Method, Electronic Device, Program Product and Medium for Detecting Loading of a Truck Bed

Abstract

The present invention provides a method for detecting the loading of a truck bed, an electronic device, a program product, and a medium. The present invention relates to the field of artificial intelligence technology. The present invention aims to solve the problems of low efficiency and high time cost in loading detection. The method includes: a data acquisition step: acquiring data; an alignment step: aligning the center of the truck bed with the loading port in the transverse direction according to the acquired data; a loading step: opening the loading port to load the truck bed; a judgment step: detecting whether the detection area near the inner wall of the truck bed far from the loading port is full of materials. If so, execute the material stop step; if not, continue to execute the loading step; and a material stop step: closing the loading port to stop loading the truck bed, then driving the truck bed away from the loading port, and executing the data acquisition step for the next truck bed. This method can improve the detection efficiency under the condition of automation, accurately detect the loading in real time, and ensure the uniform loading of materials.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a method for detecting the loading of a hopper, an electronic device, a program product, and a medium. Background Art

[0002] Most minerals are mined underground, and a large number of roadways need to be excavated underground. The risk coefficient of underground mine mining is relatively high. Once accidents such as water inrush, collapse, and leakage of toxic gases occur, it is extremely difficult to evacuate and rescue underground workers. Therefore, the requirements for unmanned and intelligent underground mine mining are relatively urgent.

[0003] An important link in the unmanned operation of underground mines is the loading process at the loading port (also known as the "chute inlet"). The current loading method is for a feeder and a transport vehicle driver to cooperate to control the opening and closing of the loading port by means of a pull rod or a remote control to promote and prevent materials from entering the hopper. The difficulty in this process lies in controlling the speed and total amount of discharging. If the loading is too little, the loading efficiency will be reduced; if the loading is too much, the materials will overflow and spill, accumulating on the road surface and affecting the driving safety of vehicles.

[0004] Although there are currently several methods for detecting automatic loading, these methods detect the loading of the entire hopper, resulting in low detection efficiency and high time costs. In addition, these methods must be executed after the discharging stops or even after the hopper has driven out, and it is impossible to judge the total loading amount while discharging, nor can it exclude the interference of dust and flying stones generated during the discharging process to the sensor and the resulting inaccurate detection. It is also impossible to fine-tune the position of the hopper during the loading process to ensure that the materials are evenly loaded in the hopper, and thus it is impossible to eliminate the center of gravity shift caused by uneven loading of the materials.

[0005] Therefore, there is an urgent need to provide a method for detecting the loading of a hopper, which can improve the detection efficiency, accurately detect the loading in real time, and ensure the even loading of the materials under the condition of automation. Summary of the Invention

[0006] In view of the above problems, the present invention provides a method for detecting the loading of a hopper, where the hopper includes an inner wall located inside the hopper, an outer wall located outside the hopper, a top wall connecting adjacent inner and outer walls, and a bottom wall located at the bottom of the hopper. The method includes: a collection step: collecting data; an alignment step: aligning the center of the hopper with the loading port in the horizontal direction according to the collected data; a loading step: opening the loading port to load the hopper; a judgment step: detecting whether the detection area near the inner wall of the hopper far from the loading port is full of materials. If so, execute the stop loading step; if not, continue to execute the loading step; and a stop loading step: closing the loading port to stop loading the hopper, then driving the hopper away from the loading port, and executing the collection step for the next hopper.

[0007] According to one aspect of the present invention, the collected data includes: collecting data points of the ground when there is no hopper below the loading port, identifying the data points of the ground as ground points and recording the height values of the ground points; and collecting data points of the hopper that moves below the loading port and recording the height values of the hopper corresponding to the data points of the hopper, and then identifying the data points of the hopper as: top wall points, distributed along the top wall, having the largest and constant height values; bottom wall points, distributed along the bottom wall, having a constant height value that is greater than the height value of the ground points and less than the height value of the top wall points; and inner wall points, distributed along the inner wall, having height values that vary within the range defined by the height value of the bottom wall points and the height value of the top wall points.

[0008] According to one aspect of the present invention, the aligning step includes: determining the coordinates of the center of the hopper according to the coordinates of the top wall points, bottom wall points and inner wall points in a plane perpendicular to the vertical direction and correcting the position of the hopper so that the center is aligned with the loading port.

[0009] According to one aspect of the present invention, the detection area is defined as an area composed of bottom wall points that are at a distance d a from the inner wall points and away from the center of the hopper, where 15 cm ≤ d a ≤ 50 cm.

[0010] According to one aspect of the present invention, the hopper has four inner walls that enclose a rectangular shape. The four inner walls include one inner wall close to the loading port and three inner walls away from the loading port when the center of the hopper is aligned with the loading port in the lateral direction. The detection area only extends along the three inner walls to form a "[" shape.

[0011] According to one aspect of the present invention, detecting whether the detection area near the inner wall of the hopper away from the loading port is full of material includes: collecting data points of the material in the detection area of the hopper and identifying the data points of the material as material points. The material points have variable height values that are greater than the height value of the bottom wall points, and detecting whether the difference between the height value of the top wall points and the height value of the material points is less than or equal to a threshold as the material accumulates.

[0012] According to one aspect of the present invention, the collecting step further includes setting up a spatial rectangular coordinate system before collecting data. The spatial rectangular coordinate system includes: a y-axis pointing in the transverse direction and aligned with the loading port, an x-axis pointing in the longitudinal direction towards one end of the carriage, a z-axis pointing in the vertical direction towards the ground, and a coordinate origin fixed at a position higher than the loading port. When the center is aligned with the loading port in the transverse direction, the coordinate origin is aligned with the center in the vertical direction. Among them, detecting whether the material is full in the detection area near the inner wall of the carriage far from the loading port is performed in the following manner: If there is a material point satisfying z m ≥z t -z diffth and x>0 in the detection area, then the value of c p is incremented by 1; if there is a material point satisfying z m ≥z t -z diffth and x<0 in the detection area, then the value of c n is incremented by 1; if c p ≥c th and c n ≥c th , it means that the material is full in the detection area near the inner wall of the carriage far from the loading port; and if c p ≥c th and c n =0, or c n ≥c th and c p =0, it means that the material is unevenly distributed on the bottom wall; among them, z m is the height value of the material point, z t is the height value of the top wall point, z diffth is the threshold value of the difference between the height value of the top wall point and the height value of the material point, c p is the counter for material points with an x coordinate greater than 0, c n is the counter for material points with an x coordinate less than 0, c th is c p and c n 's threshold value, and the initial values of c p and c n are 0.

[0013] According to one aspect of the present invention, the method further includes an adjustment step: If c p ≥c th and c n =0, then the carriage moves a distance d p in the positive x-axis direction to continue the loading step; and if c n ≥c th and c pIf = 0, the carriage moves a distance d in the negative x-axis direction. n , to continue with the loading step, where 40 cm ≤ d p ≤ 80 cm, 40 cm ≤ d n ≤ 80 cm.

[0014] According to one aspect of the present invention, a sensor is installed at the origin of coordinates to collect data points, so as to obtain the reflectivity of the data points for the electromagnetic waves emitted by the sensor and the coordinates of the data points.

[0015] According to one aspect of the present invention, the method further includes a denoising step located between the loading step and the judgment step: if the material point satisfies r < r th , then remove the material point; and if the material point satisfies r ≥ r th , then retain the material point; where r is the reflectivity of the material point, and r th is the reflectivity threshold of the reflectivity.

[0016] According to one aspect of the present invention, the denoising step further includes: setting a circle with the material point as the center and a radius of R in the xy plane; if there are only n or fewer adjacent material points to the material point as the center that satisfy d z < d zth , then remove the material point as the center; and if there are n or more adjacent material points to the material point as the center that satisfy d z < d zth , then retain the material point as the center; where d z is the distance of the adjacent material point along the z-axis from the circle, and d zth is the threshold of d z , 5 cm ≤ d zth ≤ 10 cm, 5 ≤ n ≤ 20, 5 cm ≤ R ≤ 30 cm.

[0017] According to one aspect of the present invention, , where z g is the height value of the ground point, is the average height value of the ground point, z f is the noise fluctuation range, if z f ≥ 50 cm, then it is determined that there is an interference target on the ground or the installation position is not level.

[0018] According to another aspect of the present invention, there is provided an electronic device, which includes: at least one processor; a sensor for transmitting the collected data to the at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the method according to any one of the above aspects.

[0019] According to still another aspect of the present invention, there is provided a computer program product, which includes: a computer program that, when executed by a processor, implements the method according to any one of the above aspects.

[0020] According to yet another aspect of the present invention, there is provided a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of the above aspects is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Through the following description of the embodiments of the present invention with reference to the drawings, the above content and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0022] Figure 1 is an exemplary arrangement that can execute the method for detecting the loading of a hopper according to an embodiment of the present invention, showing a hopper filled with material, a loading port for loading the hopper, and a sensor;

[0023] Figure 2 is Figure 1 a top view of the exemplary arrangement in, showing the detection area of the hopper and omitting the sensor and the actual material loaded into the hopper;

[0024] Figure 3 is a schematic diagram showing the distribution of various collected data points on the hopper and on the ground;

[0025] Figure 4 is a schematic diagram showing a circle and adjacent material points in the denoising step;

[0026] Figure 5 is a flowchart of the method for detecting the loading of a hopper according to an embodiment of the present invention; and

[0027] Figure 6 is a block diagram of an electronic device for implementing the method for detecting the loading of a hopper according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The technical solution of the present invention will be further specifically described below through embodiments in conjunction with the accompanying drawings. In the specification, the same or similar reference numerals indicate the same or similar components. The following description of the embodiments of the present invention with reference to the accompanying drawings is intended to explain the general concept of the present invention and should not be construed as a limitation on the present invention.

[0029] In addition, in the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of this disclosure. However, it is obvious that one or more embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in diagrammatic form to simplify the drawings.

[0030] See Figures 1 to 6 , the present invention discloses a method 1000 for detecting the loading 400 of a hopper 100. The hopper 100 includes an inner wall 110 located inside the hopper, an outer wall 120 located outside the hopper, a top wall 130 connecting adjacent inner walls 110 and outer walls 120, and a bottom wall 140 located at the bottom of the hopper. For the sake of convenience of description, the material that leaves the loading port 200 and has not been loaded into the hopper 100 is referred to as virtual material 600, and the material that leaves the loading port 200 and has been loaded into the hopper 100 is referred to as real material 400. Unless otherwise specified, the term "material" in the following text generally refers to real material 400. Before loading, the hopper 100 is moved below the loading port 200, and a sensor 661 is installed above the hopper 100 and higher than the loading port 200 to collect data, which can effectively avoid the interference of virtual material 600 and dust and flying stones during the loading process on the sensing accuracy of the sensor 661. A suitable device such as a lidar can be used as the sensor 661. The data collected by the sensor 661 specifically refers to data points. As further described below, the information obtained from the data points includes the reflectivity r of the electromagnetic wave emitted by the sensor 661 and the coordinates x, y, z of the data points.

[0031] The method 1000 includes: a collection step S1100: collecting data; an alignment step S1200: aligning the center 150 of the hopper 100 with the loading port 200 in the transverse direction D1 according to the collected data; a loading step S1300: opening the loading port 200 to load the hopper 100; a judgment step S1500: detecting whether the material 400 fills the detection area 160 near the inner wall 110 of the hopper 100 that is far from the loading port 200. If so, execute the stop loading step S1700, and if not, continue to execute the loading step S1300; and a stop loading step S1700: closing the loading port 200 to stop loading the hopper 100, then driving the hopper 100 away from the loading port, and performing the collection step S1100 on the next hopper.

[0032] The data acquisition step S1100 further includes setting up a spatial rectangular coordinate system before data acquisition. The spatial rectangular coordinate system includes: a y-axis pointing along the transverse direction D1 and aligned with the loading port 200, an x-axis pointing along the longitudinal direction D2 towards one end of the hopper 100, a z-axis pointing along the vertical direction D3 (i.e., the height direction) towards the ground 500, and a coordinate origin O fixed at a position higher than the loading port 200. Before data acquisition, the hopper 100 is used to position the coordinate origin O such that when the center 150 of the hopper 100 is aligned with the loading port 200 along the transverse direction D1, the coordinate origin O is aligned with the center 150 along the vertical direction D3. See Figures 1 to 3 , the sensor 661 is located at the coordinate origin O. For clarity, Figure 2 and 3 the sensor 661 is not shown. The center 150 is the geometric center of the bottom wall 140 and is schematically represented by the point on the bottom wall 140 indicated by the indication line of 150 in Figure 3 .

[0033] See Figure 2 , in an embodiment of the present invention, the hopper 100 has four inner walls 110 that enclose a rectangular shape. The four inner walls 110 include one inner wall 110 close to the loading port 200 and three inner walls 110 far from the loading port 200 when the center 150 of the hopper 100 is aligned with the loading port 200 along the transverse direction D1. The detection area 160 only extends in an "L" shape along the three inner walls 110, as shown by the diagonal area in Figure 2 . For clearly showing the detection area 160, in Figure 2The sensor 661 is omitted in [description]. However, those skilled in the art should understand that the present invention is not limited to this. The hopper 100 may also have a plurality of inner walls enclosing other shapes, and the detection area only extends along the inner wall away from the loading port 200. The reason for setting the detection area like this is that the present invention realizes that after leaving the loading port 200, the material 400 first fills the area near the inner wall 110 close to the loading port 200. Then, as the material 400 accumulates in the hopper 100, the limited area near the inner wall 110 close to the loading port 200 cannot accommodate the increasing material 400. Thus, the increasing material 400 gradually accumulates in the area near the inner wall 110 away from the loading port 200 through the area near the center 150 of the hopper 100 from the area near the inner wall 110 close to the loading port 200 until the area near the inner wall 110 away from the loading port 200 is filled. This shows that as long as the area near the inner wall 110 away from the loading port 200 is filled, other areas in the hopper 100 should also be filled. Therefore, setting the detection area to only extend along the inner wall away from the loading port 200 instead of extending throughout the area inside the hopper 100 greatly reduces the amount of data related to the detection area collected by the sensor 661 compared with the case of setting the detection area to extend throughout the area inside the hopper 100. Correspondingly, it reduces the time spent on processing data and also avoids the interference caused by dust and flying stones in other areas in the hopper 100 except the area near the inner wall 110 away from the loading port 200 to the data measured by the sensor.

[0034] That is, the method 1000 of the present invention proposes to detect whether the detection area 160 near the inner wall 110 of the hopper 100 away from the loading port 200 is filled with the material 400, rather than detecting whether the entire hopper 100 is filled with the material 400. This not only avoids the interference of false materials 600 and most noise targets (such as dust and flying stones), realizes efficient real-time dynamic loading detection, but also significantly improves the practicability of the method 1000. Because the overflow and spillage of the material 400 in the mine are mainly caused by the local height of the material 400 exceeding the top wall 130 of the hopper 100, rather than directly caused by the total amount of the accumulated material 400. Detecting whether the detection area 160 near the inner wall 110 of the hopper 100 away from the loading port 200 is filled with the material 400 not only greatly improves the detection accuracy and efficiency compared with detecting whether the entire hopper 100 is filled with the material 400, but also is technically easy to implement.

[0035] The data collection includes: collecting data points of the ground 500 when there is no hopper 100 below the loading port 200 (see Figure 3 , for the convenience of description and clarity, Figure 3 the sensor 661 is omitted in [description]), identifying the data points of the ground 500 as ground points 510 and recording the height value z of the ground points 510g , where , z g is the height value of the ground point 510, is the average height value of the ground point 510, z f is the noise fluctuation range. If z f ≥ 50 cm, it is determined that there is an interference target such as a large stone or the installation position is not level on the ground 500. At this time, manual intervention is required; and data points 111, 131, 141 of the hopper 100 moved to below the loading port 200 are collected and the height values z i , z t , z b corresponding to the data points 111, 131, 141 of the hopper 100 are recorded. Then, according to the height value z g of the ground point 510 and the height values z i , z t , z b of the hopper 100, the data points 111, 131, 141 of the hopper 100 are identified as: the top wall point 131, distributed along the top wall 130, having the maximum and constant height value z t ; the bottom wall point 141, distributed along the bottom wall 140, having a constant height value z g that is greater than the height value z t of the ground point 510 and smaller than the height value z b of the top wall point 131; and the inner wall point 111, distributed along the inner wall 110, having a height value z b that varies within the range defined by the height value z t of the bottom wall point 141 and the height value z i of the top wall point 131. For the sake of convenience of description, the height values z g , z i , z t , z b are all measured starting from the origin O of the space rectangular coordinate system, that is, the position where the sensor 661 is located. Figure 3 In it, the direction indicated by the z-axis is the negative direction, so that the height values z g , z i , z t , z b are all negative numbers. Figure 3 In it, the direction indicated by the x-axis is the positive direction, and the direction opposite to the direction indicated by the x-axis is the negative direction. The detection area 160 is defined as the bottom wall point 141 that is at a distance d a (see Figure 2 ) from the inner wall point 111 and away from the center 150 of the hopper 100. (For the sake of clarity, Figure 3Only the region composed of partial bottom wall points 141 distributed along the bottom wall 140 is shown, where 15 cm ≤ d a ≤ 50 cm.

[0036] The alignment step S1200 includes: determining the coordinates of the center 150 of the hopper 100 according to the coordinates of the top wall point 131, the bottom wall point 141, and the inner wall point 111 in the plane xy perpendicular to the vertical direction D3, and correcting the position of the hopper 100 so that the center 150 is aligned with the loading port 200 along the transverse direction D1.

[0037] The detection area 160 for detecting whether the material 400 is full, which is near the inner wall 110 of the hopper 100 far from the loading port 200, includes: collecting data points of the material 400 in the detection area 160 of the hopper 100 and identifying the data points of the material 400 as material points 410. As Figure 3 shown, the material points 410 are schematically shown arranged in two columns along the vertical direction D3, and the material points 410 have a height value z with a larger variation than the height value z of the bottom wall point 141 b . Detect the height value z of the top wall point 131 m and the difference between the height value z of the material points 410 t to determine whether it is less than or equal to the threshold as the material 400 accumulates. In this way, it is possible to judge the total amount of the loaded material 400 while loading the material 400, greatly improving the efficiency of the loading detection. m The detection area 160 for detecting whether the material 400 is full, which is near the inner wall 110 of the hopper 100 far from the loading port 200, is executed in the following manner: If every time a material point 410 satisfying z

[0038] ≥ z m ≥ z t - z diffth and x > 0 appears in the detection area 160, then the value of c p increases by 1; if every time a material point 410 satisfying z m ≥ z t - z diffth and x < 0 appears in the detection area 160, then the value of c n increases by 1; if c p ≥ c th and c n ≥ c th , it means that the material 400 fills the detection area 160 near the inner wall 110 of the hopper 100 far from the loading port 200; and if c p ≥ c th and c n = 0, or c n ≥ c th and cp = 0 indicates that the material 400 is unevenly distributed on the bottom wall 140; where z m is the height value of the material point 410, z t is the height value of the top wall point 131, z diffth is the height value z of the top wall point 131 t and the height value z of the material point 410 m is the threshold of the difference, c p is the counter for the material point 410 with an x - coordinate greater than 0, c n is the counter for the material point 410 with an x - coordinate less than 0, c th is c p and c n is the threshold of c p and c n The initial values of and c are 0.

[0039] The method 1000 further includes an adjustment step S1600: If c p ≥ c th and c n = 0, this indicates that the part of the detection area 160 with an x - coordinate less than 0 is not fully filled, then the hopper 100 moves a distance d p in the positive x - axis direction, so that the loading port 200 fills the unfilled part specifically to continue the loading step S1300; and if c n ≥ c th and c p = 0, this indicates that the part of the detection area 160 with an x - coordinate greater than 0 is not fully filled, then the hopper 100 moves a distance d n in the negative x - axis direction, so that the loading port 200 fills the unfilled part specifically to continue the loading step S1300, where 40cm ≤ d p ≤ 80cm, 40cm ≤ d n ≤ 80cm. The adjustment step S1600 can finely adjust the position of the hopper 100 during the loading process to ensure that the material 400 is evenly loaded in the hopper 100, and thus can also eliminate the center - of - gravity shift of the hopper 100 caused by the uneven loading of the material 400.

[0040] The method 1000 further includes a denoising step S1400 located between the loading step S1300 and the judgment step S1500: If the material point satisfies r < r th , this indicates that the material point represents dust composed of fine particles with relatively large gaps between each other, and the dust causes only a small amount of electromagnetic waves to be reflected back by its fine particles, so the reflectivity value is low, then the material point needs to be removed; if the material point satisfies r ≥ r th, which indicates that the material point 410 represents the material 400 filled in the carriage 100 with very small gaps between each other, then the material point 410 is retained; where r is the reflectivity of the material point 410, and r th is the reflectivity threshold of the reflectivity.

[0041] The denoising step further includes: setting a circle in the xy plane with the material point 410 as the center and a radius of R (see Figure 4 ); if there are only n or fewer adjacent material points 410 to the material point 410 as the center that satisfy d z < d zth , this indicates that the material point 410 as the center has fewer adjacent material points and is a particle or flying stone suspended in the air, then the material point 410 as the center is removed; and if there are n or more adjacent material points 410 to the material point 410 as the center that satisfy d z < d zth , this indicates that the material point 410 as the center has more adjacent points and is the material 400 filled in the carriage 100, then the material point 410 as the center is retained; where d z is the distance of the adjacent material point from the circle along the z-axis or the vertical direction D3, and d zth is the threshold of d z , 5 cm ≤ d zth ≤ 10 cm, 5 ≤ n ≤ 20, 5 cm ≤ R ≤ 30 cm.

[0042] By adopting the denoising step, the noise interference can be effectively reduced, the detection accuracy can be improved, so that the method 1000 is applicable to the harsh environment with much dust in the mine scene and meets the actual application requirements.

[0043] While the method 1000 according to the present invention meets the standards of unmanned, automated, and intelligent, it also greatly eliminates the gap between unmanned operation in the mine and manual operation in terms of operation process and operation efficiency, ensures that the efficiency of unmanned operation in the mine is not lower than that of manual operation, and also reduces the transformation cost of related hardware control devices.

[0044] Figure 6 The schematic block diagram of an exemplary electronic device 60 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0045] As Figure 6 shown, the electronic device 60 includes a computing unit 61 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 62 or a computer program loaded from a storage unit 68 into a random access memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the electronic device 60 can also be stored. The computing unit 61, the ROM 62, and the RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0046] A plurality of components in the electronic device 60 are connected to the I / O interface 65, including: an input unit 66, which, for example, includes the sensor 661, a keyboard, a mouse, etc.; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a magnetic disk, an optical disc, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0047] The computing unit 61 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 61 executes the various methods and processes described above, such as executing the method 1000 for detecting the loading 400 of the hopper 100. For example, in some embodiments, the method 1000 for detecting the loading 400 of the hopper 100 can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 68. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the computing unit 61, one or more steps of the method 1000 for detecting the loading 400 of the hopper 100 described above can be executed. Optionally, in other embodiments, the computing unit 61 can be configured to execute the method 1000 for detecting the loading 400 of the hopper 100 in any other suitable manner (e.g., by means of firmware).

[0048] It should be understood that the various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present invention can be achieved, and no limitation is imposed herein.

[0049] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0050] The program code for implementing the methods of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0051] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0052] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0053] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0054] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0055] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0056] Those skilled in the art can understand that the above-described embodiments are all exemplary, and those skilled in the art can make improvements thereto. The structures described in various embodiments can be freely combined without conflicts in structure or principle.

[0057] After describing in detail the preferred embodiments of the present invention, those skilled in the art can clearly understand that various changes and modifications can be made without departing from the scope and spirit of the present invention, and the present invention is not limited to the implementation manners of the exemplary embodiments set forth in the specification.

Claims

1. A method for detecting loading of a truck bucket, wherein the truck bucket comprises an inner wall located inside the truck bucket, an outer wall located outside the truck bucket, a top wall connecting adjacent inner walls and outer walls, and a bottom wall located at the bottom of the truck bucket, characterized in that: The method comprises: Collection steps: Collect data; Alignment step: aligning the center of the bucket with the loading port in the lateral direction according to the collected data; Loading steps: open the loading port to load the truck bed; Determining step: detecting whether the material is fully filled in a detection area located near the inner wall of the bucket away from the loading port, if yes, executing the material stopping step, if not, continuing to execute the material loading step; and Stopping step: closing the loading port to stop loading the bucket, then driving the bucket away from the loading port, and performing a collection step for the next bucket, wherein the collected data includes: Collecting data points of the ground below the loading port when there is no bucket, identifying the data points of the ground as ground points and recording height values ​​of the ground points; and Collect data points of the bucket moved below the loading port and record height values ​​corresponding to the data points of the bucket, and then identify the data points of the bucket according to the height values ​​of the ground points and the height values ​​of the bucket as: top wall points, distributed along the top wall, with a maximum and constant height value; bottom wall points, distributed along the bottom wall, with a constant height value greater than the height value of the ground points and smaller than the height value of the top wall points; and inner wall points, distributed along the inner wall, with height values ​​varying within a range defined by the height values ​​of the bottom wall points and the top wall points, The method of detecting whether the material is filled in a detection area located near the inner wall of the bucket far from the loading port comprises: collecting data points of the material loaded into the bucket in the detection area and identifying the data points of the material as material points, wherein the material points have a height value with a greater change than the height value of the bottom wall point, and detecting whether the difference between the height value of the top wall point and the height value of the material point is less than or equal to a threshold value as the material accumulates, The collecting step also includes setting a spatial rectangular coordinate system before collecting data, the spatial rectangular coordinate system including: a y-axis pointing to and aligning with the charging port in the transverse direction, an x-axis pointing to one end of the bucket in the longitudinal direction, a z-axis pointing to the ground in the vertical direction, and a coordinate origin fixed at a position higher than the charging port, when the center is aligned with the charging port in the transverse direction, the coordinate origin is aligned with the center in the vertical direction, The detection area near the inner wall of the bucket away from the loading port for detecting whether the material is full is performed in the following manner: If there is a z m ≥z t -z diffth and x>0, then c p The value of is increased by 1; If there is a z m ≥z t -z diffth and x<0, then c n The value of is increased by 1; If c p ≥c th And c n ≥c th , it means that the material is fully loaded in the detection area located near the inner wall of the truck bed away from the loading port; and If c p ≥c th And c n =0, or c n ≥c th And c p =0, it means that the material is unevenly distributed on the bottom wall; Among them, z m is the height value of the material point, z t is the height value of the top wall point, z diffth is the threshold value of the difference between the height value of the top wall point and the height value of the material point, c p is a counter for material points with an x-coordinate greater than 0, c n is a counter for material points with an x-coordinate less than 0, c th c p and c n The threshold value, c p and c n The initial value of is 0.

2. The method according to claim 1, characterized in that The aligning step includes determining the coordinates of the center of the bucket based on the coordinates of the top wall point, the bottom wall point and the inner wall point in a plane perpendicular to the vertical direction and correcting the position of the bucket so that the center is aligned with the loading port.

3. The method according to claim 2, characterized in that The detection area is defined by the distance d from the inner wall point a and the area consisting of the bottom wall points away from the center of the bucket, where 15 cm ≤ d a ≤50cm.

4. The method according to claim 3, characterized in that The truck bucket has four inner walls forming a rectangular shape, the four inner walls including an inner wall close to the loading port and three inner walls away from the loading port when the center of the truck bucket is aligned with the loading port in the transverse direction, and the detection area extends only along the three inner walls in a "[" shape.

5. The method according to claim 1, characterized in that Also includes adjustment steps: If c p ≥c th And c n =0, the bucket moves a distance d in the positive direction of the x-axis p , to continue with the loading step; as well as If c n ≥c th And c p =0, the bucket moves a distance d in the negative direction of the x-axis n , to continue with the loading step, Among them, 40cm≤d p ≤80cm, 40cm≤d n ≤80cm.

6. The method according to claim 1 or 5, characterized in that: The sensor is installed at the coordinate origin to collect data points to obtain the reflectivity of the data points to the electromagnetic waves emitted by the sensor and the coordinates of the data points.

7. The method according to claim 6, characterized in that It also includes a denoising step between the loading step and the judgment step: If the material point satisfies r<r th , then remove the material point; as well as If the material point satisfies r ≥ r th , then retain the material point; Among them, r is the reflectivity of the material point, and r th is the reflectivity threshold of the reflectivity.

8. The method according to claim 7, characterized in that The denoising step further comprises: Set a circle with the material point as the center and R as the radius in the xy plane; If there are only n or more than n satisfying d z <d zth The material points adjacent to the material point as the center of the circle are removed; and If there are n or more satisfying d z <d zth If the material point adjacent to the material point as the center of the circle is selected, the material point as the center of the circle is retained; Among them, d z is the distance of the adjacent material point from the circle along the z axis, and d zth is d z The threshold value is 5cm≤d zth ≤10cm, 5≤n≤20, 5cm≤R≤30cm.

9. The method according to any one of claims 1 to 5, 7 and 8, characterized in that ， Among them, z g is the height value of the ground point, is the average height of the ground points, z f is the noise fluctuation range, if z f ≥50cm, it is determined that there is an interfering target on the ground or the installation position is not level.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; a sensor for transmitting collected data to the at least one processor; and a memory, communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

11. A computer program product, characterized in that The computer program product comprises: A computer program which, when executed by a processor, implements the method according to any one of claims 1 to 9.

12. A computer readable medium, characterized in that The computer readable medium stores a computer program, which implements the method according to any one of claims 1 to 9 when executed by a processor.

Images