Vehicle positioning processing method, device, electronic device and storage medium

Abstract

The vehicle positioning processing method, device, electronic device, and storage medium provided by the embodiments of the present application relate to the field of autonomous driving technology. This method can be applied to scenarios such as ports, mines, trunk logistics, highways, or urban traffic. The method includes: obtaining the vehicle state vector at time k of the vehicle; obtaining the number of runs of the filter and the first filtering window length of the filter; when the number of runs of the filter is greater than or equal to the first filtering window length, re-obtaining the state noise covariance matrix at time k according to the state vector of the vehicle at time k; estimating the state vector of the vehicle at time k according to the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k+1. When the operating state of the vehicle changes, recalculating the noise matrix so that the noise matrix of the filter matches the operating state of the vehicle can improve the accuracy of the filter's estimation of the vehicle state, thereby improving the accuracy of vehicle positioning.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular, to a vehicle positioning processing method, device, electronic device, and storage medium. Background Art

[0002] High-precision and reliable vehicle positioning is one of the key technologies for autonomous driving and an important prerequisite for the vehicle to correctly perform operations such as perception, planning, and control.

[0003] A multi-sensor fusion positioning system for autonomous vehicles usually uses an error-state Kalman filtering model to optimally estimate and fuse the information of each sensor to achieve precise positioning of the vehicle.

[0004] However, in actual use scenarios, interference factors such as high-frequency jitter during vehicle driving, impact during loading and unloading of goods, and extreme temperature in the operating environment will cause changes in the noise characteristics of the positioning sensor, resulting in a mismatch of the error model, affecting the estimation accuracy of the Kalman filter, and thus leading to inaccurate vehicle positioning. Summary of the Invention

[0005] Embodiments of this application provide a vehicle positioning processing method, device, electronic device, and storage medium, which can adjust the parameter matrix of the filter according to the motion state of the vehicle to make the error model of the filter match the noise characteristics of the sensor, thereby improving the accuracy of vehicle positioning.

[0006] In a first aspect, embodiments of this application provide a vehicle positioning processing method, including: obtaining a vehicle state vector at the k-th moment of the vehicle; wherein, the vehicle state vector includes at least one of the position, speed, attitude, and acceleration of the vehicle obtained through the vehicle sensor;

[0007] Obtaining the number of runs of the filter and the first filtering window length of the filter;

[0008] When the number of runs of the filter is greater than or equal to the first filtering window length, according to the state vector of the vehicle at the k-th moment, re-obtaining the state noise covariance matrix at the k-th moment;

[0009] Estimating the state vector of the vehicle at the k-th moment according to the state noise covariance matrix at the k-th moment to obtain the state vector of the vehicle at the (k + 1)-th moment. By updating the covariance noise matrix, the model accuracy of the filter can be improved, thereby ensuring high-precision estimation and enhancing the system's ability to cope with environmental interference.

[0010] Optionally, the re-obtaining the state noise covariance matrix at the k-th moment includes:

[0011] Obtain the coefficient matrix of the error equation according to the motion parameters of the vehicle at time k;

[0012] Obtain the second filtering window length of the filter at time k according to the driving state of the vehicle from time k - 1 to time k;

[0013] Determine the state noise covariance matrix at time k according to the coefficient matrix of the error equation and the second filtering window length. By adjusting the filtering window length, dynamic adaptation to sensor errors can be achieved.

[0014] Optionally, the determining the state noise covariance matrix at time k according to the coefficient matrix of the error equation and the second filtering window length includes:

[0015] Determine the generalized inverse coefficient matrix at time k according to the coefficient matrix of the error equation;

[0016] Determine the state noise covariance matrix at time k according to the generalized inverse coefficient matrix and the second filtering window length.

[0017] Optionally, the driving state includes: heading angle. The obtaining the second filtering window length of the filter according to the driving state of the vehicle from time k - 1 to time k includes:

[0018] Determine the change amplitude of the vehicle's heading angle according to the heading angle of the vehicle at time k - 1, the heading angle at time k, and a preset heading angle threshold;

[0019] Determine the second filtering window length according to the change amplitude of the heading angle and the initial filtering window length.

[0020] Optionally, the determining the second filtering window length according to the change amplitude of the heading angle and the initial filtering window length includes:

[0021] Determine the vehicle motion state change weight according to the change amplitude of the heading angle; the greater the change amplitude of the heading angle, the smaller the vehicle motion state change weight;

[0022] Determine the second filtering window length according to the vehicle motion state change weight and the initial filtering window length.

[0023] Optionally, the method further includes:

[0024] Determine the third filtering window length according to the preset precision factor and the preset confidence factor of the vehicle;

[0025] Round up the third filtering window length to obtain the initial filtering window length.

[0026] Optionally, after filtering the state vector of the vehicle at time k according to the state noise covariance matrix, the method further includes:

[0027] Reset the number of runs of the filter;

[0028] Update the first filtering window length of the filter to the second filtering window length.

[0029] In a second aspect, an embodiment of the present application further provides a vehicle positioning processing device, including:

[0030] A first acquisition module, configured to acquire the vehicle state vector of the vehicle at time k; wherein, the vehicle state vector includes at least one of the position, speed, attitude, and acceleration of the vehicle acquired by the vehicle sensor;

[0031] A second acquisition module, configured to acquire the number of runs of the filter and the first filtering window length of the filter;

[0032] A processing module, configured to, when the number of runs of the filter is greater than or equal to the first filtering window length, re-acquire the state noise covariance matrix at time k according to the state vector of the vehicle at time k;

[0033] A filtering module, configured to filter the state vector of the vehicle at time k according to the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k+1.

[0034] Optionally, the vehicle positioning processing device can be used to execute the vehicle positioning processing method according to any one of the first aspect.

[0035] In a third aspect, the present application provides an electronic device, including: a memory and a processor;

[0036] The memory is used to store computer instructions; the processor is used to run the computer instructions stored in the memory to implement the method according to any one of the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method according to any one of the first aspect.

[0038] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method according to any one of the first aspect.

[0039] Sixth aspect, an embodiment of the present application provides a chip or a chip system, which includes at least one processor and a communication interface. The communication interface and the at least one processor are interconnected by a line. The at least one processor is configured to run a computer program or instruction to execute the vehicle positioning processing method described in the possible implementation manners of the first aspect. Among them, the communication interface in the chip may be an input / output interface, a pin, a circuit, etc.

[0040] In a possible implementation, the chip or chip system described above in the present application further includes at least one memory, and instructions are stored in the at least one memory. The memory may be a storage unit inside the chip, for example, a register, a cache, etc., or may be a storage unit of the chip (for example, a read-only memory, a random access memory, etc.).

[0041] The vehicle positioning processing method, device, electronic device, and storage medium provided by the embodiments of the present application obtain the vehicle state vector at time k of the vehicle; obtain the number of runs of the filter and the first filtering window length of the filter; when the number of runs of the filter is greater than or equal to the first filtering window length, re-obtain the state noise covariance matrix at time k according to the state vector of the vehicle at time k; filter the state vector of the vehicle at time k according to the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k+1. Through the above method, the noise matrix of the filter can be updated according to the running state of the vehicle. When the running state of the vehicle changes, the noise matrix is recalculated so that the noise matrix of the filter matches the running state of the vehicle, which can improve the accuracy of the filter's estimation of the vehicle state and thus improve the accuracy of vehicle positioning estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flowchart of the vehicle positioning processing method provided by an embodiment of the present application Figure 1 ;

[0043] Figure 2 is a flowchart of the vehicle positioning processing method provided by an embodiment of the present application Figure 2 ;

[0044] Figure 3 is a schematic diagram of the process of vehicle positioning processing provided by an embodiment of the present application;

[0045] Figure 4 is a schematic diagram of the structure of the vehicle positioning processing device provided by an embodiment of the present application;

[0046] Figure 5 is a schematic diagram of the structure of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Apparently, the described embodiments are some, but not all, of the embodiments of this application.

[0048] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects, and no limitation is imposed on their sequence. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0049] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0050] It should be noted that in the embodiments of this application, "when..." can be at the instant when a certain situation occurs or within a period of time after a certain situation occurs. The embodiments of this application do not make specific limitations in this regard.

[0051] High-precision and reliable positioning of vehicles is one of the key technologies for autonomous driving and an important prerequisite for a vehicle to correctly perform operations such as perception, planning, and control.

[0052] A multi-sensor fusion positioning system for autonomous vehicles usually uses an error-state Kalman filter model to optimally estimate and fuse the data collected by each positioning sensor to achieve precise positioning of the vehicle.

[0053] However, in actual use scenarios, interference factors such as high-frequency jitter during vehicle driving, impact during loading and unloading of goods, and extreme temperatures in the operating environment will cause changes in the noise characteristics of vehicle positioning sensors, resulting in a mismatch between the error-state Kalman filter model and the sensor noise characteristics. In the case of a mismatch between the filter model and the sensor noise characteristics, when optimally estimating the vehicle positioning, it will affect the estimation accuracy of the vehicle positioning result, thereby causing the vehicle positioning to be inaccurate.

[0054] In view of this, an embodiment of the present application provides a vehicle positioning processing method, which can adjust the noise matrix of the error state Kalman filter model in a timely manner according to the running state of the vehicle, so that the error state Kalman filter model is adapted to the sensor noise characteristics in different vehicle states, which can improve the model accuracy of the filter and thus improve the accuracy of vehicle positioning.

[0055] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. These several specific embodiments below can be implemented independently or in combination with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0056] The vehicle in the embodiment of the present application can be a vehicle with an autonomous driving function. The execution subject of the embodiment of the present application can be the autonomous driving system of the vehicle or the cloud server connected to the vehicle. When the autonomous driving system of the vehicle is the execution subject, the autonomous driving system of the vehicle can analyze and process the positioning data collected by the positioning sensors of the vehicle and output a positioning result. When the cloud server is the execution subject, the autonomous driving system of the vehicle can upload the collected positioning data to the cloud server and receive the positioning result returned by the cloud server.

[0057] It can be understood that the autonomous driving system of the vehicle can be a system that realizes autonomous driving tasks through software, or a system that realizes autonomous driving tasks through a combination of software and hardware. The embodiment of the present application does not limit this.

[0058] Optionally, the type of the vehicle can be a truck, a freight car, a sedan, etc. The embodiment of the present application does not limit the type of the vehicle.

[0059] The following takes the autonomous driving system of the vehicle (hereinafter referred to as the vehicle for short) as an example to introduce the vehicle positioning processing method provided by the embodiment of the present application.

[0060] Figure 1 is a flow diagram of the vehicle positioning processing method provided by the embodiment of the present application Figure 1 as Figure 1 shown, including the following steps:

[0061] S101. Obtain the vehicle state vector at the k-th moment of the vehicle.

[0062] In the embodiment of the present application, the state vector of the vehicle at the k-th moment includes at least one state of position, speed, attitude, and acceleration of the vehicle obtained through vehicle sensors for describing the vehicle at the k-th moment.

[0063] Among them, the vehicle sensor can be a vehicle positioning sensor. For example, it can be one or more of sensors such as a Global Navigation Satellite System (GNSS), an Inertial Measurement Unit (IMU), a wheel speed meter, a visual odometer, a laser odometer, etc.

[0064] If there are multiple vehicle sensors, the corresponding vehicle state vector can be the state vector obtained after fusion processing of the positioning data of multiple sensors. The specific implementation method can refer to various implementation methods in the prior art, and the embodiments of the present application will not elaborate here.

[0065] In the embodiments of the present application, the vehicle can obtain the vehicle positioning data collected by the sensor through interaction with the vehicle sensor, and obtain the vehicle state vector at time k by analyzing and processing the positioning data.

[0066] S102. Obtain the number of times the filter runs and the first filtering window length of the filter.

[0067] In the embodiments of the present application, the number of times the filter runs can refer to the number of times the filter performs filtering processing on the collected vehicle positioning data. Among them, filtering can be to filter out the noise in the measured waveform, making the obtained data more approximate to the real situation and smoother. The filtering window length can be the maximum number of filtering data allowed to be written in the filtering window. The first filtering window length can be the filtering window length of the currently set filter.

[0068] In the embodiments of the present application, the vehicle can obtain the current number of times the filter runs and the first filtering window length of the filter through interaction with the filter.

[0069] Optionally, the filter in the embodiments of the present application can be a Kalman filter or other types of filters. The embodiments of the present application do not limit the type of the filter.

[0070] S103. When the number of times the filter runs is greater than or equal to the first filtering window length, re-obtain the state noise covariance matrix at time k according to the state vector of the vehicle at time k.

[0071] In the embodiments of the present application, the state noise covariance matrix can represent the degree of linear correlation between different noises of the vehicle at time k. For example, state noise, measurement noise, etc.

[0072] When the vehicle determines that the number of times the filter runs at time k is greater than or equal to the first filtering window length, it can re-calculate the state noise covariance matrix at time k according to the state vector of the vehicle to obtain a noise covariance matrix that matches the running state of the vehicle.

[0073] Exemplarily, the coefficient matrix corresponding to the recomputed noise covariance matrix can be determined according to the error state system equation and the measurement equation of the vehicle state vector, and the filtering window length matching the current operating state can be determined according to the heading angle of the vehicle. The state noise covariance matrix at time k is calculated based on the coefficient matrix and the filtering window length matching the previous operating state.

[0074] S104. Estimate the state vector of the vehicle at time k based on the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k + 1.

[0075] In the embodiment of the present application, when the vehicle obtains the state noise covariance matrix at time k, the state noise covariance matrix at time k can be input into the filter, so that the filter performs filtering processing on the state vector of the vehicle at time k according to the new state noise covariance matrix.

[0076] In the embodiment of the present application, the specific implementation manner of filtering the state vector of the vehicle at time k to obtain the state vector of the vehicle at time k + 1 can refer to various implementation manners in the prior art, and will not be elaborated herein in the embodiment of the present application.

[0077] The vehicle positioning processing method provided in the embodiment of the present application includes obtaining the vehicle state vector of the vehicle at time k; obtaining the number of runs of the filter and the first filtering window length of the filter; when the number of runs of the filter is greater than or equal to the first filtering window length, re-obtaining the state noise covariance matrix at time k according to the state vector of the vehicle at time k; estimating the state vector of the vehicle at time k based on the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k + 1. Through the above method, the noise matrix of the filter can be updated according to the operating state of the vehicle, and when the operating state of the vehicle changes, the noise matrix is recomputed so that the noise matrix of the filter matches the operating state of the vehicle, which can improve the accuracy of the filter's estimation of the vehicle state, thereby improving the accuracy of vehicle positioning estimation.

[0078] Figure 2 is a schematic flow of the vehicle positioning processing method provided in the embodiment of the present application Figure 2 , on the basis of the embodiment shown in Figure 1 , the process of the vehicle positioning processing method is further described. As shown in Figure 2 , it includes:

[0079] S201. Obtain the vehicle state vector of the vehicle at time k, the number of runs of the filter, and the first filtering window length of the filter.

[0080] The specific implementation manner of S201 in the embodiment of the present application is the same as that in Figure 1In the illustrated embodiment, the specific implementation manners of S101 to S102 are similar and will not be elaborated here.

[0081] S202. Determine whether the number of running times of the filter is greater than or equal to the first filtering window length. If so, the steps shown in S203 can be executed. If not, the steps shown in S206 can be executed.

[0082] S203. Obtain the coefficient matrix of the error equation according to the motion parameters of the vehicle at time k.

[0083] In the embodiment of the present application, the error equation can be the vehicle inertial navigation error dynamics equation, and the motion parameters are the vehicle speed, acceleration, etc.

[0084] When the motion parameters of the vehicle at time k are obtained, the motion parameters of the vehicle measured by the inertial navigation system can be substituted into the error equation to obtain the coefficient matrices of each item of the error equation, including the state transition coefficient matrix A k , the system state noise coefficient matrix B k , and the measurement coefficient matrix C k . Among them, each coefficient matrix of the error equation is also called each coefficient matrix of the filter model. The specific implementation process can refer to various implementation manners in the prior art, and the embodiment of the present application will not elaborate on this.

[0085] S204. Obtain the second filtering window length of the filter at time k according to the driving state of the vehicle from time k - 1 to time k.

[0086] In the embodiment of the present application, the driving state of the vehicle includes the heading angle of the vehicle. The vehicle heading angle can be the angle between the vehicle centroid speed and the horizontal axis in the ground coordinate system, and is used to characterize the vehicle motion state. For example, the heading angles of the vehicle during straight driving and turning are different.

[0087] Exemplarily, the vehicle can determine the change range of the vehicle heading angle according to the heading angle of the vehicle at time k - 1, the heading angle of the vehicle at time k, and a preset heading angle threshold; and determine the second filtering window length according to the change range of the heading angle and the initial filtering window length.

[0088] In the embodiment of the present application, the heading angle of the vehicle at time k - 1 and the heading angle of the vehicle at time k can be calculated according to the data collected by the vehicle positioning sensor. The preset heading angle threshold can be the maximum threshold of the allowable heading angle change of the vehicle.

[0089] Exemplarily, the change range of the vehicle heading angle can satisfy the following formula:

[0090]

[0091] Among them, ψ kis the heading angle at time k, ψ k-1 is the heading angle at time k - 1, ξ k is the change amplitude of the heading angle, and |·| represents taking the absolute value.

[0092] In the embodiments of the present application, the initial filter window length can be a reference value for adjusting the filter window length, and can be calculated according to the preset parameters of the vehicle.

[0093] Exemplarily, according to the preset accuracy factor and the preset confidence factor of the vehicle, determine the third filter window length; round up the third filter window length to obtain the initial filter window length.

[0094] Among them, the preset accuracy factor can be used to characterize the error of the positioning result allowed by the vehicle. The larger the preset accuracy factor, the larger the error of the allowed positioning result. Both the preset accuracy factor and the preset confidence factor can be empirical values.

[0095] The third filter window length can satisfy the following formula:

[0096]

[0097] Among them, ∈∈(0, 1) is the preset accuracy factor, and τ∈(0, 1) is the preset confidence factor.

[0098] When the preset accuracy factor and the preset confidence factor of the vehicle are determined, the third filter window length can be the minimum value obtained according to the above inequality.

[0099] After rounding up the third filter window length, the initial filter window length is obtained. For example, if the third filter window length is 100.3, then the initial filter window length is 101.

[0100] In the embodiments of the present application, when determining the change amplitude of the vehicle's heading angle and the initial filter window length, the second filter window length can be determined according to the following method.

[0101] Exemplarily, according to the change amplitude of the heading angle, determine the vehicle motion state change weight; the larger the change amplitude of the heading angle, the smaller the vehicle motion state change weight; according to the vehicle motion state change weight and the initial filter window length, determine the second filter window length.

[0102] The vehicle motion state change weight can satisfy the following formula:

[0103]

[0104] Among them, η kis the weight of the vehicle motion state change, and a is a preset slope factor. It can be seen from the above formula that the greater the change amplitude of the heading angle, the smaller the weight of the vehicle motion state change.

[0105] The length of the second filtering window can satisfy the following formula:

[0106]

[0107] where N0 is the initial filtering window length, denotes rounding up, and N k is the length of the second filtering window.

[0108] S205. Determine the state noise covariance matrix at time k according to the error equation coefficient matrix and the length of the second filtering window.

[0109] Exemplarily, determine the generalized inverse coefficient matrix at time k according to the error equation coefficient matrix; determine the state noise covariance matrix at time k according to the generalized inverse coefficient matrix and the length of the second filtering window.

[0110] The generalized inverse coefficient matrix at time k can satisfy the following formula:

[0111]

[0112] where is the transpose matrix of the coefficient matrix B k .

[0113] The state noise covariance matrix can satisfy the following formula:

[0114]

[0115] where represents the change amount of the state estimate at time j, and P k is the state estimation error covariance matrix at time k. P k-1 is the state estimation error covariance matrix at time k-1. A k-1 is the coefficient matrix at time k-1.

[0116] S206. Filter the state vector of the vehicle at time k according to the state noise covariance matrix.

[0117] In the embodiments of the present application, filtering the state vector of the vehicle at time k can be performed using standard Kalman filtering.

[0118] Exemplarily, the error state system equation and the measurement equation are as follows:

[0119]

[0120] Among them, x k , w k , z k , v k are respectively the state vector, state noise vector, measurement vector and measurement noise vector of the system at time k, and A k , B k , C k are respectively the corresponding coefficient matrices.

[0121] Both the state noise and the measurement noise follow a standard normal distribution:

[0122] w ~ N(0, Q)

[0123] v ~ N(0, R)

[0124] That is:

[0125]

[0126]

[0127] Among them, N(0, σ) represents a normal distribution with a mean of 0 and a variance of σ, E[·] represents taking the expected value, and Q k , R k are respectively the state noise covariance matrix and the measurement noise covariance matrix at time k.

[0128] Estimate the state vector at time k+1 through the state vector at time k, and calculate the one-step prediction of the state vector and the one-step prediction of the state estimation error covariance matrix

[0129]

[0130]

[0131] According to the measurement information at time k, the optimal estimate of the state vector at time k+1 can be obtained and the state estimation error covariance matrix P k+1 :

[0132]

[0133]

[0134]

[0135]

[0136] Among them, M k is the observation error variance matrix, K kis the Kalman gain matrix.

[0137] Optionally, in some embodiments, after filtering the state vector at time k, the running count of the filter may also be reset; and the first filtering window length of the filter is updated to the second filtering window length. That is, the running count of the filter is set to 0, and when the next filtering is performed, the corresponding filtering count is 0 and the filtering window length is the second filtering window length.

[0138] In summary, the vehicle positioning processing method provided by the embodiments of the present application, as Figure 3 shown, judges according to the change of the fusion positioning result of the positioning sensor with the heading angle, determines the state of the vehicle according to the change of the vehicle's heading angle, and updates the noise variance matrix of the filter, realizing the dynamic adaptation of the noise variance matrix of the filter to the sensor noise. When the state of the vehicle is steady, a longer filtering window is set to ensure the unbiasedness of the estimation result; when the state of the vehicle is dynamic, a shorter filtering window is set to ensure the timely tracking of the error. It can improve the accuracy of the estimation of the vehicle positioning result and reduce the risk of autonomous driving. Thus, the anti-environmental interference ability of the vehicle positioning system is improved.

[0139] The embodiments of the present application also provide a vehicle positioning processing device.

[0140] Figure 4 is a schematic structural diagram of the vehicle positioning processing device 40 provided by the embodiments of the present application, as Figure 4 shown, including:

[0141] A first acquisition module 401, configured to acquire the vehicle state vector of the vehicle at time k; wherein, the vehicle state vector includes at least one of the position, speed, attitude, and acceleration of the vehicle acquired by the vehicle sensor.

[0142] A second acquisition module 402, configured to acquire the running count of the filter and the first filtering window length of the filter.

[0143] A processing module 403, configured to re-acquire the state noise covariance matrix at time k according to the state vector of the vehicle at time k when the running count of the filter is greater than or equal to the first filtering window length.

[0144] A filtering module 404, configured to estimate the state vector of the vehicle at time k according to the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k + 1.

[0145] Optionally, the processing module 403 is further configured to obtain a coefficient matrix of the error equation according to the motion parameters of the vehicle at the k-th moment; obtain a second filtering window length of the filter at the k-th moment according to the driving states of the vehicle from the (k-1)-th moment to the k-th moment; and determine a state noise covariance matrix at the k-th moment according to the coefficient matrix of the error equation and the second filtering window length.

[0146] Optionally, the processing module 403 is further configured to determine a generalized inverse coefficient matrix at the k-th moment according to the coefficient matrix of the error equation; and determine a state noise covariance matrix at the k-th moment according to the generalized inverse coefficient matrix and the second filtering window length.

[0147] Optionally, the processing module 403 is further configured to determine a change amplitude of the vehicle's heading angle according to the heading angle of the vehicle at the (k-1)-th moment, the heading angle at the k-th moment, and a preset heading angle threshold; and determine the second filtering window length according to the change amplitude of the heading angle and an initial filtering window length.

[0148] Optionally, the processing module 403 is further configured to determine a vehicle motion state change weight according to the change amplitude of the heading angle; the greater the change amplitude of the heading angle, the smaller the vehicle motion state change weight; and determine the second filtering window length according to the vehicle motion state change weight and the initial filtering window length.

[0149] Optionally, the processing module 403 is further configured to determine a third filtering window length according to a preset precision factor and a preset confidence factor of the vehicle; and round up the third filtering window length to obtain the initial filtering window length.

[0150] Optionally, the processing module 403 is further configured to reset the running times of the filter; and update a first filtering window length of the filter to the second filtering window length.

[0151] The vehicle positioning processing device provided in the embodiments of the present application may execute the technical solutions of the vehicle positioning processing method provided in any of the above embodiments, and the principles and technical effects are similar, which will not be elaborated here.

[0152] The embodiments of the present application further provide an electronic device.

[0153] Figure 5 The following is a schematic structural diagram of an electronic device provided by the present application. As Figure 5 shown, the electronic device 50 may include: at least one processor 501, a memory 502, and a communication interface 503.

[0154] The memory 502 is used to store a program. Specifically, the program may include program code, and the program code includes computer operation instructions.

[0155] The memory 502 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0156] The processor 501 is used to execute the computer-executable instructions stored in the memory 502 to implement the vehicle positioning processing method described in the foregoing method embodiments. Among them, the processor 501 may be a central processing unit (CPU for short), or an application specific integrated circuit (ASIC for short), or one or more integrated circuits configured to implement the embodiments of the present application.

[0157] In a specific implementation, if the communication interface 503, the memory 502, and the processor 501 are implemented independently, the communication interface 503, the memory 502, and the processor 501 can be connected to each other through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0158] Optionally, the processor 501 can also be connected to an external positioning sensor through the communication interface 503 to obtain vehicle positioning data collected by the positioning sensor.

[0159] Optionally, the electronic device may further include a display device 504. The display device 504 can be coupled to the processor 501, and the processor 501 controls the display device 504 to display the positioning result sent by the processor 501.

[0160] Optionally, in a specific implementation, if the communication interface 503, the memory 502, and the processor 501 are integrated on a chip, the communication interface 503, the memory 502, and the processor 501 can complete communication through an internal interface.

[0161] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the technical solutions of the foregoing vehicle positioning processing method embodiments are implemented, and the implementation principles and technical effects are similar and will not be elaborated here.

[0162] In one possible implementation, the computer-readable medium may include random access memory (RAM), read-only memory (ROM), compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or any other medium targeted to carry or store the required program code in the form of instructions or data structures and accessible by a computer. Moreover, any connection is properly termed a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. As used herein, disk and optical disc include optical disc, laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, where disks typically reproduce data magnetically, while optical discs utilize lasers to optically reproduce data. Combinations of the above should also be included within the scope of computer-readable media.

[0163] An embodiment of the present application also provides a computer program product, including a computer program, which implements the technical solutions of the above-described embodiment of the vehicle positioning processing method when executed by a processor. The implementation principle and technical effects are similar and will not be elaborated herein.

[0164] In the specific implementation of the above terminal device or server, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0165] Those skilled in the art can understand that all or part of the steps of any of the above method embodiments can be completed by hardware associated with program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, all or part of the steps of the above method embodiments are executed.

[0166] If the technical solution of the present application is implemented in the form of software and sold or used as a product, it can be stored in a computer-readable storage medium. Based on such an understanding, all or part of the technical solution of the present application can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a computer program or several instructions. The computer software product enables a computer device (which can be a personal computer, a server, a network device or a similar electronic device) to execute all or part of the steps of the method described in the embodiments of the present application.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle positioning processing method, characterized in that, Including: Obtain the vehicle state vector of the vehicle at time k; wherein, the vehicle state vector includes at least one of the position, speed, attitude, and acceleration of the vehicle obtained by the vehicle sensor; Obtain the number of runs of the filter and the first filtering window length of the filter; When the number of runs of the filter is greater than or equal to the first filtering window length, re-obtain the state noise covariance matrix at time k according to the state vector of the vehicle at time k; Filter the state vector of the vehicle at time k according to the state noise covariance matrix at time k to obtain the state vector of the vehicle at time k+1.

2. The method according to claim 1, wherein The re-obtaining the state noise covariance matrix at time k includes: Obtain the error equation coefficient matrix according to the motion parameters of the vehicle at time k; Obtain the second filtering window length of the filter at time k according to the driving state of the vehicle from time k-1 to time k; Determine the state noise covariance matrix at time k according to the error equation coefficient matrix and the second filtering window length.

3. The method according to claim 2, wherein The determining the state noise covariance matrix at time k according to the error equation coefficient matrix and the second filtering window length includes: Determine the generalized inverse coefficient matrix at time k according to the error equation coefficient matrix; Determine the state noise covariance matrix at time k according to the generalized inverse coefficient matrix and the second filtering window length.

4. The method according to claim 2, wherein The driving state includes: heading angle. The obtaining the second filtering window length of the filter according to the driving state of the vehicle from time k-1 to time k includes: Determine the change range of the vehicle heading angle according to the heading angle of the vehicle at time k-1, the heading angle at time k, and a preset heading angle threshold; Determine the second filtering window length according to the change range of the heading angle and the initial filtering window length.

5. The method according to claim 4, wherein The determining the second filtering window length according to the change range of the heading angle and the initial filtering window length includes: Determine the vehicle motion state change weight according to the change range of the heading angle; the greater the change range of the heading angle, the smaller the vehicle motion state change weight; Determine the second filtering window length according to the vehicle motion state change weight and the initial filtering window length.

6. The method according to claim 4, wherein The method further includes: Determine the third filtering window length according to the preset accuracy factor and the preset confidence factor of the vehicle; Round up the third filtering window length to obtain the initial filtering window length.

7. The method according to any one of claims 2-6, characterized in that, After filtering the state vector of the vehicle at time k according to the state noise covariance matrix, the method further includes: Reset the number of runs of the filter; Update the first filtering window length of the filter to the second filtering window length.

8. A vehicle positioning processing device, characterized in that, Including: The first obtaining module is used to obtain the vehicle state vector of the vehicle at time k; wherein, the vehicle state vector includes at least one of the position, speed, attitude, and acceleration of the vehicle obtained by the vehicle sensor; The second obtaining module is used to obtain the number of runs of the filter and the first filtering window length of the filter; A processing module, configured to, when the number of running times of the filter is greater than or equal to the length of the first filtering window, re-obtain the state noise covariance matrix at the k-th moment according to the state vector of the vehicle at the k-th moment; A filtering module, configured to filter the state vector of the vehicle at the k-th moment according to the state noise covariance matrix at the k-th moment to obtain the state vector of the vehicle at the (k + 1)-th moment.

9. An electronic device, characterized in that, Comprising: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1-7.

Images