Mine truck collision detection method, system and device and computer readable storage medium

Abstract

The invention discloses a mine truck collision detection method, system and device and a computer readable storage medium, and relates to the technical field of mine hole collision detection, and the method specifically comprises the steps: determining a target safety distance based on the real-time vehicle speed and load of a target mine truck and the real-time roadway curvature of a mine hole wall; and collision detection is carried out according to the real-time distance between the target mine truck and the mine hole wall and the target safety distance. According to the invention, the detection precision of the collision of the mine truck in the mine is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine tunnel collision detection, and particularly relates to a mine truck collision detection method, system, device and computer readable storage medium. BACKGROUND

[0002] With the continuous advancement of smart mine construction, the automatic driving technology of mine trucks has become an important development direction for improving mining efficiency and ensuring operation safety. However, due to the particularity of the mine tunnel environment, such as narrow space, complex structure, no GPS signal and insufficient illumination, the method of detecting the collision of mine trucks by the preset safety distance in the prior art has low precision.

[0003] Therefore, how to improve the detection precision of the collision of mine trucks in the mine tunnel is a problem to be solved at present. SUMMARY

[0004] The present application provides a mine truck collision detection method, system, device and computer readable storage medium, which can improve the detection precision of the collision of mine trucks in the mine tunnel.

[0005] In a first aspect, the present application provides a mine truck collision detection method, which comprises: determining a target safety distance based on the real-time speed and load of a target mine truck and the real-time roadway curvature of a mine tunnel wall; detecting collision according to the real-time distance between the target mine truck and the mine tunnel wall and the target safety distance.

[0006] In combination with the first aspect, in an implementation mode, the target safety distance is determined based on the real-time speed and load of the target mine truck and the real-time roadway curvature of the mine tunnel wall, which comprises: substituting the real-time speed, real-time roadway curvature and load into a first calculation formula to obtain the target safety distance, wherein the first calculation formula is:

[0007] In the formula, is the real-time speed; is the real-time roadway curvature; is the load; is the target safety distance.

[0008] In combination with the first aspect, in an implementation mode, the collision detection according to the real-time distance between the target mine truck and the mine tunnel wall and the target safety distance comprises: if the real-time distance is less than the safety distance, it is determined that there is a collision risk between the target mine truck and the mine tunnel wall; If the real-time distance is not less than the safety distance, it is determined that there is no collision risk between the target mine truck and the mine wall.

[0009] In combination with the first aspect, in an implementation, after the step of determining that there is no collision risk between the target mine truck and the mine wall, the method further includes: obtaining point cloud coordinates of the convex hull vertex of the mine wall, and projecting the point cloud coordinates into a vehicle coordinate system to obtain new point cloud coordinates; determining, based on the new point cloud coordinates and a mine truck safety envelope, whether there is a collision risk between the target mine truck and the mine wall, the mine truck safety envelope being a spatial range in which the target mine truck is located.

[0010] In combination with the first aspect, in an implementation, the determining, based on the new point cloud coordinates and the mine truck safety envelope, whether there is a collision risk between the target mine truck and the mine wall includes: determining whether the new point cloud coordinates are within the mine truck safety envelope; if yes, it is determined that there is a collision risk between the target mine truck and the mine wall; if no, it is determined that there is no collision risk between the target mine truck and the mine wall.

[0011] In combination with the first aspect, in an implementation, before the step of performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance, the method further includes: obtaining a point cloud dataset and a reflection intensity corresponding to each point cloud data in the point cloud dataset; determining, based on the reflection intensity, a preset target mine truck intensity range, and a preset mine wall intensity range, first point cloud data corresponding to the target mine truck and second point cloud data corresponding to the mine wall from the point cloud dataset; compensating the first point cloud data based on IMU data of the target mine truck to obtain modified first point cloud data; determining the real-time distance between the target mine truck and the mine wall according to the second point cloud data and the modified first point cloud data.

[0012] In combination with the first aspect, in an implementation, the compensating the first point cloud data based on the IMU data of the target mine truck to obtain the modified first point cloud data includes: dividing the first point cloud data into multiple point cloud segments according to a preset timestamp; rotating and translating coordinates in each point cloud segment based on the IMU data of the target mine truck to obtain the modified first point cloud data.

[0013] Secondly, the embodiments of the present application provide a mine truck collision detection system, which includes: The first processing module is configured to determine the target safety distance based on the real-time speed and load of the target mine truck and the real-time roadway curvature of the mine wall; The second processing module is configured to perform collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance.

[0014] In a third aspect, an embodiment of the present application provides a mine truck collision detection device, which comprises a processor, a memory, and a mine truck collision detection program stored in the memory and executable by the processor, wherein the mine truck collision detection program, when executed by the processor, implements the steps of the mine truck collision detection method according to any one of the preceding aspects.

[0015] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a mine truck collision detection program, wherein the mine truck collision detection program, when executed by a processor, implements the steps of the mine truck collision detection method according to any one of the preceding aspects.

[0016] The technical scheme provided by the embodiments of the present application has the following beneficial effects: By calculating the dynamic safety distance based on the real-time speed, the real-time roadway curvature and the load, the precision deviation caused by simply relying on the fixed safety distance value set by experience is avoided, and the collision detection precision of the mine truck is greatly improved by performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 FIG. 1 is a flowchart of the mine truck collision detection method according to an embodiment of the present application; Figure 2 FIG. 3 is a detailed flowchart of step S20 in the mine truck collision detection method according to an embodiment of the present application; Figure 1 Figure 3 FIG. 5 is a flowchart of determining the real-time distance between the target mine truck and the mine wall in the mine truck collision detection method according to an embodiment of the present application; Figure 4 FIG. 7 is a hardware structure diagram of the mine truck collision detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] ​In order to make the personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0019] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described in detail with reference to the drawings.

[0020] In a first aspect, the embodiments of the present application provide a mine truck collision detection method.

[0021] In an embodiment, with reference to Figure 1 , Figure 1 The flowchart of the mine truck collision detection method embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the mine truck collision detection method comprises: Figure 1 Step S10: determining a target safety distance based on the real-time speed and load of the target mine truck and the real-time roadway curvature of the mine wall.

[0022] Exemplarily, in the embodiments of the present application, the target safety distance refers to the minimum distance required to ensure the safe driving of the target mine truck in the mine environment, so as to avoid collision or other safety accidents; the target mine truck refers to the mine truck being monitored and requiring the calculation of the target safety distance; the real-time speed of the target mine truck refers to the instantaneous speed of the mine truck when driving in the mine, which is a key factor determining the required safety distance of the mine truck during driving; the load of the target mine truck refers to the sum of the current cargo weight carried by the mine truck and the weight of the truck itself, which affects the stability and braking distance of the mine truck; and the real-time roadway curvature of the mine wall refers to the degree of curvature of the mine wall.

[0023] Specifically, the real-time speed affects the braking time and reaction time, and determines the required safety distance of the mine truck when driving in the mine wall; the load affects the stability and braking efficiency of the mine truck, and the greater the load, the longer the safety distance; and the roadway curvature affects the turning stability and reaction time of the mine truck when driving, and the greater the curvature, the longer the required safety distance. Therefore, the target safety distance can be calculated by combining these parameters together, so as to ensure the safe driving of the mine truck in the complex mine environment, and thus avoid collision and accidents.

[0024] Step S20: performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance.

[0025] ​Exemplarily, in the embodiment of the present application, the real-time distance refers to the instantaneous distance between the target mine truck and the mine wall, which can be measured, calculated and monitored in real time by a sensor device such as a laser radar; and the collision detection is performed by comparing the size relationship between the real-time distance and the target safety distance calculated in advance, so as to avoid the collision of the target mine truck in the complex mine environment.

[0026] The present application calculates the dynamic safety distance based on the real-time vehicle speed, real-time roadway curvature and load, avoids the precision deviation caused by simply relying on the fixed safety distance value set by experience, and performs the collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance, thereby greatly improving the precision of the collision detection of the mine truck.

[0027] Further, in an embodiment, the target safety distance is determined based on the real-time vehicle speed and load of the target mine truck and the real-time roadway curvature of the mine wall, and includes: The real-time vehicle speed, real-time roadway curvature and load are substituted into the first calculation formula to obtain the target safety distance, and the first calculation formula is:

[0028] In the formula, is the real-time vehicle speed; is the real-time roadway curvature; is the load; is the target safety distance.

[0029] Exemplarily, it should be noted that, 1 second is the human physiological reaction time, represents the reaction distance corresponding to the human physiological reaction time; based on the kinetic principle, it can be deduced that the braking distance is proportional to the load, and through the test data, it is deduced that the safety distance increases by 0.03 meters when the mass increases by 1 ton, so the 0.03m in the embodiment is the braking distance, wherein the load here is a dimensionless parameter in calculation; 0.15 is the curve compensation coefficient, and the unit is square meter, so represents the geometric compensation; in summary, the target safety distance = reaction distance + braking distance + geometric compensation.

[0030] Specifically, the real-time vehicle speed , the real-time roadway curvature and the load are substituted into the first calculation formula to obtain the target safety distance .

[0031] For example, when v = 2.78 m / s (10 km / h), m = 80, k = 0.067 m -1At this time, Dsafe = 1.2 x 2.78 + 0.03 x 80 + 0.15 x 0.067 = 3.61 m.

[0032] Further, in an embodiment, referring to Fig. 2, the collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance comprises: Figure 2 Step S201: If it is detected that the real-time distance is less than the safety distance, it is determined that there is a collision risk between the target mine truck and the mine wall. Step S202: If it is detected that the real-time distance is not less than the safety distance, it is determined that there is no collision risk between the target mine truck and the mine wall.

[0033] Illustratively, in the embodiments of the present application, the collision detection can be achieved by comparing the real-time distance between the target mine truck and the mine wall with the target safety distance calculated, if the real-time distance is less than or equal to the target safety distance, it indicates that the distance between the target mine truck and the mine wall is insufficient, and the system can determine that there is a collision risk between the mine truck and the mine wall, and further can trigger an alarm or an automatic avoidance operation; on the contrary, if the real-time distance is greater than the target safety distance, it indicates that the distance between the target mine truck and the mine wall is sufficient, and the system can determine that there is no collision risk between the mine truck and the mine wall, and the target mine truck can continue to drive safely.

[0034] Further, in an embodiment, after the step of determining that there is no collision risk between the target mine truck and the mine wall, further comprising: Obtaining the point cloud coordinates of the mine wall convex hull vertex, and projecting the point cloud coordinates to the vehicle body coordinate system to obtain new point cloud coordinates; Determining whether there is a collision risk between the target mine truck and the mine wall based on the new point cloud coordinates and the mine truck safety envelope, the mine truck safety envelope being a spatial range in which the target mine truck is located.

[0035] Illustratively, in the embodiments of the present application, the mine wall convex hull refers to the protruding part in the mine, and the mine wall convex hull vertex is the boundary point of all protruding parts in the geometric shape of the mine wall; the mine truck safety envelope is a spatial range in which the target mine truck is located, and the specific size thereof can be determined according to the type of the mine truck, which is not limited herein, for example, the mine truck safety envelope can be preferably a spatial range corresponding to 10.5 meters in length x 4.5 meters in width x 4.0 meters in height.

[0036] Specifically, the point cloud data of the mine wall can be obtained by point cloud scanning technology, for example, a 16-line simulation laser radar can be established, with a vertical field of view angle of 30 。 and a horizontal resolution of 0.1 。 ​, single-frame scanning can obtain about 3000 effective point cloud data, the point cloud density reaches 200 points per square meter, and then the coordinates of the mine wall convex hull vertex can be extracted from the point cloud data; The point cloud coordinates are converted from the mine coordinate system to the vehicle coordinate system to obtain new point cloud coordinates, and the relative position between the target mine truck and the mine wall can be correctly represented; Whether the target mine truck and the mine wall exist collision risk is further judged by judging the position relationship between the new point cloud coordinates and the mine truck safety envelope. The principle and implementation process of the point cloud scanning technology are well known in the art, and for the sake of brevity, they will not be described here.

[0037] Further, in an embodiment, the determination of whether the target mine truck and the mine wall exist collision risk based on the new point cloud coordinates and the mine truck safety envelope includes: determining whether the new point cloud coordinates are within the mine truck safety envelope; if yes, it is determined that the target mine truck and the mine wall exist collision risk; if no, it is determined that the target mine truck and the mine wall do not exist collision risk.

[0038] Exemplarily, in the embodiment of the present application, the new point cloud coordinates and the safety envelope of the mine truck can be compared. If the new point cloud coordinates fall within the safety envelope of the mine truck, it means that some parts of the target mine truck have contacted the mine wall, and the system can determine that the mine truck and the mine wall exist collision risk, and then trigger an alarm or automatic avoidance. If the new point cloud coordinates are not within the safety envelope of the mine truck, it means that the target mine truck and the mine wall maintain a sufficient distance, and the system can determine that the mine truck and the mine wall do not exist collision risk, and can continue to drive safely. The above judgment process verifies the situation without collision risk twice, thereby greatly reducing the false positive rate of collision detection.

[0039] Further, in an embodiment, referring to Figure 3 , before the step of performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance, it further includes: Step P10: obtaining a point cloud data set and a reflection intensity corresponding to each point cloud data in the point cloud data set; Step P20: determining first point cloud data corresponding to the target mine truck and second point cloud data corresponding to the mine wall from the point cloud data set based on the reflection intensity, the preset target mine truck intensity range and the preset mine wall intensity range; Step P30: compensating the first point cloud data based on the IMU data of the target mine truck to obtain the corrected first point cloud data; Step P40: determining the real-time distance between the target mine truck and the mine wall according to the second point cloud data and the corrected first point cloud data.

[0040] Exemplarily, in the embodiment of the present application, the reflection intensity reflects the strength of signal return, and is usually used to distinguish the material and distance of different objects; the specific values of the preset target mine truck intensity range and the preset mine wall intensity range can be determined according to actual needs, which are not limited here; the point cloud data set includes the point cloud data of the target mine truck and the point cloud data of the mine wall, but at this time it cannot be distinguished which point cloud data belongs to the target mine truck and which point cloud data belongs to the mine wall, so further determination is needed.

[0041] Specifically, the point cloud data set can be obtained by a laser radar sensor or the like, and the reflection intensity corresponding to each point cloud data can be obtained; then, the point cloud data related to the target mine truck is filtered out from the point cloud data set according to the preset mine truck reflection intensity range, to form the first point cloud data, and the point cloud data related to the mine wall is extracted from the point cloud data set according to the preset mine wall reflection intensity range, to form the second point cloud data; the IMU (Inertial Measurement Unit) provides the motion information of the target mine truck in the three-dimensional space, which usually includes accelerometer data and gyroscope data, i.e., provides the linear acceleration information and angular velocity information of the target mine truck in three axial directions, and the position and attitude (including rotation matrix and displacement vector) of the target mine truck at each time point can be obtained by integrating the linear acceleration and angular velocity; therefore, to improve the detection accuracy, the first point cloud data corresponding to the target mine truck can be compensated by the IMU data of the target mine truck to correct the possible errors thereof, and finally the corrected first point cloud data is obtained.

[0042] It can be understood that the point-to-plane distance calculation method is used, and the shortest distance formula between the target mine truck and the mine wall plane is used to calculate the distance between them in real time, for subsequent collision detection according to the real-time distance; wherein the point-to-plane distance calculation method is a common knowledge in the art, and will not be described here for the sake of brevity.

[0043] Further, in an embodiment, the compensation of the first point cloud data based on the IMU data of the target mine truck to obtain the corrected first point cloud data comprises: dividing the first point cloud data into a plurality of point cloud segments according to a preset time stamp; rotating and translating the coordinates in each point cloud segment based on the IMU data of the target mine truck to obtain the corrected first point cloud data.

[0044] Illustratively, in the embodiments of the present application, the preset timestamp refers to a certain time interval, and the specific value can be determined according to actual needs, which is not limited here, for example, the preset timestamp can be preferably 5ms; the first point cloud data corresponding to the target mine truck can be divided into point cloud data of multiple time periods (i.e. multiple point cloud segments) according to the timestamp, and each point cloud segment represents the point cloud information in a specific time window. This division helps to reduce the calculation complexity of each point cloud segment, reduces the required calculation resources during processing, and makes the subsequent rotation compensation and translation compensation more efficient and accurate.

[0045] Specifically, since the target mine truck will turn or vibrate during movement, its attitude (orientation) will change, which will cause the coordinate system of the point cloud data to rotate relative to the fixed coordinate system. In order to correct this problem, the IMU data corresponding to each point cloud segment can be extracted, and each point cloud coordinate in the point cloud segment can be rotated and transformed according to the rotation matrix in the IMU data, thereby obtaining the new coordinates of each point in the point cloud segment.

[0046] It should be noted that since the position of the target mine truck will change during movement, the overall point cloud will also be translated. In order to solve this problem, translation compensation can be performed based on the displacement information in the IMU data, that is, the new coordinates obtained after rotation compensation can be translated and transformed according to the displacement vector in the IMU data, thereby obtaining the corrected point cloud coordinates. All corrected point cloud coordinates are used as the corrected first point cloud data. The specific implementation process of rotation transformation and translation transformation is well known in the art, and will not be described here for the sake of brevity.

[0047] In a second aspect, the embodiments of the present application also provide a mine truck collision detection system, which comprises: A first processing module for determining a target safety distance based on the real-time speed and load of the target mine truck and the real-time roadway curvature of the mine wall; A second processing module for performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance.

[0048] Further, in an embodiment, the first processing module is specifically configured to: Substitute the real-time speed, real-time roadway curvature and load into the first calculation formula to obtain the target safety distance, and the first calculation formula is:

[0049] In the formula, is the real-time speed; is the real-time roadway curvature; is the load; is the target safety distance.

[0050] Further, in an embodiment, the second processing module is specifically configured to: if the real-time distance is detected to be less than the safety distance, determining that there is a collision risk between the target mine truck and the mine wall; if the real-time distance is detected to be not less than the safety distance, determining that there is no collision risk between the target mine truck and the mine wall.

[0051] Further, in an embodiment, the second processing module is specifically further configured to: obtain point cloud coordinates of the convex hull vertex of the mine wall, and project the point cloud coordinates to the vehicle body coordinate system to obtain new point cloud coordinates; determine, based on the new point cloud coordinates and a mine truck safety envelope, whether there is a collision risk between the target mine truck and the mine wall, the mine truck safety envelope being a spatial range in which the target mine truck is located.

[0052] Further, in an embodiment, the second processing module is specifically further configured to: determine whether the new point cloud coordinates are within the mine truck safety envelope; if yes, determining that there is a collision risk between the target mine truck and the mine wall; if no, determining that there is no collision risk between the target mine truck and the mine wall.

[0053] Further, in an embodiment, the second processing module is specifically further configured to: obtain the point cloud data set and the reflection intensity corresponding to each point cloud data in the point cloud data set; determine, based on the reflection intensity, a preset target mine truck intensity range, and a preset mine wall intensity range, first point cloud data corresponding to the target mine truck and second point cloud data corresponding to the mine wall from the point cloud data set; compensate the first point cloud data based on the IMU data of the target mine truck to obtain modified first point cloud data; determine, according to the second point cloud data and the modified first point cloud data, a real-time distance between the target mine truck and the mine wall.

[0054] Further, in an embodiment, the second processing module is specifically further configured to: divide the first point cloud data into a plurality of point cloud segments according to a preset time stamp; rotate and compensate coordinates in each point cloud segment based on the IMU data of the target mine truck to obtain modified first point cloud data.

[0055] The application calculates a dynamic safety distance based on real-time vehicle speed, real-time tunnel curvature and load, avoids the precision deviation caused by the fixed safety distance value set by experience alone, and performs collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance, thereby greatly improving the precision of mine truck collision detection.

[0056] The functions of each module in the mine truck collision detection system correspond to the steps in the mine truck collision detection method, and the functions and implementation processes are not repeated here.

[0057] In a third aspect, the embodiments of the application provide a mine truck collision detection device. The mine truck collision detection device can be a personal computer (PC), a notebook computer, a server, or other device with data processing function.

[0058] Reference Figure 4 , Figure 4 The hardware structure of the mine truck collision detection device involved in the embodiments of the application is shown in the figure. In the embodiments of the application, the mine truck collision detection device can include a processor, a memory, a communication interface, and a communication bus.

[0059] The communication bus can be of any type, used to interconnect the processor, the memory, and the communication interface.

[0060] The communication interface includes input / output (I / O) interface, physical interface, and logical interface, which are used to interconnect the devices inside the mine truck collision detection device, and are used to interconnect the mine truck collision detection device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0061] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0062] The processor can be a general processor, which can invoke a mine truck collision detection program stored in the memory and execute the mine truck collision detection method provided in the embodiments of the present application. For example, the general processor can be a central processing unit (CPU). The method executed when the mine truck collision detection program is invoked can refer to the embodiments of the mine truck collision detection method of the present application, which will not be described here.

[0063] Those skilled in the art can understand that the hardware structure shown in the above-mentioned Figure 4 The hardware structure shown in the above-mentioned

[0064] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium.

[0065] The computer readable storage medium of the present application stores a mine truck collision detection program, wherein when the mine truck collision detection program is executed by the processor, the steps of the mine truck collision detection method described above are implemented.

[0066] The method implemented when the mine truck collision detection program is executed can refer to the embodiments of the mine truck collision detection method of the present application, which will not be described here.

[0067] It should be noted that the above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0068] The terms "comprising" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device. The terms "first", "second" and "third" and the like descriptions are used to distinguish different objects, and do not represent the order or limit the types of "first", "second" and "third".

[0069] In the description of the embodiments of the present application, "exemplary", "for example" or "for instance" is used to mean as an example, illustration or description. Any embodiment or design scheme described as "exemplary", "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. On the contrary, the words "exemplary", "for example" or "for instance" are used to present the relevant concept in a specific way.

[0070] In the description of the embodiments of the present application, unless otherwise specified, " / " means the meaning of or, for example, A / B can mean A or B; the text "and / or" only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone, and in addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0071] In some of the processes described in the embodiments of the present application, a plurality of operations or steps are included in a specific order, but it should be understood that these operations or steps can be executed or in parallel without the order in which they appear in the embodiments of the present application, and the serial number of the operation is only used to distinguish different operations, and the serial number itself does not represent any execution order. In addition, these processes can include more or fewer operations, and these operations or steps can be executed in sequence or in parallel, and these operations or steps can be combined.

[0072] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) as described above, and includes a plurality of instructions for making a terminal device execute the method described in each embodiment of the present application.

[0073] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method of mine truck collision detection, characterized by, The mine truck collision detection method comprises: determining a target safety distance based on real-time vehicle speed and load of the target mine truck and real-time roadway curvature of the mine wall; performing collision detection according to real-time distance between the target mine truck and the mine wall and the target safety distance.

2. The mining truck collision detection method of claim 1, wherein, The determination of the target safety distance based on the real-time vehicle speed and load of the target mine truck and the real-time roadway curvature of the mine wall comprises: substituting the real-time vehicle speed, the real-time roadway curvature and the load into a first calculation formula to obtain the target safety distance, wherein the first calculation formula is: In the formula, is the real-time vehicle speed; is the real-time tunnel curvature; is the load; is the target safety distance.

3. The mining truck collision detection method of claim 1, wherein, The collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance comprises: if the real-time distance is detected to be less than the safety distance, it is determined that there is a collision risk between the target mine truck and the mine wall; if the real-time distance is detected to be not less than the safety distance, it is determined that there is no collision risk between the target mine truck and the mine wall.

4. The mining truck collision detection method of claim 1, wherein, After the step of determining that there is no collision risk between the target mine truck and the mine wall, the method further comprises: obtaining point cloud coordinates of convex hull vertices of the mine wall and projecting the point cloud coordinates into a vehicle coordinate system to obtain new point cloud coordinates; determining whether there is a collision risk between the target mine truck and the mine wall based on the new point cloud coordinates and a mine truck safety envelope, wherein the mine truck safety envelope is a spatial range in which the target mine truck is located.

5. The mining truck collision detection method of claim 4, wherein, The determination of whether there is a collision risk between the target mine truck and the mine wall based on the new point cloud coordinates and the mine truck safety envelope comprises: determining whether the new point cloud coordinates are within the mine truck safety envelope; if yes, it is determined that there is a collision risk between the target mine truck and the mine wall; if no, it is determined that there is no collision risk between the target mine truck and the mine wall.

6. The mining truck collision detection method of claim 1, wherein, Before the step of performing collision detection according to the real-time distance between the target mine truck and the mine wall and the target safety distance, the method further comprises: obtaining a point cloud dataset and a reflection intensity corresponding to each point cloud data in the point cloud dataset; determining first point cloud data corresponding to the target mine truck and second point cloud data corresponding to the mine wall from the point cloud dataset based on the reflection intensity, a preset target mine truck intensity range and a preset mine wall intensity range; compensating the first point cloud data based on IMU data of the target mine truck to obtain modified first point cloud data; determining the real-time distance between the target mine truck and the mine wall according to the second point cloud data and the modified first point cloud data.

7. The mining truck collision detection method of claim 6, wherein, The compensation of the first point cloud data based on the IMU data of the target mine truck to obtain the modified first point cloud data comprises: dividing the first point cloud data into multiple point cloud segments according to a preset timestamp; rotating and translating coordinates in each point cloud segment based on the IMU data of the target mine truck to obtain the modified first point cloud data.

8. A mine truck collision detection system characterized by, The mine truck collision detection system comprises: a first processing module configured to determine a target safety distance based on real-time vehicle speed and load of the target mine truck and real-time roadway curvature of the mine wall; a second processing module configured to perform collision detection according to real-time distance between the target mine truck and the mine wall and the target safety distance.

9. A mine truck collision detection apparatus, characterized by The mine truck collision detection device comprises a processor, a memory, and a mine truck collision detection program stored on the memory and executable by the processor, wherein the mine truck collision detection program, when executed by the processor, implements the steps of the mine truck collision detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a mine truck collision detection program, wherein the mine truck collision detection program, when executed by a processor, implements the steps of the mine truck collision detection method according to any one of claims 1 to 7.

Images