Multi-sensor fusion vehicle speed estimation method and related device

Abstract

The present invention relates to the field of vehicle speed estimation. Disclosed are a multi-sensor fusion vehicle speed estimation method and a related device, which mainly aim to solve the problem of low accuracy of vehicle speed data acquired from a single channel. The method comprises: determining an initial sensing data set of a target vehicle, wherein the sensing data set comprises sensing vehicle speed data and a corresponding sensor noise standard deviation, and the sensing vehicle speed data is acquired on the basis of a sensor of the target vehicle or a connected sensor; on the basis of an unsupervised clustering algorithm, removing abnormal sensor data in the initial sensing data set so as to determine a target sensing data set; and on the basis of the target sensing data set, determining fused vehicle speed data of the target vehicle. The present invention is used in a multi-sensor fusion vehicle speed estimation process.

Description

Multi-sensor fusion vehicle speed estimation method and related equipment Technical Field

[0001] This invention relates to the field of vehicle speed estimation, and in particular to a multi-sensor fusion vehicle speed estimation method and related equipment. Background Technology

[0002] Vehicle speed estimation algorithms are fundamental to many vehicle control algorithms, such as stability control. By estimating the vehicle's actual speed, these algorithms provide a known quantity that is then passed to other algorithm modules. Therefore, the accuracy of vehicle speed estimation directly impacts other vehicle control algorithms and is a crucial component of vehicle control.

[0003] Current vehicle speed estimation algorithms employ various technical approaches. Some integrate acceleration data from vehicle inertial navigation, but this suffers from accumulated integration errors. Others convert wheel speed into vehicle speed, but these methods are inaccurate during skidding and turning. All of these existing technologies that acquire vehicle speed data from a single source have inherent errors and relatively low accuracy. Summary of the Invention

[0004] In view of the above problems, the present invention provides a multi-sensor fusion vehicle speed estimation method and related equipment, the main purpose of which is to solve the problem of low accuracy of vehicle speed data obtained from a single channel.

[0005] To address at least one of the aforementioned technical problems, in a first aspect, the present invention provides a multi-sensor fusion vehicle speed estimation method, the method comprising:

[0006] Determine the initial sensor data set of the target vehicle, wherein the sensor data set includes the vehicle speed data and the corresponding sensor noise standard deviation, and the vehicle speed data is obtained based on its own sensor or network sensor;

[0007] Abnormal sensor data in the initial sensing data set are removed based on an unsupervised clustering algorithm to determine the target sensing data set;

[0008] The fused vehicle speed data of the target vehicle is determined based on the target sensor data set.

[0009] Optionally, the step of removing abnormal sensor data from the initial sensing data set based on an unsupervised clustering algorithm to determine the target sensing data set includes:

[0010] The aggregation degree of the initial sensing data set is calculated iteratively to obtain an aggregation degree set, wherein the aggregation degree set is sorted by size;

[0011] Determine the maximum clustering degree in the set of clustering degrees;

[0012] If the maximum clustering degree is greater than the preset clustering degree, the sensor dataset corresponding to the maximum clustering degree is obtained as the target sensing data set.

[0013] Optionally, the step of iteratively calculating the clustering degree of the initial sensing data set to obtain a clustering degree set includes:

[0014] Positioning error sensor;

[0015] Remove the vehicle speed data corresponding to the error sensor to obtain a second set of sensor data;

[0016] Obtain the standard deviation of the second sensor data set to determine the degree of clustering.

[0017] Optionally, obtaining the standard deviation of the second sensing data set to determine the clustering degree includes:

[0018] The aggregation degree is calculated based on the following formula:

[0019]

[0020] Where L represents the degree of aggregation. The standard deviation of the second sensor data set and is an adjustable weighting coefficient, and N is the total amount of data in the second sensor data set.

[0021] Optionally, the positioning error sensor includes:

[0022] Determine the average value of the vehicle speed data in the initial sensing data set;

[0023] A vehicle speed difference set is constructed based on the vehicle speed difference between each sensor vehicle speed data in the initial sensor data set and the average value;

[0024] Determine the maximum speed difference in the set of speed differences;

[0025] The sensor corresponding to the maximum vehicle speed difference is determined to be an error sensor.

[0026] Optionally, determining the fused vehicle speed data of the target vehicle based on the target sensing data set includes:

[0027] Obtain the probability density function value of the target sensing data set, wherein the target sensing data set is assumed to follow a normal distribution;

[0028] Using the vehicle speed data in the target sensing data set as single observation data, the probability of the occurrence of the target sensing data set is obtained, wherein the probability is a function of the desired vehicle speed;

[0029] The true vehicle speed corresponding to the case with the highest probability is determined based on the maximum likelihood estimation method;

[0030] The fused vehicle speed data is determined based on the actual vehicle speed corresponding to the case with the highest probability.

[0031] Optionally, determining the fused vehicle speed data based on the actual vehicle speed corresponding to the case with the highest probability includes:

[0032] The fused vehicle speed data is determined based on the following formula:

[0033]

[0034] in, To integrate vehicle speed data, M represents the total amount of target sensor data. For the vehicle speed data in the target sensor dataset, The sensor noise standard deviation corresponding to the vehicle speed data is denoted as .

[0035] Secondly, embodiments of the present invention also provide a multi-sensor fusion vehicle speed estimation device, comprising:

[0036] The first determining unit is configured to determine the initial sensing data set of the target vehicle, wherein the sensing data set includes sensing vehicle speed data and the corresponding sensor noise standard deviation, and the sensing vehicle speed data is obtained based on its own sensor or network sensor.

[0037] The second determining unit is configured to remove abnormal sensor data from the initial sensing data set based on an unsupervised clustering algorithm to determine the target sensing data set;

[0038] The third determining unit is configured to determine the fused vehicle speed data of the target vehicle based on the target sensing data set.

[0039] To achieve the above objectives, according to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein, when the program is executed by a processor, the steps of the multi-sensor fusion vehicle speed estimation method described above are implemented.

[0040] To achieve the above objectives, according to a fourth aspect of the present invention, an electronic device is provided, including at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the multi-sensor fusion vehicle speed estimation method described above.

[0041] By employing the above technical solution, the multi-sensor fusion vehicle speed estimation method and related equipment provided by this invention address the problem of low accuracy in vehicle speed data acquired through single channels. This invention determines an initial sensor data set for the target vehicle, wherein the sensor data set includes sensor speed data and corresponding sensor noise standard deviations, the sensor speed data being acquired based on the vehicle's own sensors or connected sensors. An abnormal sensor data in the initial sensor data set is removed using an unsupervised clustering algorithm to determine a target sensor data set. The fused vehicle speed data for the target vehicle is then determined based on the target sensor data set. In this solution, considering the advent of the intelligent connected vehicle era, each vehicle can obtain multiple vehicle speed estimation information from different sources. For vehicle speed estimation information obtained from multiple sources, the unsupervised clustering algorithm and multi-sensor fusion algorithm are used to fuse the information to obtain the vehicle's own speed estimation information, which has the advantage of higher accuracy compared to vehicle speed data acquired through a single channel.

[0042] Accordingly, the multi-sensor fusion vehicle speed estimation device, equipment, and computer-readable storage medium provided in the embodiments of the present invention also have the above-mentioned technical effects.

[0043] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0044] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0045] Figure 1 shows a flowchart of a multi-sensor fusion vehicle speed estimation method provided by an embodiment of the present invention;

[0046] Figure 2 shows a schematic block diagram of a multi-sensor fusion vehicle speed estimation device provided in an embodiment of the present invention;

[0047] Figure 3 shows a schematic block diagram of the composition of a multi-sensor fusion vehicle speed estimation electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0049] To address the issue of low accuracy in vehicle speed data acquired through single channels, this invention provides a multi-sensor fusion vehicle speed estimation method, as shown in Figure 1. The method includes:

[0050] S101. Determine the initial sensor data set of the target vehicle, wherein the sensor data set includes the vehicle speed data and the corresponding sensor noise standard deviation, and the vehicle speed data is obtained based on its own sensor or network sensor.

[0051] It is important to note that connected vehicle speed sensors that collect the vehicle speed data are classified according to their purpose, not the type of information collected. For example, if a camera collects video information, but a vehicle speed estimation algorithm module is used to estimate vehicle speed from the video, then the camera and the vehicle speed estimation algorithm module can be defined together as a vehicle speed estimation sensor.

[0052] Based on their source, sensors can be divided into two categories: One category is on-board vehicle speed sensors, including but not limited to vehicle speed sensors composed of on-board inertial navigation IMUs, wheel speed counters, and vehicle speed estimation algorithm modules, or vehicle speed sensors composed of on-board cameras and video-based real-time vehicle speed estimation algorithm modules; the other category is connected vehicle speed sensors, including but not limited to smart cameras on intelligent connected roads, vehicle speed estimation algorithm modules based on camera video information, and modules that communicate with vehicles in real time, or other types of connected vehicle speed sensors. Each connected vehicle speed sensor collects speed information from multiple target vehicles and transmits the speed information to the target vehicles in real time.

[0053] Furthermore, considering that sensor information generally contains noise, this embodiment assumes that each sensor can pre-acquire and store the standard deviation of its inherent noise, and maintain and update it. To ensure the effectiveness of data fusion, the vehicle speed sensor simultaneously transmits the standard deviation of its inherent noise while transmitting vehicle speed information in real time.

[0054] Specifically, this application assumes that the target vehicle receives a set of N sensors from the vehicle itself or from the network. } The transmitted signals. Each sensor transmits the target vehicle's speed information and its inherent noise standard deviation. .

[0055] S102. Abnormal sensor data in the initial sensing data set are removed based on an unsupervised clustering algorithm to determine the target sensing data set.

[0056] Based on the above approach, this application considers that data from some sensors may contain errors under specific conditions. For example, estimating vehicle speed using wheel speed can be inaccurate when tires slip, and estimating vehicle speed in real-time using video data collected by cameras can also be inaccurate in extreme weather conditions. Therefore, multiple sensors are needed to complement each other to ensure the accuracy of vehicle speed estimation under various conditions. Although common vehicle speed estimation algorithms classify sensor inaccuracies and use prior knowledge to correct them, such algorithms require manual prediction of potential sensor anomalies and the development of specific countermeasures for different situations.

[0057] The above-mentioned step S102 also includes S1021, S1022, and S1023:

[0058] S1021. Calculate the clustering degree of the initial sensing data set in a loop to obtain a clustering degree set, wherein the clustering degree set is sorted by size.

[0059] The steps in S1021 above also include S10211, S10212 and S10213:

[0060] S10211, Positioning error sensor; specifically, including:

[0061] Determine the average value of the vehicle speed data in the initial sensing data set; construct a vehicle speed difference set based on the vehicle speed difference between each vehicle speed data in the initial sensing data set and the average value; determine the maximum vehicle speed difference in the vehicle speed difference set; determine the sensor corresponding to the maximum vehicle speed difference as an error sensor.

[0062] S10212. Remove the vehicle speed data corresponding to the error sensor to obtain a second set of sensor data;

[0063] S10213. Obtain the standard deviation of the second sensor data set to determine the clustering degree. Specifically, this includes calculating the clustering degree based on the following formula:

[0064]

[0065] Where L represents the degree of aggregation. The standard deviation of the second sensor data set and is an adjustable weighting coefficient, and N is the total amount of data in the second sensor data set.

[0066] S1022. Determine the maximum clustering degree in the set of clustering degrees.

[0067] S1023. If the maximum aggregation degree is greater than the preset aggregation degree, obtain the sensor dataset corresponding to the maximum aggregation degree as the target sensing data set.

[0068] The above steps S1021, S1022, and S1023 specifically include the following 1-9 steps:

[0069] Step 1: Assuming the initial sensor data set contains N vehicle speed data points, calculate the average value of the N vehicle speed data points. .

[0070]

[0071] Step 2: Calculate the set of speed differences between N sensor speed data points and the average speed. } .

[0072]

[0073] Step 3: Sort the vehicle speed differences, find the largest vehicle speed difference, and determine the sensor corresponding to the largest vehicle speed difference as the error sensor.

[0074] Step 4: Assuming the sensor speed index corresponding to the largest speed difference is j, remove the sensor speed data of the error sensor with the largest speed difference. The second set of sensor data mentioned above is obtained, namely } , .

[0075] Step 5: Calculate the standard deviation of the second sensor data set. :

[0076]

[0077] Step 6: Define the clustering degree of the second sensor data set as L, and calculate the clustering degree of the remaining vehicle speed sets:

[0078]

[0079] In the formula, L represents the degree of aggregation. The standard deviation of the second sensor data set and is an adjustable weighting coefficient, and N is the total amount of data in the second sensor data set.

[0080] Record the current set's element information and clustering index, then return to step 1.

[0081] Step 7, Loop Termination Condition: The loop ends when only one sensor data remains in the set.

[0082] Step 8: Assume the set of clustering degrees obtained through multiple iterations is { } i=1,2...N; Sort the elements in this set of clustering degrees.

[0083] Step 9: Filtering Result Judgment: Take the maximum clustering degree in the clustering degree set. If the maximum clustering degree Less than the given preset clustering degree If the data does not have a clustering effect, it is assumed that the sensor data of the current vehicles are different and it is impossible to determine which sensors are abnormal.

[0084]

[0085] For example, if the maximum clustering degree Greater than the above-mentioned preset aggregation degree Then take the maximum clustering degree. The corresponding loop contains a sensor dataset, which is taken as the normal sensor dataset, i.e., the target sensing data set. Let's assume that the final dataset contains M (M>1) vehicle speed data points. } M. The standard deviation of the inherent noise of the sensor to which the data belongs is selected to obtain the set of target sensing data from the normal sensors. .

[0086] Based on the above scheme, this application assumes that most sensors operate normally under normal circumstances, with only a small number of sensors occasionally exhibiting inaccurate predictions. To address this phenomenon, this invention employs an unsupervised clustering algorithm to automatically identify the small subset of abnormal sensor data without needing to predict potential sensor anomalies.

[0087] S103. Determine the fused vehicle speed data of the target vehicle based on the target sensing data set.

[0088] The above-mentioned step S103 also includes S1031:

[0089] Obtain the probability density function value of the target sensing data set, wherein the target sensing data set is assumed to follow a normal distribution;

[0090] Using the vehicle speed data in the target sensing data set as single observation data, the probability of the occurrence of the target sensing data set is obtained, wherein the probability is a function of the desired vehicle speed;

[0091] The true vehicle speed corresponding to the case with the highest probability is determined based on the maximum likelihood estimation method;

[0092] The fused vehicle speed data is determined based on the actual vehicle speed corresponding to the scenario with the highest probability. Specifically, this includes:

[0093] The fused vehicle speed data is determined based on the following formula:

[0094]

[0095] in, To integrate vehicle speed data, M represents the total amount of target sensor data. For the vehicle speed data in the target sensor dataset, The sensor noise standard deviation corresponding to the vehicle speed data is denoted as .

[0096] For example, assume that the data from each sensor follows a normal distribution, and the expected value is the true vehicle speed. Then the probability density function As shown below:

[0097]

[0098] In the target sensing data set In this context, using the transmitted vehicle speed data as a single observation, and assuming that the data distributions of the observers are independent of each other, the probability P of this observation combination can be expressed as:

[0099]

[0100] The above probability uses the expected vehicle speed as the unknown quantity, and the probability of this observation combination can be expressed as a function of the expected vehicle speed. .

[0101]

[0102] Use the maximum likelihood estimation method to obtain the true vehicle speed that maximizes the probability under this observation combination. :

[0103]

[0104] The solution yields the actual vehicle speed. Multi-sensor fusion estimation:

[0105]

[0106] in, To integrate vehicle speed data, M represents the total amount of target sensor data. For the vehicle speed data in the target sensor dataset, The sensor noise standard deviation corresponding to the vehicle speed data is denoted as .

[0107] Finally, the estimated vehicle speed is sent to other control modules to complete vehicle control.

[0108] It should be noted that this application also includes the calculation of the confidence level of the vehicle speed estimate. The aforementioned confidence level characterizes the accuracy of the data estimated after the fusion of multiple sensors. This invention uses the sensor aggregation degree obtained in the second step. The indicator serves as the confidence level of the merged data.

[0109] By employing the above technical solution, the multi-sensor fusion vehicle speed estimation method provided by this invention addresses the problem of low accuracy in vehicle speed data acquired through single channels. This invention determines an initial sensor data set for the target vehicle, wherein the sensor data set includes sensor speed data and corresponding sensor noise standard deviations, the sensor speed data being acquired based on the vehicle's own sensors or connected sensors. An abnormal sensor data in the initial sensor data set is removed using an unsupervised clustering algorithm to determine a target sensor data set. The fused vehicle speed data for the target vehicle is then determined based on the target sensor data set. In this solution, considering the advent of the intelligent connected vehicle era, each vehicle can obtain multiple vehicle speed estimation information from different sources. For vehicle speed estimation information obtained from multiple sources, the method utilizes unsupervised clustering and multi-sensor fusion algorithms to fuse the data, thereby obtaining its own vehicle speed estimation information. Compared to vehicle speed data acquired through a single channel, this method has the advantage of higher accuracy.

[0110] Furthermore, as an implementation of the method shown in Figure 1, this embodiment of the invention also provides a multi-sensor fusion vehicle speed estimation device for implementing the method shown in Figure 1. This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment, but it should be clear that the device in this embodiment can correspondingly implement all the contents of the aforementioned method embodiment. As shown in Figure 2, the device includes: a first determining unit 21, a second determining unit 22, and a third determining unit 23, wherein:

[0111] The first determining unit 21 is configured to determine the initial sensing data set of the target vehicle, wherein the sensing data set includes sensing vehicle speed data and the corresponding sensor noise standard deviation, and the sensing vehicle speed data is obtained based on its own sensor or network sensor.

[0112] The second determining unit 22 is configured to remove abnormal sensor data from the initial sensing data set based on an unsupervised clustering algorithm to determine the target sensing data set.

[0113] The third determining unit 23 is configured to determine the fused vehicle speed data of the target vehicle based on the target sensing data set.

[0114] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and by adjusting kernel parameters, a multi-sensor fusion vehicle speed estimation method can be implemented, addressing the problem of low accuracy in vehicle speed data acquired from single channels.

[0115] This invention provides a computer-readable storage medium including a stored program that, when executed by a processor, implements the multi-sensor fusion vehicle speed estimation method.

[0116] This invention provides a processor for running a program, wherein the program executes the multi-sensor fusion vehicle speed estimation method during runtime.

[0117] This invention provides an electronic device, which includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the multi-sensor fusion vehicle speed estimation method described above.

[0118] This invention provides an electronic device 30, as shown in FIG3. The electronic device 30 includes at least one processor 301, and at least one memory 302 and bus 303 connected to the processor 301. The processor 301 and the memory 302 communicate with each other through the bus 303. The processor 301 is configured to call program instructions in the memory to execute the above-mentioned multi-sensor fusion vehicle speed estimation method.

[0119] The smart electronic devices mentioned in this article can be PCs, tablets, mobile phones, etc.

[0120] This application also provides a computer program product that, when executed on a process management electronic device, is suitable for executing a program that initializes the steps of the above-described multi-sensor fusion vehicle speed estimation method.

[0121] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0122] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0124] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0125] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0126] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute the memory control flow shown in the corresponding embodiment of FIG1.

[0127] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0128] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0130] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0132] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0133] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A multi-sensor fusion method for vehicle speed estimation, characterized in that, include: Determine the initial sensor data set of the target vehicle, wherein the sensor data set includes the vehicle speed data and the corresponding sensor noise standard deviation, and the vehicle speed data is obtained based on its own sensor or network sensor; Abnormal sensor data in the initial sensing data set are removed based on an unsupervised clustering algorithm to determine the target sensing data set; The fused vehicle speed data of the target vehicle is determined based on the target sensor data set.

2. The method according to claim 1, characterized in that, The step of removing anomalous sensor data from the initial sensor data set using an unsupervised clustering algorithm to determine the target sensor data set includes: The aggregation degree of the initial sensing data set is calculated iteratively to obtain an aggregation degree set, wherein the aggregation degree set is sorted by size; Determine the maximum clustering degree in the set of clustering degrees; If the maximum clustering degree is greater than the preset clustering degree, the sensor dataset corresponding to the maximum clustering degree is obtained as the target sensing data set.

3. The method according to claim 2, characterized in that, The iterative calculation of the clustering degree of the initial sensing data set to obtain a clustering degree set includes: Positioning error sensor; Remove the vehicle speed data corresponding to the error sensor to obtain a second set of sensor data; Obtain the standard deviation of the second sensor data set to determine the degree of clustering.

4. The method according to claim 3, characterized in that, The step of obtaining the standard deviation of the second sensor data set to determine the clustering degree includes: The aggregation degree is calculated based on the following formula: ； Where L represents the degree of aggregation. The standard deviation of the second sensor data set and is an adjustable weighting coefficient, and N is the total amount of data in the second sensor data set.

5. The method according to claim 3, characterized in that, The positioning error sensor includes: Determine the average value of the vehicle speed data in the initial sensing data set; A vehicle speed difference set is constructed based on the vehicle speed difference between each sensor vehicle speed data in the initial sensor data set and the average value; Determine the maximum speed difference in the set of speed differences; The sensor corresponding to the maximum vehicle speed difference is determined to be an error sensor.

6. The method according to claim 1, characterized in that, The step of determining the fused vehicle speed data of the target vehicle based on the target sensor data set includes: Obtain the probability density function value of the target sensing data set, wherein the target sensing data set is assumed to follow a normal distribution; Using the vehicle speed data in the target sensing data set as single observation data, the probability of the occurrence of the target sensing data set is obtained, wherein the probability is a function of the desired vehicle speed; The true vehicle speed corresponding to the case with the highest probability is determined based on the maximum likelihood estimation method; The fused vehicle speed data is determined based on the actual vehicle speed corresponding to the case with the highest probability.

7. The method according to claim 6, characterized in that, Determining the fused vehicle speed data based on the actual vehicle speed corresponding to the case with the highest probability includes: The fused vehicle speed data is determined based on the following formula: ； in, To integrate vehicle speed data, M represents the total amount of target sensor data. For the vehicle speed data in the target sensor dataset, The sensor noise standard deviation corresponding to the vehicle speed data is denoted as .

8. A multi-sensor fusion vehicle speed estimation device, characterized in that, include: The first determining unit is configured to determine the initial sensing data set of the target vehicle, wherein the sensing data set includes sensing vehicle speed data and the corresponding sensor noise standard deviation, and the sensing vehicle speed data is obtained based on its own sensor or network sensor. The second determining unit is configured to remove abnormal sensor data from the initial sensing data set based on an unsupervised clustering algorithm to determine the target sensing data set; The third determining unit is configured to determine the fused vehicle speed data of the target vehicle based on the target sensing data set.

9. The apparatus according to claim 8, characterized in that, The step of removing anomalous sensor data from the initial sensor data set using an unsupervised clustering algorithm to determine the target sensor data set includes: The aggregation degree of the initial sensing data set is calculated iteratively to obtain an aggregation degree set, wherein the aggregation degree set is sorted by size; Determine the maximum clustering degree in the set of clustering degrees; If the maximum clustering degree is greater than the preset clustering degree, the sensor dataset corresponding to the maximum clustering degree is obtained as the target sensing data set.

10. The apparatus according to claim 9, characterized in that, The iterative calculation of the clustering degree of the initial sensing data set to obtain a clustering degree set includes: Positioning error sensor; Remove the vehicle speed data corresponding to the error sensor to obtain a second set of sensor data; Obtain the standard deviation of the second sensor data set to determine the degree of clustering.

11. The apparatus according to claim 10, characterized in that, The step of obtaining the standard deviation of the second sensor data set to determine the clustering degree includes: The aggregation degree is calculated based on the following formula: ； Where L represents the degree of aggregation. The standard deviation of the second sensor data set and is an adjustable weighting coefficient, and N is the total amount of data in the second sensor data set.

12. The apparatus according to claim 10, characterized in that, The positioning error sensor includes: Determine the average value of the vehicle speed data in the initial sensing data set; A vehicle speed difference set is constructed based on the vehicle speed difference between each sensor vehicle speed data in the initial sensor data set and the average value; Determine the maximum speed difference in the set of speed differences; The sensor corresponding to the maximum vehicle speed difference is determined to be an error sensor.

13. The apparatus according to claim 8, characterized in that, The step of determining the fused vehicle speed data of the target vehicle based on the target sensor data set includes: Obtain the probability density function value of the target sensing data set, wherein the target sensing data set is assumed to follow a normal distribution; Using the vehicle speed data in the target sensing data set as single observation data, the probability of the occurrence of the target sensing data set is obtained, wherein the probability is a function of the desired vehicle speed; The true vehicle speed corresponding to the case with the highest probability is determined based on the maximum likelihood estimation method; The fused vehicle speed data is determined based on the actual vehicle speed corresponding to the case with the highest probability.

14. The apparatus according to claim 13, characterized in that, Determining the fused vehicle speed data based on the actual vehicle speed corresponding to the case with the highest probability includes: The fused vehicle speed data is determined based on the following formula: ； in, To integrate vehicle speed data, M represents the total amount of target sensor data. For the vehicle speed data in the target sensor dataset, The sensor noise standard deviation corresponding to the vehicle speed data is denoted as .

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed by a processor, it implements the steps of the multi-sensor fusion vehicle speed estimation method as described in any one of claims 1 to 7.

16. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the multi-sensor fusion vehicle speed estimation method as described in any one of claims 1 to 7.

Images