch 36, an engine mode selection switch 192, and a driving mode selection switch 223 connected via an input / output signal processing unit (including a communication unit) not shown, thereby obtaining positioning information (aircraft position information) from the positioning device 30, detection and detection information from the group of sensors N, photography information and body temperature information from the surveillance camera 41 and the camera unit U, and operation information from the engine mode selection switch 192 and the driving mode selection switch 223.

[0054] The control device C is equipped with ECUs for controlling each mechanism of the vehicle, and more specifically, it is equipped with an operation system ECU 50 that controls the operation of each mechanism of the work vehicle 1, and a control system ECU 54 that determines the operation method (operation rules) of each mechanism. As shown in Fig. 6, the operation system ECU 50 is equipped with an engine ECU 51 that controls the operation of the engine E, a travel system ECU 52 that controls the operation of mechanisms related to travel such as the steering device 31, transmission 32, and braking device 33, and a work machine ECU 53 that controls the operation (lifting and lowering) of the lifting device 12.

[0055] As described above, the steering device 51 is configured to include a steering actuator and the like, and is a device that automatically steers the steering wheel 9 during automatic driving. The speed change device 32 is a transmission housed in the transmission case 10, and is a device that changes the speed of the rotational power output from the engine E. In addition, the braking device 33 is a device that controls the drive of the work machine W.

[0056] The control device C includes a communication unit 60, which is a communication mechanism that connects with an external device physically separated from the control device C via a network NW and exchanges information through communication. In this embodiment, the communication unit 60 is connected to at least the mobile information terminal 100, and is capable of sending and receiving information.

[0057] The mobile information terminal 100 also includes a touch panel display 101 (see FIGS. 1 and 7), a small camera 100a capable of generating image data by taking pictures, and an image acquisition unit 101 that acquires the image data generated by the small camera 100a and stores it in a storage unit (not shown).The mobile information terminal 100 also includes a face authentication information creation unit 102 that is a program downloadable via the Internet from an external server or the like and is capable of creating face authentication information, and a teacher information creation unit 103 that creates teacher information (also called teacher data).

[0058] The facial authentication information creation unit 102 is a program that enables facial image information for authentication to be registered in the user authentication information database D1 together with a user ID that uniquely identifies the user U by sending image data of the entire face of the user U captured by the compact camera 100a to the control device C, and accepts input of information required to create facial authentication information from the user U. The teacher information creation unit 103 is a program that creates teacher information, the details of which will be described later.

[0059] <6. Control examples using control devices (control ECUs)> The configuration of the control system ECU 54 will be described in more detail below, along with control examples. The control system ECU 54 includes, as control programs, a user authentication unit 55 that authenticates a user U, a driving control unit 56 that controls the driving of the vehicle, an alertness estimation unit 57 that calculates an estimated value of the alertness indicating the level of alertness of the worker, a drowsiness prevention unit 58 that prevents the worker from falling asleep, and a projection device control unit 59 that controls the operation of the projection device 44. Here, the user U refers to the worker who performs work using the work vehicle 1. In other words, there is a different user U for each work vehicle 1. Note that the alertness is the degree to which the worker is alert, rather than being in a state of hazy consciousness due to drowsiness or the like, and the alertness estimated value, which will be described later, is an estimated value of the alertness, which is defined as a numerical value that increases as the worker becomes more alert, taking zero when the worker is asleep, for example.

[0060] The control system ECU 54 also has databases capable of registering and storing various types of information, such as a user authentication information database D1 that stores user authentication information (for example, fingerprint information and facial information of user U), a work information database D2 that stores work-related information, a training information database D3 that stores training information described below, and a monitoring information database D4 that stores (also referred to as recording) monitoring information described below. The work information includes, for example, field information that is information about the field, a planned travel route for travel, and the working width of the work implement W. The field information includes field information necessary for the work, such as the shape, position, size, area, latitude, longitude, and altitude of each field to be worked on.

[0061] [Control example] (I) User authentication process The control device C performs user authentication processing using the user authentication unit 55. In this user authentication processing, before work begins, the user authentication unit 55 authenticates the fingerprint and face of the user U who is attempting to use the work vehicle 1, and if both authentications are successful, the control device C permits the engine E to be started by operating the engine key switch 36. In other words, even if the user U who is attempting to use the work vehicle 1 operates the engine key switch 36 when fingerprint and face authentication has not been successful, the control device C will not start the engine E. This makes it possible to prevent unexpected incidents such as theft of the work vehicle 1 by suspicious individuals.

[0062] Here, before work begins, the user authentication information database D1 is registered in advance with fingerprint information of the user(s) U who will use the work vehicle 1, and facial image information for authentication, which is a photograph of the entire face for authentication purposes. The fingerprint information of the user U can be registered in the user authentication information database D1 together with a user ID that uniquely identifies the user U from the fingerprint authentication sensor 9s through a predetermined operation. The facial image information for authentication can be registered in the user authentication information database D1 together with a user ID that uniquely identifies the user U by photographing the worker with the worker photographing camera 42 through a predetermined operation. As described above, the user U can register the facial image information for authentication in the user authentication information database D1 together with a user ID that uniquely identifies the user U by activating the facial authentication information creation unit 102 of the mobile information terminal 100. The facial image information can be registered in the user authentication information database D1 together with a user ID that uniquely identifies the user U.

[0063] In the user authentication process, the timing of authentication of user U's fingerprint is, for example, when user U enters the cockpit 7r and places his or her authentication finger (e.g., thumb) on the fingerprint authentication sensor 9s, the fingerprint read data of the fingerprint authentication sensor 9s is sent to the control device C, and the analyzed fingerprint read data of user U is compared with the authentication fingerprint information registered in the user authentication information database D1, and if matching data (fingerprint) is found, authentication of user U's fingerprint is successful.

[0064] In the user authentication process, the timing of authentication of the user U's face is, for example, when the user U sits in the cockpit 8, the control device C recognizes the person by analyzing the photographic information of the worker photographing camera 42, and thereby starts authentication of the user U's face. Next, the control device C (face authentication unit 55b) further analyzes the photographic information of the worker, compares the analyzed face image of the user U with the face image information for authentication registered in the user authentication information database D1, and if matching data (face) is found, authentication of the user U's face is successful.

[0065] Furthermore, the face of a user U approaching the work vehicle 1 may be authenticated by analyzing the photographic information from the surveillance camera 41. Furthermore, if no matching data is found as a result, the user U is deemed to be an unauthorized user, and an alarm (not shown) may be set off. At this time, a warning may be displayed on the front windshield 71 and the left and right side windows 72, 72 by the projection device 44. This makes it possible to more effectively prevent theft by suspicious individuals.

[0066] The user authentication process by the user authentication unit 55 can also be configured to permit operation of the engine E by operating the engine key switch 36 if either fingerprint or face authentication is successful. This reduces security, but improves convenience because the user U can select either fingerprint or face authentication. Furthermore, if authentication information for both fingerprints and faces is registered, authentication can be performed more quickly.

[0067] (II) Manual driving mode, automatic driving mode, road driving mode The driving control unit 56 includes a manual driving control unit 56a that controls driving in the manual driving mode, an automatic driving control unit 56b that controls driving in the automatic driving mode, and an on-road driving control unit 56c that controls driving in the on-road driving mode 56c. Here, controlling driving means, in more detail, acquiring necessary detection information from the sensor group N to execute each mode, and sending necessary control commands to the operating ECU 50 when each mode is selected.

[0068] Each operation mode is well known and will not be described in detail, but in the automatic operation mode, a planned travel route according to the work content of the work implement W is determined in advance for each field, converted into data, and stored in the work information database D2, and based on the measurement results of the positioning device 30, each part such as the engine E, steering device 51, transmission device 52, braking device 53, and lifting device 12 is controlled so that the implement travels along the stored planned travel route. Typically, to travel efficiently across the entire field, a route is designed that alternates between straight travel routes and turning routes, and the spacing between the straight travel routes is determined by the working width of the work implement W so that the working areas do not overlap. Furthermore, a specific planned travel route is designed depending on the shape and size of the field, and the width, length, and number of ridges formed in the field. The planned travel route may be designed by the control device C that receives information about the field and input from the operator, or the control device C may be configured to obtain information about the planned travel route designed by an external computer via the network NW.

[0069] In the manual driving mode, the operator can steer the machine by operating the steering wheel 9 to travel in a field. Similarly, in the road driving mode, the operator can steer the machine by operating the steering wheel 9 to travel on the road, but as described above, the upper limit of the vehicle speed is controlled so that the machine can travel at low speeds in the manual driving mode and at high speeds in the road driving mode.

[0070] (III) Drowsiness prevention treatment The alertness estimation unit 57 has the function of calculating an alertness estimation value, which is an estimate of the alertness of the worker, and is equipped with a learning model unit 57a that uses a machine learning algorithm to generate a drowsiness score (an index value that indicates the degree of drowsiness, for example, the higher the number, the stronger the drowsiness), a worker monitoring unit 57b that monitors the worker's biometric information, an environment monitoring unit 57c that monitors the worker's environmental information, and an alertness estimation value calculation unit 57d that calculates the alertness estimation value.

[0071] The learning model unit 57a is a trained model that has been trained using machine learning algorithms such as neural networks having predetermined parameters to generate a drowsiness score indicating the degree of drowsiness of the worker when photographic information captured by the worker photographing camera 42 is input.

[0072] In machine learning of a trained model, a large amount of training information (training data) is input using a machine learning algorithm such as a neural network as described above. The training information includes data in which a predetermined drowsiness score is linked to image data of a full face of a worker (however, this does not necessarily have to be the person performing the work). The drowsiness score can be a numerical parameter (in this embodiment, a numerical parameter ranging from 0 to 5) that numerically represents the user's desire for sleep, i.e., drowsiness. For example, a higher drowsiness score indicates greater drowsiness.

[0073] Here, an example of creating teaching information will be described with reference to FIG. Fig. 7 is an explanatory diagram showing an example of the procedure for creating teacher information. First, when creating teacher information, an operator (or an administrator) starts the program of the teacher information creation unit 103 of the mobile information terminal 100 by a predetermined operation. Fig. 7 shows an image of the display screen of the display 101 of the mobile information terminal 100 when the program is started.

[0074] 7, image data including the face of worker U captured by compact camera 100a is displayed in real time on display 101. In order to create teacher information including image data accurately capturing the entire face, display 101 displays a message 102 prompting worker U to place the face of worker U within a frame 103, a selection unit 104 for selecting a drowsiness score to be linked to the image data, and a display unit 105 for selecting the image data capturing the entire face currently displayed on display 101. and a register button 105 for linking the selected drowsiness score with the selected drowsiness score and registering it in the teacher information database D3. The illustrated example shows an image in which a value of 4 is selected as the drowsiness score. In this embodiment, the worker (user U) checks his / her own face (or that of another person) being photographed using the compact camera 100a, selects a drowsiness score from 0 to 5 by touching the selection unit 104, and touches the register button 105. The image data displayed on the display 101 is linked with the selected drowsiness score, transmitted to the control device C, and registered in the teacher information database D3. However, the above-described method of creating teacher information is merely an example. For example, image data acquired from the worker-photographing camera 42 may be used. Alternatively, the image data may be acquired from a cloud on the Internet, and the drowsiness score may be linked by an operator or a computer that has viewed the acquired image. It is preferable that the drowsiness score is evaluated based on facial expressions such as the degree of head tilt and the degree of eye closure of the worker in the image data (a person or a computer selects and registers the drowsiness score).

[0075] The worker monitoring unit 57b is a program that monitors and records the worker's biometric information while the worker is working. Specifically, the worker monitoring unit 57b acquires photographic information from the worker photographing camera 42 while the worker is working, and analyzes the acquired photographic information to measure, for example, the worker's pulse, the number of blinks per unit time, breathing, number of yawns, etc. at predetermined time intervals, and records the measured biometric information over time in the monitoring information database D4. Furthermore, the worker's body temperature information is acquired from the body temperature measuring camera 43, and is recorded in the monitoring information database D4 together with time information. This allows the control device C to acquire information regarding changes in the worker's body temperature. The worker's pulse may also be measured and acquired using fingerprint authentication 9s.

[0076] The worker monitoring unit 57c is a program that monitors and records environmental information about the worker while he or she is working. Here, environmental information refers to information about the worker's working environment. Specifically, the environment monitoring unit 57c acquires measurement information from the temperature sensor 40 during work, calculates the temperature difference between the inside and outside of the cockpit 7r, and records this information over time in the monitoring information database D4. The environment monitoring unit 57c also acquires information about the carbon dioxide concentration inside the cockpit 7r from the carbon dioxide concentration measurement sensor 27 and records this information over time.

[0077] The estimated arousal level calculation unit 57d executes an arousal level estimation process for calculating an estimated arousal level. Fig. 8 is a flowchart showing an example of the arousal level estimation process. When the wakefulness estimation process starts, the wakefulness estimation value calculation unit 57d acquires the latest shooting information from the worker shooting camera 42 (step #1). Subsequently, the acquired shooting information is input to the learning model unit 57a, and the learning model unit 57a acquires information (numerical value) of the generated drowsiness score. Furthermore, a first evaluation value, which is an evaluation value of the wakefulness level, is calculated based on the acquired numerical value of the drowsiness score (step #2). Here, the larger the drowsiness score, the lower the calculated first evaluation value. As an example, the first evaluation value can be a numerical value from 0 to 5, and when the drowsiness score is 0, the first evaluation value is 5; when the drowsiness score is 1, the first evaluation value is 4; when the drowsiness score is 2, the first evaluation value is 3; when the drowsiness score is 4, the first evaluation value is 1; and when the drowsiness score is 5, the first evaluation value is 0.

[0078] Next, the alertness estimation value calculation unit 57d acquires the worker's biological information recorded in the monitoring information database D4 (Step #3). Then, based on the acquired biological information, a second evaluation value, which is an evaluation value of the alertness level, is calculated (Step #4). As a first calculation method, the second evaluation value can be calculated based on changes in the worker's body temperature by referring to the body temperature information recorded by the body temperature measurement camera 43. For example, since people generally become drowsy when their body temperature changes, the second evaluation value is calculated by comparing the worker's body temperature from a predetermined time ago (e.g., 5 minutes) with the most recent body temperature. The smaller the difference in body temperature, the lower the calculated second evaluation value. Specifically, the second evaluation value ranges from 0 to 5. If there is no difference in body temperature, the second evaluation value is 5; if the difference in body temperature is 0.1 degrees, the second evaluation value is 4; if the difference in body temperature is 0.2 degrees, the second evaluation value is 3; if the difference in body temperature is 0.3 degrees, the second evaluation value is 2; if the difference in body temperature is 0.4 degrees, the second evaluation value is 1; and if the difference in body temperature is 0.5 degrees or more, the second evaluation value is 0.

[0079] As a second calculation method, the second evaluation value is calculated to be lower the more times the person yawns, based on the number of times the person yawns within a predetermined period of time (for example, from the present time until five minutes ago). Specifically, the second evaluation value is calculated as follows: 0 yawns = 5, 1 yawn = 4, 2 yawns = 3, 3 yawns = 2, 4 yawns = 1, and 5 or more yawns = 0.

[0080] As another calculation method, the second evaluation value can be calculated based on changes in the respiration or pulse rate over a predetermined time period (for example, from the present time to five minutes ago). In this case, the stronger the drowsiness, the slower the respiration or pulse rate. Therefore, the slower the respiration or pulse rate over a predetermined time period (for example, from the present time to five minutes ago), the lower the calculated second evaluation value. In this way, the second evaluation value can be calculated using a number of methods that utilize biological information, but in this embodiment, the second evaluation value is calculated based on body temperature. The system may be configured so that the worker's desired calculation method can be selected by a predetermined operation.

[0081] Next, the alertness estimation value calculation unit 57d acquires environmental information recorded in the monitoring information database D4 (step #4). Then, based on the acquired environmental information, it calculates a third evaluation value, which is an evaluation value of the alertness level (step #5). As a first calculation method, the third evaluation value can be calculated based on the most recent record of carbon dioxide concentration in the cockpit 7r. For example, since people generally become more drowsy as the carbon dioxide concentration in the air increases, the higher the carbon dioxide concentration, the lower the calculated third evaluation value. Specifically, the third evaluation value is a number between 0 and 5, and can be calculated as follows: when the carbon dioxide concentration is 500 ppm or less, the third evaluation value is 5; when the carbon dioxide concentration is greater than 500 ppm and less than 700 ppm, the third evaluation value is 4; when the carbon dioxide concentration is greater than 700 ppm and less than 900 ppm, the third evaluation value is 3; when the carbon dioxide concentration is greater than 900 ppm and less than 1100 ppm, the third evaluation value is 2; when the carbon dioxide concentration is greater than 1100 ppm and less than 1300 ppm, the third evaluation value is 1; and when the carbon dioxide concentration is 1500 ppm or more, the third evaluation value is 0.

[0082] As a second calculation method, the third evaluation value can be calculated based on the latest temperature difference between the inside and outside of the cockpit 7r measured by the temperature sensor 40. For example, since people generally become more drowsy the greater the temperature difference between indoors and outdoors, the greater the temperature difference, the lower the calculated third evaluation value. Specifically, the third evaluation value can be a numerical value between 0 and 5, with the third evaluation value being 5 when the temperature difference is within ±1°C, 4 when the temperature difference is within ±1 to ±3°C, 3 when the temperature difference is within ±3 to ±5°C, 2 when the temperature difference is within ±5 to ±7°C, 1 when the temperature difference is within ±7 to ±10°C, and 0 when the temperature difference is ±10°C or more. As described above, the third evaluation value can be calculated using multiple methods utilizing environmental information. In this embodiment, the third evaluation value is calculated based on the carbon dioxide concentration. The system may be configured to allow the operator to select a desired calculation method through a predetermined operation.

[0083] Next, the arousal level estimated value calculation unit 57d calculates the arousal level estimated value using the calculated first to third evaluation values. The arousal level estimated value can be calculated, for example, by adding the first to third evaluation values after applying a predetermined weighting to each of them. For example, the weighting coefficients of each evaluation value can be set to a value between 0 and 1 according to the importance of each evaluation value, with the sum total being 1. In this case, for example, if the weighting coefficient α of the first evaluation value is set to 0.6, the weighting coefficient β of the second evaluation value is set to 0.3, and the weighting coefficient γ of the third evaluation value is set to 0.1, and the first evaluation value is set to 3, the second evaluation value is set to 4, and the third evaluation value is set to 5, the arousal level estimated value can be calculated as 3.5. In this way, the arousal level estimated value (in this embodiment, the arousal level estimated value is defined as a value between 0 and 5 that increases as the worker becomes more alert) can be calculated by comprehensively considering the worker's facial expression, biological information, and environmental information.

[0084] The weighting coefficients for each evaluation value may be configured to be adjustable by a predetermined operation by the operator. In this case, it is preferable to set the weighting coefficients for the first to third evaluation values to be large for evaluation values that the user U wants to emphasize in calculating the estimated value of the wakefulness level, and conversely, the coefficients for evaluation values that the user U thinks can be ignored may be set to 0.

[0085] The drowsiness prevention unit 58 is a program that functions to prevent the worker from falling asleep, and includes a drowsiness determination unit 58a that determines whether the worker is falling asleep, an alert unit 58b that causes the drowsiness prevention means (air conditioner 7e, audio output device 7p, projection device 44) to issue an alert to prevent the worker from falling asleep, and an emergency stop unit 58c that brings the vehicle to an emergency stop, and executes a drowsiness prevention process. Figure 9 is a flowchart showing an example of the drowsiness prevention process. The drowsiness prevention process is started, for example, when automatic driving in the automatic driving mode is started.

[0086] When the doze prevention process is initiated, the doze prevention unit 58 executes the wakefulness estimation process through the process of the doze determination unit 58a (step #21). The calculated wakefulness estimation value is then acquired from the wakefulness estimation value calculation unit 57d (step #22). Subsequently, it is determined whether the acquired wakefulness estimation value is equal to or less than a predetermined reference value (step #23). Here, the predetermined reference value is a threshold value set for determining whether the worker is wakeful. If the wakefulness estimation value is greater than the reference value, the worker is estimated to be wakeful. On the other hand, if the wakefulness estimation value is equal to or less than the reference value, the worker is estimated to be in a state of drowsiness or the like. Note that, as an example, if the above method is configured to calculate the wakefulness estimation value as a numerical value from 0 to 5, the reference value can be set to 3.5. The reference value may be configured so that the worker can change or adjust the setting value by a predetermined operation.

[0087] When the estimated level of alertness is greater than the reference value (N in step #23), it is determined whether the automatic driving mode has been terminated (step #24) to determine whether it is necessary to terminate the drowsiness prevention process itself. It is determined whether the automatic driving mode has been terminated (step #24). When the automatic driving mode has been terminated, the drowsiness prevention process is terminated (Y in step #24). When the automatic driving mode continues, the process returns to step #21.

[0088] On the other hand, if the estimated alertness level is equal to or lower than the reference value (Y in step #23), it is estimated that the operator is in a state of drowsiness or other drowsiness, and the alert unit 58b issues an alert (step #25). Specifically, the audio output device 7p can be configured to output an audio warning message, and the projection device 44 can be configured to display a warning message (e.g., "Caution! Drowsiness has been detected. Please raise your hand to cancel the message") on the front windshield 71 and the left and right side windows 72, 72. Displaying a warning message on the front windshield 71 and the left and right side windows 72, 72 using the projection device 44 in this way impacts the operator, urging them to be alert and ensuring that the warning message is more clearly visible. Furthermore, the air conditioning unit 7e can be configured to increase the airflow by supplying air that is either warmer or cooler than the temperature inside the cockpit 7r. This appeals to the operator's senses and urges them to be alert.

[0089] After issuing the alert, the drowsiness prevention unit 58 determines whether the worker makes a reaction to cancel the alert within a predetermined time (e.g., 30 seconds) (step #27). A reaction to cancel the alert is a reaction that indicates that the worker is awake. For example, the control device C acquires image information from the worker imaging camera 42 and analyzes the acquired image information to determine that the worker has made a reaction such as raising their hand or waving their hand, thereby determining that a reaction to cancel the alert has occurred. Alternatively, in addition to this, the control device C may determine that the worker has operated one of various operating members as a reaction that indicates that the worker is awake. Furthermore, a microphone may be provided in the cockpit 7r, and the presence of the worker's voice may be determined to be a reaction to cancel the alert.

[0090] If the operator responds to cancel the alert within a predetermined time after issuing the alert, the drowsiness prevention unit 58 can determine that the operator is awake or has become awake, and therefore cancels the alert and returns to step #21 (step #27). On the other hand, if the operator does not respond to cancel the alert within a predetermined time after issuing the alert, it can be determined that the operator is dozing or is in a state of mental drowsiness or the like, and therefore the emergency stop unit 58c stops the vehicle from running and terminates the drowsiness prevention processing (step #28). This prevents the vehicle from running (automatic driving) when the operator is dozing or is in a state of mental drowsiness or the like, thereby improving safety.

[0091] The embodiments of the present invention have been described above. The present invention is not limited to the above-described embodiments. It goes without saying that modifications may be made as appropriate within the scope of the technical concept. Other embodiments will be described below.

[0092] 7. Another embodiment of the obstacle sensor 10(a) and 10(b) are schematic left side views of a work vehicle 1 according to another embodiment. As shown in Figures 10(a) and 10(b), the obstacle sensor 20 (rear sensor 22) is disposed at the rear of the traveling body 2, at the tip of a mounting stay 20r that can be swiveled up and down by a motor, and by raising and lowering the work equipment W and raising and lowering the obstacle sensor 20 (rear sensor 22) in the opposite direction, the work equipment W is prevented from entering the detection range 20x of the sensor and interfering with the detection of obstacles.

[0093] <8. Correcting the working width by tilting the machine body> FIG. 11 is a schematic rear view of a work vehicle 1 according to another embodiment. As shown in FIG. 11 , when the field and the machine body are inclined at an angle θ with respect to the horizontal plane, the control device C may be configured to correct the working width L to L cos θ when designing the planned travel path. The angle θ is detected by the IMU of the positioning device 30. That is, for efficient travel, it is usually preferable to calculate the planned travel path using the working width L as the spacing between straight travel paths. However, if the entire field is inclined, traveling along straight travel paths at an interval of the working width L in a planar view will result in overlapping work areas. Therefore, by correcting the working width L to L cos θ, the error in the working width L caused by the inclination can be corrected and overlapping work areas can be prevented.

[0094] <9. Designing a straight driving route> 12(a) and 12(b) are explanatory diagrams relating to the design of a straight driving route. 12(a) and 12(b) show a map of the field to be worked on and a contour line t1. When the control device C acquires map information of the field including the elevation in designing the planned travel route, if a ridge exists in the field, as shown in FIG. 12(a), it is preferable to calculate an imaginary line t21 of the ridge and design the direction of the straight travel route parallel to the direction F perpendicular to the imaginary line t21. Furthermore, if no ridge exists in the field, it is preferable to calculate an imaginary line t22 parallel to the contour line and design the direction of the straight travel route parallel to the direction F perpendicular to the imaginary line t22, as shown in FIG. 12(b).

[0095] <10. Other embodiments> 6 to 9, an embodiment has been described in which an alert is issued when an estimated alert level is calculated and it is determined that the worker is dozing or in a state of drowsiness or other drowsiness, but it is also possible to configure the system so that an alert is issued to the worker in accordance with conditions such as the worker's biological information and environmental information recorded in the monitoring information database D4, without relying on the calculation of an estimated alert level. For example, in the dozing prevention process, steps #21 to #23 in Fig. 9 can be replaced with branching processes based on the following conditions: (1) The latest temperature difference between the inside and outside of the cockpit 7r measured by the temperature sensor 40 is greater than or equal to a predetermined value (for example, ±3 degrees). (2) The carbon dioxide concentration in the cockpit 7r is at a specified value (for example, 1000 ppm or more). (3) The worker's temperature from a specified time before (e.g., 5 minutes) is compared with the latest temperature, and the difference in temperature is a specified value (e.g., 0.3 degrees or more). (4) A predetermined time (e.g., 5 minutes) has passed since the start of the automatic driving mode. If all of the above (1) to (4) are true, the process proceeds to step #25, and if any of them are false, the process proceeds to step #24.

[0096] The control device C may be configured to calculate the direction of the worker's line of sight by analyzing the direction of the worker's face and line of sight contained in the photographic information from the worker photographing camera 44, and to display an image by the projection device 44 on the glass in the direction of the worker's line of sight out of the front windshield 71 and the left and right side windows 72, 72. This makes it easier for the worker to check the image, and when the attention drawing unit 58b draws attention, the attention can be drawn in a direction that is appropriate for the worker's line of sight.

[0097] In the present invention, an embodiment has been described in which the drowsiness prevention processing is executed during automatic driving, with the aim of preventing the operator from falling asleep during automatic driving mode. However, the drowsiness prevention processing can also be applied to prevent the operator from falling asleep during manual driving mode or road driving mode. [Explanation of symbols]

[0098] 1 Tractor (work vehicle) 2 Running vehicle 3 Body frame 4 front wheels 5 rear wheels 6. Bonnet 7 Control Unit 7a Cabin 7r cockpit 8. Cockpit 9. Steering wheel 9s fingerprint authentication sensor 12 Lifting device 20 Obstacle Sensor 21 Front sensor 22 Rear sensor 26 Lift arm sensor 30 Positioning device 36 Engine key switch 40 Temperature Sensor 40a Indoor temperature sensor 40b Outside air temperature sensor 41 Surveillance Camera 42 Worker camera 43 Body Temperature Camera 100 Mobile Information Terminals 100a small camera E-Engine S navigation satellite W Work Machine

Claims

1. A work vehicle equipped with a work implement and configured to be able to automatically drive in a field, and equipped with a control room in a cabin, a worker photographing camera that photographs the worker; A temperature measurement camera that measures the worker's temperature, a carbon dioxide concentration measurement sensor for measuring a carbon dioxide concentration in the cockpit; a learning model unit that is trained by machine learning to generate a drowsiness score indicating the degree of drowsiness of the worker using a machine learning algorithm having predetermined parameters when the photographing information of the worker photographing camera is input; The system includes an alertness estimation unit that calculates an estimated value of the alertness indicating the level of alertness of the worker, and an attention calling means that calls the attention of the worker to prevent the worker from falling asleep, Equipped with When autonomous driving is started, the alertness estimation unit acquires the drowsiness score from the learning model unit, and calculates an estimated value of the alertness level from information on the acquired drowsiness score, information on changes in the worker's body temperature acquired from the body temperature measurement camera, and information on the carbon dioxide concentration acquired from the carbon dioxide concentration measurement sensor; A work vehicle characterized in that, when the calculated estimated value of the alertness level is equal to or less than a reference value, the alerting means issues an alert to the worker.

2. The front windshield and the left and right side windows in the cockpit are made of transparent screen glass that is translucent and can display projected images, A projection device disposed in the cockpit is configured to project and display images onto the front windshield and the left and right side windows, 2. The work vehicle according to claim 1, wherein the attention-attracting means is configured to display a warning message on the front windshield and the left and right side windows by the projection device.

3. 3. The work vehicle according to claim 1, wherein after issuing a warning by the warning means, photographic information from the worker photographing camera is acquired, and it is determined whether the worker responds to cancel the warning, and if the worker does not respond to cancel the warning within a predetermined time, the work vehicle stops traveling.

Images