Autonomous travel system for work vehicle

Abstract

To provide a technique associated with an autonomous travel system for a farm work vehicle, enabling the farm work vehicle to autonomously travel along a ridge with high precision, regardless of the shape change of the ridge.SOLUTION: An autonomous travel system for a farm work vehicle makes a farm work vehicle 10, which performs farm work by straddling a ridge 5 in a farm field, autonomously travel along the ridge 5. The autonomous travel system comprises: the farm work vehicle 10 comprising a pair of travel parts 20, provided at intervals so as to travel on travel planes 7I, 7II on both sides of one line of the ridge 5; a ridge tracking LiDAR 50 which is installed on the farm work vehicle 10 so as to incorporate the travel planes 7I, 7II on both sides of the ridge 5, straddled by the farm work vehicle 10, into a detection area; and a controller for, on the basis of information on the two lines of the travel planes 7I, 7II, estimating a center line RCL of the ridge 5 straddled by the farm work vehicle 10, and on the basis of an error between the center line RCL of the ridge 5 estimated and a center line of the farm work vehicle 10, making the farm work vehicle 10 travel along the ridge 5.SELECTED DRAWING: Figure 13

Description

Technical Field

[0001] The present invention relates to an autonomous driving system for a work vehicle, and more particularly to an autonomous driving system for a work vehicle that autonomously drives the work vehicle along a ridge.

Background Art

[0002] Conventionally, in order to save labor and improve efficiency in agricultural work, various autonomous driving systems have been proposed that automatically follow ridges for agricultural work vehicles that perform agricultural work across ridges in a field. Some of such autonomous driving systems control the positional relationship between the ridge and the planting unit based on the positional change of a pressure-sensitive ridge detection plate that comes into contact with the ridge. However, in such an autonomous driving system, there is a problem that the ridge may be damaged or shaved by the ridge detection plate, and the detection accuracy is low because it receives vibrations caused by the contact between the ridge detection plate and the ridge.

[0003] Therefore, for example, in Patent Document 1, a traveling vehicle is equipped with a planting unit that can be adjusted to move left and right, and an ultrasonic ridge sensor for detecting the distance to a transplanting ridge for transplanting seedlings is provided in the planting unit. Based on the output signal of the ridge sensor, a transplanter has been proposed that controls the left and right movement of the planting unit to automatically follow the planting unit along the transplanting ridge.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the device of the above Patent Document 1, since an ultrasonic ridge sensor that does not come into contact with the ridge is used, it is possible to suppress damaging or shaving the ridge.

[0006] However, in the case of the one in Patent Document 1, when detecting the distance from the ridge surface with a ridge sensor, if the shape of the ridge is distorted, it becomes difficult to detect the distance from the ridge. Therefore, there is a problem that the robustness (the property of being less affected by disturbances) against the shape change of the ridge is low.

[0007] The present invention has been made in view of such a point, and an object thereof is to provide a technique for autonomously driving a work vehicle along a ridge with high accuracy in an autonomous driving system of a work vehicle without being influenced by the shape change of the ridge.

Means for Solving the Problem

[0008] In order to achieve the above object, in the autonomous driving system of a work vehicle according to the present invention, among a point group composed of a plurality of points on the ridge and on the traveling surface, only the point group on a flat surface extending in the horizontal direction is extracted to estimate a point on the center line of the ridge group.

[0009] Specifically, the present invention is directed to an autonomous driving system for a work vehicle that autonomously drives a work vehicle along a ridge while straddling the ridge group in a farm field having a ridge group composed of a plurality of ridges and a traveling surface formed between adjacent ridges.

[0010] And this autonomous driving system includes a distance sensor installed on the work vehicle, an estimation means for estimating the center line of the ridge group straddled by the work vehicle based on the information detected by the distance sensor, and a control means for driving the work vehicle along the ridge group based on the error between the center line of the ridge group estimated by the estimation means and the center line of the work vehicle. In a point group composed of a plurality of points on the traveling surface located on both sides of the ridge, a point on the center line of the ridge group is estimated by extracting a point group on a flat surface extending in the horizontal direction. It is characterized by being configured as such.

[0011] According to this configuration, rather than the ridges themselves, where the environment, shape, etc. are likely to change significantly due to the growth of planted crops, etc., based on information regarding a flat surface that extends in the horizontal direction and where changes in the environment, shape, etc. are smaller than those of the ridges, the estimation means estimates the center line of the ridge group. Therefore, even if the base of a ridge, etc. has collapsed locally, the center line of the ridge group can be accurately estimated.

[0012] Moreover, since the center line of the ridge group is estimated based on information regarding a flat surface that extends in the horizontal direction, the error is reduced by half compared to the case where the center line of the ridge group is estimated based on information regarding either one of the running surfaces. Therefore, the estimation accuracy of the center line of the ridge group can be further enhanced.

[0013] As described above, according to the present invention, since the center line of the ridge group is estimated based on information regarding a flat surface that extends in the horizontal direction and where changes in the environment, shape, etc. are relatively small, the agricultural work vehicle can be autonomously run along the ridges with high accuracy without being affected by changes in the shape of the ridges.

[0014] Furthermore, a point group composed of a plurality of points on each normal plane in the inclined portion of the ridge and a point group composed of a plurality of points on the top surface of the ridge are acquired, and only the flat point group among them is configured to be extracted.

[0015] Also, the estimation means excludes the point groups on the inclined normal planes on both sides of the ridge group from among the point groups on the ridge group and on the two running surfaces on both sides of the ridge group, and excludes the point group on the top surface of the ridge group by extracting the point group included in a predetermined height range that is the height near the lower end of the ridge group. Among the point groups on each of the running surfaces that are the extracted point groups, the midpoint between the point closest to the ridge group among the point groups on one of the running surfaces and the point closest to the ridge group among the point groups on the other running surface is estimated as the point on the center line of the ridge group.

[0016] As another solution for achieving the above object, the present invention is directed to an autonomous driving system for a work vehicle that performs work across a group of ridges in a field having a group of ridges formed of a plurality of ridges and a traveling surface formed between adjacent ridges, and autonomously drives the work vehicle along the ridges.

[0017] The autonomous driving system includes a distance sensor installed on the work vehicle, an estimation means for estimating the center line of the group of ridges straddled by the work vehicle based on the information detected by the distance sensor, and a control means for driving the work vehicle along the group of ridges based on the error between the center line of the group of ridges estimated by the estimation means and the center line of the work vehicle. The system is configured to estimate a point on the center line of the group of ridges from a point group composed of a plurality of points on the traveling surface located on both sides of the ridges.

Advantages of the Invention

[0018] As described above, according to the autonomous driving system for an agricultural work vehicle according to the present invention, the work vehicle can be autonomously driven along the group of ridges with high accuracy without being affected by the shape change of the group of ridges.

Brief Description of the Drawings

[0019]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0020] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings.

[0021] -Autonomous Driving System- FIG. 1 is a diagram schematically showing an autonomous driving system 1 of a farming work vehicle (work vehicle) 10 according to the present embodiment. This autonomous driving system 1 enables the farming work vehicle 10 to autonomously drive in a farm field 3 having a plurality of ridges 5 and a driving surface 7 formed between adjacent ridges 5, 5, and also on a headland 9 extending in the arrangement direction of the ridges 5 on both outer sides in the longitudinal direction of the ridges 5, without requiring an operation by an operator or the like.

[0022] More specifically, this autonomous driving system 1 causes the farming work vehicle 10 that performs farming work while straddling the ridges 5 in the farm field 3 to autonomously drive along the longitudinal direction of the ridges 5, and also causes the farming work vehicle 10 to autonomously exit from the ridge 5 to the headland 9, drive on the headland 9, and enter from the headland 9 to the ridge 5. To enable such autonomous driving, the autonomous driving system 1 of the present embodiment includes, as shown in FIG. 1, markers 80 erected at both end portions 5f in the longitudinal direction of every other ridge 5, the farming work vehicle 10, a ridge-following LiDAR 50, a marker detection LiDAR 60 (see FIG. 3 etc.), and a control device 70 (see FIG. 2).

[0023] <Marker> The marker 80 is, for example, a white wooden stake, and as shown in FIG. 1, is driven into both end portions 5f in the longitudinal direction of every other ridge 5. Note that the material and shape of the marker 80 are not particularly limited. Also, in the present embodiment, markers 80 are erected on every other ridge 5, but as will be described later, when the farming work vehicle 10 straddles the marker 80, markers 80 may be erected at both end portions 5f in the longitudinal direction of all the ridges 5.

[0024] <Farming work vehicle> FIG. 2 is a side view schematically showing the agricultural work vehicle 10, FIG. 3 is a plan view schematically showing the agricultural work vehicle 10 with the crawler pitch widened, and FIG. 4 is a plan view schematically showing the agricultural work vehicle 10 with the crawler pitch narrowed. The agricultural work vehicle 10 performs a weeding operation while straddling the ridge 5 in the field 3. As shown in FIGS. 2 to 4, it includes a pair of left and right traveling units 20, a gantry unit 30, a gantry lifting mechanism 36, a weeding attachment 40, an attachment lifting mechanism 45, a ridge-following LiDAR 50, a marker detection LiDAR 60, and a control device 70.

[0025] The pair of left and right traveling units 20 are provided spaced apart from each other in the machine width direction so as to travel on the traveling surfaces 7, 7 on both sides of a single ridge 5, respectively. As shown in FIG. 2, each traveling unit 20 has a drive wheel 21, a driven wheel 22, two idler wheels 23, 24, a frame 25, a crawler belt 26, a traveling motor unit 27, and a traveling battery 29. The drive wheel 21, the driven wheel 22, and the two idler wheels 23, 24 are rotatably supported by the frame 25. The crawler belt 26 is wound around the drive wheel 21, the driven wheel 22, and the two idler wheels 23, 24 so as to be externally connected. The traveling motor unit 27 is a unit in which a motor and a speed reducer are integrated, and is disposed in an in-wheel shape on the drive wheel 21. The traveling battery 29 is disposed on the frame 25 above the traveling motor unit 27.

[0026] Each traveling unit 20 is configured to travel on the traveling surface 7 by the driving force of the drive wheel 21 (traveling motor unit 27) driven by the electric power supplied from the traveling battery 29, while the crawler belt 26 is guided by the driven wheel 22 and the two idler wheels 23, 24. Note that the forward movement (forward rotation), backward movement (reverse rotation), and stop of each traveling unit 20 are controlled by the control device 70.

[0027] As shown in FIGS. 3 and 4, the gantry portion 30 is formed in a substantially rectangular shape in plan view and is provided above the traveling portions 20 so as to span the pair of traveling portions 20. The gantry portion 30 has a pair of left and right vertical frame members 31 extending in the longitudinal direction of the machine body, and first to fourth horizontal frame members 32, 33, 34, 35 connecting the pair of left and right vertical frame members 31 in the machine body width direction. As shown in FIG. 2, the pair of left and right vertical frame members 31 are respectively connected to the frames 25 of the pair of left and right traveling portions 20 via a gantry elevating mechanism 36. Thus, by changing the width of the gantry portion 30, the crawler pitch is changed.

[0028] FIG. 5 is a diagram schematically explaining the crawler pitch variable structure. As shown in FIG. 5, the first to fourth horizontal frame members 32, 33, 34, 35 have a pair of left and right outer pipe portions 32a, 33a, 34a, 35a and inner pipe portions 32b, 33b, 34b, 35b fitted inside the pair of left and right outer pipe portions 32a, 33a, 34a, 35a. Among the first to fourth horizontal frame members 32, 33, 34, 35, the second horizontal frame member 33 is provided with a width variable screw portion 33c.

[0029] In this gantry portion 30, when the width variable screw portion 33c is manually rotated in one direction, as shown by the black arrows in FIG. 5, in the second horizontal frame member 33, the left and right outer pipe portions 33a approach each other, and the inner pipe portion 33b is adapted to fit within the left and right outer pipe portions 33a. Accordingly, also in the first, third, and fourth horizontal frame members 32, 34, 35, the inner pipe portions 32b, 34b, 35b fit within the left and right outer pipe portions 32a, 34a, 35a, and as shown in FIG. 4, the interval in the machine body width direction of the pair of left and right vertical frame members 31 is relatively narrowed. Then, since the pair of left and right vertical frame members 31 are respectively connected to the frames 25 of the pair of left and right traveling portions 20, when the width variable screw portion 33c is rotated in one direction, the crawler pitch is relatively narrowed.

[0030] On the other hand, when the variable-width screw portion 33c is manually rotated in the other direction, as shown by the white arrow in Fig. 5, in the second horizontal frame member 33, the left and right outer pipe portions 33a are separated, and the inner pipe portion 33b is exposed from the left and right outer pipe portions 33a. Along with this, in the first, third, and fourth horizontal frame members 32, 34, and 35 as well, the inner pipe portions 32b, 34b, and 35b are exposed from the left and right outer pipe portions 32a, 34a, and 35a, and as shown in Fig. 3, the interval in the machine width direction between the pair of left and right vertical frame members 31 relatively expands, whereby the crawler pitch relatively expands.

[0031] As shown in Fig. 2, the gantry lifting mechanism 36 includes a first link arm 37, a second link arm 38, and an electro-hydraulic cylinder 39. The first and second link arms 37 and 38 form a substantially X shape as shown in Fig. 2 by the intermediate portion of the first link arm 37 and the intermediate portion of the second link arm 38 being swingably connected to each other. The upper end portion of the first link arm 37 is rotatably and slidably connected to the vertical frame member 31, and the lower end portion thereof is rotatably and non-slidably connected to the frame 25 of the traveling unit 20. On the other hand, the upper end portion of the second link arm 38 is rotatably and non-slidably connected to the vertical frame member 31, and the lower end portion thereof is rotatably and slidably connected to the frame 25 of the traveling unit 20. The electro-hydraulic cylinder 39 is fixed to the vertical frame member 31, and the tip of the rod 39a is connected to the upper end portion of the first link arm 37.

[0032] In the pedestal lifting mechanism 36 configured as described above, when the rod 39a of the electro-hydraulic cylinder 39 extends, the upper end of the first link arm 37 and the upper end of the second link arm 38 move apart in the front-rear direction, and the upper end of the first link arm 37 and the lower end of the second link arm 38, as well as the lower end of the first link arm 37 and the upper end of the second link arm 38, approach each other in the vertical direction, causing the pedestal portion 30 to descend. On the other hand, when the rod 39a of the electro-hydraulic cylinder 39 retracts, the upper end of the first link arm 37 and the upper end of the second link arm 38 approach each other in the front-rear direction, and the upper end of the first link arm 37 and the lower end of the second link arm 38, as well as the lower end of the first link arm 37 and the upper end of the second link arm 38, move apart in the vertical direction, causing the pedestal portion 30 to ascend.

[0033] The weeding attachment 40 is attached to the agricultural work vehicle 10 so as to be liftable via an attachment lifting mechanism 45, and is configured to weed weeds and the like growing between the ridges 5 by being towed by the agricultural work vehicle 10. Specifically, the weeding attachment 40 has a cultivator 41 for weeding, a rake 43 (a hoe) for leveling the soil clods discharged from the cultivator 41, and the like.

[0034] <Ridge-following LiDAR> FIG. 6 is a perspective view schematically showing the installation positions of the LiDARs 50 and 60 on the agricultural work vehicle 10. The ridge-following LiDAR (distance sensor) 50 is a 2D-LiDAR with an opening angle of 270°, suitable for measurement and detection in a plane, and measures the distance to an object by measuring the time it takes for the laser light to hit the object and bounce back. As shown in FIG. 6, this ridge-following LiDAR 50 is attached to the central portion in the machine width direction at the front end of the pedestal portion 30 (the first horizontal frame member 32) via the first to third brackets 51, 55, and 65.

[0035] More specifically, the first bracket 51 includes a rectangular rear wall portion 52 that is bolted to the first horizontal frame member 32 of the gantry portion 30 and extends downward, a rectangular horizontal wall portion 53 that extends forward from the lower end portion of the rear wall portion 52, and a rectangular front wall portion 54 that extends downward from the front end portion of the horizontal wall portion 53. The second bracket 55 includes a rectangular support wall portion 56 parallel to the front wall portion 54 and a mounting wall portion 57 that extends forward from the left end portion of the support wall portion 56. Further, the third bracket 65 includes a rectangular support wall portion 66 parallel to the mounting wall portion 57 and a rectangular mounting wall portion 67 that extends to the right side in the machine width direction from the upper end portion of the support wall portion 66. An arcuate long hole 56a that extends in the machine width direction and curves downward is formed through the support wall portion 56, while an arcuate long hole 57a that extends in the front-rear direction and curves obliquely downward is formed through the mounting wall portion 57.

[0036] The second bracket 55 is attached to the first bracket 51 so as to be variable in the left-right angle by fastening the support wall portion 56 to the front wall portion 54 with a bolt 58 slidably inserted into the long hole 56a. The third bracket 65 is attached to the second bracket 55 so as to be variable in the front-rear angle by fastening the support wall portion 66 to the mounting wall portion 57 with a bolt 59 slidably inserted into the long hole 57a. Thus, the ridging LiDAR 50 is attached to the upper surface of the mounting wall portion 67 of the third bracket 65. Therefore, the ridging LiDAR 50 is attached to the gantry portion 30 via the first to third brackets 51, 55, 65 so as to be variable in both the left-right angle and the front-rear angle.

[0037] FIG. 7 is a diagram schematically illustrating the detection direction of the ridging LiDAR 50. As shown in FIG. 7, the ridging LiDAR 50 is attached to the center portion in the machine width direction at the front end portion of the gantry portion 30 in a state where the front-rear angle is set such that the detection plane DP and the ground G form an angle of 30°. Therefore, the ridging LiDAR 50 can detect the distance to the ridges 5 and the traveling surface 7 in front of the agricultural work vehicle 10. Information regarding the ridges 5 and the traveling surface 7 detected by the ridging LiDAR 50 is input to the control device 70.

[0038] <LiDAR for Marker Detection> The LiDAR 60 for marker detection is also a 2D-LiDAR with an opening angle of 270°, similar to the LiDAR 50 for ridge imitation. As shown in FIG. 6, this LiDAR 60 for marker detection is attached to the front end of the right end in the machine width direction of the gantry part 30 via a lifting bracket 61.

[0039] More specifically, the lifting bracket 61 has a rectangular cylindrical support part 62 attached to the front end of the right vertical frame member 31 in the gantry part 30 by welding or the like, a rectangular cylindrical support pipe 63 that is fitted and inserted inside the support part 62 and extends vertically, and a mounting plate 64 provided at the lower end of the support pipe 63. The LiDAR 60 for marker detection is attached to the upper surface of the mounting plate 64.

[0040] A plurality of concave portions 63a arranged at equal intervals in the vertical direction are formed on the left side surface in the machine width direction of the support pipe 63. Also, two concave portions 62a arranged in the vertical direction at the same interval as the concave portions 63a are formed on the left side surface in the machine width direction of the support part 62. Therefore, when the support pipe 63 is fitted and inserted inside the support part 62, the two concave portions 62a of the support part 62 fit into the concave portions 63a arranged in the vertical direction of the support pipe 63.

[0041] When the concave portion 62a of the support part 62 fits into the concave portion 63a of the support pipe 63, it is possible to support the weights of the support pipe 63, the mounting plate 64, and the LiDAR 60 for marker detection. On the other hand, when an operator moves the support pipe 63 up and down, it is formed to a depth such that it comes out of the concave portion 63a of the support pipe 63. That is, the LiDAR 60 for marker detection can be variably adjusted in height with respect to the gantry part 30 by moving the support pipe 63 up and down with respect to the support part 62. Thereby, for example, even when the gantry part 30 is raised by the gantry lifting mechanism 36, it is possible to maintain the height of the LiDAR 60 for marker detection constant by pulling down the support pipe 63.

[0042] FIG. 8 is a diagram schematically illustrating a detection area DA of the marker detection LiDAR 60. In the present embodiment, since the marker detection LiDAR 60 is disposed at the right end in the vehicle width direction at the front end of the agricultural work vehicle 10 and has an opening angle of 270°, as shown in FIG. 8, a range behind the marker detection LiDAR 60 and on the left side in the vehicle width direction becomes a blind spot, while the other ranges become the detection area DA. Note that the detection area DA in FIG. 8 is schematically illustrated for the sake of explanation, and actually, the marker detection LiDAR 60 is configured to be able to detect objects in a farther range. Information regarding the object detected by the marker detection LiDAR 60 is input to the control device 70.

[0043] <Control device> As shown in FIG. 2, the control device 70 is installed on, for example, the gantry portion 30. The control device 70 controls the electro-hydraulic cylinder 39 of the gantry lifting mechanism 36, the attachment lifting mechanism 45, etc., and based on the detection results of the ridge-following LiDAR 50 and the marker detection LiDAR 60, controls the traveling motor unit 27 of the traveling unit 20 to cause the agricultural work vehicle 10 to travel in the field 3 or to travel and turn on the headland 9.

[0044] For example, if the control device 70 rotates the traveling motor units 27 of the left and right traveling units 20 forward together, the agricultural work vehicle 10 moves forward, while if the control device 70 rotates the traveling motor units 27 of the left and right traveling units 20 backward together, the agricultural work vehicle 10 moves backward. Also, if the control device 70 creates a rotational speed difference between the traveling motor units 27 of the left and right traveling units 20, the agricultural work vehicle 10 turns in the direction where the traveling motor unit 27 with the slower rotation is provided. Further, if the control device 70 rotates the traveling motor unit 27 of one traveling unit 20 forward and rotates the traveling motor unit 27 of the other traveling unit 20 backward, the agricultural work vehicle 10 can perform a sharp turn.

[0045] -Autonomous driving- Next, the autonomous driving of the agricultural work vehicle 10 in the present embodiment will be described.

[0046] As described above, the autonomous driving system 1 of the present embodiment causes the agricultural work vehicle 10 to autonomously exit from the ridge 5 to the headland 9, travel on the headland 9, and enter from the headland 9 to the ridge 5, and (2) causes the agricultural work vehicle 10 to autonomously travel along the longitudinal direction of the ridge 5.

[0047] <Regarding (1) Autonomous driving and autonomous turning on the headland> In the present embodiment, when the agricultural work vehicle 10 exits from the ridge 5 to the headland 9, travels on the headland 9, and enters from the headland 9 to the ridge 5, the agricultural work vehicle 10 is caused to travel and turn while simultaneously detecting a plurality of markers 80 by the marker detection LiDAR 60.

[0048] Specifically, when the agricultural work vehicle 10 traveling across the ridge 5 approaches the headland 9, the marker detection LiDAR 60 detects a plurality of markers 80 erected at the longitudinal ends 5f of every other ridge 5. Based on this detection result, the control device 70 acquires the end (end point position) of the ridge 5 during work and causes the agricultural work vehicle 10 to exit from the ridge 5 to the headland 9.

[0049] Here, if the turning center of the agricultural work vehicle 10 is shifted left and right, the position of the center line VCL of the agricultural work vehicle 10 after turning with respect to the headland 9 will be different between the case of turning right and the case of turning left. For this reason, in the present embodiment, when the agricultural work vehicle 10 is turned on the headland 9, the control device 70 is configured to turn the agricultural work vehicle 10 only in the direction in which the marker detection LiDAR 60 is arranged, that is, to the right.

[0050] Therefore, when the exit from the headland 9 is completed, while the marker detection LiDAR 60 detects a plurality of markers 80, the control device 70 turns the agricultural work vehicle 10 to the right (clockwise). Since the turning direction is limited to the direction in which the marker detection LiDAR 60 is arranged, the plurality of markers 80 do not enter the blind spot of the marker detection LiDAR 60, so it is possible to continue detecting the plurality of markers 80 even during turning. In this way, from the exit from the headland 9 to the completion of turning, since the marker detection LiDAR 60 continues to detect a plurality of markers 80, it is possible to continuously calculate the attitude of the agricultural work vehicle 10 with respect to the ridge 5, and thereby it is possible to improve the turning angle accuracy.

[0051] Then, when the agricultural work vehicle 10 that is moving forward or backward on the headland 9 after the completion of turning approaches the next ridge 5, the marker detection LiDAR 60 detects a plurality of markers 80 erected near the next ridge 5, and the control device 70 turns the agricultural work vehicle 10 to the right again. Also in this case, the marker detection LiDAR 60 continues to detect a plurality of markers 80. After the completion of turning, based on this detection result, the control device 70 acquires the end (starting point position) of the next ridge 5 and makes the agricultural work vehicle 10 enter from the headland 9 to the ridge 5.

[0052] As described above, in the autonomous driving system 1 of the present embodiment, it is possible to improve the turning angle accuracy with a single marker detection LiDAR 60 without using a direction sensor or the like. Therefore, it is possible to suppress an increase in cost and make the agricultural work vehicle 10 autonomously exit from the ridge 5 and enter the ridge 5 with high accuracy.

[0053] <(2) Autonomous driving along the ridge> In order to make the agricultural work vehicle 10 autonomously drive along the ridge 5, it is necessary to acquire the center line RCL of the reference ridge 5. Hereinafter, the estimation method of the center line RCL of the ridge 5 in the autonomous driving system 1 of the present embodiment will be described. However, in order to facilitate understanding of the present invention, prior to this, the conventional estimation method of the center line RCL of the ridge 5 will be described.

[0054] FIG. 18 is a diagram schematically explaining a conventional method for estimating the center line RCL of the ridge 5. In the conventional estimation method, as shown in FIG. 18, in the ridge 5 between the running surfaces 7 on which a pair of left and right traveling units 120 are running, that is, in the ridge 5 straddled by the agricultural work vehicle, one of the left and right flank surfaces 5b, 5c, i.e., the flank surface 5b, is detected by a distance sensor 150 provided on the agricultural work vehicle, and based on the detection result, the center line RCL of the ridge 5 is generally estimated.

[0055] However, in such a conventional estimation method, when the shape of the ridge 5 is collapsed (for example, as shown in FIG. 18, when the hem 5d of the flank surface 5b of the ridge 5 is collapsed), it becomes difficult to detect the distance to the flank surface 5b, so there is a problem that the robustness against the shape change of the ridge 5 is low.

[0056] Moreover, in the conventional estimation method, since the center line RCL of the ridge 5 is estimated based on the information of one flank surface 5b, there is a risk of being affected by detection errors. Therefore, in order to acquire the information of the flank surfaces 5b, 5c on both sides of the ridge 5, it is conceivable to increase the distance sensors 150, but this causes a problem of increased cost.

[0057] Therefore, in the autonomous driving system 1 according to the present embodiment, the agricultural work vehicle 10 is controlled based on the information regarding the running surfaces 7 on both sides adjacent to the ridge 5 straddled by the agricultural work vehicle 10. Specifically, based on the information regarding the two running surfaces 7 detected by the ridge-following LiDAR 50, the center line RCL of the ridge 5 straddled by the agricultural work vehicle 10 is estimated, and based on the error between the estimated center line RCL of the ridge 5 and the center line VCL of the agricultural work vehicle 10, the control device 70 is configured to cause the agricultural work vehicle 10 to run along the ridge 5.

[0058] FIG. 9 is a diagram schematically illustrating the detection area DA of the ridge - mimicking LiDAR 50. FIG. 9(a) is a side view, and FIG. 9(b) is a plan view. In FIG. 9, the arrow X indicates the front side in the longitudinal direction of the vehicle body, the arrow Y indicates the left side in the vehicle body width direction, and the arrow Z indicates the upper side in the vertical direction. As described above, since the ridge - mimicking LiDAR 50 is attached to the center portion in the vehicle body width direction at the front end of the gantry portion 30 such that the detection plane DP and the ground G form an angle of 30°, as shown in FIG. 9(a), it is configured to detect the distance to the ridge 5 and the traveling surface 7 in front of the agricultural work vehicle 10. Therefore, as shown in FIG. 9(b), the ridge - mimicking LiDAR 50 includes the ridges 5I, 5II, 5III in front of the agricultural work vehicle 10 and the traveling surfaces 7I, 7II further in front of the ridges 5I, 5II, 5III in the detection area DA.

[0059] FIGS. 10 to 14 are diagrams schematically illustrating a method for estimating the center line RCL of the ridge 5 in the autonomous driving system 1. When estimating the center line RCL of the ridge 5, the ridge - mimicking LiDAR 50 detects, as shown in FIG. 10, the ridge 5 straddled by the agricultural work vehicle 10 and the traveling surfaces 7I, 7II on both sides of the ridge 5. More specifically, among the plurality of points P detected by the ridge - mimicking LiDAR 50, as shown by the broken - line frame in FIG. 10, the control device 70 extracts a point group composed of a plurality of points on the left - hand traveling surface 7I, a point group composed of a plurality of points on the left - hand normal surface 5b of the ridge 5, a point group composed of a plurality of points on the top surface 5a of the ridge 5, a point group composed of a plurality of points on the right - hand normal surface 5c of the ridge 5, and a point group composed of a plurality of points on the right - hand traveling surface 7II.

[0060] Next, the control device 70 extracts a flat point group from these point groups. More specifically, the control device 70 obtains the normal line of the plane where each point P exists from the information around each point P, and extracts only the point group on a flat surface where the normal lines are substantially perpendicular. By such processing, as shown in FIG. 11, the point groups on the left - hand normal surface 5b of the ridge 5 and the right - hand normal surface 5c of the ridge 5, where the normal lines are inclined, are excluded. As a result, as shown by the broken - line frame in FIG. 11, the point group on the left - hand traveling surface 7I, the point group on the top surface 5a of the ridge 5, and the point group on the right - hand traveling surface 7II are extracted by the control device 70.

[0061] Next, the control device 70 extracts the point groups included in a predetermined height range from the point group on the left traveling surface 7I, the point group on the top surface 5a of the ridge 5, and the point group on the right traveling surface 7II. Here, the "predetermined height range" can be, for example, the height near the lower end of the ridge 5. By such processing, the point group on the top surface 5a of the ridge 5 is excluded, and as shown by the broken line frame in FIG. 12, only the point group on the left traveling surface 7I and the point group on the right traveling surface 7II are clustered by the control device 70.

[0062] Next, as shown by the broken line frame in FIG. 13, the control device 70 estimates the midpoint between the point PI closest to the ridge 5 among the point group on the left traveling surface 7I and the point PII closest to the ridge 5 among the point group on the right traveling surface 7II as the center line RCL of the ridge 5 (more precisely, the point on the center line RCL). Then, the control device 70 causes the agricultural work vehicle 10 to travel along the ridge 5 based on the error between the estimated center line RCL of the ridge 5 and the center line VCL of the agricultural work vehicle 10.

[0063] For example, if the center line VCL of the agricultural work vehicle 10 is to the left of the estimated center line RCL of the ridge 5, the control device 70 drives the traveling motor unit 27 of the left traveling unit 20 at a rotational speed higher than that of the traveling motor unit 27 of the right traveling unit 20 to steer the agricultural work vehicle 10 to the right. Further, when the deviation between the center line VCL of the agricultural work vehicle 10 and the estimated center line RCL of the ridge 5 is greater than a first predetermined amount, the control device 70 corrects the traveling direction of the agricultural work vehicle 10 while reducing the speed of the agricultural work vehicle 10. Furthermore, when the deviation between the center line VCL of the agricultural work vehicle 10 and the estimated center line RCL of the ridge 5 is greater than a second predetermined amount (> the first predetermined amount), the control device 70 corrects the traveling direction of the agricultural work vehicle 10 by performing a super precise turning.

[0064] As described above, according to the present embodiment, instead of the ridge 5 itself where the environment, shape, etc. are likely to change significantly due to the growth of planted crops, etc., based on the information regarding the traveling surfaces 7I and 7II on both sides of the ridge 5 where the changes in the environment, shape, etc. are smaller than those of the ridge 5, the control device 70 estimates the center line RCL of the ridge 5. Therefore, as shown in FIG. 18 above, even if the bottom 5d of the ridge 5 is locally collapsed, the center line RCL of the ridge 5 can be accurately estimated.

[0065] Moreover, since the center line RCL of the ridge 5 is estimated from the point cloud that satisfies the condition of being included in a flat predetermined height range on the traveling surfaces 7I and 7II on both sides of the ridge 5, even if there are some irregularities on the traveling surfaces 7I and 7II, the traveling surfaces 7I and 7II can be determined under the same conditions on the left and right sides of the ridge 5. Therefore, while reflecting the shape of the ridge 5, the center line RCL of the ridge 5 can be estimated with even higher accuracy.

[0066] Here, the case where the bottom of the ridge 5 is locally collapsed will be described. In the example shown in FIG. 14, since the left bottom of the original ridge 5 is the point 5d1, the midpoint between this point 5d1 and the right bottom (point 5d2) of the ridge 5 becomes the center line RCL of the ridge 5. If the center line RCL of the ridge 5 is estimated based on the point 5d1' that is closest to the ridge 5 among the point cloud on the left traveling surface 7I, the distance ΔE between the point 5d1 and the point 5d1' will directly become the error, resulting in a relatively large error ΔE.

[0067] In this regard, in the present embodiment, the control device 70 estimates the midpoint between the point 5d1' that is closest to the ridge 5 among the point cloud on the left traveling surface 7I and the point 5d2 that is closest to the ridge 5 among the point cloud on the right traveling surface 7II as the point on the center line RCL' of the ridge 5. Therefore, even when the bottom of the ridge 5 is locally collapsed, the error (ΔE / 2) is halved, so that the estimation accuracy of the center line RCL' of the ridge 5 can be further improved.

[0068] FIG. 15 is a diagram schematically explaining the relationship between the arrangement position of the ridging LiDAR 50 and the detectable point cloud. In FIG. 15, above the height VH at which two virtual extension surfaces VP1 and VP2 obtained by extending the normal surfaces 5b and 5c on both sides of the ridge 5 upward intersect, and the region sandwiched between the two virtual extension surfaces VP1 and VP2 is defined as region RI, below the height VH at which the virtual extension surfaces VP1 and VP2 intersect, and the region sandwiched between the virtual extension surfaces VP1 and VP2 is defined as region RIII, the region to the left of region RI and region RIII is defined as region RII, and the region to the right of region RI and region RIII is defined as region RIV.

[0069] As shown in region RIII of FIG. 15, if the installation height of the ridging LiDAR 50C on the agricultural work vehicle 10 is too low, the ridging LiDAR 50C can only detect the top surface 5a of the ridge 5, and it becomes difficult to detect the running surfaces 7I and 7II on both sides of the ridge 5. Also, as shown in region RII of FIG. 15, if the installation position of the ridging LiDAR 50B in the body width direction of the agricultural work vehicle 10 is too biased to the left, the ridge shoulder 5e of the ridge 5 will block the field of view of the ridging LiDAR 50B, and the point 5d2' on the right running surface 7II will be detected as the inner end point 5d2, resulting in an error ΔE as shown in FIG. 15 between the original center line RCL of the ridge 5. The same applies to region RIV of FIG. 15. In these cases, it becomes difficult to accurately estimate the center line RCL of the ridge 5, so it becomes difficult to make the agricultural work vehicle 10 autonomously travel along the ridge 5 with high precision. In the worst case, it is also assumed that the agricultural work vehicle 10 will come into contact with the ridge 5.

[0070] Therefore, as shown in FIG. 12, the ridgeline-following LiDAR 50 is installed on the agricultural work vehicle 10 at a height equal to or higher than the height VH at which two virtual extension surfaces VP1 and VP2 that extend upward the side slopes 5b and 5c on both sides of the ridge 5 straddled by the agricultural work vehicle 10 intersect, and at a position in the width direction of the vehicle body that is within the region sandwiched by the two virtual extension surfaces VP1 and VP2, that is, preferably within the region RI. By arranging the ridgeline-following LiDAR 50 within the region RI in this way, it becomes possible to always detect the traveling surfaces 7I and 7II on both adjacent sides of the ridge 5 by the ridgeline-following LiDAR 50. That is, as long as it is within the region RI, even if the position of the ridgeline-following LiDAR 50 is slightly displaced left and right like the ridgeline-following LiDAR 50A due to the inclination of the agricultural work vehicle 10 or the like, it becomes possible to always detect the traveling surfaces 7I and 7II on both adjacent sides of the ridge 5.

[0071] In this regard, in the present embodiment, as described above, the ridgeline-following LiDAR 50 is attached to the center in the width direction of the front end of the gantry portion 30, and the installation height is variable by changing the height of the gantry portion 30 by the gantry lifting mechanism 36. Therefore, the ridgeline-following LiDAR 50 can always be placed within the region RI, and thereby, it becomes possible to always detect the traveling surfaces 7I and 7II on both adjacent sides of the ridge 5.

[0072] FIG. 16 is a diagram schematically explaining the relationship between the case where the detection direction of the ridgeline-following LiDAR 50 is directed vertically downward and the case where it is directed obliquely downward in the front. The error ΔE0 in FIG. 16 is the deviation of the center line VCL of the agricultural work vehicle 10 with respect to the center line RCL of the ridge 5 when the detection direction of the ridgeline-following LiDAR 50 is directed vertically downward, and the error ΔE1 in FIG. 16 is the deviation of the center line VCL of the agricultural work vehicle 10 with respect to the center line RCL of the ridge 5 when the detection direction of the ridgeline-following LiDAR 50 is directed obliquely downward in the front.

[0073] Generally, when the center line VCL of the agricultural work vehicle 10 straddling the ridge 5II is inclined with respect to the center line RCL of the ridge 5II, the distance between the two center lines is small directly below the agricultural work vehicle 10 and increases as the distance from the agricultural work vehicle 10 increases. Therefore, when the ridge-following LiDAR 50 is installed so that the running surfaces 7I and 7II directly below the agricultural work vehicle 10 are included in the detection area, it is difficult for the posture (direction) of the agricultural work vehicle 10 to be reflected in the error ΔE0 between the center line RCL of the ridge 5 and the center of the agricultural work vehicle 10.

[0074] Moreover, as shown in FIG. 16, considering the posture of the agricultural work vehicle 10, even though the center line VCL of the agricultural work vehicle 10 is deviated by an error ΔE1 to the left with respect to the center line RCL of the ridge 5, directly below the agricultural work vehicle 10, it may be detected that the center line VCL of the agricultural work vehicle 10 is deviated by an error ΔE0 to the right with respect to the center line RCL of the ridge 5. In such a case, if the agricultural work vehicle is steered to the left so that the error ΔE0 becomes 0, it is also assumed that the right rear end of the agricultural work vehicle 10 may come into contact with the normal plane of the right ridge III.

[0075] In this regard, in the present embodiment, as described above, the ridge-following LiDAR 50 is installed on the agricultural work vehicle 10 obliquely downward in the front so that the running surface 7 in front of the agricultural work vehicle 10 becomes the detection area. Therefore, the posture of the agricultural work vehicle 10 can also be reflected in the estimated error ΔE1 between the center line RCL of the ridge 5 and the center line VCL of the agricultural work vehicle 10, and the agricultural work vehicle 10 can be reliably autonomously run along the ridge 5.

[0076] (Other Embodiments) The present invention is not limited to the embodiments and can be implemented in various other forms without departing from its spirit or main features.

[0077] In the above embodiment, the crawler pitch of the agricultural work vehicle 10 is set so as to perform a weeding operation while straddling one ridge 5. However, the present invention is not limited to this, and the crawler pitch of the agricultural work vehicle 10 may be set so as to perform a weeding operation while straddling two or more ridges 5 (ridge group).

[0078] In the above embodiment, the normal vector is obtained from the information around each point to extract the point cloud on the flat surface. However, the present invention is not limited to this. For example, as shown in FIG. 17, a predetermined height range (H1 and H2 in the example of FIG. 17) is set, and the point cloud included in this predetermined height range may be estimated as the point cloud on the flat surface. In FIG. 17, PI is the point closest to the ridge 5 on the left running surface 7I included in the range of height H1, PII is the point PII closest to the ridge 5 on the right running surface 7II included in the range of height H1, PI' is the point closest to the ridge 5 on the left running surface 7I included in the range of height H2 (<H1), PII' is the point PII closest to the ridge 5 on the right running surface 7II included in the range of height H2, B1 is the distance between PI and PII, B2 is the distance between PI' and PII', A1 is the distance between the center line RCL of the ridge 5 and PI, and A2 is the distance between the center line RCL of the ridge 5 and PI'.

[0079] Also in this case, an error ΔE may occur between A1 and A2 depending on the way of setting the height range. However, by estimating the center line RCL of the ridge 5 based on the information on the two running surfaces 7I and 7II, the error is halved, so the estimation accuracy of the center line RCL of the ridge 5 can be improved.

[0080] As described above, the above-described embodiment is merely an example in every respect and should not be construed in a limiting sense. Further, all modifications and changes belonging to the equivalent scope of the claims are within the scope of the present invention.

Industrial Applicability

[0081] According to the present invention, it is possible to autonomously run a farm work vehicle along a ridge with high accuracy without being affected by the shape change of the ridge, so it is extremely useful when applied to the autonomous driving system of a farm work vehicle.

Explanation of Signs

[0082] 1 Autonomous driving system 3 Farm field 5 Ridge 5b Normal plane 5c Normal plane 7 Traveling surface 10 Agricultural work vehicle 20 Traveling section 50 Mu-imitation LiDAR (distance sensor) 70 Control device (estimation means) (control means) E Error RCL Center line RI Region VCL Center VP1 Virtual extension surface VP2 Virtual extension surface P Point

Claims

1. An autonomous driving system for a work vehicle that autonomously drives along ridges in a field having a group of ridges composed of a plurality of ridges and a driving surface formed between adjacent ridges, while performing work across the group of ridges, comprising: a distance sensor installed on the work vehicle; estimating means for estimating a center line of the group of ridges straddled by the work vehicle based on information detected by the distance sensor; control means for driving the work vehicle along the group of ridges based on an error between the center line of the group of ridges estimated by the estimating means and the center line of the work vehicle; and characterized in that, in a point group composed of a plurality of points on the driving surfaces located on both sides of the ridge, points on the center line of the group of ridges are estimated by extracting a point group on a flat surface extending in the horizontal direction. An autonomous driving system for a work vehicle.

2. When extracting the flat point group, further obtaining a point group composed of a plurality of points on each normal plane in the inclined portion of the ridge and a point group composed of a plurality of points on the top surface of the ridge, and extracting only the flat point group among them. The autonomous driving system for a work vehicle according to claim 1.

3. The estimating means excludes point groups on the inclined normal planes on both sides of the group of ridges from among the point groups on the group of ridges and on the two driving surfaces on both sides of the group of ridges, and excludes the point group on the top surface of the group of ridges by extracting the point group included in a predetermined height range that is the height near the lower end of the group of ridges. Among the point groups on the respective driving surfaces that are the extracted point groups, the midpoint between the point closest to the group of ridges among the point groups on one driving surface and the point closest to the group of ridges among the point groups on the other driving surface is estimated as the point on the center line of the group of ridges. The autonomous driving system for a work vehicle according to claim 1.

4. An autonomous driving system for a work vehicle that autonomously drives along ridges in a field having a group of ridges composed of a plurality of ridges and a driving surface formed between adjacent ridges, while performing work across the group of ridges, comprising: a distance sensor installed on the work vehicle; estimating means for estimating a center line of the group of ridges straddled by the work vehicle based on information detected by the distance sensor; Control means for causing the work vehicle to travel along the ridge group based on an error between the center line of the ridge group estimated by the estimation means and the center line of the work vehicle. An autonomous driving system for a work vehicle, characterized in that it is configured to estimate a point on the center line of the ridge group from a point group composed of a plurality of points on the traveling surface located on both sides of the ridge.

Images