Vehicle control method, vehicle control program, and vehicle control system

Abstract

The invention provides a vehicle control method, a vehicle control program, and a vehicle control system, which can prevent the work efficiency of a work vehicle from being reduced and enable the work vehicle to execute an appropriate response to an obstacle. When a work vehicle (10) automatically travels along a target route, an acquisition processing unit (511) acquires distance information of a distance to a detection object detected by an obstacle sensor (54), and image information of a captured image of the detection object captured by a camera (53). The determination processing unit (512) determines the type of the object to be detected on the basis of the image information. The response processing unit (112) causes the work vehicle (10) to execute response processing corresponding to the type of detection object and the distance information.

Description

Technical Field

[0001] The present invention relates to a technology for controlling the behavior of a work vehicle when a detection target such as an obstacle is detected. Background Art

[0002] In the past, there are known working vehicles equipped with obstacle sensors such as infrared sensors and ultrasonic sensors that can detect a detection object within a detection range during automatic driving (see, for example, Patent Document 1). When the detection object is an obstacle, the working vehicle performs avoidance control to avoid collision with the obstacle.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2021-65115

[0004] However, in the prior art, the presence or absence of an obstacle is determined based on the distance to the detection object. Therefore, even if the detection object is an object that the working vehicle does not need to perform an avoidance action (a harvesting object, a harvesting object, or other working object), if the distance to the detection object becomes below a threshold, the working vehicle will perform an avoidance action. Therefore, the working efficiency of the working vehicle is reduced. Summary of the invention

[0005] An object of the present invention is to provide a vehicle control method, a vehicle control program, and a vehicle control system that can prevent a decrease in the working efficiency of a working vehicle and enable the working vehicle to execute appropriate processing for an obstacle.

[0006] The vehicle control method of the present invention is a method for performing the following processing when a working vehicle is automatically traveling along a target path, namely: obtaining distance information of the distance to a detection object detected by a detection unit; obtaining image information of a captured image of the detection object captured by a capturing unit; determining the type of the detection object based on the image information; and causing the working vehicle to perform a response process corresponding to the type of the detection object and the distance information.

[0007] The vehicle control program of the present invention is a program for causing one or more processors to execute the following processing when a working vehicle is automatically traveling along a target path, namely: obtaining distance information of the distance to a detection object detected by a detection unit; obtaining image information of an image captured by a capturing unit of the detection object; determining the type of the detection object based on the image information; and causing the working vehicle to execute response processing corresponding to the type of the detection object and the distance information.

[0008] The vehicle control system of the present invention comprises an acquisition processing unit, a determination processing unit and a response processing unit. The acquisition processing unit acquires distance information of the distance to the detection object detected by the detection unit and image information of the image of the detection object photographed by the photographing unit when the working vehicle is automatically traveling along the target path. The determination processing unit determines the type of the detection object based on the image information. The response processing unit causes the working vehicle to execute response processing corresponding to the type of the detection object and the distance information.

[0009] According to the present invention, it is possible to provide a vehicle control method, a vehicle control program, and a vehicle control system that can prevent a decrease in the working efficiency of a working vehicle and enable the working vehicle to execute appropriate processing for an obstacle. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a block diagram showing the configuration of an automatic driving system according to an embodiment of the present invention.

[0011] Figure 2 This is an external view showing an example of a work vehicle according to an embodiment of the present invention.

[0012] Figure 3 This is a diagram showing an example of a travel route of a work vehicle according to an embodiment of the present invention.

[0013] Figure 4 This is a diagram showing an example of the detection range of the obstacle sensor provided in the work vehicle according to the embodiment of the present invention.

[0014] Figure 5 This is a diagram showing an example of a likelihood threshold used in the automatic driving system according to the embodiment of the present invention.

[0015] Figure 6 This is a diagram showing an example of a countermeasure process executed in the work vehicle according to the embodiment of the present invention.

[0016] Figure 7 This is a diagram showing an example of a menu screen displayed on the operation terminal according to the embodiment of the present invention.

[0017] Figure 8 This is a diagram showing an example of a driving screen displayed on the operation terminal according to the embodiment of the present invention.

[0018] Fig. 9 This is a diagram showing an example of a sensitivity setting screen displayed on the operation terminal according to the embodiment of the present invention.

[0019] Fig. 10AThis is a diagram showing an example of a likelihood threshold value according to the sensitivity used in the automatic driving system according to the embodiment of the present invention.

[0020] Fig. 10B This is a diagram showing an example of a likelihood threshold value according to the sensitivity used in the automatic driving system according to the embodiment of the present invention.

[0021] Fig.11 This is a diagram showing an example of a control target setting screen displayed on the operation terminal according to the embodiment of the present invention.

[0022] Fig.12 This is a flowchart showing an example of the procedure of the automatic driving process executed by the automatic driving system according to the embodiment of the present invention.

[0023] Fig.13A This is a diagram showing another example of the likelihood threshold used in the automatic driving system according to the embodiment of the present invention.

[0024] Fig. 13B This is a diagram showing another example of the likelihood threshold used in the automatic driving system according to the embodiment of the present invention.

[0025] Fig. 13C This is a diagram showing another example of the likelihood threshold used in the automatic driving system according to the embodiment of the present invention.

[0026] Fig.14 This is a diagram showing an example of a monitoring mode setting screen displayed on the operation terminal according to the embodiment of the present invention.

[0027] Fig.15 This is a diagram showing an example of a work mode setting screen displayed on the operation terminal according to the embodiment of the present invention.

[0028] Fig.16 This is a diagram showing an example of a work mode setting screen displayed on the operation terminal according to the embodiment of the present invention.

[0029] Description of reference numerals:

[0030] 1…Automatic driving system; 10…Work vehicle; 11…Vehicle control device; 14…Work machine; 15…Obstacle detection device; 20…Operation terminal; 51…Detection control unit; 52…Storage unit; 53…Camera (shooting unit); 54…Obstacle sensor (detection unit); 111…Driving processing unit; 112…Response processing unit; 211…Setting processing unit; 212…Output processing unit; 511…Acquisition processing unit; 512…Judgment processing unit; 513…Output processing unit; F…Field; R…Target path; Ra…Stop control range; Rb…Deceleration control range; Rc…Report control range; Rd1…First detection range; Rd2…Second detection range; Rm1…First measurement range; Rm2…Second measurement range; Th1…Likelihood threshold (threshold); Th2…Likelihood threshold (threshold); Th3…Likelihood threshold (threshold). DETAILED DESCRIPTION

[0031] The following embodiment is an example of embodying the present invention and does not limit the technical scope of the present invention.

[0032] like Figure 1 As shown, the automatic driving system 1 according to the embodiment of the present invention includes a work vehicle 10 and an operation terminal 20. The work vehicle 10 and the operation terminal 20 can communicate via a communication network N1. For example, the work vehicle 10 and the operation terminal 20 can communicate via a mobile phone line network, a packet line network, or a wireless LAN.

[0033] In this embodiment, the working vehicle 10 is described by taking a tractor as an example. In addition, as another embodiment, the working vehicle 10 may also be a combine harvester, a rice transplanter, a construction machine, or a snowplow. The working vehicle 10 is a machine capable of Figure 3 ) according to a preset target path R. For example, the work vehicle 10 can automatically travel along the pre-generated target path R based on the position information of the current position of the work vehicle 10 calculated by the positioning unit 17.

[0034] For example, the work vehicle 10 Figure 3 In the working area of ​​the field F shown in FIG. 1 , the working vehicle 10 travels back and forth in parallel from the travel start position S to the travel end position G. The outer peripheral side of the field F is, for example, the field head area, and the working vehicle 10 turns in the field head area. The target path R is not limited to Figure 3 The paths shown can be appropriately set according to the content of the work.

[0035] The operation terminal 20 is a mobile terminal capable of remotely operating the work vehicle 10, and is composed of, for example, a tablet terminal, a notebook personal computer, a smart phone, etc. The staff (operator) can perform setting operations on various setting items in the operation terminal 20. In addition, the operation terminal 20 displays information such as the working status and driving status of the work vehicle 10 in automatic driving. The staff can grasp the working status and driving status in the operation terminal 20.

[0036] [Work vehicle 10]

[0037] like Figure 1 and Figure 2 As shown, the work vehicle 10 includes a vehicle control device 11, a storage unit 12, a travel device 13, a work machine 14, an obstacle detection device 15, a communication unit 16, a positioning unit 17, etc. The vehicle control device 11 is electrically connected to the storage unit 12, the travel device 13, the work machine 14, the obstacle detection device 15, and the positioning unit 17. In addition, the vehicle control device 11 and the obstacle detection device 15 may be configured to be able to communicate wirelessly, and the vehicle control device 11 and the positioning unit 17 may be configured to be able to communicate wirelessly.

[0038] The communication unit 16 is a communication interface for connecting the work vehicle 10 to the communication network N1 by wire or wirelessly and performing data communication with external devices (such as the operation terminal 20 ) via the communication network N1 in accordance with a predetermined communication protocol.

[0039] The storage unit 12 is a non-volatile storage unit such as a HDD (Hard Disk Drive) or an SSD (Solid State Drive) that stores various information. The storage unit 12 stores information for causing the vehicle control device 11 to execute the automatic driving process described later (see Fig.12 ) and other control programs such as an automatic driving program. For example, the automatic driving program is recorded non-temporarily on a computer-readable recording medium such as a CD or a DVD, read by a predetermined reading device (not shown) and stored in the storage unit 12. In addition, the automatic driving program can also be downloaded from a server (not shown) to the work vehicle 10 via the communication network N1 and stored in the storage unit 12. In addition, the storage unit 12 stores data on the target path R generated in the operation terminal 20, etc.

[0040] The travel device 13 is a driving unit that drives the work vehicle 10. Figure 2As shown, the travel device 13 includes an engine 131, front wheels 132, rear wheels 133, a transmission 134, a front axle 135, a rear axle 136, a steering wheel 137, etc. In addition, the front wheels 132 and the rear wheels 133 are respectively provided on the left and right sides of the work vehicle 10. In addition, the travel device 13 is not limited to a wheel type including the front wheels 132 and the rear wheels 133, and may also be a crawler type including crawlers provided on the left and right sides of the work vehicle 10.

[0041] The engine 131 is a driving source such as a diesel engine or a gasoline engine that is driven by fuel supplied to a fuel tank not shown. The travel device 13 may also be equipped with an electric motor as a driving source in addition to the engine 131 or instead of the engine 131. In addition, a generator not shown is connected to the engine 131, and power is supplied from the generator to electrical components such as the vehicle control device 11, the obstacle detection device 15, and the positioning unit 17 provided in the work vehicle 10, as well as batteries and the like. In addition, the above-mentioned battery is charged by the power supplied from the above-mentioned generator. Moreover, the electrical components such as the vehicle control device 11, the obstacle detection device 15, and the positioning unit 17 provided in the work vehicle 10 can still be driven by the power supplied from the above-mentioned battery after the engine 131 stops.

[0042] The driving force of the engine 131 is transmitted to the front wheel 132 via the transmission 134 and the front axle 135, and is transmitted to the rear wheel 133 via the transmission 134 and the rear axle 136. In addition, the driving force of the engine 131 is also transmitted to the work machine 14 via the PTO shaft (not shown). When the work vehicle 10 is automatically driven, the travel device 13 performs a driving action according to the command of the vehicle control device 11. In addition, the travel device 13 causes the work vehicle 10 to decelerate or stop according to the command of the vehicle control device 11.

[0043] The work machine 14 is, for example, a tiller, a lawn mower, a plow, a fertilizer spreader, a sprayer (agent spreader), a scraper, or a seed drill, and can be loaded and unloaded from the work vehicle 10. Thus, the work vehicle 10 can use each work machine 14 to perform various operations. Figure 2 , the working machine 14 is a tiller. For example, the working machine 14 is mounted on the rear of the working vehicle 10. The working vehicle 10 performs tillage work by mounting the working machine 14 on the rear and traveling in the field F.

[0044] The steering wheel 137 is an operating unit operated by a worker or the vehicle control device 11. For example, in the travel device 13, according to the operation of the steering wheel 137 by the vehicle control device 11, the angle of the front wheel 132 is changed by a hydraulic power steering mechanism (not shown), thereby changing the traveling direction of the work vehicle 10.

[0045] In addition to the steering wheel 137, the travel device 13 is also provided with a shift lever, an accelerator, a brake, etc. (not shown) which are operated by the vehicle control device 11. In the travel device 13, according to the operation of the shift lever by the vehicle control device 11, the gear of the transmission 134 is switched to a forward gear or a reverse gear, etc., so that the travel mode of the work vehicle 10 is switched to forward or reverse, etc. In addition, the vehicle control device 11 operates the accelerator to control the rotation speed of the engine 131. In addition, the vehicle control device 11 operates the brake to brake the rotation of the front wheel 132 and the rear wheel 133 using an electromagnetic brake.

[0046] The positioning unit 17 is a communication device including a positioning control unit 171, a storage unit 172, a communication unit 173, and a positioning antenna 174. Figure 2 As shown, the positioning unit 17 is arranged on the upper part of the cabin 138 where the staff is riding. In addition, the installation place of the positioning unit 17 is not limited to the cabin 138. In addition, the positioning control unit 171, the storage unit 172, the communication unit 173 and the positioning antenna 174 of the positioning unit 17 can also be dispersed and arranged at different positions in the work vehicle 10. In addition, as described above, the positioning unit 17 is connected to the above-mentioned battery, and the positioning unit 17 can also operate when the engine 131 is stopped. In addition, as the positioning unit 17, for example, a mobile phone terminal, a smart phone or a tablet terminal, a quantum compass, etc. can also be used instead.

[0047] The positioning control unit 171 is a computer system having one or more processors, and storage memories such as non-volatile memory and RAM. The storage unit 172 is a non-volatile memory that stores a program for causing the positioning control unit 171 to perform positioning processing, as well as data such as positioning information and movement information. For example, the above-mentioned program is non-temporarily recorded on a computer-readable recording medium such as a CD or DVD, read by a predetermined reading device (not shown) and stored in the storage unit 172. In addition, the above-mentioned program can also be downloaded from a server (not shown) to the positioning unit 17 via the communication network N1 and stored in the storage unit 172.

[0048] The communication unit 173 is a communication interface for connecting the positioning unit 17 to the communication network N1 in a wired or wireless manner and performing data communication with an external device such as a base station server via the communication network N1 in accordance with a predetermined communication protocol.

[0049] The positioning antenna 174 is an antenna that receives radio waves (GNSS signals) transmitted from satellites.

[0050] The positioning control unit 171 calculates the current position of the work vehicle 10 based on the GNSS signal received from the satellite by the positioning antenna 174. For example, when the work vehicle 10 is automatically traveling in the field F, if the positioning antenna 174 receives radio waves (transmission time, orbit information, etc.) respectively transmitted from a plurality of satellites, the positioning control unit 171 calculates the distance between the positioning antenna 174 and each satellite, and calculates the current position (latitude and longitude) of the work vehicle 10 based on the calculated distance. In addition, the positioning control unit 171 may also perform positioning based on the real-time kinematic method (RTK-GNSS positioning method (RTK method)) in which the current position of the work vehicle 10 is calculated using correction information corresponding to a base station (reference station) close to the work vehicle 10. In this way, the work vehicle 10 automatically travels using the positioning information based on the RTK method. In addition, the current position of the work vehicle 10 may be the same position as the positioning position (e.g., the position of the positioning antenna 174) or may be a position deviated from the positioning position.

[0051] When the work vehicle 10 detects a detection object during automatic driving, the obstacle detection device 15 determines the type of the detection object (human, vehicle, other (structure, material, etc.)), and outputs the determination result to the vehicle control device 11. Specifically, the obstacle detection device 15 includes a detection control unit 51, a storage unit 52, a camera 53, an obstacle sensor 54, a communication unit 55, etc. The obstacle detection device 15 may be composed of a single unit and mounted on the work vehicle 10, or a plurality of components may be dispersedly arranged on the work vehicle 10.

[0052] The communication unit 55 is a communication interface for connecting the obstacle detection device 15 to the communication network N1 in a wired or wireless manner and performing data communication with external equipment (such as the operation terminal 20 ) via the communication network N1 in accordance with a predetermined communication protocol.

[0053] The storage unit 52 is a non-volatile storage unit such as a HDD or SSD that stores various information. The storage unit 52 stores a control program such as an obstacle detection program for causing the obstacle detection device 15 to perform obstacle detection processing. For example, the obstacle detection program is non-temporarily recorded on a computer-readable recording medium such as a CD or a DVD, read by a predetermined reading device (not shown), and stored in the storage unit 52. In addition, the obstacle detection program can also be downloaded from a server (not shown) to the obstacle detection device 15 via the communication network N1 and stored in the storage unit 52.

[0054] The camera 53 is a digital camera that captures an image of a subject within a predetermined capturing range and outputs the image as digital image data. The camera 53 continuously captures the subject at a predetermined frame rate, generates frame images (captured images) of a predetermined resolution, and sequentially transmits the frame images to the detection control unit 51. The camera 53 transmits the image data of the captured images to the operation terminal 20 via the communication unit 55. The operation terminal 20 can display the captured images on the operation screen of the operation display unit 23 (see FIG. 21 ). Figure 8 ).

[0055] The camera 53 includes a front camera 53f capable of capturing a front capturing range as viewed from the work vehicle 10, and a rear camera 53r capable of capturing a rear capturing range as viewed from the work vehicle 10. Figure 2 As shown, the front camera 53f is arranged on the upper front side of the cabin 138, and the rear camera 53r is arranged on the upper rear side of the cabin 138.

[0056] The obstacle sensor 54 is a sensor that detects a detection object within a specified detection range using infrared rays, ultrasonic waves, or the like. For example, the obstacle sensor 54 may be a laser radar sensor (distance sensor) that can use lasers to measure the distance to the detection object in three dimensions, or may be a sonar sensor having multiple sonars that can use ultrasonic waves to measure the distance to the detection object. The obstacle sensor 54 is disposed at the central front portion, central rear portion, right portion, left portion, etc. of the body of the work vehicle 10 to monitor the surroundings of the work vehicle 10 and detect obstacles. In the present embodiment, the obstacle sensor 54 includes a front obstacle sensor 54f that can detect a detection object within a detection range in front of the work vehicle 10, and a rear obstacle sensor 54r that can detect a detection object within a detection range behind the work vehicle 10. As shown in FIG. Figure 2 As shown, the front obstacle sensor 54f is arranged at the upper front side of the cabin 138, and the rear obstacle sensor 54r is arranged at the upper rear side of the cabin 138. Alternatively, the front camera 53f and the front obstacle sensor 54f may be composed of one unit, and the rear camera 53r and the rear obstacle sensor 54r may be composed of one unit. In addition, the respective arrangement positions and numbers of the camera 53 and the obstacle sensor 54 are not limited and may be determined according to the application.

[0057] exist Figure 4 , an example of the measurement range (detection range) of each of the front obstacle sensor 54f and the rear obstacle sensor 54r is shown. In addition, hereinafter, the front obstacle sensor 54f and the rear obstacle sensor 54r are collectively referred to as "obstacle sensor 54".

[0058] The obstacle sensor 54 measures the distance to each distance measurement point (measurement object) existing in the measurement range using, for example, laser (near infrared laser, etc.), and generates a distance image based on the measurement information. The obstacle sensor 54 includes an electronic control unit incorporating a microcontroller, etc., and a processing unit constructed by various control programs, etc., and is connected to the detection control unit 51, the vehicle control device 11, etc. via CAN so as to be able to communicate with each other.

[0059] like Figure 2 and Figure 4 As shown, for the front obstacle sensor 54f, a first measurement range Rm1 in front of the cabin 138 is set as the measurement range, and for the rear obstacle sensor 54r, a second measurement range Rm2 in the rear of the cabin 138 is set as the measurement range.

[0060] like Figure 4 As shown, the front obstacle sensor 54f and the rear obstacle sensor 54r are arranged on the left-right center line of the work vehicle 10, similarly to the front camera 53f and the rear camera 53r. The front obstacle sensor 54f is arranged at the left-right center position of the upper part of the front end side of the cabin 138 in a posture with a low front and a high rear when looking down at the front side of the work vehicle 10 from the upper side. Thus, the prescribed range of the front obstacle sensor 54f on the front side of the vehicle body with the left-right center line of the work vehicle 10 as the axis of symmetry is set as the first measurement range Rm1. The rear obstacle sensor 54r is arranged at the left-right center position of the upper part of the rear end side of the cabin 138 in a posture with a high front and a low rear when looking down at the rear side of the work vehicle 10 from the upper side. Thus, the prescribed range of the rear obstacle sensor 54r on the rear side of the vehicle body with the left-right center line of the work vehicle 10 as the axis of symmetry is set as the second measurement range Rm2.

[0061] The front obstacle sensor 54f and the rear obstacle sensor 54r measure the distance from each sensor 54f, 54r to each distance measuring point of the first measurement range Rm1 or the second measurement range Rm2 by a TOF (Time Of Flight) method, wherein the TOF method measures the distance to the distance measuring point based on the round trip time until the irradiated laser reaches the distance measuring point and returns. The front obstacle sensor 54f and the rear obstacle sensor 54r scan the laser vertically and horizontally at high speed over the entire first measurement range Rm1 or the second measurement range Rm2, and sequentially measure the distance to the distance measuring point at each scanning angle (coordinate), thereby performing three-dimensional measurement in the first measurement range Rm1 or the second measurement range Rm2. The front obstacle sensor 54f and the rear obstacle sensor 54r sequentially measure the intensity (reflection intensity) of the reflected light from each distance measuring point obtained when the laser is scanned vertically and horizontally at high speed over the entire first measurement range Rm1 or the second measurement range Rm2. The front obstacle sensor 54f and the rear obstacle sensor 54r repeatedly measure the distance to each distance measurement point, each reflection intensity, and the like in the first measurement range Rm1 or the second measurement range Rm2 in real time.

[0062] The front obstacle sensor 54f and the rear obstacle sensor 54r generate a distance image based on the measured distance to each ranging point, the scanning angle (coordinates) for each ranging point, and other measurement information, and extract the ranging point group inferred to be an obstacle, and send the measurement information related to the extracted ranging point group to the detection control unit 51 as measurement information related to the obstacle.

[0063] In addition, the front obstacle sensor 54f and the rear obstacle sensor 54r perform a cutting process and a masking process on the first measurement range Rm1 or the second measurement range Rm2 based on the vehicle body information, etc., so that the detection range of the front obstacle sensor 54f and the rear obstacle sensor 54r for detecting obstacles is limited to the first detection range Rd1 set on the forward side of the work vehicle 10 and the second detection range Rd2 set on the backward side of the work vehicle 10 (see Figure 4 ).

[0064] The front obstacle sensor 54f and the rear obstacle sensor 54r obtain the maximum left and right width of the vehicle body including the working machine 14 (the left and right width of the tiller in this embodiment) by communicating with the vehicle control device 11 during the cutting process, and add a predetermined safety zone to the maximum left and right width of the vehicle body, thereby setting the detection target width W1 of the obstacle. Then, the left and right ranges deviating from the detection target width W1 in the first measurement range Rm1 and the second measurement range Rm2 are set as the first non-detection range Rn based on the cutting process and are removed from each detection range Rd1, Rd2.

[0065] During the masking process, the front obstacle sensor 54f and the rear obstacle sensor 54r set the range obtained by adding the specified safety zone to the range where the front end side of the work vehicle 10 enters the first measurement range Rm1 and the range where the rear end side of the work machine 14 enters the second measurement range Rm2 as the second non-detection range Rs based on the masking process and remove it from each detection range Rd1, Rd2.

[0066] By limiting the obstacle detection range to the first detection range Rd1 and the second detection range Rd2, the increase in detection load caused by the front obstacle sensor 54f and the rear obstacle sensor 54r detecting obstacles that deviate from the detection object width W1 and have no possibility of colliding with the work vehicle 10 is avoided, and the possibility of misdetecting the front end side of the work vehicle 10 and the rear end side of the work machine 14 that enter the first measurement range Rm1 or the second measurement range Rm2 as obstacles is avoided.

[0067] The information on the first detection range Rd1 , the second detection range Rd2 , the first non-detection range Rn, and the second non-detection range Rs is included in the distance image, and is sent to the detection control unit 51 together with the distance image.

[0068] like Figure 4 As shown, the detection ranges Rd1 and Rd2 of the front obstacle sensor 54f and the rear obstacle sensor 54r are divided into a stop control range Ra, a deceleration control range Rb, and a report control range Rc based on the collision determination process in which the collision prediction time becomes a set time (for example, 3 seconds). Specifically, the stop control range Ra is set to the range from the front obstacle sensor 54f or the rear obstacle sensor 54r to the determination reference position of the collision determination process. The deceleration control range Rb is set to the range from the determination reference position to the deceleration start position. The report control range Rc is set to the range from the deceleration start position to the measurement limit position of the front obstacle sensor 54f or the rear obstacle sensor 54r. The above-mentioned determination reference position is set to a position that is a certain distance L1 (for example, 2m) away from the front end or rear end of the vehicle body including the work machine 14 in the front-rear direction of the vehicle body. In this embodiment, the range of distance L1 from the work vehicle 10 is set as the stop control range Ra, the range from distance L1 to distance L2 (for example, less than 10m) is set as the deceleration control range Rb, and the range from distance L2 to distance L3 (for example, less than 20m) is set as the reporting control range Rc.

[0069] In addition, each control range Ra, Rb, and Rc in the first detection range Rd1 of the front obstacle sensor 54f and the second detection range Rd2 of the rear obstacle sensor 54r can be set according to the type, model, work content, vehicle speed, etc. of the work vehicle 10. In addition, the first measurement range Rm1 of the front obstacle sensor 54f and the second measurement range Rm2 of the rear obstacle sensor 54r may not be cut.

[0070] The detection control unit 51 determines the type of the detection object (measurement object) based on the captured image obtained from the camera 53 and the measurement information obtained from the obstacle sensor 54, and outputs the determination result to the vehicle control device 11. In addition, the detection control unit 51 may also determine the type of the detection object (measurement object) based on the captured image obtained from the camera 53. Hereinafter, the case where the detection object in front is detected when the work vehicle 10 is traveling forward is described as an example, and the case where the detection object in the rear is detected when the work vehicle 10 is traveling backward is omitted.

[0071] The detection control unit 51 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various calculations. The ROM is a non-volatile storage unit that pre-stores control programs such as BIOS and OS for the CPU to perform various calculations. The RAM is a volatile or non-volatile storage unit that stores various information and is used as a temporary storage memory (operating area) for various processes performed by the CPU. In addition, the detection control unit 51 controls the obstacle detection device 15 by executing various control programs pre-stored in the ROM or the storage unit 52 by the CPU.

[0072] Specifically, if Figure 1 As shown in FIG. 1 , the detection control unit 51 includes various processing units such as an acquisition processing unit 511, a determination processing unit 512, and an output processing unit 513. In addition, the obstacle detection device 15 functions as the various processing units by executing various processes according to the obstacle detection program by the CPU. In addition, a part or all of the processing units may be composed of electronic circuits. In addition, the obstacle detection program may be a program for causing a plurality of processors to function as the processing units.

[0073] The acquisition processing unit 511 acquires the captured images from the camera 53 and acquires the measurement information from the obstacle sensor 54. Specifically, when the work vehicle 10 starts to travel automatically, the acquisition processing unit 511 sequentially acquires the captured images of the captured range in the front direction of travel from the front camera 53f during the automatic travel. The acquisition processing unit 511 stores the acquired captured images in the storage unit 52. In addition, when the work vehicle 10 starts to travel automatically, the acquisition processing unit 511 sequentially acquires the first detection range Rd1 (refer to the first detection range Rd2) in the front direction of travel from the front obstacle sensor 54f during the automatic travel. Figure 4 The acquisition processing unit 511 stores the acquired measurement information in the storage unit 52.

[0074] The determination processing unit 512 determines the type of the detection object based on the captured image and the measurement information obtained by the acquisition processing unit 511. Specifically, the determination processing unit 512 performs image analysis on the captured image to determine the type of the detection object (person, vehicle, structure, material, work object (harvesting object, harvesting object, etc.)). The determination processing unit 512 can also use a known inference model (learned model) to infer the type of the detection object.

[0075] In addition, the determination processing unit 512 calculates the likelihood (certainty) of the determination result when determining the type of the detection object. Specifically, the determination processing unit 512 calculates the likelihood (probability) based on the distance information included in the above-mentioned measurement information, that is, the distance from the work vehicle 10 (here, the front end of the work vehicle 10) to the detection object. The determination processing unit 512 calculates the likelihood in such a way that the shorter the distance, the higher the likelihood.

[0076] For example, when the determination processing unit 512 determines that the detection object is a person based on the captured image, if the distance to the detection object is longer than the specified distance, the likelihood of the person is calculated as "50%", and when the distance to the detection object is closer than the specified distance, the likelihood of the person is calculated as "90%". Similarly, when the determination processing unit 512 determines that the detection object is a vehicle based on the captured image, the likelihood of the vehicle is calculated based on the distance to the detection object.

[0077] In addition, the determination processing unit 512 may also calculate the likelihood based on the above-mentioned distance information and the above-mentioned captured image. For example, in a case where the above-mentioned captured image contains only a part of the detection object and is in a state where it is difficult to grasp the entire detection object, the determination processing unit 512 calculates the likelihood of the detection object to be lower than the case where the above-mentioned captured image contains the entire detection object. Therefore, for example, the determination processing unit 512 determines that the detection object is a person based on the above-mentioned captured image, and when the distance to the detection object is closer than the specified distance, when a part of the person is not captured in the captured image, the determination processing unit 512 calculates the likelihood as a likelihood (for example, "70%) lower than the likelihood ("90%) when the entire person is captured in the captured image. In this way, the determination processing unit 512 may also adjust the likelihood according to the shooting state of the detection object contained in the above-mentioned captured image.

[0078] In addition, the determination processing unit 512 may also calculate the likelihood based only on the above-mentioned captured image. For example, the larger the size of the detection object reflected in the above-mentioned captured image, the easier it is to determine the type of the detection object, and the smaller the size of the detection object reflected in the above-mentioned captured image, the more difficult it is to determine the type of the detection object. Therefore, in the case where the size of the detection object reflected in the above-mentioned captured image is large, the determination processing unit 512 calculates the likelihood of the detection object to be high, and in the case where the size of the detection object reflected in the above-mentioned captured image is small, the determination processing unit 512 calculates the likelihood of the detection object to be low. For example, the determination processing unit 512 determines that the detection object is a person based on the above-mentioned captured image, and in the case where the reflection of the detection object is large, the likelihood is calculated as "90%", and in the case where the reflection of the detection object is small, the likelihood is calculated as "70%". In this way, the determination processing unit 512 may also calculate the likelihood based on the size (occupied area, etc.) of the detection object contained in the above-mentioned captured image.

[0079] The output processing unit 513 outputs the determination result of the determination processing unit 512 to the vehicle control device 11. Specifically, the output processing unit 513 outputs the determination result (type of detection object), the likelihood of the determination result corresponding to the distance to the detection object, and the likelihood threshold value corresponding to the distance to the detection object (see Figure 5 ) is output to the vehicle control device 11.

[0080] The likelihood threshold is a setting parameter for determining whether to make the work vehicle 10 execute a prescribed response process (e.g., stop process, deceleration process, reporting process, etc.), and is a threshold value for the calculated likelihood. For example, when the calculated likelihood exceeds the likelihood threshold, the work vehicle 10 is made to execute the response process.

[0081] Here, the shorter the distance to the detection object, the smaller the likelihood threshold is set. Figure 5 As shown, when the distance from the work vehicle 10 to the detection object is less than L1 (for example, 2m), the detection control unit 51 sets the likelihood threshold to Th1 (for example, 50%), and when the distance from the work vehicle 10 to the detection object is greater than L2 (where L1 < L2), the likelihood threshold is set to Th2 (for example, 90%) (where Th1 < Th2). In addition, when the distance from the work vehicle 10 to the detection object is greater than L1 and less than L2, the detection control unit 51 sets the likelihood threshold corresponding to the distance to between Th1 and Th2.

[0082] In addition, the likelihood threshold is set to different values ​​depending on the content of the response process. Figure 5 As shown, the detection control unit 51 sets different likelihood thresholds for the stop control range Ra for executing the stop process, the deceleration control range Rb for executing the deceleration process, and the report control range Rc for executing the report process. Specifically, in the stop control range Ra close to the working vehicle 10, since there is no margin until the detection object is approached or in contact, the detection control unit 51 sets the likelihood threshold to be low even for the detection object with low likelihood, so that the response process can be easily performed. On the other hand, in the report control range Rc far from the working vehicle 10, since there is a margin until the detection object is approached or in contact, the detection control unit 51 sets the likelihood threshold to be high, so that only the detection object with high likelihood is selected to perform the response process. In addition, in the deceleration control range Rb, the closer the distance to the working vehicle 10, the lower the likelihood threshold is set by the detection control unit 51, so that the closer the distance to the detection object, the easier it is to perform the response process.

[0083] The detection control unit 51 pre-sets a likelihood threshold value corresponding to the distance from the work vehicle 10 to the detection target (see Figure 5 ) information and stores it in the storage unit 52.

[0084] The output processing unit 513 refers to Figure 5 The likelihood threshold value setting information of the detection object is obtained, and the likelihood threshold value corresponding to the distance from the work vehicle 10 to the detection object is obtained. For example, when the determination processing unit 512 determines that the detection object at the position of the distance Lx from the work vehicle 10 is a person and calculates the likelihood of the person as X1%, the output processing unit 513 outputs the determination result including the type of the detection object "person", the likelihood "X1%", and the likelihood threshold value "Thx" corresponding to the distance Lx to the vehicle control device 11.

[0085] Thus, the detection control unit 51 determines the type of the detection target (measurement target) each time it acquires a captured image from the camera 53 and obtains measurement information from the obstacle sensor 54 during the automatic driving of the work vehicle 10 , and sequentially outputs the determination results to the vehicle control device 11 .

[0086] Upon acquiring the above-described determination result output from the obstacle detection device 15 (detection control unit 51 ), the vehicle control device 11 causes the work vehicle 10 to execute a countermeasure process corresponding to the above-described determination result.

[0087] The vehicle control device 11 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various calculations. The ROM is a non-volatile storage unit that pre-stores control programs such as BIOS and OS for the CPU to perform various calculations. The RAM is a volatile or non-volatile storage unit that stores various information and is used as a temporary storage memory for various processes performed by the CPU. In addition, the vehicle control device 11 controls the work vehicle 10 by executing various control programs pre-stored in the ROM or the storage unit 12 by the CPU.

[0088] Specifically, if Figure 1 As shown, the vehicle control device 11 includes various processing units such as a driving processing unit 111 and a response processing unit 112. In addition, the vehicle control device 11 functions as the various processing units by executing various processing according to the automatic driving program by the CPU. In addition, a part or all of the processing units may also be composed of electronic circuits. In addition, the automatic driving program may also be a program for making a plurality of processors function as the processing units. In addition, the automatic driving program includes the vehicle control program of the present invention.

[0089] The travel processing unit 111 controls the travel of the work vehicle 10. For example, when the travel mode of the work vehicle 10 is automatic travel (automatic travel mode), the travel processing unit 111 causes the work vehicle 10 to travel automatically based on the position information (positioning information) indicating the current position of the work vehicle 10 located by the positioning unit 17. For example, if the work vehicle 10 meets the start conditions for automatic travel and obtains a travel start instruction from the staff, the travel processing unit 111 causes the work vehicle 10 to start automatic travel based on the above positioning information. In addition, the travel processing unit 111 causes the work vehicle 10 to travel according to the target path R (refer to the target path R) pre-generated and set in the operation terminal 20. Figure 3 ) automatically travels from the driving starting position S to the driving ending position G.

[0090] In addition, when the driving mode of the work vehicle 10 is manual driving (manual driving mode), the work vehicle 10 can be driven manually based on the operation of the operator (manual steering operation). For example, the driving processing unit 111 obtains operation information corresponding to the operation operation such as steering wheel operation, gear shift operation, driving direction switching operation, brake operation, etc. performed by the operator, and causes the driving device 13 to perform the driving action based on the operation information.

[0091] When the work vehicle 10 detects an obstacle during automatic driving, the response processing unit 112 causes the work vehicle 10 to execute a predetermined response process. Specifically, the response processing unit 112 causes the work vehicle 10 to execute a response process corresponding to the type of the detection object detected by the obstacle detection device 15. In addition, the response processing unit 112 causes the work vehicle 10 to execute a response process corresponding to the type of the detection object detected by the obstacle detection device 15 and the distance to the detection object detected by the obstacle detection device 15.

[0092] For example, when the work vehicle 10 detects a detection object during automatic driving, the obstacle detection device 15 outputs a message including the type of the detection object, the likelihood of the type, and a likelihood threshold value corresponding to the distance to the detection object (see Figure 5 ), the response processing unit 112 obtains the above-mentioned determination result. The response processing unit 112 determines whether it is necessary to make the work vehicle 10 perform the response processing based on the above-mentioned determination result. If it is determined that the work vehicle 10 needs to perform the response processing, the response processing unit 112 makes the work vehicle 10 perform the response processing. In addition, the response processing unit 112 makes the work vehicle 10 perform the response processing based on the likelihood calculated by the obstacle detection device 15. A specific example of the response processing is described below.

[0093] For example, Figure 6 As shown, the obstacle detection device 15 detects the detection object at the position P1 which is away from the work vehicle 10 by a distance Lc (where L2<Lc<L3), and determines that the detection object is a "person". When the likelihood of the person is calculated as "A1"%, when the likelihood "A1"% exceeds the likelihood threshold Th2 corresponding to the distance Lc, the processing unit 112 determines that the person is within the report control range Rc (refer to Figure 4) detects an obstacle within the working vehicle 10, thereby causing the working vehicle 10 to perform a reporting process. For example, the response processing unit 112 causes a warning sound to be reported from the working vehicle 10. As another embodiment, the response processing unit 112 may also cause a warning sound to be reported from the working vehicle 10 and cause the operation terminal 20 to display a warning message. In addition, the response processing unit 112 may also change the warning sound (increasing the volume, shortening the reporting cycle, etc.) as the distance Lc becomes smaller (the working vehicle 10 approaches the obstacle). In this way, it is possible to alert the person in front of the working vehicle 10 at an early stage. Therefore, for example, by having a person move, it is possible to avoid interruption of the working vehicle 10's operation, thereby allowing it to continue working.

[0094] In addition, when the likelihood "A1"% is less than the likelihood threshold Th2, the response processing unit 112 does not perform the report processing. As a result, it is possible to suppress excessive report processing. In this way, in the report control range Rc, when the distance from the work vehicle 10 to the detection object is long, there is a margin until the detection object is approached or contacted. In this case, since only obstacles that become the object of the response processing can be reliably determined, it is possible to suppress excessive report processing by setting the likelihood threshold high.

[0095] In addition, for example, Figure 6 As shown, the obstacle detection device 15 detects the detection object at the position P2 which is a distance Lb (where L1<Lb<L2) away from the work vehicle 10, and determines that the detection object is a "person". When the likelihood of the person is calculated as "A2"%, when the likelihood "A2"% exceeds the likelihood threshold Th3 corresponding to the distance Lb, the processing unit 112 determines that the person is within the deceleration control range Rb (refer to Figure 4 ) and the working vehicle 10 performs a deceleration process. For example, the response processing unit 112 decelerates the working vehicle 10 in automatic driving from a preset vehicle speed. As another embodiment, the response processing unit 112 may also perform both the deceleration process and the reporting process. In addition, the response processing unit 112 may also output a warning sound corresponding to the vehicle speed (the faster the vehicle speed, the louder the volume, etc.). In this way, the safety of the person in front of the working vehicle 10 can be ensured.

[0096] In addition, when the likelihood "A2"% is less than the likelihood threshold, the response processing unit 112 does not perform the deceleration process. In this way, in the deceleration control range Rb, the likelihood threshold is changed according to the distance. Therefore, when the distance from the work vehicle 10 is far, since there is a margin until the detection object is approached or contacted, by setting the likelihood threshold high, it is possible to suppress excessive deceleration processing. When the distance from the work vehicle 10 is close, since there is no margin until the detection object is approached or contacted, by setting the likelihood threshold low, it is possible to easily perform the deceleration process to ensure safety.

[0097] In addition, for example, Figure 6 As shown, the obstacle detection device 15 detects the detection object at the position P3 which is away from the work vehicle 10 by a distance La (where 0<La<L1), and determines that the detection object is a "person". When the likelihood of the person is calculated as "A3"%, when the likelihood "A3"% exceeds the likelihood threshold Th1 corresponding to the distance La, the processing unit 112 determines that the person is within the stop control range Ra (refer to Figure 4 ) detects an obstacle, thereby causing the work vehicle 10 to execute a stop process. For example, the response processing unit 112 temporarily stops the work vehicle 10 that is traveling automatically. As another embodiment, the response processing unit 112 may also execute both the stop process and the report process. In this way, the safety of the person in front of the work vehicle 10 can be ensured.

[0098] In addition, when the likelihood "A3"% is less than the likelihood threshold, the response processing unit 112 does not execute the stop processing. In this way, in the stop control range Ra, when the distance to the work vehicle 10 is short, there is no margin until the detection object is close or in contact, so by setting the likelihood threshold low, it is possible to ensure safety by executing the stop processing even for the detection object with a low possibility of being an obstacle.

[0099] As described above, when the likelihood of a detection target detected during the automatic driving of the work vehicle 10 exceeds the likelihood threshold value corresponding to the distance to the detection target, the response processing unit 112 causes the work vehicle 10 to execute response processing.

[0100] Here, when the detection object is a detection object that does not require the work vehicle 10 to perform a response process, the response processing unit 112 omits the response process. For example, when the detection object is a work object (harvesting object, harvesting object, etc.) of the work vehicle 10, since it is not necessary for the work vehicle 10 to perform a response process, the response processing unit 112 omits the response process. In addition, the obstacle detection device 15 can also be configured to: when it is determined that the detection object is a detection object that does not require the work vehicle 10 to perform a response process, the determination result is not output to the vehicle control device 11. The obstacle detection device 15 can determine whether the detection object is a detection object that requires the work vehicle 10 to perform a response process based on the above-mentioned captured image. In addition, the obstacle detection device 15 can also be configured to: determine whether the calculated likelihood exceeds the likelihood threshold, and when the likelihood exceeds the likelihood threshold, output the determination result to the vehicle control device 11, and when the likelihood is below the likelihood threshold, do not output the determination result to the vehicle control device 11.

[0101] In addition, the response processing may also include avoidance driving (avoidance processing) in which the work vehicle 10 avoids obstacles. For example, when the detection object is still detected even after the report processing and the deceleration processing are performed, or when the likelihood exceeds the likelihood threshold, when the distance from the work vehicle 10 to the detection object becomes less than the specified distance, the response processing unit 112 generates an avoidance path for avoiding the detection object, so that the work vehicle 10 travels on the avoidance path. In addition, the response processing unit 112 may also decide whether to perform a stop process or an avoidance process according to the type of the detection object. For example, when the detection object is a moving object (a person, a vehicle, etc.), the response processing unit 112 performs a stop process, and when the detection object is a fixed object, the response processing unit 112 performs an avoidance process.

[0102] In the above embodiment, the obstacle detection device 15 is a separate device from the vehicle control device 11 , but in another embodiment, the obstacle detection device 15 and the vehicle control device 11 may be an integrated device. In addition, the detection control unit 51 may be included in the vehicle control device 11 .

[0103] [Operation terminal 20]

[0104] like Figure 1 As shown, the operation terminal 20 is an information processing device including an operation control unit 21, a storage unit 22, an operation display unit 23, a communication unit 24, etc. The operation terminal 20 may be constituted by a mobile terminal such as a tablet terminal or a smartphone.

[0105] The communication unit 24 is a communication interface for connecting the operation terminal 20 to the communication network N1 by wire or wirelessly and performing data communication with one or more external devices such as the work vehicles 10 via the communication network N1 in accordance with a predetermined communication protocol.

[0106] The operation display unit 23 is a user interface having a display unit such as a liquid crystal display or an organic EL display for displaying various information, and an operation unit such as a touch panel, a mouse or a keyboard for accepting operations. The staff can operate the above-mentioned operation unit in the operation screen displayed on the above-mentioned display unit to perform operations to register various information (the work vehicle information, field information, work information, etc. described later). In addition, the staff can operate the above-mentioned operation unit to issue a work start instruction, a travel stop instruction, etc. to the work vehicle 10. In addition, the staff can grasp the driving state of the work vehicle 10 that is automatically driving along the target path R in the field F based on the driving trajectory displayed on the operation terminal 20 and the image captured by the camera 53 at the place where the work vehicle 10 leaves (refer to Figure 8 ). In addition, the staff can understand the obstacle detection results displayed on the operation terminal 20, the execution status of the corresponding processing, etc.

[0107] The storage unit 22 is a non-volatile storage unit such as a HDD or SSD that stores various information. A control program for causing the operation control unit 21 to execute various control processes is stored in the storage unit 22. For example, the control program is non-temporarily recorded on a computer-readable recording medium such as a CD or a DVD, read by a predetermined reading device (not shown) and stored in the storage unit 22. In addition, the control program can also be downloaded from a server (not shown) to the operation terminal 20 via the communication network N1 and stored in the storage unit 22.

[0108] The operation control unit 21 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various calculations. The ROM is a non-volatile storage unit that pre-stores control programs such as BIOS and OS for the CPU to perform various calculations. The RAM is a volatile or non-volatile storage unit that stores various information and is used as a temporary storage memory (operating area) for various processes performed by the CPU. In addition, the operation control unit 21 controls the operation terminal 20 by executing various control programs pre-stored in the ROM or the storage unit 22 by the CPU.

[0109] like Figure 1As shown, the operation control unit 21 includes various processing units such as a setting processing unit 211 and an output processing unit 212. In addition, the operation control unit 21 functions as the various processing units by executing various processes according to the control program by the CPU. In addition, a part or all of the processing units may also be composed of electronic circuits. In addition, the control program may also be a program for causing a plurality of processors to function as the processing units.

[0110] The setting processing unit 211 sets various setting information for making the work vehicle 10 perform automatic driving. Specifically, the setting processing unit 211 sets information related to the work vehicle 10 (hereinafter referred to as the work vehicle information). The setting processing unit 211 sets the information by the worker performing an operation in the operation terminal 20 to register information such as the type (model) of the work vehicle 10, the position of the work vehicle 10 where the positioning antenna 174 is installed, the type of the work machine 14, the size and shape of the work machine 14, the position of the work machine 14 relative to the work vehicle 10, the speed and engine speed of the work vehicle 10 during operation, and the speed and engine speed of the work vehicle 10 during turning.

[0111] For example, the setting processing unit 211 causes the operation display unit 23 to display Figure 7 The worker selects, for example, “work machine registration” on the menu screen D1 to register the work machine information related to the work machine 14 .

[0112] The setting processing unit 211 sets information related to the field F (hereinafter referred to as field information). The setting processing unit 211 performs setting operations on the operation terminal 20 to determine the position and shape of the field F, the travel start position S for starting the operation, and the travel end position G for ending the operation (see FIG. Figure 3 ), and the working direction are set by an operation to register the information such as the field direction. The working direction refers to the direction in which the working vehicle 10 is driven while the working machine 14 is working in the working area excluding the head of the field and the non-working area from the field F. For example, the worker selects "field registration" on the menu screen D1 to register the field information.

[0113] The information on the position and shape of the field F can be automatically acquired, for example, by a worker riding on the work vehicle 10 and driving around the periphery of the field F and recording the change of the position information of the positioning antenna 174 at that time. Alternatively, the position and shape of the field F can be acquired based on a polygon obtained by the worker operating the operation terminal 20 while displaying a map on the operation terminal 20 to specify a plurality of points on the map. The area specified by the acquired position and shape of the field F is an area (travel area) in which the work vehicle 10 can travel.

[0114] In addition, the setting processing unit 211 sets information on how to perform the operation specifically (hereinafter referred to as operation information). The setting processing unit 211 is configured to set the operation information such as the presence or absence of the coordinated operation of the unmanned operation vehicle 10 and the manned operation vehicle 10, the number of operation paths skipped when the operation vehicle 10 turns at the head of the field, i.e., the number of skips, the width of the head of the field, and the width of the non-cultivated land. For example, the worker selects "operation registration" on the menu screen D1 to register the operation information.

[0115] In addition, the setting processing unit 211 generates a target path R, which is a path for the work vehicle 10 to automatically travel, based on the above-mentioned setting information. The target path R is, for example, a work path from the travel start position S to the travel end position G (see Figure 3 ). Figure 3 The target path R shown includes a straight path for the work vehicle 10 to travel back and forth in parallel in the field F, and a turning path connecting the work paths. The setting processing unit 211 generates and stores the target path R of the work vehicle 10 based on the above-mentioned setting information. For example, the worker selects "path creation" on the menu screen D1 to instruct the generation of the target path R. In addition, the setting processing unit 211 can generate and store a plurality of target paths R corresponding to the work content for one field F.

[0116] The output processing unit 212 outputs the route data of the target route R to the work vehicle 10 . For example, when a worker selects a desired target route R on the operation screen and instructs to start work, the output processing unit 212 outputs the route data of the selected target route R to the work vehicle 10 .

[0117] The work vehicle 10 is configured such that the path data of the target path R generated in the operation terminal 20 is transferred to the work vehicle 10 and stored in the storage unit 12, and the work vehicle 10 can autonomously travel along the target path R while detecting the current position of the work vehicle 10 through the positioning antenna 174. In addition, the current position of the work vehicle 10 is usually consistent with the position of the positioning antenna 174.

[0118] When the current position coincides with the travel start position S, if the worker presses the work start button on the operation screen to give a work start instruction, the work vehicle 10 starts to travel automatically through the travel processing unit 111, and the work machine 14 starts to perform (refer to Figure 2 That is, the operation control unit 21 allows the automatic travel of the work vehicle 10 on the condition that the current position is consistent with the travel start position S. In addition, the conditions for allowing the automatic travel of the work vehicle 10 are not limited to the above conditions.

[0119] The travel processing unit 111 of the work vehicle 10 automatically travels the work vehicle 10 from the travel start position S to the travel end position G according to the target route R acquired from the operation terminal 20 .

[0120] When the operation control unit 21 obtains a detection result indicating that an obstacle has been detected from the work vehicle 10, the operation control unit 21 displays the driving screen D2 (see FIG. Figure 8 ) so that the detected position of the obstacle is displayed in the captured image captured by the camera 53. Thus, the worker can confirm on the operation terminal 20 whether the work vehicle 10 has detected the obstacle, whether the work vehicle 10 has slowed down or stopped, the appearance of the obstacle, etc.

[0121] Here, the staff can set the setting information, i.e., sensitivity, in the operation terminal 20 to make the above-mentioned response process easy or difficult to execute. In other words, the above-mentioned sensitivity is a setting parameter that makes it easy or difficult to identify the detection object as an obstacle. Fig. 9 , an example of a sensitivity setting screen D3 for accepting sensitivity setting operations is shown. For example, if the sensitivity is set to "high", the likelihood threshold becomes lower. As a result, even for a detection object with a low likelihood, the likelihood is likely to exceed the likelihood threshold, so it is easy to generate a response process (stop process, deceleration process, report process), so that safety is improved. On the other hand, since it is easy to perform response processes excessively, operating efficiency is reduced. In contrast, if the sensitivity is set to "low", the likelihood threshold becomes higher. As a result, even for a detection object with a high likelihood, the likelihood is unlikely to exceed the likelihood threshold, so it is difficult to generate a response process (stop process, deceleration process, report process), so that excessive response processes are suppressed and operating efficiency is improved. On the other hand, since it is difficult to perform response processes, safety is reduced.

[0122] The operator can set the sensitivity according to the purpose of the work vehicle 10. The obstacle detection device 15 sets the likelihood threshold according to the operator's setting operation of the sensitivity. Fig. 10A As shown, information of a plurality of (here, three) likelihood threshold values ​​corresponding to the sensitivities (“high”, “medium”, and “low”) may be pre-registered in the storage unit 52. The obstacle detection device 15 obtains the likelihood threshold value corresponding to the sensitivity selected by the operator in the sensitivity setting screen D3 from the storage unit 52.

[0123] like Fig. 10A As shown, for the multiple likelihood thresholds corresponding to the sensitivity, the likelihood thresholds may be equal in the stop control range Ra and the report control range Rc, and different in the deceleration control range Rb for each sensitivity. Fig. 10B As shown, for the multiple likelihood thresholds corresponding to the sensitivity, the likelihood thresholds may be different for each sensitivity in each range of the stop control range Ra, the deceleration control range Rb, and the report control range Rc. The obstacle detection device 15 may also set the likelihood threshold according to the setting operation of the likelihood threshold by the operator (the input operation of "X" %).

[0124] As another embodiment, the obstacle detection device 15 may also automatically set the sensitivity based on the state of the field F and the content of the operation. That is, the detection control unit 51 may also automatically set the likelihood threshold based on at least one of the state of the field F and the content of the operation performed by the work vehicle 10. For example, when the work vehicle 10 is performing a harvesting operation of grain stalks, when the detection object such as a person is in a state of being blocked by the grain stalks, in order to improve safety, the detection control unit 51 sets the sensitivity to be high (sets the likelihood threshold to be low). In addition, for example, when the work vehicle 10 is performing a tillage operation, when the field F as a whole is in a state of good visibility, in order to improve the work efficiency, the detection control unit 51 sets the sensitivity to be low (sets the likelihood threshold to be high).

[0125] In addition, the detection control unit 51 may set the likelihood threshold and sensitivity based on the type of the work machine 14, the work content, etc. set by the worker in the operation terminal 20, and may set the likelihood threshold and sensitivity based on the state of the field F captured by the camera 53. In addition, the detection control unit 51 may change the sensitivity based on the sensitivity change operation of the worker after the work vehicle 10 starts to travel automatically. In addition, the detection control unit 51 may detect the change of the state of the field F based on the captured image after the work vehicle 10 starts to travel automatically, and change the likelihood threshold and sensitivity based on the change of the state of the field F.

[0126] In addition, the operator may also set the type of the detection object (control object) for which the response process should be executed in the operation terminal 20. That is, the detection control unit 51 may be able to set whether to make the work vehicle 10 execute the response process for each type of the detection object. Fig.11 , an example of a control object setting screen D4 for accepting a setting operation of a control object is shown. For example, in the control object setting screen D4, "person", "vehicle", and "other" are displayed as selectable. "Other" includes structures, materials, and the like.

[0127] The staff selects one or more types (control objects) of "people", "vehicles", and "others" for which response processing should be performed. In addition, for example, if the staff selects all of "people", "vehicles", and "others", response processing is easy to generate for various detection objects, so that safety is improved, but work efficiency is reduced. In addition, for example, if the staff selects only "people", it is difficult to generate response processing for detection objects other than people, so safety is reduced, but work efficiency is improved.

[0128] The detection control unit 51 performs obstacle detection processing (likelihood calculation processing, etc.) for the control object set by the staff in the operation terminal 20. In addition, the response processing unit 112 performs response processing for the control object set by the staff in the operation terminal 20. In addition, safety may be prioritized in the initial setting and all of "person", "vehicle", and "other" may be selected.

[0129] As another embodiment, the detection control unit 51 can set the likelihood threshold and sensitivity according to each control object. For example, for "people", the detection control unit 51 prioritizes safety and sets the likelihood threshold low (sets the sensitivity high), and prioritizes work efficiency and sets the likelihood threshold high (sets the sensitivity low) for "vehicles" and "others". In addition, for example, the detection control unit 51 sets the likelihood threshold low (for example, set to 60%) for "people" and "vehicles", and sets the likelihood threshold high (for example, set to 80%) for "others" such as animals. In addition, as another embodiment, when the staff selects the "safety priority mode", the detection control unit 51 sets the sensitivity to "high", and when the staff selects the "operability priority mode", the detection control unit 51 sets the sensitivity to "low".

[0130] In addition, the operation terminal 20 may also be a website (agriculture support website) that can access the agriculture support service provided by the server (not shown) via the communication network N1. In this case, the operation terminal 20 can function as an operation terminal of the above-mentioned server by executing a browser program through the operation control unit 21. In addition, the above-mentioned server has the above-mentioned processing units and executes each process.

[0131] [Automatic driving processing]

[0132] Below, refer to Fig.12An example of the automatic driving process performed by the vehicle control device 11 and the obstacle detection device 15 will be described. For example, the automatic driving process is started by the vehicle control device 11 and the obstacle detection device 15 when the work vehicle 10 starts automatic driving. The automatic driving process includes the obstacle detection process performed by the obstacle detection device 15.

[0133] In addition, the present invention can also be understood as an invention of an automatic driving method in which the vehicle control device 11 and the obstacle detection device 15 execute part or all of the automatic driving process, or an invention of an automatic driving program for causing the vehicle control device 11 and the obstacle detection device 15 to execute part or all of the automatic driving method. In addition, the automatic driving process can also be executed by one or more processors. The automatic driving program includes an obstacle detection program.

[0134] In step S1, the vehicle control device 11 determines whether the work vehicle 10 is in a state where it can travel automatically. If the work vehicle 10 satisfies the start conditions for automatic travel (S1: Yes), the vehicle control device 11 moves the process to step S2. The vehicle control device 11 waits until the work vehicle 10 satisfies the start conditions for automatic travel (S1: No).

[0135] In step S2, the vehicle control device 11 starts the automatic driving of the work vehicle 10. For example, if a worker issues a driving start instruction on the operation screen of the operation terminal 20, the operation control unit 21 outputs the driving start instruction to the work vehicle 10. If the driving start instruction is obtained from the operation terminal 20, the vehicle control device 11 starts the automatic driving of the work vehicle 10. As a result, the work vehicle 10 moves along the target path R (see FIG. 1 ) in the field F. Figure 3 ) starts automatic driving and starts the work performed by the work machine 14.

[0136] In step S3, the obstacle detection device 15 determines whether the detection object is detected. Specifically, the obstacle detection device 15 determines the type of the detection object (measurement object) based on the captured image obtained from the camera 53 and the measurement information obtained from the obstacle sensor 54. Fig.11 ), the obstacle detection device 15 determines that the detection object is detected (S3: Yes), and moves the process to step S4. If the detection object is not detected, or if the type of the determined detection object is not included in the pre-set control object (S3: No), the obstacle detection device 15 moves the process to step S9.

[0137] In step S4, the obstacle detection device 15 calculates the likelihood of the detected object. For example, when the obstacle detection device 15 determines that the detected object is a person based on the captured image, the obstacle detection device 15 calculates the likelihood (probability) indicating the possibility (certainty) of being a person based on the distance to the detected object. In addition, for example, when the obstacle detection device 15 determines that the detected object is a vehicle based on the captured image, the obstacle detection device 15 calculates the likelihood indicating the possibility of being a vehicle based on the distance to the detected object. When the obstacle detection device 15 calculates the likelihood, it presents the determination result (type of the detected object), the likelihood for the determination result, and the likelihood threshold value corresponding to the distance to the detected object (refer to Figure 5 ) is output to the vehicle control device 11. In addition, the obstacle detection device 15 can also determine the type of the detection object (human, vehicle, etc.) based on the captured image, and calculate the likelihood of the type of the detection object based on the size (occupied area, etc.) of the detection object reflected in the above-mentioned captured image.

[0138] Next, in step S5, the vehicle control device 11 determines whether the likelihood of the detection object calculated by the obstacle detection device 15 exceeds the likelihood threshold. If the vehicle control device 11 determines that the likelihood of the detection object exceeds the likelihood threshold (S5: Yes), the process moves to step S6. On the other hand, if the vehicle control device 11 determines that the likelihood of the detection object is less than the likelihood threshold (S5: No), the process moves to step S9.

[0139] In step S6, the vehicle control device 11 causes the work vehicle 10 to execute a response process. Specifically, the vehicle control device 11 causes the work vehicle 10 to execute a response process (stop process, deceleration process, reporting process) corresponding to the position of the detection object. For example, when the position of the detection object is within the reporting control range Rc (refer to Figure 4 ), the vehicle control device 11 causes a warning sound to be issued from the work vehicle 10. In addition, for example, when the position of the detection object is within the deceleration control range Rb, the vehicle control device 11 decelerates the speed of the work vehicle 10. In addition, for example, when the position of the detection object is within the stop control range Ra, the vehicle control device 11 stops the work vehicle 10.

[0140] Next, in step S7, the vehicle control device 11 determines whether the detection object has moved. For example, when the detection object moves to the first detection range Rd1 (refer to Figure 4 ), the vehicle control device 11 determines that the detection object has moved (S7: Yes), and moves the process to step S8. While the detection object is within the first detection range Rd1, the vehicle control device 11 repeatedly executes the processes of steps S4 to S6 (S7: No).

[0141] In step S8, the vehicle control device 11 ends the response process. For example, if the detection object located in the report control range Rc moves outside the first detection range Rd1, the vehicle control device 11 stops the report process. In addition, for example, if the detection object located in the deceleration control range Rb moves outside the first detection range Rd1, the vehicle control device 11 returns the speed of the work vehicle 10 to the original speed. In addition, for example, if the detection object located in the stop control range Ra moves outside the first detection range Rd1, the vehicle control device 11 cancels the temporary stop of the work vehicle 10 and restarts the automatic driving.

[0142] Next, in step S9, the vehicle control device 11 determines whether the work vehicle 10 has completed the work. For example, when the work vehicle 10 reaches the travel end position G (refer to Figure 3 ), the vehicle control device 11 determines that the work vehicle 10 has completed the work (S9: Yes), and ends the above-mentioned automatic driving process. The vehicle control device 11 repeatedly performs the above-mentioned process until the work vehicle 10 reaches the driving end position G (S9: No). As described above, the vehicle control device 11 and the obstacle detection device 15 perform the above-mentioned automatic driving process.

[0143] As described above, when the work vehicle 10 is automatically traveling along the target path R, the automatic driving system 1 of the present embodiment obtains the distance information of the distance to the detection object detected by the obstacle sensor 54, and obtains the image information of the image of the detection object captured by the camera 53. In addition, the automatic driving system 1 determines the type of the detection object based on the above image information, and causes the work vehicle 10 to execute a response process corresponding to the type of the detection object. In addition, the automatic driving system 1 causes the work vehicle 10 to execute a response process corresponding to the type of the detection object and the distance information.

[0144] In addition, in the automatic driving system 1, the likelihood of the type of the detection object is calculated based on the above-mentioned image information, and when the calculated likelihood exceeds the likelihood threshold value (see Figure 5 ), the work vehicle 10 executes the corresponding processing. In addition, in the automatic driving system 1, the type of the detection object can also be determined based on the above-mentioned image information and the above-mentioned distance information. In addition, in the automatic driving system 1, the likelihood of the type of the detection object can also be calculated based on the above-mentioned image information and the above-mentioned distance information.

[0145] Furthermore, in the automatic driving system 1 , the likelihood threshold value may be set to a smaller value as the distance from the work vehicle 10 to the detection target is shorter.

[0146] According to the above configuration, for example, when the detection object is a detection object (operation object, etc.) that does not require the work vehicle 10 to perform a response process, the response process can be omitted, and when the detection object is a detection object (person, vehicle, etc.) that requires the work vehicle 10 to perform a response process, the response process can be performed. Thus, it is possible to prevent the work efficiency of the work vehicle 10 from being reduced, and to allow the work vehicle 10 to perform appropriate response processes for obstacles.

[0147] According to the above configuration, for example, in the notification control range Rc far from the work vehicle 10, the work efficiency is prioritized, and when the likelihood of the detection object is high, the work vehicle 10 is caused to perform the response process (notification process) (see Figure 5 and Figure 6 ). In addition, for example, in the stop control range Ra where the distance to the work vehicle 10 is short, safety is prioritized, and the work vehicle 10 is caused to perform a response process (stop process) even when the likelihood of the detection object is low. In addition, for example, in the deceleration control range Rb, the closer the distance is, the easier it is to perform a response process (deceleration process), and the farther the distance is, the more difficult it is to perform a response process (deceleration process).

[0148] The present invention is not limited to the above-mentioned embodiments, but may also be the following embodiments. Figure 6 As shown in FIG. 1 , the likelihood threshold is set to change linearly in the deceleration control range Rb (distance L1 to L2). Fig.13A As shown, the likelihood threshold may be set to a constant value (Th1) in the stop control range Ra (distance 0 to L1), and may be set to a constant value (Th2) in the report control range Rc (distance L2 to L3). In addition, the likelihood threshold may be set to Th1 at the distance L1 of the stop control range Ra, and the likelihood threshold may be set to Th2 at the distance L2 of the report control range Rc, and in the deceleration control range Rb (distance L1 to L2), the likelihood threshold may be set to change linearly between Th1 and Th2.

[0149] In addition, if Fig. 13B As shown, the likelihood threshold may also be set to three stages. For example, in the stop control range Ra (distance 0 to L1), the likelihood threshold is set to Th1, in the deceleration control range Rb (distance L1 to L2), the likelihood threshold is set to Th4 (where Th1 < Th4 < Th2), and in the reporting control range Rc (distance L2 to L3), the likelihood threshold is set to Th2.

[0150] Alternatively, the likelihood threshold may be set to change linearly in the entire range (distance 0 to L3) of the stop control range Ra, the deceleration control range Rb, and the notification control range Rc.

[0151] In addition, in the above-mentioned embodiment, the likelihood threshold is set according to the distance from the work vehicle 10 to the detection object. Fig. 13C As shown, the likelihood threshold may be set to a constant value (e.g., Th1) in the entire range (distance 0 to L3) of the stop control range Ra, the deceleration control range Rb, and the notification control range Rc. For example, the detection control unit 51 sets the likelihood threshold to a low value when safety is prioritized, and sets the likelihood threshold to a high value when work efficiency is prioritized. In addition, the detection control unit 51 may set a constant value of the likelihood threshold according to the state of the field F, the work content, and each of the control objects.

[0152] In addition, as another embodiment, the automatic driving system 1 may also be a method that does not utilize the above-mentioned likelihood information. For example, in the automatic driving system 1, it may also be that: the staff can set the content of the response processing corresponding to the distance (range) according to each type of the detection object. For example, the staff sets the response processing (such as stop processing, deceleration processing, report processing, etc.) corresponding to the distance to the detection object according to each type (human, vehicle, other) of the detection object (control object) in the setting screen. Thus, for example, when the distance to the detection object is L0, if the detection object is a person, the work vehicle 10 is stopped, and if the detection object is a vehicle, the work vehicle 10 is decelerated, etc., and the response processing can be different according to the type of the detection object and the above-mentioned distance. In addition, in this case, it may also be that: the staff can set the threshold value of the above-mentioned distance (the range of each response processing) according to each type of the detection object.

[0153] In addition, as another embodiment, the automatic driving system 1 may also execute a response process corresponding to a detection object that is closer to the work vehicle 10. Specifically, the automatic driving system 1 executes a response process when detecting a detection object that is less than a predetermined distance from the work vehicle 10, and does not execute a response process when detecting a detection object that is more than a predetermined distance from the work vehicle 10.

[0154] In addition, as another embodiment, the automatic driving system 1 may also set a priority according to the type of the detection object. For example, the automatic driving system 1 sets the priority of a person higher than that of a vehicle. In this case, when a person and a vehicle are detected at the same distance, the automatic driving system 1 executes the response process corresponding to the detection object with the higher priority. Here, the automatic driving system 1 executes the response process set to a person. In addition, in this case, it may also be possible for the staff to set the priority of each type of the detection object.

[0155] [Other methods for setting the likelihood threshold]

[0156] Hereinafter, specific examples (first to third setting methods) of other setting methods of the likelihood threshold will be described.

[0157] [1st setting method]

[0158] In the first setting method, the detection control unit 51 sets the likelihood threshold value according to the setting content of the monitoring mode in the automatic driving mode. Specifically, the work vehicle 10 includes a short-distance mode (short-distance monitoring mode) that can control the movement of the work vehicle 10 within a specified range from the work vehicle 10, and a long-distance mode (long-distance monitoring mode) that can control the movement of the work vehicle 10 via the communication network N1 (Internet, etc.) (can be operated via cloud connection), and the vehicle control device 11 can set or switch the short-distance mode and the long-distance mode. In addition, it can also be: the short-distance mode is a monitoring mode that can control the movement of the work vehicle 10 through short-distance communication, and the long-distance mode is a monitoring mode that can control the movement of the work vehicle 10 through long-distance communication. In addition, the short-distance mode can also be a remote control mode, and the long-distance mode can also be a smartphone mode. In addition, the vehicle control device 11 can control the movement of the work vehicle 10 according to the set monitoring mode. For example, the worker can select the short-distance mode or the long-distance mode on the setting screen D5 of the operating device (on-board monitor) fixed in the cockpit 138 of the work vehicle 10 or the operating terminal 20 brought into the cockpit 138 by the worker. Fig.14 , an example of the setting screen D5 is shown. The vehicle control device 11 sets the monitoring mode selected by the operator and executes a process corresponding to the set monitoring mode.

[0159] For example, when the vehicle control device 11 is set to the short-distance mode, the worker can start / stop the automatic driving of the work vehicle 10, set / change the speed and engine speed of the work vehicle 10, raise / lower the work machine 14, etc., through a mobile terminal such as a smartphone, a tablet terminal, or a remote controller. On the other hand, when the vehicle control device 11 is set to the long-distance mode, the worker can check the camera image during the automatic driving, or perform remote operations such as stopping the automatic driving of the work vehicle 10, setting / changing the speed and engine speed of the work vehicle 10, raising / lowering the work machine 14, etc., through an operation terminal such as a smartphone, a tablet terminal (operation terminal 20), or a personal computer.

[0160] The detection control unit 51 sets the likelihood threshold value according to whether the monitoring mode is set to the short-distance mode or the long-distance mode. For example, when the monitoring mode is set to the short-distance mode, the detection control unit 51 sets the likelihood threshold value to a high value, so that it is difficult to identify the detection object as an obstacle (reducing sensitivity). In this case, when the detection control unit 51 determines that the detection object is indeed an obstacle (person, vehicle, etc.), that is, when a detection object with a high likelihood is detected, the vehicle control device 11 performs a response process (stop process, deceleration process, report process). As a result, in the case of the short-distance mode, safety can be guaranteed and work efficiency can be improved.

[0161] In contrast, when the monitoring mode is set to the long-distance mode, the detection control unit 51 sets the likelihood threshold to a low value, so that the detection object is easily identified as an obstacle (increasing sensitivity). In this case, when the detection control unit 51 determines that the detection object is likely to be an obstacle (a person, a vehicle, etc.), that is, when a detection object with a low likelihood is detected, the vehicle control device 11 performs a response process (stop process, deceleration process, reporting process). As a result, in the long-distance mode, automatic driving can be performed with greater safety.

[0162] [Second setting method]

[0163] In the second setting method, the detection control unit 51 sets the likelihood threshold value according to the position of the detection object. Specifically, the detection control unit 51 sets different likelihood threshold values ​​according to the situation where the detection object is located in the field and the situation where it is located outside the field. For example, the detection control unit 51 pre-sets (registers) a first likelihood threshold value applied when the detection object is detected in the field, and a second likelihood threshold value applied when the detection object is detected outside the field. In addition, the detection control unit 51 sets the second likelihood threshold value to a value higher than the first likelihood threshold value. That is, the detection control unit 51 sets the first likelihood threshold value to a low value (sets the sensitivity to a high value) so that the detection object is easily identified as an obstacle, and sets the second likelihood threshold value to a high value (sets the sensitivity to a low value) so that the detection object is difficult to be identified as an obstacle.

[0164] When the work vehicle 10 detects a detection object during automatic driving, the detection control unit 51 determines whether the detection object is located inside or outside the field F based on the distance from the work vehicle 10 to the detection object and the shape data (map information) of the field F. When the detection control unit 51 determines that the detection object is located inside the field F, it determines whether the detection object is an obstacle based on the first likelihood threshold. Specifically, when the likelihood of the detection object exceeds the first likelihood threshold, the detection control unit 51 determines that the detection object is an obstacle. In contrast, when the detection object is located outside the field F, the detection control unit 51 determines whether the detection object is an obstacle based on the second likelihood threshold. Specifically, when the likelihood of the detection object exceeds the second likelihood threshold, the detection control unit 51 determines that the detection object is an obstacle.

[0165] The vehicle control device 11 performs a response process (stop process, deceleration process, report process) when the detection control unit 51 determines that the detection object is an obstacle. According to the above structure, since it is difficult to perform a response process even if a detection object outside the field is detected, the number of reports can be reduced or unnecessary driving control (deceleration, stop) can be avoided for a detection object outside the field F that has a low possibility of contact with the work vehicle 10. Therefore, the trouble of the staff's confirmation work can be reduced, and the work efficiency can be improved. In addition, when the likelihood of the detection object detected outside the field exceeds the second likelihood threshold, that is, when an obstacle outside the field is detected, the vehicle control device 11 may not perform the stop process and the deceleration process, but only perform the report process (reporting a warning sound from the work vehicle 10 to the surroundings, notifying a warning message to the operation terminal 20, etc.). In addition, during the above-mentioned reporting process, the vehicle control device 11 may change the reporting method (increasing the volume, shortening the reporting cycle, increasing the notification frequency of the warning message, emphasizing the warning message, etc.) as the distance to the obstacle becomes smaller (the work vehicle 10 approaches the obstacle).

[0166] [Third setting method]

[0167] In the third setting method, the detection control unit 51 sets the likelihood threshold value according to the operation mode (single operation mode, coordinated operation mode). Specifically, the staff can choose whether the operation in a field F is performed by one work vehicle 10 (single operation mode) or by multiple work vehicles 10 (coordinated operation mode). In the single operation mode, one work vehicle 10 automatically drives and operates in the field F, and in the coordinated operation mode, multiple work vehicles 10 automatically drive and operate in the field F in a coordinated manner. For example, the staff can select the single operation mode or the coordinated operation mode in the setting screen D6 of the operating device (on-board monitor) or the operating terminal 20. Fig.15 , an example of the setting screen D6 is shown. The vehicle control device 11 sets the work mode selected by the worker and executes a process corresponding to the set work mode.

[0168] The detection control unit 51 sets the likelihood threshold value according to whether the operation mode is set to a single operation mode or a coordinated operation mode. For example, when the detection control unit 51 is set to a single operation mode, the likelihood threshold value is set to a high value, so that it is difficult to identify the detection object as an obstacle (reducing sensitivity). In this case, when the detection control unit 51 determines that the detection object is indeed an obstacle (a person, a vehicle, etc.), that is, when a detection object with a high likelihood is detected, the vehicle control device 11 performs a response process (stop process, deceleration process, report process). As a result, in the case of a single operation mode, safety can be guaranteed and operation efficiency can be improved.

[0169] In contrast, when the operation mode is set to the coordinated operation mode, the detection control unit 51 sets the likelihood threshold to a low value, so that the detection object is easily identified as an obstacle (increasing sensitivity). In this case, when the detection control unit 51 determines that the detection object seems to be an obstacle (a person, a vehicle, etc.), that is, when a detection object with a low likelihood is detected, the vehicle control device 11 performs a response process (stop process, deceleration process, report process). Thus, in the case of the coordinated operation mode, since other working vehicles 10 are easily identified, it is possible to improve safety and perform automatic driving.

[0170] In addition, as another embodiment of the third setting method, the detection control unit 51 may set the likelihood threshold to a low value (set the sensitivity to high) when the single operation mode is set, and may set the likelihood threshold to a high value (set the sensitivity to low) when the coordinated operation mode is set. Thus, for example, in the coordinated operation mode, it is difficult to perform response processing, so the operating efficiency of the coordinated operation can be improved. In addition, in the coordinated operation mode, the driving path (target path) is set in a manner that the multiple working vehicles 10 do not contact each other, so even if the sensitivity is set to a low level, safety can be ensured.

[0171] In addition, as another embodiment of the third setting method, the detection control unit 51 may also, when the worker selects the cooperative operation mode, Fig.16 In the setting screen D6 shown, the selection operation of the priority mode in the cooperative operation is accepted. For example, the worker can select the "safety priority mode" that prioritizes safety or the "operability priority mode" that prioritizes operation efficiency in the cooperative operation mode. When the worker selects the "safety priority mode", the detection control unit 51 sets the sensitivity to high, and when the worker selects the "operability priority mode", the sensitivity is set to low.

[0172] In addition, the detection control unit 51 may also set the likelihood threshold of the workability priority mode in the coordinated work mode to a value lower than the likelihood threshold in the independent work mode (set the sensitivity to be high). That is, the detection control unit 51 may also set the magnitude of the likelihood threshold of the work mode to satisfy the relationship of "likelihood threshold of coordinated work mode / safety priority mode" < "likelihood threshold of coordinated work mode / workability priority mode" < "likelihood threshold of independent work mode".

[0173] In addition, the detection control unit 51 may also set the likelihood threshold of the workability priority mode in the coordinated work mode to a value higher than the likelihood threshold in the independent work mode (set the sensitivity to be low). That is, the detection control unit 51 may also set the magnitude of the likelihood threshold of the work mode to satisfy the relationship of "likelihood threshold of coordinated work mode / safety priority mode" < "likelihood threshold of independent work mode" < "likelihood threshold of coordinated work mode / workability priority mode".

[0174] As another example of a method for setting the likelihood threshold, the detection control unit 51 may also set the likelihood threshold based on the position of the worker relative to the work vehicle 10. Specifically, when the worker is within a specified distance from the work vehicle 10, the worker can visually determine obstacles, so the detection control unit 51 sets the likelihood threshold to a high value (sets the sensitivity to a low value). In contrast, when the worker is beyond the specified distance from the work vehicle 10, the worker cannot visually determine obstacles, so the detection control unit 51 sets the likelihood threshold to a low value (sets the sensitivity to a high value). In addition, the detection control unit 51 may also be set so that the likelihood threshold becomes lower as the distance between the work vehicle 10 and the worker becomes farther, thereby setting the likelihood threshold based on the distance.

[0175] [Additional Notes on the Invention]

[0176] Hereinafter, the summary of the invention extracted from the above-mentioned embodiments will be supplemented. In addition, each structure and each processing function described in the following supplementary notes can be selected and combined arbitrarily.

[0177] <Note 1>

[0178] A vehicle control method, wherein:

[0179] When the working vehicle automatically drives according to the target path, the following processing is performed, namely:

[0180] acquiring distance information of a distance to a detection object detected by a detection unit;

[0181] Acquiring image information of an image of the detection object captured by a capturing unit;

[0182] Determining the type of the detection object based on the image information; and

[0183] The work vehicle is caused to execute a response process corresponding to the type of the detection object and the distance information.

[0184] <Note 2>

[0185] In the vehicle control method described in Supplement 1,

[0186] The likelihood of the type of the detection target is calculated based on the image information, and the work vehicle is caused to execute the response process based on the calculated likelihood.

[0187] <Note 3>

[0188] In the vehicle control method described in Supplement 1,

[0189] The likelihood of the type of the detection object is calculated based on the image information and the distance information, and the work vehicle is caused to execute the response process based on the calculated likelihood.

[0190] <Note 4>

[0191] In the vehicle control method described in Supplementary Note 3,

[0192] The likelihood is calculated such that the shorter the distance is, the higher the likelihood is.

[0193] <Note 5>

[0194] In the vehicle control method according to any one of Supplementary Notes 2 to 4,

[0195] When the likelihood exceeds a threshold value, the work vehicle is caused to execute the countermeasure process.

[0196] <Note 6>

[0197] In the vehicle control method described in Supplementary Note 5,

[0198] The threshold value is set to be smaller as the distance is shorter.

[0199] <Note 7>

[0200] In the vehicle control method described in Appendix 5 or 6,

[0201] The threshold value is set to a different value depending on the content of the response process.

[0202] <Note 8>

[0203] In the vehicle control method described in Supplement 7,

[0204] In the case where the response process is a process of stopping the work vehicle that is automatically traveling, the threshold is set to a first threshold.

[0205] When the countermeasure process is a process of decelerating the work vehicle that is traveling automatically or a process of reporting warning information from the work vehicle, the threshold value is set to a second threshold value that is larger than the first threshold value.

[0206] <Note 9>

[0207] In the vehicle control method according to any one of Supplementary Notes 6 to 8,

[0208] The setting information, namely, the sensitivity, can be set to make the above-mentioned countermeasure processing easier or more difficult to execute.

[0209] The threshold value is further set according to the sensitivity.

[0210] <Note 10>

[0211] In the vehicle control method described in Supplementary Note 9,

[0212] The above sensitivity is set according to the user's operation.

[0213] <Note 11>

[0214] In the vehicle control method according to any one of Supplementary Notes 5 to 8,

[0215] The threshold value is set based on at least one of a state of a work area in which the work vehicle automatically travels and a content of a work performed by the work vehicle.

[0216] <Note 12>

[0217] In the vehicle control method described in Supplementary Notes 5 to 8,

[0218] The threshold value is set according to the type of the detection object.

[0219] <Note 13>

[0220] In the vehicle control method described in Supplementary Notes 5 to 8,

[0221] The work vehicle includes a short-distance mode capable of controlling the movement of the work vehicle within a predetermined range, and a long-distance mode capable of controlling the movement of the work vehicle outside the predetermined range.

[0222] The threshold value is set to be either a threshold value corresponding to the short-distance mode or a threshold value corresponding to the long-distance mode.

[0223] <Note 14>

[0224] In the vehicle control method described in Supplementary Notes 5 to 8,

[0225] The threshold value is set to a different value depending on whether the detection object is located inside a work area in which the work vehicle automatically drives or outside the work area.

[0226] <Note 15>

[0227] In the vehicle control method described in Supplementary Notes 5 to 8,

[0228] The above-mentioned working vehicle includes a single working mode in which the working vehicle performs working independently, and a coordinated working mode in which the working vehicle performs working in coordination with other working vehicles.

[0229] The threshold value is set to be either a threshold value corresponding to the individual operation mode or a threshold value corresponding to the cooperative operation mode.

[0230] <Note 16>

[0231] In the vehicle control method according to any one of Supplementary Notes 1 to 15,

[0232] Whether or not to cause the work vehicle to execute the countermeasure process can be set for each type of the detection object.

Claims

1. A vehicle control method, characterized in that: When the working vehicle automatically drives according to the target path, the following processing is performed, namely: acquiring distance information of a distance to a detection object detected by a detection unit; Acquiring image information of an image of the detection object captured by a capturing unit; Determining the type of the detection object based on the image information; as well as The work vehicle is caused to execute a response process corresponding to the type of the detection object and the distance information.

2. The vehicle control method according to claim 1, characterized in that: The likelihood of the type of the detection target is calculated based on the image information, and the work vehicle is caused to execute the handling process based on the calculated likelihood.

3. The vehicle control method according to claim 1, characterized in that: The likelihood of the type of the detection object is calculated based on the image information and the distance information, and the work vehicle is caused to execute the handling process based on the calculated likelihood.

4. The vehicle control method according to claim 3, characterized in that: The likelihood is calculated in such a manner that the shorter the distance is, the higher the likelihood is.

5. The vehicle control method according to claim 2, characterized in that: When the likelihood exceeds a threshold value, the work vehicle is caused to execute the countermeasure process.

6. The vehicle control method according to claim 5, characterized in that: The threshold value is set to be smaller as the distance is shorter.

7. The vehicle control method according to claim 6, characterized in that: The threshold value is set to a different value depending on the content of the processing.

8. The vehicle control method according to claim 7, characterized in that: When the response process is a process of stopping the work vehicle that is traveling automatically, the threshold is set to a first threshold. When the response process is a process of decelerating the work vehicle that is traveling automatically or a process of reporting warning information from the work vehicle, the threshold is set to a second threshold that is larger than the first threshold.

9. The vehicle control method according to any one of claims 6 to 8, characterized in that: The setting information, namely, the sensitivity, can be set to make the above-mentioned countermeasure processing easier or more difficult to execute. The threshold is further set according to the sensitivity.

10. The vehicle control method according to claim 9, characterized in that: The sensitivity is set according to the user's operation.

11. The vehicle control method according to any one of claims 6 to 8, characterized in that: The threshold value is set based on at least one of a state of a work area in which the work vehicle performs automatic driving and content of work performed by the work vehicle.

12. The vehicle control method according to claim 5, characterized in that: The threshold is set according to the type of the detection object.

13. The vehicle control method according to claim 5, characterized in that: The work vehicle includes a short-distance mode capable of controlling the movement of the work vehicle within a predetermined range, and a long-distance mode capable of controlling the movement of the work vehicle outside the predetermined range. The threshold is set to be either a threshold corresponding to the short-distance mode or a threshold corresponding to the long-distance mode.

14. The vehicle control method according to claim 5, characterized in that: The threshold value is set to a different value depending on whether the detection target is located inside a work area in which the work vehicle performs automatic driving or whether the detection target is located outside the work area.

15. The vehicle control method according to claim 5, characterized in that: The work vehicle includes a single work mode for working alone and a coordinated work mode for working in coordination with other work vehicles. The threshold value is set to be either a threshold value corresponding to the individual operation mode or a threshold value corresponding to the cooperative operation mode.

16. The vehicle control method according to any one of claims 1 to 8, characterized in that: Whether or not to cause the work vehicle to execute the countermeasure process can be set for each type of the detection object.

17. A vehicle control program, characterized in that: The vehicle control program is used to cause one or more processors to execute the following processing when the work vehicle automatically drives according to the target path, namely: acquiring distance information of a distance to a detection object detected by a detection unit; Acquiring image information of an image of the detection object captured by a capturing unit; Determining the type of the detection object based on the image information; as well as The work vehicle is caused to execute a response process corresponding to the type of the detection object and the distance information.

18. A vehicle control system, characterized in that: have: an acquisition processing unit that acquires distance information of a distance to a detection object detected by the detection unit and image information of an image of the detection object captured by the imaging unit when the work vehicle is automatically traveling along a target path; a determination processing unit that determines the type of the detection object based on the image information; as well as A response processing unit causes the work vehicle to execute a response process corresponding to the type of the detection object and the distance information.

Images