Retaining wall dynamic identification method and system

Abstract

The invention discloses a retaining wall dynamic identification method and system, and the method comprises the steps: carrying out the automatic coarse positioning of the position of a retaining wall through the positioning information of a vehicle body, camera data, laser radar data and other multi-sensing data when the vehicle body enters a waste dump area, and carrying out the combined recognition and positioning of the position of the retaining wall through combining with the information of surrounding vehicles, therefore, high-precision and real-time retaining wall area information is provided for the vehicles, the dumping operation can be directly carried out in a new dumping area under the condition that acquisition in advance is not needed, meanwhile, when the retaining wall area changes, the area between the vehicles can be effectively identified, and the dynamic identification of the position of the retaining wall can be really realized in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of retaining wall identification, and more specifically, to a retaining wall dynamic identification method and system. Background Art

[0002] The retaining wall of the mine dump plays a vital role in the safety of the mine. Traditional manned vehicles mainly rely on manual visual identification of retaining walls, and at the same time combine the force information of the vehicle to accurately control the vehicle during dumping, ensuring that the dump is not left in the dump, and preventing the vehicle from crossing the dump wall, causing rollover accidents and casualties. After the unmanned vehicles in the mine area began to operate, the identification and positioning of retaining walls became one of the key factors restricting the efficiency of the unmanned driving system. At present, unmanned vehicles mainly have the following ways to identify retaining walls:

[0003] 1. By establishing the trajectory of bulldozers and other operating equipment when building retaining walls, the position of the retaining wall is manually edited and determined. This has the advantages of high precision and accurate data. However, due to the slow changes in the position of the retaining wall or temporary maintenance, the validity of its position data gradually decreases after the data is generated. At the same time, as time goes by, it may become invalid after 1 to 2 weeks, which brings greater safety risks to the long-term operation of the unmanned driving system and a faster rate of efficiency decline.

[0004] Second, real-time identification through roadside cameras or lidar can effectively make up for the real-time problems caused by manual editing of trajectory lines. However, since the retaining wall is not straight, the data validity of the blocked area is poor. In addition, with the intensive operation of vehicles, there are many areas that are continuously blocked during operation, the ability to perceive local changes is weak, and the accuracy is limited, and there are still safety risks.

[0005] 3. By deploying positioning markers, optical fibers and other equipment on the retaining wall, the displacement of the retaining wall can be monitored in real time. The data information is accurate and real-time, but the system is often not recoverable, the investment is large, and the system is difficult to maintain. It cannot be quickly repaired after local damage, and the repeated investment after the retaining wall is moved is also large. It is not suitable for the needs of long-term large-scale operations in mining areas.

[0006] In addition, the above three identification methods all require the pre-collection of environmental information of the retaining wall in order to provide an effective soil discharge position for the unmanned driving system in subsequent operations.

[0007] In summary, at this stage, there is an urgent need to develop a retaining wall dynamic identification method and system to solve the above-mentioned technical problems. Summary of the invention

[0008] An object of the present invention is to provide a new technical solution for a retaining wall dynamic identification method and system.

[0009] According to a first aspect of the present invention, a method for dynamic identification of a retaining wall is provided, the method comprising:

[0010] Step S1: Recording the initial position of each unmanned vehicle entering the spoil dump area;

[0011] Step S2: Acquire initial image data and initial laser radar data of the retaining wall when the unmanned vehicle is located at the initial position;

[0012] Step S3: determining an initial rough surface of the retaining wall based on the initial image data and the initial laser radar data;

[0013] Step S4: selecting an initial soil discharge area from the initial rough surface;

[0014] Step S5: determining the initial running trajectory and the initial rough collision critical position of the unmanned vehicle according to the initial rough curved surface and the initial soil dumping area;

[0015] Step S6: repeating the above steps S2 to S3, obtaining the rough surfaces of the retaining wall corresponding to multiple positions of the unmanned vehicle in the process of driving from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establishing the rough surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough surface;

[0016] Step S7: Calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of the multiple unmanned vehicles.

[0017] According to the method of the first aspect of the present invention, the step S7 further includes:

[0018] Step S8: determining the current running track of each unmanned vehicle based on the high-precision curved surface of the retaining wall, the current ultrasonic radar data and the inertial navigation data of each unmanned vehicle, so as to control the corresponding unmanned vehicle to run to the corresponding dumping area;

[0019] Step S9: Calculating the supplementary curved surface of the retaining wall based on the position information, ultrasonic radar data and inertial navigation data of multiple positions of the unmanned vehicles in the process of running to the corresponding dumping area according to the corresponding current running tracks;

[0020] Step S10: Generate a high-precision surface of the earth discharge area based on the high-precision surface of the retaining wall and the supplementary surface.

[0021] According to the method of the first aspect of the present invention, the step S10 further comprises: obtaining a hidden crack pit area based on the high-precision curved surface and the supplementary curved surface of the retaining wall.

[0022] According to the method of the first aspect of the present invention, the step S3 specifically comprises: determining the initial rough surface of the retaining wall based on the initial image data, the initial lidar data, and calibration parameters of the camera and the lidar.

[0023] According to the method of the first aspect of the present invention, step S4 specifically comprises: selecting an area at the minimum curvature in the initial rough surface and closest to the unmanned vehicle as the initial soil discharge area, wherein the width of the initial soil discharge area is not less than 2 times the width of the unmanned vehicle.

[0024] According to the method of the first aspect of the present invention, the step S5 specifically comprises: determining the initial running trajectory and the initial rough collision critical position of the unmanned vehicle based on the normal of the initial rough curved surface and the section of the initial soil dumping area.

[0025] According to the method of the first aspect of the present invention, step S7 specifically comprises: using a pre-established artificial intelligence model to process the rough surface matrix of the retaining walls of the multiple unmanned vehicles to obtain a high-precision surface of the retaining wall.

[0026] According to a second aspect of the present invention, a retaining wall dynamic identification system is provided, the system comprising:

[0027] A first processing module is configured to record the initial position of each unmanned vehicle entering the spoil dump area;

[0028] A second processing module is configured to obtain initial image data and initial laser radar data of the retaining wall when the unmanned vehicle is located at the initial position;

[0029] A third processing module is configured to determine an initial rough surface of the retaining wall based on the initial image data and the initial LiDAR data;

[0030] A fourth processing module is configured to select an initial soil dumping area from the initial rough curved surface;

[0031] A fifth processing module is configured to determine a preliminary running trajectory and an initial rough collision critical position of the unmanned vehicle according to the initial rough curved surface and the initial soil dumping area;

[0032] a sixth processing module, configured to calculate the coarse curved surfaces of the retaining wall corresponding to a plurality of positions of the unmanned vehicle in the process of the unmanned vehicle traveling from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establish a coarse curved surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough curved surface;

[0033] The seventh processing module is configured to calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of multiple unmanned vehicles.

[0034] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the method for dynamic identification of a retaining wall as described in the first aspect of the present invention are implemented.

[0035] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method for dynamic identification of a retaining wall as described in the first aspect of the present invention are implemented.

[0036] According to an embodiment disclosed in the present invention, a retaining wall dynamic identification method and system of the present invention has the following beneficial effects:

[0037] The dynamic identification method of retaining walls of the present invention utilizes multiple sensor data such as vehicle positioning information, camera data, and laser radar data to automatically and roughly locate the position of the retaining wall when entering the spoil dump area. At the same time, combined with the surrounding vehicle information, the position of the retaining wall is jointly identified and located, thereby providing vehicles with high-precision, real-time retaining wall area information, and realizing that spoil operations can be directly carried out in a new spoil dump area without prior collection. At the same time, when the retaining wall area changes, the area between vehicles can be effectively identified, thereby truly realizing real-time dynamic identification of the retaining wall position.

[0038] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0040] Figure 1 A schematic diagram of a flow chart of a method for dynamic identification of a retaining wall provided according to an embodiment;

[0041] Figure 2 A structural schematic diagram of a retaining wall dynamic identification system provided according to an embodiment;

[0042] Figure 3 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0043] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0044] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] Embodiment 1:

[0048] See also Figure 1 As shown, an embodiment of the present invention provides a method for dynamic identification of a retaining wall, the method comprising:

[0049] Step S1: Record the initial position of each unmanned vehicle entering the spoil dump area.

[0050] It should be noted that when unmanned vehicles are operating in a mining area, there are often more than two vehicles that need to enter the spoil dump area in sequence or simultaneously to carry out spoil operations. In the method of this embodiment, the initial position of the unmanned vehicle entering the spoil dump area is first recorded, and the initial position of the vehicle can be obtained through a positioning device (such as GPS) on the unmanned vehicle.

[0051] Step S2: Acquire initial image data and initial lidar data of the retaining wall when the unmanned vehicle is at an initial position.

[0052] In the method of this embodiment, when the unmanned vehicle enters the spoil dump area, it is also necessary to simultaneously obtain the initial image data and initial LiDAR data of the retaining wall at the initial position through the on-board camera and LiDAR sensor on the unmanned vehicle.

[0053] Step S3: Determine the initial rough surface of the retaining wall based on the initial image data and the initial LiDAR data.

[0054] Optionally, step S3 in the method of this embodiment is specifically: determining the initial rough surface of the retaining wall based on the initial image data, the initial lidar data, and the calibration parameters of the vehicle-mounted camera and the lidar.

[0055] It should be noted that the initial rough curved surface in this embodiment is a preliminary three-dimensional model of the retaining wall.

[0056] Step S4: selecting an initial dumping area from the initial rough surface;

[0057] Optionally, step S4 in the method of this embodiment is specifically: selecting the area at the minimum curvature in the initial rough surface and closest to the unmanned vehicle as the initial soil dumping area, wherein the width of the initial soil dumping area is not less than twice the width of the unmanned vehicle.

[0058] Step S5: determining the initial running trajectory and the initial rough collision critical position of the driverless vehicle according to the initial rough surface and the initial soil dumping area.

[0059] Optionally, in the method of this embodiment, the initial running trajectory and the initial rough collision critical position of the unmanned vehicle are determined based on the normals of the initial rough curved surface and the initial soil dumping area section.

[0060] It should be noted that in this embodiment, for the unmanned vehicle entering the spoil area, the initial rough surface (i.e., the initial three-dimensional model of the retaining wall) is first determined through the initial image data and the initial laser radar, and then the initial spoil area is determined by the initial rough surface, and then the initial running track and rough collision critical position of the unmanned vehicle are determined based on the initial rough surface and the initial spoil area, so that the unmanned vehicle can first drive according to the initial running track and rough collision critical position. The initial rough surface, initial spoil area, initial running track and rough collision critical position here are not very accurate and need to be further refined later.

[0061] Step S6: Repeat the above steps S2 to S3 to obtain the rough surfaces of the retaining wall corresponding to multiple positions of the unmanned vehicle in the process of driving from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establish the rough surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough surface.

[0062] In the method of this embodiment, while the unmanned vehicle is driving along the initial running trajectory, several positions can be selected to obtain the rough surface of the retaining wall at each position, and then the retaining wall rough surface matrix is ​​established in combination with the initial rough surface.

[0063] It should be noted that the number of positions selected in this embodiment can be 3, 4, 5, etc., which is determined according to actual needs and is not specifically limited here.

[0064] Step S7: Calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of multiple unmanned vehicles.

[0065] Optionally, step S7 in the method of this embodiment is specifically: using a pre-established artificial intelligence model to process the rough surface matrix of the retaining walls of multiple unmanned vehicles to obtain a high-precision surface of the retaining wall.

[0066] It should be noted that in this embodiment, the input retaining wall rough surface matrix can be calculated and processed by the 3D artificial intelligence AI large model to obtain a high-precision surface of the retaining wall. Compared with the initial rough surface established previously, the high-precision surface established in this step has better accuracy and can more accurately plan the running trajectory of the driverless car.

[0067] Step S8: Determine the current running track of each unmanned vehicle based on the high-precision surface of the retaining wall, the current ultrasonic radar data and inertial navigation data of each unmanned vehicle, so as to control the corresponding unmanned vehicle to run to the corresponding earth discharge area.

[0068] In the method of this embodiment, high-precision surfaces, ultrasonic radar data and inertial navigation data are combined to determine the current running trajectory of the unmanned vehicle, thereby improving the trajectory control accuracy of the unmanned vehicle.

[0069] Step S9: Calculating the supplementary curved surface of the retaining wall based on the position information, ultrasonic radar data and inertial navigation data of multiple positions in the process of multiple unmanned vehicles running to the corresponding dumping area according to the corresponding current running tracks;

[0070] Since the retaining wall area is in a state of slow change over a long period of time and is greatly affected by rain and freezing, there may be problems such as hidden cracks and collapse, and local data are changing. Therefore, the high-precision surface may not be able to cover all operating conditions. Therefore, supplementary surfaces of the retaining wall are obtained to supplement it.

[0071] Step S10: Generate a high-precision surface of the earth discharge area based on the high-precision surface of the retaining wall and the supplementary surface.

[0072] Optionally, step S10 in the method of this embodiment further includes: obtaining a hidden crack pit area based on the high-precision curved surface and the supplementary curved surface of the retaining wall.

[0073] In this embodiment, the supplementary surface can be superimposed on the high-precision surface of the retaining wall to generate high-precision surfaces of all soil discharge areas in real time. At the same time, it can assist in generating hidden crack pit areas to reduce the risk of subsequent vehicles getting stuck.

[0074] The following is a detailed description of the dynamic identification method of a retaining wall according to an embodiment of the present invention using a specific embodiment:

[0075] 1. When unmanned vehicles are operating in the mining area, there are often more than two vehicles in the retaining wall area that need to enter the dump area in sequence or simultaneously to carry out dumping operations;

[0076] 2. When the first vehicle M1 enters the dumping area, its initial position P1 is recorded. Based on the vehicle camera data C, the laser radar data L, and the calibration parameters T of the two, the initial rough surface A1B1 of the retaining wall can be obtained. The area with the lowest curvature of the initial rough surface and closest to the vehicle is selected as the initial dumping area L, where L is not less than twice the width of the vehicle;

[0077] 3. According to the normal F of the section of the initial rough surface A1B1 and the initial soil dumping area L, determine the initial running trajectory, and automatically run to the collision critical point P2 in the area without collision risk;

[0078] 4. During the operation of the first vehicle, a series of rough surfaces A2B2~AnBn can be formed through a series of points between P1 and P2, and combined with A1B1 to form a matrix [P, AB];

[0079] 5. At the same time, more than one other vehicle in the dump area gradually enters the dump area, and these vehicles M2~Mn also form corresponding running trajectories PM21PM22~PMn1PMn2, which are recorded together with the matrix of the first vehicle as the retaining wall rough surface matrix [M, P, AB];

[0080] 6. The input matrix [M, P, AB] is calculated by the 3D artificial intelligence AI model to obtain the high-precision surface A'B' of the retaining wall;

[0081] 7. The unmanned vehicle moves to the dumping area P3 based on the high-precision curved surface A'B' of the retaining wall, as well as the ultrasonic radar data R and inertial navigation data G of the vehicle;

[0082] 8. Since the retaining wall area is in a state of slow change for a long time and is greatly affected by rain and freezing, there may be problems such as hidden cracks and collapses. In addition, the local data is changing, so the high-precision surface may not be able to cover all operating conditions. Therefore, the position information, ultrasonic radar data, and inertial navigation data of the P2 to P3 area are recorded as a matrix [P, R, G];

[0083] 9. The [P, R, G] data is trained through the artificial intelligence AI big model to obtain the supplementary surface A"B" of the retaining wall. By superimposing the supplementary surface A"B" with the high-precision surface A'B', the high-precision surface AoBo of all soil discharge areas can be generated in real time. At the same time, it can assist in the generation of hidden crack pit area F to reduce the risk of subsequent vehicles getting stuck.

[0084] The retaining wall dynamic identification method of the embodiment of the present invention has the following advantages:

[0085] 1. No prior surveying or mapping is required to enter the dumping area for operation;

[0086] 2. The fusion of multi-sensor data across vehicles can generate high-precision real-time spoil wall surface. The more vehicles there are in the common recognition method, the more occlusions there are, and the lower the data accuracy is. However, the more vehicles there are in the method of the present invention, the higher the accuracy is;

[0087] 3. Provide supplementary surfaces for the contact area between the vehicle and the retaining wall to further improve the accuracy of the retaining wall data, and assist in providing data on hidden cracks and pits to reduce the risk of vehicle getting stuck and improve the safety of soil discharge.

[0088] To summarize, the dynamic identification method of the retaining wall in the embodiment of the present invention utilizes multi-sensor data such as the positioning information of the vehicle body, camera data, and lidar data to automatically and roughly locate the position of the retaining wall when entering the spoil dump area. At the same time, combined with the surrounding vehicle information, the position of the retaining wall is jointly identified and located, thereby providing the vehicle with high-precision and real-time retaining wall area information, so that the spoil dump operation can be carried out directly in the new spoil dump area without prior collection. At the same time, when the retaining wall area changes, the area between vehicles can be effectively identified, thereby truly realizing the dynamic identification of the retaining wall position in real time.

[0089] Embodiment 2:

[0090] The embodiment of the present invention provides a retaining wall dynamic identification system 100, see Figure 2 As shown, the system 100 includes:

[0091] The first processing module 10 is configured to record the initial position of each unmanned vehicle entering the spoil dump area;

[0092] The second processing module 20 is configured to obtain initial image data and initial laser radar data of the retaining wall when the unmanned vehicle is located at the initial position;

[0093] A third processing module 30 is configured to determine an initial rough surface of the retaining wall based on the initial image data and the initial LiDAR data;

[0094] The fourth processing module 40 is configured to select an initial soil dumping area from the initial rough curved surface;

[0095] A fifth processing module 50 is configured to determine a preliminary running trajectory and an initial rough collision critical position of the unmanned vehicle according to the initial rough curved surface and the initial soil dumping area;

[0096] The sixth processing module 60 is configured to calculate the rough curved surfaces of the retaining wall corresponding to multiple positions of the unmanned vehicle in the process of driving from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establish the rough curved surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough curved surface;

[0097] The seventh processing module 70 is configured to calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of the multiple unmanned vehicles.

[0098] Optionally, the retaining wall dynamic identification system of this embodiment further includes:

[0099] an eighth processing module, configured to determine the current running track of each unmanned vehicle based on the high-precision curved surface of the retaining wall, the current ultrasonic radar data and the inertial navigation data of each unmanned vehicle, so as to control the corresponding unmanned vehicle to run to the corresponding earth discharge area;

[0100] A ninth processing module is configured to calculate a supplementary curved surface of the retaining wall based on position information, ultrasonic radar data, and inertial navigation data at multiple positions in the process of the multiple unmanned vehicles running to the corresponding dumping area according to the corresponding current running tracks;

[0101] The tenth processing module is configured to generate a high-precision surface of the soil discharge area based on the high-precision surface of the retaining wall and the supplementary surface.

[0102] Optionally, the tenth processing module in the retaining wall dynamic identification system of the embodiment of the present invention is further configured to obtain the hidden crack pit area based on the high-precision curved surface and supplementary curved surface of the retaining wall.

[0103] Optionally, the third processing module 30 in the retaining wall dynamic recognition system of the embodiment of the present invention is specifically configured to determine the initial rough surface of the retaining wall based on the initial image data, the initial lidar data, and calibration parameters of the camera and the lidar.

[0104] Optionally, the fourth processing module 40 in the retaining wall dynamic identification system of an embodiment of the present invention is specifically configured to select an area at the minimum curvature in the initial rough surface and closest to the unmanned vehicle as the initial soil discharge area, wherein the width of the initial soil discharge area is not less than 2 times the width of the unmanned vehicle.

[0105] Optionally, the fifth processing module 50 in the retaining wall dynamic identification system of the embodiment of the present invention is specifically configured to determine the initial running trajectory and the initial rough collision critical position of the unmanned vehicle based on the normal of the initial rough curved surface and the initial soil dumping area section.

[0106] Optionally, the seventh processing module 70 in the retaining wall dynamic recognition system of the embodiment of the present invention is specifically configured to use a pre-established artificial intelligence model to process the rough surface matrix of the retaining walls of multiple unmanned vehicles to obtain a high-precision surface of the retaining wall.

[0107] Embodiment three:

[0108] The present invention discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a retaining wall dynamic identification method in any one of the first embodiments disclosed in the present invention are implemented.

[0109] Figure 3 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 3 As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the housing of the electronic device, or an external keyboard, touch pad or mouse, etc.

[0110] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] Embodiment 4:

[0112] The embodiment of the present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a retaining wall dynamic identification method in any one of the embodiments of the present invention are implemented.

[0113] Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0115] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for dynamic identification of retaining walls, characterized in that: The method comprises: Step S1: Recording the initial position of each unmanned vehicle entering the spoil dump area; Step S2: Acquire initial image data and initial laser radar data of the retaining wall when the unmanned vehicle is located at the initial position; Step S3: determining an initial rough surface of the retaining wall based on the initial image data and the initial laser radar data; Step S4: selecting an initial soil discharge area from the initial rough curved surface; Step S5: determining the initial running trajectory and the initial rough collision critical position of the unmanned vehicle according to the initial rough curved surface and the initial soil dumping area; Step S6: repeating the above steps S2 to S3, obtaining the rough surfaces of the retaining wall corresponding to multiple positions of the unmanned vehicle in the process of driving from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establishing the rough surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough surface; Step S7: Calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of the multiple unmanned vehicles.

2. The dynamic identification method of retaining wall according to claim 1, characterized in that: After step S7, the following steps are also included: Step S8: determining the current running track of each unmanned vehicle based on the high-precision curved surface of the retaining wall, the current ultrasonic radar data and the inertial navigation data of each unmanned vehicle, so as to control the corresponding unmanned vehicle to run to the corresponding dumping area; Step S9: Calculating the supplementary curved surface of the retaining wall based on the position information, ultrasonic radar data and inertial navigation data of multiple positions of the unmanned vehicles in the process of running to the corresponding dumping area according to the corresponding current running tracks; Step S10: Generate a high-precision surface of the earth discharge area based on the high-precision surface of the retaining wall and the supplementary surface.

3. The dynamic identification method of retaining wall according to claim 2 is characterized in that: The step S10 also includes: obtaining a hidden crack pit area according to the high-precision curved surface and the supplementary curved surface of the retaining wall.

4. The method for dynamic identification of retaining walls according to claim 1, characterized in that: The step S3 specifically includes: determining the initial rough surface of the retaining wall based on the initial image data, the initial lidar data, and the calibration parameters of the camera and the lidar.

5. The method for dynamic identification of retaining walls according to claim 1, characterized in that: The step S4 specifically includes: selecting the area at the minimum curvature in the initial rough surface and closest to the unmanned vehicle as the initial soil dumping area, wherein the width of the initial soil dumping area is not less than 2 times the width of the unmanned vehicle.

6. The method for dynamic identification of retaining walls according to claim 1, characterized in that: The step S5 specifically includes: determining the initial running trajectory and the initial rough collision critical position of the unmanned vehicle according to the normal of the initial rough curved surface and the section of the initial soil dumping area.

7. The method for dynamic identification of retaining walls according to any one of claims 1 to 6, characterized in that: The step S7 specifically includes: using a pre-established artificial intelligence model to process the rough surface matrix of the retaining walls of the multiple unmanned vehicles to obtain a high-precision surface of the retaining wall.

8. A dynamic identification system for retaining walls, characterized in that: The system comprises: A first processing module is configured to record the initial position of each unmanned vehicle entering the spoil dump area; A second processing module is configured to obtain initial image data and initial laser radar data of the retaining wall when the unmanned vehicle is located at the initial position; A third processing module is configured to determine an initial rough surface of the retaining wall based on the initial image data and the initial LiDAR data; A fourth processing module is configured to select an initial soil dumping area from the initial rough curved surface; A fifth processing module is configured to determine a preliminary running trajectory and an initial rough collision critical position of the unmanned vehicle according to the initial rough curved surface and the initial soil dumping area; a sixth processing module, configured to calculate the coarse curved surfaces of the retaining wall corresponding to a plurality of positions of the unmanned vehicle in the process of the unmanned vehicle traveling from the initial position to the initial rough collision critical position according to the preliminary running trajectory, and establish a coarse curved surface matrix of the retaining wall of the unmanned vehicle in combination with the initial rough curved surface; The seventh processing module is configured to calculate the high-precision surface of the retaining wall based on the rough surface matrix of the retaining wall of multiple unmanned vehicles.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in the retaining wall dynamic identification method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for dynamic identification of a retaining wall according to any one of claims 1 to 7 are implemented.

Images