Method for estimating elevation of road surface in front of axis based on laser radar and related equipment

Abstract

The invention relates to the technical field of automobile intelligent driving, in particular to a method and related equipment for estimating elevation of a road surface in front of an axle based on a laser radar, and the method comprises the steps: obtaining three-dimensional point cloud data of the road surface in front of a vehicle; preprocessing the obtained three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; the elevation information of the road surface in front of the axle is calculated through the road surface feature data and the three-dimensional point cloud data, the elevation information is estimated to obtain an estimation result, the estimation result is fed back to a vehicle automatic driving system, and the elevation estimation work of the road surface in front of the axle is completed. The accuracy of the road surface information in front of the vehicle is improved, and meanwhile the driving safety and stability are improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile intelligent driving technology, and in particular to a method for estimating the elevation of an axle-front road surface based on a laser radar and related equipment. Background Art

[0002] With the rapid development of autonomous driving technology, the ability to perceive the vehicle's driving environment has become critical. As one of the important factors affecting vehicle driving safety, accurate acquisition of road elevation information is crucial for path planning, speed control, and obstacle avoidance decisions of autonomous vehicles.

[0003] The road surface is the main source of vehicle excitation, so the road surface input directly affects the smoothness of the vehicle's driving, ride comfort and handling stability. An effective way to improve these performances is to adjust the vehicle's active suspension system or semi-active suspension system through preview control. The preview control method is divided into inter-axle preview control and front-axle preview control. Inter-axle preview control controls the rear suspension of the vehicle by sensing the vibration of the vehicle's front wheels. Due to factors such as control algorithm calculation, sensor data acquisition delay and actuator response time, control hysteresis will occur. Front-axle preview control can effectively solve the above problems, but it needs to obtain the road surface information in front of the vehicle as input to provide data support and assist the vehicle to operate better. However, when collecting the road surface information in front of the vehicle, the road elevation estimation accuracy is often low and the real-time performance is poor, resulting in low accuracy of the road surface information collected in front of the vehicle. Therefore, it is of great significance to develop an efficient and accurate road elevation estimation method based on lidar. Summary of the invention

[0004] The purpose of the present invention is to provide a method and related equipment for estimating the elevation of the road surface ahead of the axle based on laser radar, so as to solve the technical problems of low accuracy and poor real-time performance of the road surface elevation estimation in the prior art.

[0005] The present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for estimating the elevation of a road surface ahead of an axle based on a laser radar, comprising: Obtain three-dimensional point cloud data of the road surface in front of the vehicle; Preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The elevation information of the road surface in front of the axle is calculated through road feature data and three-dimensional point cloud data, the elevation information is estimated to obtain an estimation result, and the estimation result is fed back to the vehicle's automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0006] Preferably, in the step of acquiring three-dimensional point cloud data of the road surface in front of the vehicle, a laser beam is emitted by a laser radar, and the laser beam scans the road surface in front of the vehicle and then feeds back three-dimensional point cloud data.

[0007] Preferably, the step of preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data specifically includes: denoising, filtering and aligning the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data.

[0008] Preferably, in the step of extracting the preprocessed pavement key point data to obtain pavement feature data, the pavement feature data includes geometric features, texture features and pavement structure features; wherein the geometric features include height, slope and curvature; and the pavement structure features include interlocking structure, concrete structure and fine-grained structure.

[0009] Preferably, in the step of calculating the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, the specific process includes: A neural network is used to learn road feature data and three-dimensional point cloud data, and an elevation information model is obtained by training. The road feature data and three-dimensional point cloud data are then input into the elevation information model for training to obtain elevation information, wherein the trained elevation information is compared and verified with the elevation data measured in the field. When there is an error, the road feature data and three-dimensional point cloud data are optimized and re-input into the elevation information model for training, and vice versa, the elevation information is estimated to obtain an estimated result.

[0010] Furthermore, in the step of comparing and verifying the elevation information obtained through training with the elevation data obtained through field measurement, the elevation data points obtained through field measurement are matched with the elevation data points predicted by the training model. When errors exist, the elevation errors between each matching point are calculated, and based on the distribution of the elevation errors between each matching point, areas with larger errors are identified. The road feature data and three-dimensional point cloud data in the areas with larger errors are then optimized and adjusted.

[0011] Furthermore, in the step of estimating the elevation information to obtain an estimation result, the elevation information includes a road surface slope assessment result, a road surface height change assessment result, and a road surface flatness assessment result; The data in the elevation model is used to calculate the ratio of the elevation difference between adjacent points to the horizontal distance to obtain the slope information assessment result; By analyzing the elevation value changes in the elevation model, the height change characteristics of the road surface can be identified, and the height change characteristics include convexities and concavities; According to the elevation model, the elevation difference between two adjacent measuring points is calculated. For the entire measuring section, the elevation differences between all adjacent measuring points are averaged to obtain the average elevation difference. Combined with the reference distance of the road surface in front of the vehicle, the road surface smoothness evaluation result is obtained. The specific formula is as follows: text Flatness index = average elevation difference / reference distance.

[0012] In a second aspect, the present invention provides a system for estimating the elevation of a road surface ahead of an axle based on a laser radar, characterized in that it includes: A data acquisition module, used to acquire three-dimensional point cloud data of the road surface in front of the vehicle; A data processing module is used to preprocess the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extract the preprocessed road surface key point data to obtain road surface feature data; The data estimation module is used to calculate the elevation information of the road surface in front of the axle through road feature data and three-dimensional point cloud data, estimate the elevation information to obtain an estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0013] In a third aspect, the present invention also provides a mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for estimating the elevation of the road surface ahead of the axle based on laser radar are implemented as described above.

[0014] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the steps of the method for estimating the elevation of the road surface ahead of the axle based on laser radar are implemented as described above.

[0015] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides a method for estimating the elevation of the road surface in front of the axle based on laser radar. The three-dimensional point cloud data of the road surface in front of the vehicle is obtained by laser radar. The laser radar can provide high-precision three-dimensional point cloud data, which is suitable for vehicles driving on different roads. It can better analyze feedback data and help accurately estimate the elevation information such as road surface characteristics, structures, obstacles, etc., thereby improving the driving comfort. The three-dimensional point cloud data of the road surface in front of the vehicle obtained is pre-processed to obtain the pre-processed road surface key point data, and the pre-processed road surface key point data is extracted to obtain the road surface feature data, which greatly enhances the feedback rate and the accuracy of information, and can monitor the elevation change of the road surface at the front axle position of the vehicle in real time, and the driving behavior is better guaranteed by data. The elevation information of the road surface in front of the axle is calculated by the road surface feature data and the three-dimensional point cloud data, and the elevation information is estimated to obtain the estimation result, which improves the road surface elevation estimation accuracy, ensures real-time performance, increases the accuracy of the road surface information in front of the vehicle, and also improves the driving safety and stability.

[0016] Furthermore, by estimating the elevation information of the road surface in front of the axle in real time, the present invention enables the autonomous driving system to promptly detect and avoid obstacles on the road surface, thereby reducing the risk of traffic accidents; high-precision road elevation estimation helps the autonomous driving system adjust the vehicle suspension system, reduce the sense of bumpiness, and improve the driving comfort of passengers. Based on the road elevation information, the autonomous driving system can optimize the vehicle's acceleration, deceleration, and steering strategies, reduce unnecessary energy consumption, and improve fuel economy or battery life. By estimating the elevation of different road conditions, the autonomous driving system can respond to various complex scenarios more flexibly, improving the adaptability and robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for estimating the elevation of a road surface ahead of an axle based on a laser radar in an embodiment of the present invention; Figure 2 Schematic diagram of the structure of the axle front road elevation estimation system based on laser radar in an embodiment of the present invention; Figure 3 A schematic diagram of a mobile terminal in an embodiment of the present invention; In the figure: 1-data acquisition module; 2-data processing module; 3-data estimation module. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] The present invention is further described in detail below in conjunction with the accompanying drawings: The purpose of the present invention is to provide a method and related equipment for estimating the elevation of the road surface ahead of the axle based on laser radar, so as to solve the technical problems of low accuracy and poor real-time performance of the road surface elevation estimation in the prior art.

[0021] Example 1 See also Figure 1 In one embodiment of the present invention, a method for estimating the elevation of a road surface ahead of an axle based on a laser radar is provided, comprising the following process: Step 1, obtaining three-dimensional point cloud data of the road surface in front of the vehicle; Specifically, in the step of obtaining the three-dimensional point cloud data of the road surface in front of the vehicle, a laser beam is emitted by a laser radar, and the laser beam scans the road surface in front of the vehicle and then feeds back the three-dimensional point cloud data.

[0022] Step 2, preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; Specifically, the acquired three-dimensional point cloud data of the road surface in front of the vehicle is preprocessed to obtain preprocessed road surface key point data, which specifically includes: denoising, filtering and aligning the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data.

[0023] In this embodiment, denoising is the first step in the preprocessing of the three-dimensional point cloud data, which aims to remove noise points in the data, that is, those abnormal points caused by measurement errors, environmental interference or equipment accuracy problems. These noise points may interfere with subsequent data analysis and processing, so they must be effectively removed. Filtering is the process of further smoothing the point cloud data and reducing noise and detail fluctuations. Through filtering, the point cloud data can be made smoother, which is conducive to subsequent data analysis and processing. Registration is the process of aligning multiple point cloud data sets with a reference coordinate system. In the processing of three-dimensional point cloud data of the road surface in front of the vehicle, since multiple scanners may be used for scanning or multiple scans may be performed, there is a certain overlap area between the point cloud data obtained. The purpose of registration is to unify these point cloud data into the same coordinate system for subsequent data analysis and processing.

[0024] Specifically, in the step of extracting the preprocessed pavement key point data to obtain pavement feature data, the pavement feature data includes geometric features, texture features and pavement structure features; wherein the geometric features include height, slope and curvature; the pavement structure features include interlocking structure, concrete structure and fine-grained structure.

[0025] In the geometric features of this embodiment, the height refers to the vertical distance of each point on the road surface relative to a reference plane. In the three-dimensional point cloud data, each point contains its X, Y, and Z coordinates, where the Z coordinate represents the height information of the point. By calculating and analyzing these height data, the undulations and overall shape of the road surface can be understood.

[0026] Slope indicates the inclination of the road surface in the horizontal direction. The slope can be obtained by calculating the ratio of the height difference between adjacent points to the horizontal distance. Slope data is of great significance for evaluating the drainage performance of the road, vehicle driving stability and safety, etc.

[0027] Curvature describes the radius of curvature or the change in curvature of the road surface in a curved section. Curvature can be obtained by analyzing the spatial distribution and geometric form of road point cloud data. Curvature data plays a key role in road design, vehicle navigation, and autonomous driving path planning.

[0028] The extraction of texture features can be done by using structure-based methods and statistical data-based methods, including using the gray-level co-occurrence matrix (GLCM) to analyze the gray-level dependency between adjacent points in the point cloud to extract texture features. In addition, wavelet transform, fractal analysis and other techniques can be used to further enrich the description of texture features.

[0029] The interlocking structure in the pavement structure characteristics refers to the structural form formed by the interlocking effect between pavement materials. This structure usually has good anti-skid performance and durability. In point cloud data, the interlocking structure can be identified by analyzing factors such as the distribution, shape and size of pavement materials.

[0030] Concrete structure refers to the road surface structure made of concrete and other materials. Concrete structure has the characteristics of high strength and good stability. In point cloud data, concrete structure can be identified by identifying factors such as the geometric shape, color changes and material properties of the road surface.

[0031] Fine-grained structure refers to the structural form of the road surface composed of fine particles. Fine-grained structure usually has better drainage and anti-skid performance. In point cloud data, fine-grained structure can be identified by analyzing factors such as the roughness, particle distribution and color change of the road surface.

[0032] Step 3: Calculate the elevation information of the road surface in front of the axle through the road feature data and the three-dimensional point cloud data, estimate the elevation information to obtain an estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0033] Specifically, in the step of calculating the elevation information of the road surface in front of the axle through the road surface characteristic data and the three-dimensional point cloud data, the specific process includes: A neural network is used to learn road feature data and three-dimensional point cloud data, and an elevation information model is obtained by training. The road feature data and three-dimensional point cloud data are then input into the elevation information model for training to obtain elevation information, wherein the trained elevation information is compared and verified with the elevation data measured in the field. When there is an error, the road feature data and three-dimensional point cloud data are optimized and re-input into the elevation information model for training, and vice versa, the elevation information is estimated to obtain an estimated result.

[0034] In this embodiment, the entire process is based on a large amount of road feature data and three-dimensional point cloud data for training and learning, and the elevation information model is obtained in a data-driven manner. The neural network has a strong nonlinear mapping ability and can learn the relationship between complex inputs and outputs. In this process, the neural network predicts the elevation information by learning the mapping relationship between road feature data and three-dimensional point cloud data and elevation information. Through continuous model verification and optimization process, the prediction accuracy and generalization ability of the model are gradually improved. When it is found that there is a large error between the model prediction result and the field measurement data, iterative optimization is performed by optimizing the input data or adjusting the model parameters.

[0035] Specifically, in the step of comparing and verifying the elevation information obtained through training with the elevation data measured in the field, the elevation data points measured in the field are matched with the elevation data points predicted by the training model. When there is an error, the elevation error between each matching point is calculated, and based on the distribution of the elevation error between each matching point, the area with large error is identified, and the road feature data and three-dimensional point cloud data in the area with large error are optimized and adjusted.

[0036] Specifically, in the step of estimating the elevation information to obtain an estimation result, the elevation information includes a road surface slope assessment result, a road surface height change assessment result, and a road surface flatness assessment result; The data in the elevation model is used to calculate the ratio of the elevation difference between adjacent points to the horizontal distance to obtain the slope information assessment result; By analyzing the elevation value changes in the elevation model, the height change characteristics of the road surface can be identified, and the height change characteristics include convexities and concavities; According to the elevation model, the elevation difference between two adjacent measuring points is calculated. For the entire measuring section, the elevation differences between all adjacent measuring points are averaged to obtain the average elevation difference. Combined with the reference distance of the road surface in front of the vehicle, the road surface smoothness evaluation result is obtained. The specific formula is as follows: text Flatness index = average elevation difference / reference distance.

[0037] In summary, the present invention provides a method for estimating the elevation of the road surface in front of the axle based on laser radar. The three-dimensional point cloud data of the road surface in front of the vehicle is obtained by laser radar. The laser radar can provide high-precision three-dimensional point cloud data, which is suitable for vehicles driving on different roads. It can better analyze feedback data and help accurately estimate the elevation information such as road surface characteristics, structures, obstacles, etc., thereby improving the driving comfort. The three-dimensional point cloud data of the road surface in front of the vehicle obtained is preprocessed to obtain the preprocessed road surface key point data, and the preprocessed road surface key point data is extracted to obtain the road surface feature data, which greatly enhances the feedback rate and the accuracy of information, and can monitor the elevation change of the road surface at the front axle position of the vehicle in real time, and the driving behavior is better guaranteed by data. The elevation information of the road surface in front of the axle is calculated by road surface feature data and three-dimensional point cloud data, and the elevation information is estimated to obtain an estimation result, which improves the road surface elevation estimation accuracy, ensures real-time performance, increases the accuracy of the road surface information in front of the vehicle, and also improves the driving safety and stability.

[0038] Example 2 according to Figure 2 As shown, this embodiment provides a system for estimating the elevation of a road surface ahead of an axle based on a laser radar, comprising a data acquisition module 1, a data processing module 2 and a data estimation module 3; Data acquisition module 1, used to acquire three-dimensional point cloud data of the road surface in front of the vehicle; Data processing module 2, used for preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The data estimation module 3 is used to calculate the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, estimate the elevation information to obtain the estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0039] Example 3 The present invention also provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, such as a laser radar-based axle front road elevation estimation program, such as Figure 3 shown.

[0040] When the processor executes the computer program, the steps of the above-mentioned method for estimating the elevation of the road surface in front of the axle based on laser radar are implemented, for example: Obtain three-dimensional point cloud data of the road surface in front of the vehicle; Preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The elevation information of the road surface in front of the axle is calculated through road feature data and three-dimensional point cloud data, the elevation information is estimated to obtain an estimation result, and the estimation result is fed back to the vehicle's automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0041] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example: Data acquisition module 1, used to acquire three-dimensional point cloud data of the road surface in front of the vehicle; Data processing module 2, used for preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The data estimation module 3 is used to calculate the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, estimate the elevation information to obtain the estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0042] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the mobile terminal.

[0043] For example, the computer program may be divided into a data acquisition module 1, a data processing module 2 and a data estimation module 3; The specific functions of each module are as follows: Data acquisition module 1, used to acquire three-dimensional point cloud data of the road surface in front of the vehicle; Data processing module 2, used for preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The data estimation module 3 is used to calculate the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, estimate the elevation information to obtain the estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

[0044] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.

[0045] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the mobile terminal by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0046] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0047] Example 4 The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method for estimating the elevation of the road surface ahead of the axle based on laser radar are implemented.

[0048] If the module / unit integrated in the mobile terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0049] Based on this understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned aggregate reinforcement learning resource scheduling method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0050] The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0051] It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for estimating the elevation of the road surface ahead of the axle based on laser radar, characterized in that: include Obtain three-dimensional point cloud data of the road surface in front of the vehicle; Preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; The elevation information of the road surface in front of the axle is calculated through road feature data and three-dimensional point cloud data, the elevation information is estimated to obtain an estimation result, and the estimation result is fed back to the vehicle's automatic driving system to complete the elevation estimation of the road surface in front of the axle.

2. The method for estimating the elevation of the road surface before the axle based on laser radar according to claim 1, characterized in that: In the step of obtaining the three-dimensional point cloud data of the road surface in front of the vehicle, a laser beam is emitted by a laser radar, and the laser beam scans the road surface in front of the vehicle and then feeds back the three-dimensional point cloud data.

3. The method for estimating the elevation of the road surface before the axle based on laser radar according to claim 1, characterized in that: The step of preprocessing the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data specifically includes: performing denoising, filtering and registration operations on the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data.

4. The method for estimating the elevation of the road surface before the axle based on laser radar according to claim 1, characterized in that: In the step of extracting the preprocessed pavement key point data to obtain pavement feature data, the pavement feature data includes geometric features, texture features and pavement structure features; wherein the geometric features include height, slope and curvature; and the pavement structure features include interlocking structure, concrete structure and fine-grained structure.

5. The method for estimating the elevation of the road surface before the axle based on laser radar according to claim 1, characterized in that: In the step of calculating the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, the specific process includes: A neural network is used to learn road feature data and three-dimensional point cloud data, and an elevation information model is obtained by training. The road feature data and three-dimensional point cloud data are then input into the elevation information model for training to obtain elevation information, wherein the trained elevation information is compared and verified with the elevation data measured in the field. When there is an error, the road feature data and three-dimensional point cloud data are optimized and re-input into the elevation information model for training, and vice versa, the elevation information is estimated to obtain an estimated result.

6. The method for estimating the elevation of the road surface ahead of the axle based on laser radar according to claim 5, characterized in that: In the step of comparing and verifying the elevation information obtained through training with the elevation data measured in the field, the elevation data points measured in the field are matched with the elevation data points predicted by the training model. When errors exist, the elevation errors between each matching point are calculated, and based on the distribution of the elevation errors between each matching point, areas with large errors are identified, and the road feature data and three-dimensional point cloud data in the areas with large errors are optimized and adjusted.

7. The method for estimating the elevation of the road surface before the axle based on laser radar according to claim 5, characterized in that: In the step of estimating the elevation information to obtain an estimation result, the elevation information includes a road surface slope assessment result, a road surface height change assessment result, and a road surface flatness assessment result; The data in the elevation model is used to calculate the ratio of the elevation difference between adjacent points to the horizontal distance to obtain the slope information assessment result; By analyzing the elevation value changes in the elevation model, the height change characteristics of the road surface can be identified, and the height change characteristics include convexities and concavities; According to the elevation model, the elevation difference between two adjacent measuring points is calculated. For the entire measuring section, the elevation differences between all adjacent measuring points are averaged to obtain the average elevation difference. Combined with the reference distance of the road surface in front of the vehicle, the road surface smoothness evaluation result is obtained. The specific formula is as follows: text Flatness index = average elevation difference / reference distance.

8. A laser radar-based system for estimating the elevation of the road surface ahead of the axle, characterized in that: include A data acquisition module (1) is used to acquire three-dimensional point cloud data of the road surface in front of the vehicle; A data processing module (2) is used to pre-process the acquired three-dimensional point cloud data of the road surface in front of the vehicle to obtain pre-processed road surface key point data, and extract the pre-processed road surface key point data to obtain road surface feature data; The data estimation module (3) is used to calculate the elevation information of the road surface in front of the axle through the road surface feature data and the three-dimensional point cloud data, estimate the elevation information to obtain an estimation result, and feed the estimation result back to the vehicle automatic driving system to complete the elevation estimation of the road surface in front of the axle.

9. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for estimating the elevation of the road surface ahead of the axle based on laser radar are implemented as described in any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for estimating the elevation of the road surface ahead of the axle based on laser radar are implemented as described in any one of claims 1 to 7.

Images