Automatic travel system

Abstract

Provided is an automatic travel system A for causing a work vehicle in a field to travel automatically, wherein the work vehicle 1 includes an obstacle classification processing unit t11 which includes: an obstacle detection sensor S1 that detects an obstacle; and an optical imaging device S5 that can acquire three-dimensional imaging information indicating the position and shape of the obstacle detected by the obstacle detection sensor S1, wherein the obstacle detected from the three-dimensional imaging information is classified. The obstacle classification processing unit t11 classifies the detected obstacle into an obstacle that does not move and an obstacle that moves. The present invention can provide an automatic travel system which can further improve safety during automatic travel with respect to a moving obstacle by means of the automatic travel system A characterized in that an obstacle avoidance route L2 during automatic travel is configured to be changeable in response to an obstacle classification result from the obstacle classification processing unit t11.

Description

Autonomous Driving System

[0001] The present invention relates to an automatic driving system for automatically driving a work vehicle.

[0002] In recent years, there has been an increasing need for smart agriculture, and in the technical field of work vehicles, efforts are being made to use positioning satellite systems such as GPS to enable work vehicles to automatically navigate unmanned fields and perform agricultural work.

[0003] In a conventional automatic driving system, as shown in Patent Document 1 below, for example, a target driving route that will travel around the field is set before work begins, and while the system is driving automatically, position information indicating the current position of the work vehicle is acquired at predetermined time intervals, and the deviation of the vehicle's position from the set target driving route (deviation in direction and distance) is calculated.The system then automatically steers the steering wheel based on the calculated deviation, allowing the work vehicle to drive automatically along the target driving route.

[0004] Furthermore, Patent Document 2 discloses an automated driving system that, when a work vehicle detects an obstacle during automated driving, generates a new avoidance route to avoid the obstacle, thereby enabling the work vehicle to automatically avoid the obstacle and continue automated driving.

[0005] JP 11-266608 A JP 2022-94624 A

[0006] Incidentally, conventional automated driving systems such as those described in Patent Document 2 are premised on the assumption that detected obstacles do not move in a series of processes for obstacle avoidance. However, in reality, when a person, an animal, a work vehicle traveling in the same field, or the like is detected as an obstacle, it is expected that the obstacle will move after detection. Therefore, there is room for improvement in terms of more reliably avoiding contact with obstacles and realizing safer automated driving.

[0007] Therefore, an object of the present invention is to provide an automatic driving system that can solve such problems and further improve safety during automatic driving against moving obstacles.

[0008] In order to achieve the above object, a first invention is an automatic driving system that automatically drives a work vehicle within a field, wherein the work vehicle is equipped with an obstacle detection sensor that detects obstacles and an optical imaging device that can acquire three-dimensional imaging information that indicates the position and shape of the obstacle detected by the obstacle detection sensor, and an obstacle classification processing unit that classifies the obstacles detected from the three-dimensional imaging information, the obstacle classification processing unit classifies the detected obstacles into non-moving obstacles and moving obstacles, and is configured to be able to change the obstacle avoidance route during automatic driving depending on the obstacle classification results by the obstacle classification processing unit.

[0009] According to the first invention, the obstacle avoidance route during automatic driving can be changed depending on the classification result of the obstacle by the obstacle classification processing unit, thereby further improving safety during automatic driving against moving obstacles.

[0010] The second invention, in addition to the configuration of the first invention, further comprises an avoidance route determination unit that determines the avoidance route, and an avoidance range setting unit that can set an avoidance range for an obstacle, wherein the avoidance route determination unit is configured to determine the avoidance route based on the avoidance range set by the avoidance range setting unit, and the avoidance range is an area that is defined by setting a forward avoidance distance, a rearward avoidance distance, a leftward avoidance distance, and a rightward avoidance distance relative to a central reference position of the body of the work vehicle.

[0011] According to the second invention, in addition to the effects of the first invention, the avoidance range can be set by determining the avoidance distance for each of the front, rear, left and right sides of the work vehicle, which allows for good automatic driving along the edges of rice paddies, etc., and further improves safety.

[0012] The third invention is characterized in that, in addition to the configuration of the second invention, the work vehicle is configured to automatically recognize the type of attached work implement by obtaining information regarding the shape of the attached work implement from the three-dimensional imaging information, thereby calculating the working width of the attached work implement and setting the avoidance range based on the calculated working width.

[0013] According to the third aspect of the present invention, in addition to the effect of the second aspect of the present invention, the size of the work machine is automatically calculated and an appropriate avoidance range is set, thereby further improving safety.

[0014] The fourth invention, in addition to the configuration of any one of the first to third inventions, is characterized in that it comprises a contact prevention processing unit that prevents contact with an obstacle, and that when an obstacle enters a set driving deceleration range during automatic driving, the contact prevention processing unit decelerates the work vehicle until the obstacle moves out of the driving deceleration range, and is configured to stop the work vehicle when an obstacle enters a set driving stop range until the obstacle moves out of the driving stop range.

[0015] According to the fourth invention, in addition to the effect of any one of the first to third inventions, safety can be further improved by slowing down or stopping the work vehicle depending on the distance between the obstacle and the work vehicle.

[0016] The fifth invention is characterized in that, in addition to the configuration of the second invention, the avoidance route determination unit reduces the avoidance angle of the avoidance route depending on the traveling speed of the work vehicle during automatic traveling, when the traveling speed is faster than a predetermined speed, and increases the avoidance angle when the traveling speed is slower than the predetermined speed.

[0017] According to the fifth aspect of the invention, in addition to the effects of the second aspect of the invention, the avoidance angle of the avoidance route can be reduced when the traveling speed is faster than a predetermined speed, and increased when the traveling speed is slower than the predetermined speed, thereby preventing slippage and improving safety. In addition, it is possible to design an appropriate avoidance route taking speed into consideration.

[0018] According to the present invention, it is possible to provide an automatic driving system that can further improve safety during automatic driving against moving obstacles.

[0019] 1 is a block diagram showing the configuration of an automated driving system according to an embodiment of the present invention. FIG. 2 is a side view of a work vehicle according to an embodiment of the present invention. FIG. 3 is a plan view of a work vehicle according to an embodiment of the present invention. FIG. 4 is an explanatory diagram for explaining a target driving route for a work vehicle. FIG. 5 is a schematic plan view of a work vehicle showing the detection range of an optical imaging device. FIG. 6 is a schematic side view of the same. FIG. 7 is an explanatory diagram for explaining a method for recognizing a work implement. FIG. 8 is an explanatory diagram for explaining the setting contents of an obstacle avoidance range in a first pattern (minimum range). FIG. 9 is an explanatory diagram for explaining the setting contents of an obstacle avoidance range in a second pattern (addition of left and right margins). FIG. 10 is an explanatory diagram for explaining the setting contents of an obstacle avoidance range in a third pattern (addition of front and rear margins). FIG. 11 is an explanatory diagram for an obstacle avoidance route according to a first avoidance range. FIG. 12 is an explanatory diagram for an obstacle avoidance route according to a second avoidance range. FIG. 13 is an explanatory diagram for an obstacle avoidance route according to a third avoidance range. FIG. 14 is an explanatory diagram for explaining the setting contents of an obstacle contact prevention range (center of the work vehicle). FIG. 15 is an explanatory diagram for explaining the setting contents of an obstacle contact prevention range (center of the work implement). FIG. 16 is a flowchart showing the processing procedure of an automated driving system when an obstacle is detected. FIG. 17 is an image of a detected obstacle. FIG. 18 is an explanatory diagram for an obstacle avoidance route according to another embodiment.

[0020] <1. Overall Configuration of Autonomous Driving System A> A preferred embodiment of the present invention will now be described in detail with reference to the accompanying drawings. Fig. 1 is a block diagram showing the configuration of an autonomous driving system A according to an embodiment of the present invention. The overall configuration of the autonomous driving system A will be described below.

[0021] As shown in Figure 1, the automated driving system A is configured to include a work vehicle 1, an information terminal T1, and a management terminal T2. The work vehicle 1, the information terminal T1, and the management terminal T2 are able to communicate with each other via a communication network N using a communication device (not shown). Note that, as a communication means via the communication network N, for example, a mobile phone network, a packet network, a wireless LAN, etc. can be used. Furthermore, the automated driving system A is able to acquire various data present on the cloud CL via the communication network N.

[0022] The work vehicle 1 is equipped with a work implement WM and is configured to be able to automatically travel in a field while performing agricultural work (hereinafter sometimes simply referred to as "work"). As shown in FIG. 1 , the work vehicle 1 is equipped, as control mechanisms, with a travel control device C1 that controls the travel of the vehicle body and a work implement control device C2 that controls the work implement WM. These control devices are information processing devices made up of a combination of multiple ECUs (Electronic Control Units). Each of the multiple ECUs is configured with a CPU that performs arithmetic processing and memory that can read and write information necessary for the arithmetic processing, and the configuration shown as functional blocks in FIG. 1 is realized by the CPU operating in accordance with various control programs stored in the memory.

[0023] The input side of these control devices is provided with an obstacle detection sensor S1, a camera S2, a positioning device S3, an inertial measurement unit S4, and an optical imaging device S5, which will be described in detail later.

[0024] The information terminal T1 is an information processing device that executes the processes required for work in cooperation with the work vehicle 1, and transmits and receives various information required for work between the work vehicle 1 and the management terminal T2, thereby, for example, causing the work vehicle 1 to perform work and causing the management terminal T2 to manage and display various information related to the work. This information terminal T1 is configured, for example, by a device such as a personal computer, smartphone, or tablet terminal.

[0025] The information terminal T1 includes an obstacle classification processing unit t11, an obstacle information storage unit t12, and an operation unit t13. These will be described in detail later, but the operation unit t13 is an input device that accepts various operations from an operator, and is configured by a device such as a keyboard or a touch panel.

[0026] The management terminal T2 is an information processing device that mainly handles management functions, and sends and receives various information necessary for work between the work vehicle 1 and the information terminal T1, thereby managing and displaying information related to work. This management terminal T2 is configured, for example, by a device such as a personal computer, smartphone, or tablet terminal.

[0027] 2. Configuration of Work Vehicle 1 Figure 2 is a side view of the work vehicle 1 according to an embodiment of the present invention. Figure 3 is a plan view of the work vehicle 1 according to an embodiment of the present invention. In this specification, unless otherwise specified, the side in the direction of travel of the work vehicle 1 indicated by the arrow F in Figures 2 and 3 is referred to as the front, the left side as viewed in the direction of travel of the work vehicle 1 is referred to as the "left," and the opposite side is referred to as the "right." The body of the work vehicle 1 is also simply referred to as the "machine body."

[0028] The work vehicle 1 in this embodiment is configured as a tractor, but is not limited to this and may be a rice transplanter, a combine harvester, a pest control machine, a harvester, etc. The work vehicle 1 is also configured as a so-called robot tractor that can automatically travel in a field R along a target travel path L.

[0029] The work vehicle 1 is equipped with a driving device M that drives the machine body, and the driving device M is equipped with an engine m1, front wheels m2, rear wheels m3, a transmission m4, a front axle m5, a rear axle m6, a steering wheel m7, etc., and is configured so that the steering wheel m7 can be automatically steered under the control of the driving control device C1.

[0030] A work machine WM that performs work on the field R is attached to the rear of the work vehicle 1. The work machine WM is drive-controlled by a work machine control device C2. The work machine WM may be, for example, a tiller, a brush cutter, a plow, a fertilizer applicator, or a seed sower, and is detachable from the main body of the work vehicle 1. In this embodiment, a tiller is attached.

[0031] The obstacle detection sensor S1 is an ultrasonic sensor that functions to detect obstacles around the work vehicle 1. This obstacle detection sensor S1 is equipped with a front obstacle sensor s11 that detects obstacles in front of the work vehicle 1, and side obstacle sensors s12, s12 that detect obstacles on the sides of the work vehicle 1.

[0032] The camera S2 captures images of the surroundings of the work vehicle 1 and acquires digital image data. The cameras S2 are installed on the front, rear, left and right sides of the body of the work vehicle 1, and are capable of capturing images in all directions of the work vehicle 1.

[0033] The positioning device S3 has a receiving antenna that receives radio waves from GNSS satellites, and is capable of acquiring position information of the current position Pa of the work vehicle 1 based on the radio waves received by the receiving antenna.

[0034] The inertial measurement unit S4 is a device (so-called IMU) that measures the three-axial tilt, acceleration, and orientation of the aircraft, and enables calculation of the traveling direction of the aircraft and correction of position information acquired by the positioning device S3. In addition to this, a separate orientation sensor may be provided to measure the orientation.

[0035] The optical imaging device S5 is a 3D lidar that acquires three-dimensional imaging information (3D image data) by irradiating an object with pulsed optical radar light and capturing scattered light. Analysis of the acquired three-dimensional imaging information enables the optical imaging device S5 to detect the distance and shape of an object within the optical radar's illumination range (detection range). This allows the optical imaging device S5 to acquire three-dimensional imaging information indicating the position and shape of an obstacle OB detected by the obstacle detection sensor S1. The optical imaging device S5 also includes a front optical imaging device s51 that detects objects in front of the work vehicle 1 and a rear optical imaging device s52 that detects objects behind the work vehicle 1. The illumination range (detection range) of the optical imaging device S5 can be adjusted vertically and horizontally.

[0036] 4 is an explanatory diagram for explaining the target travel route L of the work vehicle 1. Here, the target travel route L refers to a travel route that is the target of the work vehicle 1 during autonomous driving, and information indicating the target travel route L includes position information that indicates the trajectory of the target travel route L. Here, the target travel route L is calculated, for example, by the travel control device C1 in accordance with the following design procedure.

[0037] First, field information indicating the shape, position, and area of ​​the field is obtained from the management terminal T2, and the field area R is divided into a headland traveling area R1 where work is performed by traveling in a circular manner, and a straight traveling area R2 where work is performed by traveling in a straight line. Here, the headland traveling area R1 is set as a frame-shaped area with a preset working width W, and a rectangular straight traveling area R2 is set inside the headland traveling area R1.

[0038] Next, a headland traveling path l1 that travels in a circular manner within the headland traveling region R1 is designed (work paths VI to IX). Subsequently, a plurality of straight-line traveling paths l2 that travel in a straight line within the straight-line traveling region R2 are designed (work paths I to V). Here, the straight-line traveling paths l2 are spaced apart at a distance substantially equal to the preset working width W to prevent overlapping work from being performed at the same point. Note that point PS indicates the work start point of the work vehicle 1 within the headland traveling region R1, and point PE indicates the work end point.

[0039] Next, a non-working path 13 is designed, which is a path that does not involve work, for moving between the straight-line traveling paths 12 in a single stroke, turning between the straight-line traveling paths 12, and moving from the straight-line traveling path 12 to the headland traveling path 11. Information indicating the calculated target traveling path L as described above is stored in the traveling control device C1.

[0040] Next, the driving control device C1 sets the travel order of the work route (work routes I to IX in the illustrated example). This travel order is set based on predetermined rules, but the worker can also change it to any travel order by operating the information terminal T1. This travel order setting information is stored in the driving control device C1 along with information indicating the target travel route L. For example, in the illustrated example of FIG. 4 , the driving control device C1 sets the travel order in the following order: work route I, work route II, work route III, work route IV, work route V, work route VI, work route VII, work route VIII, and work route IX. As a result, the driving control device C1 acquires position information using the positioning device S3, while controlling the driving device M by the automatic driving processing unit c11 to travel on the target travel route L in the set travel order, thereby enabling automatic driving.

[0041] 4. Means for Recognizing Work Machine WM> The work vehicle 1 is capable of recognizing the attached work machine WM using the optical imaging device S5 by the work machine recognition unit c21. The means for recognizing the work machine WM by the work machine recognition unit c21 will be described below with reference to Figures 5, 6, 7A, and 7B.

[0042] FIG. 5 is a schematic plan view of the work vehicle showing the detection range of the optical imaging device S5, and FIG. 6 is a schematic side view. In the figures, area X1 indicates the detection range of the front optical imaging device s51, and area X2 indicates the detection range of the rear optical imaging device s52. As shown in FIGS. 5 and 6, the front optical imaging device s51 and the rear optical imaging device s52 are each configured to include a portion of the left and right rear wheels m3 as their detection ranges. As a result, the work implement recognition unit c21 analyzes the three-dimensional imaging information acquired by the optical imaging device S5 and compares the preset width of the left and right rear wheels m3, m3 with the width of the work implement WM included in the three-dimensional imaging information to calculate the working width W of the work implement WM attached to the work vehicle 1, and stores this in the work implement memory unit c22. This enables automatic setting of the working width W of the attached work implement WM.

[0043] At this time, the work implement recognition unit c21 recognizes the shape of the attached work implement WM as follows. Fig. 7A is an explanatory diagram illustrating a method for recognizing the shape of the work implement WM. Fig. 7B is the same explanatory diagram. More specifically, Fig. 7A shows the shape X3 of the rear body of the work vehicle 1 before the work implement WM is attached, which is imaged by the optical imaging device S5, and Fig. 7B shows the shape X3 of the rear body of the work vehicle 1 after the work implement WM is attached, which is imaged by the optical imaging device S5, and the shape X4 of the work implement WM. When the work implement recognition unit c21 determines that the work implement WM has been attached by known means, it compares the shape X3 of the rear body that was previously imaged with the shape X3 of the rear body that was imaged after the work implement WM was attached, and the shape X4 of the work implement WM, and recognizes the shape X4 of the work implement WM by performing processing to remove the shape X3 of the rear body that was previously imaged from the shape X3 of the rear body that was imaged after attachment and the shape X4 of the work implement WM. The information relating to the shape X4 of the work machine WM generated in this manner is stored in the work machine storage unit c22. Note that when storing the information relating to the shape X4 of the work machine WM, the amount of data required for storage can be reduced by storing the information as a point cloud image.

[0044] According to this configuration, by storing shape patterns for each type of work machine WM (for example, cultivator, brush cutter, plow, fertilizer applicator, or seed sower) in advance in the work machine memory unit c22, the work machine recognition unit c21 can automatically determine the type of the attached work machine WM from the information on the shape X4 of the work machine WM acquired by executing the above process, thereby causing the work execution unit c23 to automatically execute appropriate control according to the type of work machine WM. Furthermore, automatic setting of the working width W of the attached work machine WM makes it possible to appropriately execute the processing related to obstacle avoidance, which will be described later.

[0045] 5. Setting of Obstacle Avoidance Range When an obstacle is detected by the obstacle detection sensor S1, the obstacle avoidance processing unit c12 executes processing to avoid the obstacle. This processing will be described in detail later, but the obstacle avoidance range (i.e., the range for avoiding the obstacle) required for determining an avoidance route by the avoidance route determination unit c13 can be set in advance by the avoidance range setting unit c14 before starting work. Note that this setting can be made by operating the operation unit t13 of the information terminal T1.

[0046] The obstacle avoidance range can be set in the following three patterns. FIG. 8A is an explanatory diagram illustrating the setting of the obstacle avoidance range in the first pattern (minimum range). The first obstacle avoidance range D1 in the first pattern (minimum range) is a rectangular area defined by setting a forward avoidance distance d1, a rearward avoidance distance d2, a leftward avoidance distance d3, and a rightward avoidance distance d4 relative to the center reference position Pr of the body of the work vehicle 1. The range of the first avoidance range D1 is desirably set to correspond to the front-to-rear width and vehicle width of the work vehicle 1. When the left-to-right width of the first avoidance range D1 is smaller than the working width W, it may be configured to be automatically corrected to the working width W and set. Note that the center reference position Pr is a reference position that corresponds to the current position Pa of the work vehicle 1 during autonomous traveling. By making it possible to set the avoidance distances d3 and d4 to the left and right, respectively, relative to the center reference position Pr of the body of the work vehicle 1, it becomes possible to change the avoidance margin, for example, toward the field side or the road side, thereby improving convenience.

[0047] 8B is an explanatory diagram illustrating the setting contents of the obstacle avoidance range in the second pattern (addition of left and right margin widths). The second obstacle avoidance range D2 in the second pattern (addition of left and right margin widths) is a rectangular area defined by adding a left avoidance margin width d5 ​​and a right avoidance margin width d6 to the left and right sides in addition to the first avoidance range D1. The left avoidance margin width d5 ​​and the right avoidance margin width d6 can each be set to any width. This second avoidance range D2 allows for avoidance with more margin on the left and right sides of the work vehicle 1 than the first avoidance range D1.

[0048] 8C is an explanatory diagram illustrating the setting contents of the obstacle avoidance range in the third pattern (addition of front, rear, left and right margins). The third obstacle avoidance range D3 in the third pattern (addition of front, rear, left and right margins) is a rectangular area defined by adding a left avoidance margin width d5 ​​and a right avoidance margin width d6 to the left and right sides of the first avoidance range D1, and further adding a front margin width d7 and a rear margin width d8. The front margin width d7 and the rear margin width d8 can each be set to any width. This third avoidance range D3 allows for avoidance with more margin in the front, rear, left and right directions of the work vehicle 1 than the first avoidance range D1.

[0049] 6. Determining an Obstacle Avoidance Route> FIG. 9A is an explanatory diagram of an obstacle avoidance route L2 within a first avoidance range D1, FIG. 9B is an explanatory diagram of an obstacle avoidance route L2 within a second avoidance range D2, and FIG. 9C is an explanatory diagram of an obstacle avoidance route L2 within a third avoidance range D3.

[0050] The avoidance route determination unit c13 is capable of calculating an avoidance route L2 for each of the set first avoidance range D1, second avoidance range D2, and third avoidance range D3. The obstacle avoidance processing unit c12 can avoid obstacles detected during automated driving by correcting the target driving path L based on the calculated avoidance route L2. The operator can set in advance which of the first avoidance range D1, second avoidance range D2, and third avoidance range D3 avoidance route L2 will be used to avoid an obstacle, and this setting can be set using the information terminal T1 and can be changed as needed.

[0051] The avoidance route determination unit c13 uses the same basic method for calculating the avoidance route L2 for any of the set first avoidance range D1, second avoidance range D2, and third avoidance range D3. The avoidance route determination unit c13 calculates an avoidance start point Pst, avoidance passing point Pmd, and avoidance end point Ped based on the set first avoidance range D1, second avoidance range D2, and third avoidance range D3, and calculates the avoidance route L2 by connecting the calculated avoidance start point Pst, avoidance passing point Pmd, and avoidance end point Ped.

[0052] The avoidance start point Pst is the position of the center reference position Pr on the target traveling path L when the leading edges of the first avoidance area D1, the second avoidance area D2, and the third avoidance area D3 come into contact with an obstacle. The avoidance passing point Pmd is to the right (or left) of the obstacle and is the position of the center reference position Pr when the left and right edges of the first avoidance area D1, the second avoidance area D2, and the third avoidance area D3 come into contact with the obstacle. Furthermore, the avoidance end point Ped is the position of the center reference position Pr on the target traveling path L when the trailing edges of the first avoidance area D1, the second avoidance area D2, and the third avoidance area D3 come into contact with an obstacle.

[0053] 7. Setting of Obstacle Contact Prevention Range As described above, when an obstacle is detected by the obstacle detection sensor S1, the obstacle avoidance processing unit c12 executes processing to avoid the obstacle. Details of this processing will be described later, but the contact prevention processing unit c15 can set the obstacle contact prevention range (i.e., the range for preventing contact with the obstacle) required to prevent contact with the obstacle in advance before starting work using the contact prevention range setting unit c16. This setting can be made by operating the operation unit t13 of the information terminal T1.

[0054] 10A is an explanatory diagram illustrating the setting of the obstacle contact prevention range (centered on the work vehicle). The contact prevention range is made up of a travel stop range D4, which is a range within which the contact prevention processing unit c15 stops travel due to the intrusion of an obstacle, and a travel deceleration range D5, which is a range within which the speed is reduced below the normal speed (a preset normal speed during automatic travel) due to the intrusion of an obstacle. The travel deceleration range D5 is set around the travel stop range D4.

[0055] The travel stopping range D4 is a rectangular area defined by setting a front stopping distance d41, a rear stopping distance d42, a left stopping distance d43, and a right stopping distance d44 on the front, rear, left, and right sides relative to the center reference position Pr of the work vehicle 1. The worker can set any distance for each of these by operating the operation unit t13, but it is desirable to set distances that are larger than the front-to-rear width and vehicle width of the work vehicle 1 to prevent contact with obstacles.

[0056] The driving deceleration range D5 is a rectangular area defined by setting the front deceleration distance d51, rear deceleration distance d52, left deceleration distance d53, and right deceleration distance d54 in the front, rear, left, and right directions in addition to the front-to-back, front-to-back, left-to-right width of the driving stop range D4 relative to the center reference position Pr of the work vehicle 1.

[0057] If an obstacle enters the set travel deceleration range D5 during automatic travel, the contact prevention processing unit c15 decelerates the work vehicle 1 until the obstacle moves out of the travel deceleration range D5, and if the obstacle enters the set travel stop range D4, the contact prevention processing unit c15 stops the work vehicle 1 until the obstacle moves out of the travel stop range D4. This effectively prevents contact with obstacles.

[0058] 10B is an explanatory diagram illustrating the setting of the obstacle contact prevention range (work implement center). In addition to being set relative to the center reference position Pr of the work vehicle 1 as described above, the contact prevention range can also be set relative to the center reference position Pwm of the work implement WM. Here, the center reference position Pwm is a reference position that is set a predetermined distance behind the center reference position Pr.

[0059] As described above, the contact prevention range at the center of the work machine WM is a rectangular area defined by setting the front stopping distance d61, rear stopping distance d62, left stopping distance d63, and right stopping distance d64 in the front, rear, left, and right directions relative to the center reference position Pwm of the work machine WM. Also, the travel deceleration range D7 is a rectangular area defined by setting the front deceleration distance d71, rear deceleration distance d72, left deceleration distance d73, and right deceleration distance d74 in the front, rear, left, and right directions in addition to the front, rear, left, and right width of the travel stop range D6 in relation to the center reference position Pwm of the work machine WM.

[0060] If an obstacle enters the set travel deceleration range D7 during automatic travel, the contact prevention processing unit c15 decelerates the work vehicle 1 until the obstacle moves out of the travel deceleration range D7, and if the obstacle enters the set travel stop range D6, the contact prevention processing unit c15 stops the work vehicle 1 until the obstacle moves out of the travel stop range D6. In this way, by setting a contact prevention range centered on the work implement WM and avoiding contact, it is possible to effectively prevent the work implement WM from coming into contact with an obstacle.

[0061] When an obstacle is present in the travel deceleration range D5 or travel deceleration range D7, the contact prevention processing unit c15 decelerates the work vehicle 1, but when the obstacle is present in the travel stop range D4 or travel stop range D6, it stops the travel of the work vehicle 1. In other words, for safety reasons, when the conditions for both travel deceleration and stoppage are met, stopping is prioritized.

[0062] Furthermore, when an obstacle is present in the travel deceleration range D5 or D7, the contact prevention processing unit c15 is configured to transmit digital image data of the obstacle acquired by the camera S2 to the management terminal T2, and output the image to the camera image output unit t21 so that the manager can confirm it. At this time, the alert output unit t22 may be configured to output an alert to notify the manager. At this time, the work vehicle 1 may be configured to output an alarm such as a buzzer to the surrounding area. This improves safety.

[0063] 8. Processing Procedure When Obstacle Detected> FIG. 11 is a flowchart showing the processing procedure of the automated driving system A when an obstacle is detected. When an obstacle is detected by the obstacle detection sensor S1, the obstacle avoidance processing unit c12 notifies the information terminal T1 that an obstacle has been detected. Upon receiving the notification that an obstacle has been detected, the information terminal T1 acquires three-dimensional image information of the obstacle from the optical imaging device S5. Next, the obstacle classification processing unit t11 ​​of the information terminal T1 determines whether the obstacle has moved based on the acquired three-dimensional image information, and classifies the detected obstacle by referring to the obstacle pattern information (which stores the shape, size, etc. of the obstacle) stored in the obstacle information storage unit t12. Note that obstacle classification may be performed by analyzing digital image data of the obstacle OB acquired by the camera S2. Furthermore, whether the obstacle has moved can be determined by comparing three-dimensional image information captured at different times and calculating a change in the position of the obstacle, taking into account the traveling speed and direction of the work vehicle 1.

[0064] FIG. 12 is an illustration of a detected obstacle. As shown in FIG. 12, the obstacle classification processing unit t11 ​​classifies the detected obstacle OB into the following three patterns. The first pattern is a stationary obstacle (immobile obstacle ob1), such as a utility pole or a tree. The second pattern is a moving obstacle, such as another work vehicle ob2. The third pattern is a moving obstacle, such as a person or an animal ob3. For example, if the obstacle OB does not move within a predetermined time, it can be determined to be the first pattern. If the obstacle OB moves (i.e., if the movement speed of the obstacle OB changes at a speed different from the movement speed of the work vehicle 1), the second or third pattern can be determined by determining whether the shape, size, volume, etc. of the obstacle OB are within specified ranges.

[0065] After classifying the detected obstacle OB, the obstacle classification processing unit t11 ​​transmits information regarding the classification result to the work vehicle 1 (step S1). In this way, by having the information terminal T perform processing related to the classification of the detected obstacle OB, the load related to information processing on the work vehicle 1 is distributed, enabling rapid processing.

[0066] When the work vehicle 1 acquires information regarding the classification result of the detected obstacle OB, it performs the following processing based on the classification result. If the obstacle OB is an immovable obstacle ob1, the avoidance route determination unit c13 determines an avoidance route L2 and executes obstacle avoidance (steps S4 and S5). At this time, it is preset which of the first avoidance range D1, second avoidance range D2, and third avoidance range D3 should be used to avoid the obstacle.

[0067] When the work vehicle 1 has completed avoiding the obstacle OB, it transmits the obstacle position information to the management terminal T2 and records the position of the obstacle OB in the field map storage unit t23 and the obstacle position recording unit t24 (step S6). At this time, digital image data of the obstacle OB acquired by the camera S2 may also be recorded.

[0068] Furthermore, if the obstacle OB is another work vehicle ob2, information regarding the preset contact prevention range for the obstacle OB is acquired (step S8), and the contact prevention processing unit c15 executes contact prevention processing. During automatic driving, if the obstacle OB enters the preset deceleration range D5 or D7, the work vehicle 1 is decelerated until the obstacle OB moves out of the deceleration range D5 or D7. If the obstacle OB enters the preset stop range D4 or D6, the work vehicle 1 is stopped until the obstacle OB moves out of the stop range D4 or D6. This effectively prevents contact with the obstacle OB. Note that if the obstacle OB is outside the preset deceleration range D5 or D7 and the stop range D4 or D6, automatic driving is performed at a normal speed. Then, when the obstacle OB is no longer detected (moves out of the detection range of the obstacle detection sensor S1), the processing ends (step S9).

[0069] If the obstacle OB is a person or animal ob3, an alarm sound (buzzer) is output from the work vehicle 1 to warn people of danger or to urge animals to leave. Then, information relating to a preset contact prevention range for the obstacle OB is acquired (step S8), and the contact prevention processing unit c15 executes contact prevention processing (step S9).

[0070] Here, if the detected obstacle OB is a small animal such as a bird (a moving animal with a predetermined set size and volume or less), it does not fall under any of patterns 1 to 3, and it is determined that no avoidance is necessary, and the processing is terminated (N in step S10).

[0071] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and it goes without saying that the present invention can be modified appropriately within the scope of the technical concept.

[0072] 9. Setting of Avoidance Route L2 Figure 13 is an explanatory diagram of an obstacle avoidance route L2 according to another embodiment. Figure 13 shows an example in which the avoidance route determination unit c13 is configured to change the avoidance route L2 depending on the travel speed of the work vehicle 1. In other words, depending on the travel speed of the work vehicle 1, the avoidance angle of the avoidance route L2 (the angle between the straight direction of the target travel path L and the travel direction changed to avoid the obstacle OB) is corrected to a more obtuse angle if the speed is faster than a predetermined speed, and to a more acute angle if the speed is slower than the predetermined speed. 13, if the traveling speed is fast, it will be a first avoidance start point Pst1, and if it is slow, it will be a second avoidance start point Pst2, and the avoidance pass-through points Pmd are designed as a first avoidance pass-through point Pmd1 and a second avoidance pass-through point Pmd2 before and after the obstacle OB, and if the traveling speed is fast, it will be a first avoidance end point Ped1, and if it is slow, it will be a second avoidance end point Ped2, and these are connected to determine the avoidance route L2. In other words, if the traveling speed is fast, the avoidance route L2 will be a route that passes through the first avoidance start point Pst1, the first avoidance pass-through point Pmd1, the second avoidance pass-through point Pmd2, and the first avoidance end point Ped1, and if it is slow, it will be a route that passes through the second avoidance start point Pst2, the first avoidance pass-through point Pmd1, the second avoidance pass-through point Pmd2, and the second avoidance end point Ped2. Furthermore, the faster the traveling speed, the more desirable it is to set the first avoidance start point Pst1 closer to the traveling direction and the first avoidance end point Ped1 further behind in the traveling direction, and the slower the traveling speed, the more desirable it is to set the second avoidance start point Pst2 further behind in the traveling direction and the second avoidance end point Ped2 closer to the traveling direction. This makes it possible to prevent slipping and improve safety. In addition, it becomes possible to design an appropriate avoidance route L2 taking speed into consideration.

[0073] 10. Other Embodiments In FIG. 11 , with emphasis on work continuity, the obstacle avoidance processing unit c12 can be configured to generate an avoidance route L2 and execute avoidance when the detected obstacle OB is another work vehicle ob2 (step S7) or a person or animal ob3 (step S10). That is, processes similar to steps S3 to S5 in FIG. 11 are added immediately after step S7 and step S10, respectively. In this case, assuming that the obstacle OB moves, it is desirable for the avoidance route L2 to have a wider obstacle avoidance range in the front, rear, left, and right directions for other obstacles (pattern 2) and people or animals (pattern 3) than for the immovable obstacle ob1, compared to the case of an immovable obstacle (pattern 1). Furthermore, it is desirable for a third avoidance range D3 for an obstacle in the third pattern (adding extra width in the front, rear, left, and right directions) to be automatically selected. Therefore, it is desirable to configure the range for other obstacles (pattern 2) and people / animals (pattern 3) to be expanded by a predetermined set factor (for example, for pattern 2, the front-to-back and left-to-right width of the avoidance range is 1.2 times that of pattern 1, and for pattern 3, 1.5 times) compared to the case of immovable obstacles (pattern 1). This makes it possible to change the obstacle avoidance route during autonomous driving depending on the obstacle classification results, and to calculate and set a more optimal avoidance route to prevent contact depending on the type of obstacle.

[0074] 11 , if obstacles ob2 and ob3 of pattern 2 or pattern 3 are detected while avoidance of immovable obstacle ob1 is being performed, contact prevention processing (step S9) may be simultaneously performed. That is, even while traveling along avoidance route L2, if obstacles ob2 and ob3 enter the set deceleration ranges D5 and D7, the work vehicle 1 is decelerated until the obstacles move out of the deceleration ranges D5 and D7, and if the obstacles enter the set stop ranges D4 and D6, the work vehicle 1 is stopped until the obstacles move out of the stop ranges D4 and D6, thereby enabling more efficient and safer automated traveling.

[0075] A Automatic driving system 1 Work vehicle M Driving device m1 Engine m2 Front wheels m3 Rear wheels m4 Transmission m5 Front axle m6 Rear axle m7 Steering handle S1 Obstacle detection sensor s11 Front obstacle sensor s12 Side obstacle sensor S2 Camera S3 Positioning device S4 Inertial measurement unit S5 Optical imaging device s51 Front optical imaging device s52 Rear optical imaging device T1 Information terminal T2 Management terminal

Claims

1. An automatic driving system that automatically drives a work vehicle within a field, wherein the work vehicle is equipped with an obstacle detection sensor that detects obstacles, and an optical imaging device that can obtain three-dimensional imaging information indicating the position and shape of the obstacle detected by the obstacle detection sensor, and an obstacle classification processing unit that classifies the obstacles detected from the three-dimensional imaging information, the obstacle classification processing unit classifies the detected obstacles into non-moving obstacles and moving obstacles, and the automatic driving system is configured to be able to change the obstacle avoidance route during automatic driving depending on the obstacle classification results by the obstacle classification processing unit.

2. An automatic driving system as described in claim 1, comprising an avoidance route determination unit which determines the avoidance route, and an avoidance range setting unit which is capable of setting an avoidance range for an obstacle, wherein the avoidance route determination unit is configured to determine an avoidance route based on the avoidance range set by the avoidance range setting unit, and the avoidance range is an area defined by respectively setting a forward avoidance distance, a rearward avoidance distance, a leftward avoidance distance, and a rightward avoidance distance with respect to a central reference position of the body of the work vehicle.

3. The automatic driving system described in claim 2, characterized in that the work vehicle is configured to automatically recognize the type of attached work equipment by obtaining information regarding the shape of the attached work equipment from the three-dimensional imaging information, thereby calculating the working width of the attached work equipment, and setting the avoidance range based on the calculated working width.

4. An automated driving system as described in any one of claims 1 to 3, further comprising a contact prevention processing unit which prevents contact with an obstacle, wherein the contact prevention processing unit is configured to decelerate the work vehicle until the obstacle moves out of the driving deceleration range when an obstacle enters a set driving deceleration range during automated driving, and to stop the work vehicle until the obstacle moves out of the driving stop range when an obstacle enters a set driving stop range.

5. The automatic driving system described in claim 2, characterized in that the avoidance route determination unit reduces the avoidance angle of the avoidance route depending on the driving speed of the work vehicle during automatic driving, when the driving speed is faster than a predetermined speed, and increases the avoidance angle when the driving speed is slower than the predetermined speed.

Images