Detection system, detection method, and work vehicle
The detection system uses a three-dimensional sensor and controller to differentiate between obstacles and dust in work vehicles, ensuring accurate identification and reducing false alarms.
Patent Information
- Application Number
- JP2023072548
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-26
- Publication Date
- 2024-11-08
AI Technical Summary
In work vehicles operating in dusty environments like mines or construction sites, existing systems fail to accurately distinguish between obstacles and dust, leading to potential misidentification.
A detection system utilizing a three-dimensional sensor to detect objects, a controller to process data, and a method to differentiate between obstacles and dust by setting a determination threshold based on point cloud density and resolution, allowing for separate detection of both.
Enables accurate differentiation between obstacles and dust, preventing false detections and enhancing operational safety by correctly identifying potential hazards.
Smart Images

Figure 2024157896000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a detection system, a detection method, and a work vehicle. [Background technology]
[0002] 2. Description of the Related Art In work vehicles including unmanned vehicles, there is known a technique for determining whether or not an obstacle is present using an obstacle sensor (see, for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2023-042394 A Summary of the Invention [Problem to be solved by the invention]
[0004] A work vehicle operates in a work site where a lot of dust is generated, such as a mine or a construction site. In such a work site, there is a possibility that the dust may be detected as an obstacle. Therefore, it is desirable to detect the dust by distinguishing it from the obstacle.
[0005] An aspect of the present disclosure aims to provide a detection system, a detection method, and a work vehicle that are capable of distinguishing between obstacles and dust and detecting them. [Means for solving the problem]
[0006] According to an aspect of the present disclosure, there is provided a detection system comprising: an object detection sensor attached to a work vehicle and detecting objects present in the vicinity of the work vehicle; and a controller, wherein the controller comprises a detection unit that distinguishes between obstacles and dust based on object detection data from the object detection sensor, the object detection data from the object detection sensor including a point cloud consisting of a plurality of detection points defined on the surface of an object, and the detection unit distinguishes between obstacles and dust by comparing, for each grid dividing the detection range of the object detection sensor, the number of detection points included in the object detection data with a judgment threshold based on a point cloud density threshold defined by the resolution of the object detection sensor.
[0007] According to an aspect of the present disclosure, there is provided a detection method comprising an object detection sensor attached to a work vehicle and detecting objects present in the vicinity of the work vehicle, and a controller, the detection method acquiring object detection data from the object detection sensor including a point cloud consisting of a plurality of detection points defined on the surface of an object, and for each grid dividing the detection range of the object detection sensor, comparing the number of detection points included in the object detection data with a judgment threshold based on a point cloud density threshold defined by the resolution of the object detection sensor, to distinguish between obstacles and dust.
[0008] According to an aspect of the present disclosure, there is provided a work vehicle including the above detection system and a vehicle body. Effect of the Invention
[0009] According to aspects of the present disclosure, a detection system, a detection method, and a work vehicle are provided that are capable of distinguishing between obstacles and dust and detecting them. [Brief description of the drawings]
[0010] [Figure 1] FIG. 1 is a perspective view of a work vehicle according to an embodiment, as viewed diagonally from above and to the left front. [Diagram 2] FIG. 2 is a functional block diagram showing a detection system according to an embodiment. [Diagram 3]FIG. 3 is a block diagram illustrating a computer system according to an embodiment. [Figure 4] FIG. 4 is a schematic diagram showing an example of detection points of an object detected by a three-dimensional sensor. [Diagram 5] FIG. 5 is a schematic diagram showing an example of object detection points and grids detected by a three-dimensional sensor. [Figure 6] FIG. 6 is a schematic diagram illustrating the resolution of a three-dimensional sensor. [Figure 7] FIG. 7 is a schematic diagram showing an example of object detection. [Figure 8] FIG. 8 is a flowchart showing a detection method of the detection system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings, but the present disclosure is not limited thereto. The components of each embodiment described below can be appropriately combined. In addition, some components may not be used.
[0012] <Work vehicle> FIG. 1 is a perspective view of a transport vehicle, which is an example of a work vehicle according to an embodiment, seen from the left front upper side. The work vehicle 3 is a vehicle that operates at a work site. In the embodiment, a transport vehicle, which is an example of a work vehicle, will be described. The transport vehicle 3 is, for example, a dump truck that transports a load at a work site such as a mine. The transport vehicle 3 distinguishes between obstacles and dust present around the transport vehicle 3 and detects them. The transport vehicle 3 may be a manned dump truck that is operated by a driver's driving operation, or an unmanned dump truck that operates without a driver. The transport vehicle 3 includes a vehicle body 31, a vessel 32 supported by the vehicle body 31, a pair of left and right front wheels 38F, and a pair of left and right rear wheels 38R.
[0013] 2 is a functional block diagram showing a detection system according to an embodiment. The detection system 1 of the transport vehicle 3 includes a three-dimensional sensor (object detection sensor) 11, an output unit 12, and a controller 20. The three-dimensional sensor 11 and the controller 20 are connected to each other wirelessly or via a wire so as to be able to communicate data.
[0014] The three-dimensional sensor 11 is attached to the transport vehicle 3. In the embodiment, the three-dimensional sensor 11 is attached to the front of the transport vehicle 3. The number of the three-dimensional sensors 11 is not particularly limited, and for example, two three-dimensional sensors 11 may be arranged on the transport vehicle 3. The three-dimensional sensor 11 is an object detection sensor that detects objects existing around the transport vehicle 3. In the embodiment, the three-dimensional sensor 11 is an object detection sensor that detects objects existing in front of the transport vehicle 3. The three-dimensional sensor 11 can detect a range of, for example, about several tens of meters. The three-dimensional sensor 11 transmits the detected object detection data to the controller 20.
[0015] The three-dimensional sensor 11 acquires three-dimensional data of an object. The three-dimensional data of the object includes a point cloud consisting of a plurality of detection points defined on the surface of the object. The point cloud indicates the relative distance and relative position between the three-dimensional sensor 11 and each of the plurality of detection points defined on the surface of the object. An example of the three-dimensional sensor 11 is a laser sensor (LiDAR: Light Detection and Ranging) that detects an object by emitting laser light. Note that the three-dimensional sensor 11 may be another non-contact sensor such as an infrared sensor that detects an object by emitting infrared light or a radar sensor (RADAR: Radio Detection and Ranging) that detects an object by emitting radio waves.
[0016] The output unit 12 outputs the result of the determination by the detection unit 25 from the output unit 12. The output unit 12 is, for example, a lamp, a buzzer, etc. The output unit 12 outputs under the control of the output control unit 29.
[0017] <Transport vehicle control system (controller)> The controller 20 distinguishes between obstacles and dust around the transport vehicle 3. The controller 20 can acquire object detection data from the three-dimensional sensor 11 serving as an object detection sensor. The controller 20 includes a numerical calculation device (processor) such as a CPU (Central Processing Unit).
[0018] 3 is a block diagram showing a computer system according to an embodiment. The controller 20 includes a computer system 1000. The computer system 1000 includes a processor 1001 such as a CPU, a main memory 1002 including a non-volatile memory such as a ROM (Read Only Memory) and a volatile memory such as a RAM (Random Access Memory), a storage 1003, and an interface 1004 including an input / output circuit. The functions of the controller 20 described above are stored in the storage 1003 as a program. The processor 1001 reads the program from the storage 1003, loads it in the main memory 1002, and executes the above-mentioned processing according to the program. The program may be distributed to the computer system 1000 via a network.
[0019] In the embodiment, the controller 20 includes a sensor data acquisition unit 21, a storage unit 22, a detection unit 25, and an output control unit 29.
[0020] The sensor data acquisition unit 21 acquires object detection data from the three-dimensional sensor 11. The object detection data acquired by the sensor data acquisition unit 21 is, for example, a point cloud made up of a plurality of detection points.
[0021] The storage unit 22 includes at least one of a RAM, a ROM, a flash memory, and a hard disk drive. The storage unit 22 stores data used in the processing of the controller 20.
[0022] Storage unit 22 stores in advance the resolution of three-dimensional sensor 11. In the embodiment, storage unit 22 stores in advance the resolution of three-dimensional sensor 11 in the up-down direction.
[0023] The storage unit 22 stores a point cloud density threshold (hereinafter referred to as "density threshold") in advance. The density threshold is stored before executing the process of the flowchart shown in Fig. 8, which will be described later. The density threshold will be described later.
[0024] The detection unit 25 distinguishes between obstacles and dust and detects them based on object detection data from the three-dimensional sensor 11 as an object detection sensor. More specifically, the detection unit 25 counts the number of detection points for each grid from the object detection data. The detection unit 25 determines whether the number of detection points is equal to or greater than a determination threshold obtained by multiplying a density threshold by a coefficient. When the detection unit 25 determines that the number of detection points is equal to or greater than a determination threshold obtained by multiplying a density threshold by a coefficient, it detects the object as an obstacle. When the controller 20 does not determine that the number of detection points is equal to or greater than a determination threshold obtained by multiplying a density threshold by a coefficient, it detects the object as dust.
[0025] The detection unit 25 counts the number of detection points that are at a predetermined height or higher from the ground for each grid from the object detection data, in order to exclude detection points that detect the ground.
[0026] Fig. 4 is a schematic diagram showing an example of an object detection point by a three-dimensional sensor. Fig. 4 shows a state where a ground surface 200 ahead, a convex part 201 of the ground surface 200, and a transport vehicle 3X ahead are detected by a three-dimensional sensor 11 mounted on a transport vehicle 3. The detection point P at which the ground surface 200 ahead is detected is denoted as P. 200 The detection point P at which the convex portion 201 is detected is P 201 Let P be the detection point P where the forward transport vehicle 3X is detected. 3X Let us assume that.
[0027] Fig. 5 is a schematic diagram showing an example of detection points of an object detected by a three-dimensional sensor and a grid. Fig. 5 shows a state in which the detection range of a three-dimensional sensor 11 mounted on a transport vehicle 3 is divided into a plurality of grids G. The grids G are formed by dividing the detection range of the three-dimensional sensor 11 in a lattice shape in the left-right and front-rear directions when viewed in the up-down direction. The grids G are formed in the shape of a quadrangular prism. The lengths of the grids G in the left-right and front-rear directions when viewed in the up-down direction are not limited.
[0028] FIG. 6 is a schematic diagram for explaining the resolution of the three-dimensional sensor. For each grid G, a distance D between the vertical center line CL passing through the center point of the grid G in the vertical direction view and the three-dimensional sensor 11 is calculated. The vertical resolution of the three-dimensional sensor 11 is stored in advance in the storage unit 22. When an object is detected by the three-dimensional sensor 11, a point cloud consisting of a plurality of detection points defined on the surface of the object is obtained. If no object exists in the grid G, no point cloud is obtained other than the point cloud that detects the ground. From the height from the ground where the point cloud is obtained and the resolution, a density threshold defined by the number of detection points obtained when the laser hits an object located at that height is calculated. As shown in the following formula (1), a judgment threshold obtained by multiplying the density threshold by a coefficient is used as a judgment threshold in the detection unit 25. The coefficient is set, for example, for each work site. Decision threshold = density threshold × coefficient … (1)
[0029] FIG. 7 is a schematic diagram showing an example of object detection. In grid G, detection points P included in area A whose height from the ground is H or more are counted. Area A is set to be H or more in height from the ground in order to exclude detection points P that detect the ground. Detection point P1 is not included in area A. Detection points P2, P3, and P4 are included in area A. When the determination threshold, which is the density threshold value multiplied by the coefficient calculated by formula 1, is, for example, "3" and the number of detection points is "3", it is determined that there is an obstacle. When the determination threshold, which is the density threshold value multiplied by the coefficient calculated by formula 1, is, for example, "4" and the number of detection points is "3", it is determined that there is obstacle dust.
[0030] The output control unit 29 controls the detection result by the detection unit 25 to be output via the output unit 12. For example, the output control unit 29 outputs a control signal for turning on a lamp in a different manner when an obstacle is detected and when dust is detected. For example, the output control unit 29 outputs a control signal for sounding a buzzer in a different manner when an obstacle is detected and when dust is detected.
[0031] <Basic processing> A detection method of the detection system 1 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the detection method of the detection system according to the embodiment. While the transport vehicle 3 is in operation, the detection system 1 is started up. While the detection system 1 is running, the process of the flowchart shown in Fig. 8 is executed. While the detection system 1 is running, the three-dimensional sensor 11 detects an object.
[0032] The controller 20 acquires object detection data (step ST11). More specifically, the controller 20 acquires the object detection data from the three-dimensional sensor 11 by the sensor data acquisition unit 21. The controller 20 proceeds to step ST12.
[0033] The controller 20 counts the number of detection points for each grid (step ST12). More specifically, the controller 20 counts the number of detection points, which is the number of detection points whose height from the ground is H or more, from the object detection data for each grid, by the detection unit 25. The controller 20 proceeds to step ST13.
[0034] The controller 20 determines whether the number of detection points for each grid is 1 or more (step ST13). More specifically, if the detection unit 25 determines that the number of detection points for each grid is 1 or more (Yes in step ST13), the controller 20 proceeds to step ST14. In this case, the grid includes a detection point. If the detection unit 25 does not determine that the number of detection points for each grid is 1 or more (No in step ST13), the controller 20 proceeds to step ST18. In this case, the grid does not include a detection point.
[0035] When the controller 20 determines that the number of detection points per grid is 1 or more (Yes in step ST13), the controller 20 determines whether the number of detection points is equal to or more than a determination threshold obtained by multiplying the density threshold by a coefficient (step ST14). More specifically, when the controller 20 determines that the number of detection points is equal to or more than a determination threshold obtained by multiplying the density threshold by a coefficient (Yes in step ST14), the controller 20 proceeds to step ST15. When the controller 20 does not determine that the number of detection points is equal to or more than a determination threshold obtained by multiplying the density threshold by a coefficient (No in step ST14), the controller 20 proceeds to step ST17.
[0036] If the number of detected points is equal to or greater than the determination threshold value obtained by multiplying the density threshold value by the coefficient (Yes in step ST14), the controller 20 detects the detected points of that grid as obstacles (step ST15).The controller 20 proceeds to step ST16.
[0037] The controller 20 outputs an alarm (step ST16). More specifically, the controller 20 controls the output control section 29 to output an alarm indicating that an obstacle has been detected via the output section 12. The controller 20 proceeds to step ST18.
[0038] If it is not determined that the number of detection points is equal to or greater than the determination threshold value obtained by multiplying the density threshold value by the coefficient (No in step ST14), the controller 20 detects the detection points of that grid as dust (step ST17).The controller 20 proceeds to step ST18.
[0039] The controller 20 judges whether or not all the grids have been completed (step ST18). If the controller 20 judges that all the grids have not been completed (No in step ST18), the controller 20 executes the process of step ST12 again. If the controller 20 judges that all the grids have been completed (Yes in step ST18), the controller 20 ends the process of this flowchart.
[0040] <Effects> As described above, in the embodiment, for each grid into which the detection range of the three-dimensional sensor 11 is divided, the number of detection points included in the object detection data is compared with a judgment threshold based on a point cloud density threshold defined by the resolution of the three-dimensional sensor 11 to distinguish between obstacles and dust when detecting them. In this way, according to the embodiment, obstacles and dust can be distinguished from each other when detecting them.
[0041] In the embodiment, when the number of detection points is equal to or greater than the determination threshold, an obstacle is detected. According to the embodiment, it is possible to appropriately detect an obstacle.
[0042] In the embodiment, when the number of detection points is less than the determination threshold, it is detected as dust. The embodiment can appropriately detect dust. According to the embodiment, it is possible to suppress erroneous detection of dust as an obstacle.
[0043] In the embodiment, the number of detection points at a predetermined height or higher from the ground is compared with a determination threshold based on a point cloud density threshold defined by the resolution of the three-dimensional sensor 11. According to the embodiment, it is possible to suppress erroneous detection of the ground as an obstacle.
[0044] In the embodiment, the determination threshold is calculated by multiplying the point cloud density threshold by a coefficient. According to the embodiment, it is possible to set an appropriate determination threshold in accordance with a work site or the like.
[0045] Although the grid has been described above as being in the form of a lattice, the present invention is not limited to this and may be divided into other shapes, such as stripes.
[0046] In the embodiment, the work vehicle 3 is a dump truck, but is not limited to this. For example, the work vehicle 3 according to other embodiments may be another work vehicle such as a hydraulic excavator, a bulldozer, or a wheel loader. [Explanation of symbols]
[0047] 1...detection system, 3...transport vehicle (work vehicle), 31...vehicle body, 32...vessel, 38F...front wheel, 38R...rear wheel, 11...3D sensor (object detection sensor), 12...output section, 20...controller, 21...sensor data acquisition section, 22...memory section, 25...detection section, 29...output control section.
Claims
1. An object detection sensor that is attached to a work vehicle and detects objects present around the work vehicle; A controller; Equipped with The controller: a detection unit that distinguishes between obstacles and dust and detects them based on object detection data from the object detection sensor; Equipped with the object detection data from the object detection sensor includes a point cloud consisting of a plurality of detection points defined on a surface of the object; the detection unit compares, for each grid obtained by dividing the detection range of the object detection sensor, the number of detection points included in the object detection data with a determination threshold based on a point cloud density threshold defined by a resolution of the object detection sensor, and detects obstacles and dust in a distinguished manner. Detection system.
2. The detection unit detects an obstacle when the number of the detection points is equal to or greater than the determination threshold. The detection system of claim 1 .
3. The detection unit detects the detection point as dust when the number of the detection points is less than the determination threshold.
3. A detection system according to claim 1 or 2.
4. The detection unit compares the number of the detection points that are at a predetermined height or higher from the ground with a determination threshold based on a point cloud density threshold defined by a resolution of the object detection sensor.
3. A detection system according to claim 1 or 2.
5. The determination threshold is calculated by multiplying the point cloud density threshold by a coefficient.
3. A detection system according to claim 1 or 2.
6. An object detection sensor that is attached to a work vehicle and detects objects present around the work vehicle; A controller; A detection method comprising: acquiring object detection data including a point cloud made up of a plurality of detection points defined on a surface of an object from the object detection sensor; for each grid into which the detection range of the object detection sensor is divided, the number of detection points included in the object detection data is compared with a determination threshold based on a point cloud density threshold defined by the resolution of the object detection sensor, to distinguish and detect obstacles and dust. Detection methods.
7. A detection system according to claim 1 or 2; The car body and A work vehicle equipped with
Citation Information
Patent Citations
Unmanned vehicle, control system of unmanned vehicle, and method for controlling unmanned vehicle
JP2023042394A
