Vehicle positioning method, device and equipment and computer readable storage medium
By obtaining the sampling data of the vehicle trip and using a prediction model and combining with the neural network model for training, the problem of unreliable vehicle positioning method is solved and high-stability vehicle positioning is achieved.
Patent Information
- Application Number
- CN202411114504.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-13
AI Technical Summary
The existing vehicle positioning methods are greatly affected by the satellite signal quality and solution status, resulting in high and low positioning accuracy or unreliable problems.
By obtaining sampled data of vehicle travel, including vehicle status parameters and environmental parameters, using prediction models to predict driving distance and vehicle attitude angle, combining real coordinates to calculate predicted coordinates, and using neural network models for training and update, ensuring the stability and reliability of positioning sex.
Improves the reliability of vehicle positioning, reduces signal loss and data errors, and ensures the accuracy and stability of vehicle position.
Smart Images
Figure CN119136142A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle positioning method, device, equipment and computer-readable storage medium. Background Art
[0002] At present, satellite positioning is widely used to determine the position of the vehicle during the journey. However, this positioning method is greatly affected by factors such as satellite signal quality and solution status, resulting in high and low positioning accuracy or even failure to locate. In other words, the existing vehicle positioning method has the disadvantage of being unreliable. Summary of the invention
[0003] The present application provides a vehicle positioning method, device, equipment and computer-readable storage medium, which can solve the technical problem of unreliable vehicle positioning methods existing in the prior art.
[0004] In a first aspect, an embodiment of the present application provides a vehicle positioning method, the vehicle positioning method comprising:
[0005] Acquire the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period;
[0006] Input each sampled data and the preset duration corresponding to the preset time period into the prediction model to obtain the prediction data output by the prediction model for each input, wherein the prediction data includes the predicted driving distance and the predicted vehicle attitude angle;
[0007] Based on the actual coordinates of the vehicle's starting point and all predicted data, the predicted coordinates of the vehicle at the end of each preset time period are obtained.
[0008] In combination with the first aspect, in one implementation, before the step of inputting each sample data into the prediction model, the method further includes:
[0009] Acquire a plurality of sets of training data from a training data set, wherein a set of training data includes a sample data and a true value data, wherein the sample data includes a vehicle state parameter corresponding to a preset driving time of a vehicle in a driving scenario and a vehicle environment parameter, and the true value data includes a real driving distance and a real vehicle attitude angle corresponding to a preset driving time of a vehicle in a driving scenario;
[0010] Taking each sample data and the preset duration as a group of input samples, a plurality of groups of input samples are obtained;
[0011] Inputting a plurality of groups of input samples into a preset neural network model to obtain a plurality of sample prediction data output by the preset neural network model for the plurality of groups of input samples, the sample prediction data including a predicted driving distance and a predicted vehicle attitude angle;
[0012] Calculate the loss based on some sample prediction data and some true value data;
[0013] Check if the loss converges;
[0014] If the loss has not converged, the parameters of the preset neural network model are updated, and the step of obtaining a plurality of training data from the training data set is returned;
[0015] If the loss converges, the current preset neural network model is used as the prediction model.
[0016] In combination with the first aspect, in one implementation, the several groups of training data include training data under multiple driving scenarios.
[0017] In combination with the first aspect, in one embodiment, after the step of obtaining the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data, the method further includes:
[0018] The vehicle's travel trajectory is drawn based on the actual coordinates of the vehicle's starting point and all predicted coordinates.
[0019] In combination with the first aspect, in one implementation, the step of obtaining the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data includes:
[0020] The i-th coordinate change is obtained based on the i-th predicted data, wherein the earlier the time sequence of the sampled data corresponding to the predicted data is, the smaller the value of i is;
[0021] When i is 1, the predicted coordinates of the vehicle at the end of the i-th preset time period are obtained based on the real coordinates of the vehicle's starting point and the i-th coordinate change;
[0022] When i is greater than 1, the predicted coordinates of the vehicle at the end of the i-1th preset time period are obtained based on the predicted coordinates of the vehicle at the end of the i-1th preset time period and the i-th coordinate change.
[0023] In combination with the first aspect, in one implementation, the vehicle state parameters include vehicle speed, tire pressure, and vehicle attitude angle change, and the vehicle environment parameters include weather type.
[0024] In combination with the first aspect, in one embodiment, after the step of obtaining the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset time period in the vehicle journey, the method further includes:
[0025] Eliminate sampling data with zero speed.
[0026] In a second aspect, an embodiment of the present application provides a vehicle positioning device, the vehicle positioning device comprising:
[0027] An acquisition module is used to acquire the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey and transmit them to the prediction module, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period;
[0028] A prediction module, used to input each sampled data and a preset duration corresponding to a preset time period into a prediction model, so as to obtain prediction data output by the prediction model for each input and transmit the prediction data to the positioning module, wherein the prediction data includes a predicted driving distance and a predicted vehicle attitude angle;
[0029] The positioning module is used to obtain the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data.
[0030] In a third aspect, an embodiment of the present application provides a vehicle positioning device, which includes a processor, a memory, and a vehicle positioning program stored in the memory and executable by the processor, wherein when the vehicle positioning program is executed by the processor, the steps of the vehicle positioning method described in the first aspect are implemented.
[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle positioning program is stored, wherein when the vehicle positioning program is executed by a processor, the steps of the vehicle positioning method described in the first aspect are implemented.
[0032] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:
[0033] In this embodiment, the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset time period in the vehicle journey are obtained, and the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset time period is the start time of the next preset time period; each sampling data and the preset duration corresponding to the preset time period are input into the prediction model to obtain the prediction data output by the prediction model for each input, and the prediction data includes the predicted driving distance and the predicted vehicle attitude angle; based on the real coordinates of the starting point of the vehicle journey and all the prediction data, the predicted coordinates of the vehicle at the end time of each preset time period are obtained. This embodiment uses the vehicle state parameters and the vehicle environment parameters as basic data, and the basic data has high stability, and basically will not have signal loss, data errors, etc., and combined with the prediction model to ensure the reliability of vehicle positioning. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 This is a flow chart of an embodiment of a vehicle positioning method of the present application;
[0035] Figure 2 Schematic diagram of the scene for calculating the predicted coordinates;
[0036] Figure 3 This is a schematic diagram of the functional modules of an embodiment of the vehicle positioning device of the present application;
[0037] Figure 4 This is a schematic diagram of the hardware structure of the vehicle positioning device involved in the embodiment of the present application. DETAILED DESCRIPTION
[0038] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0039] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0040] In a first aspect, an embodiment of the present application provides a vehicle positioning method.
[0041] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the vehicle positioning method of the present application. Figure 1 As shown, the vehicle positioning method includes:
[0042] Step S10, obtaining the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period;
[0043] In this embodiment, the real coordinates of the starting point of the vehicle trip can be determined by conventional positioning methods, such as GPS positioning, integrated navigation positioning, base station positioning, etc.
[0044] According to the preset duration, the total duration of the vehicle journey is divided into multiple preset time periods. For example, the preset duration is 0.02s. Starting from the start time of the vehicle journey, the first 0.02s is the preset time period 1, the second 0.02s is the preset time period 2, and so on.
[0045] The vehicle state parameters and the vehicle environment parameters are used to predict the vehicle's travel distance and vehicle attitude angle in a preset time period. The vehicle state parameters and the vehicle environment parameters are selected according to actual needs.
[0046] Furthermore, in one embodiment, the vehicle state parameters include vehicle speed, tire pressure, and vehicle attitude angle change, and the vehicle environment parameters include weather type.
[0047] In this embodiment, for example, preset time period 1 is from time t1 to time t2, and preset time period 2 is from time t2 to time t3. At time t1, the vehicle speed V1 and tire pressure A1 are obtained through the vehicle chassis signal, the vehicle attitude angle E1 sensed by the gyroscope in the vehicle is obtained at time t1, and the vehicle attitude angle E2 sensed by the gyroscope in the vehicle is obtained at time t2. The change of E2 relative to E1 is calculated to obtain the vehicle attitude angle change Δ1, and V1, A1 and Δ1 are used as the vehicle state parameters corresponding to preset time period 1; at time t1, the weather type S1 obtained by the interaction between T-BOX and the external network is obtained, and S1 is used as the vehicle environment parameter corresponding to preset time period 1.
[0048] Similarly, at time t2, the vehicle speed V2 and tire pressure A2 are obtained through the vehicle chassis signal, and at time t3, the vehicle attitude angle E3 sensed by the gyroscope in the vehicle is obtained, and the change of E3 relative to E2 is calculated to obtain the vehicle attitude angle change Δ2, and V2, A2 and Δ2 are used as the vehicle state parameters corresponding to the preset time period 2; at time t2, the weather type S2 obtained by the interaction between T-BOX and the external network is obtained, and S2 is used as the vehicle environment parameter corresponding to the preset time period 2.
[0049] By analogy, the sampling data corresponding to each preset time period in the vehicle journey can be obtained.
[0050] Step S20, inputting each sampled data and the preset duration corresponding to the preset time period into the prediction model to obtain prediction data output by the prediction model for each input, wherein the prediction data includes a predicted driving distance and a predicted vehicle attitude angle;
[0051] In this embodiment, the prediction model is obtained based on training a neural network model, and the type of the neural network model is selected based on actual needs.
[0052] The sampled data and the preset duration corresponding to the preset time period are input into the prediction model to obtain the prediction data output by the prediction model, and the prediction data includes the predicted driving distance and the predicted vehicle attitude angle. That is, the predicted driving distance and the predicted vehicle attitude angle corresponding to each preset time period in the vehicle journey are obtained.
[0053] Step S30, based on the real coordinates of the starting point of the vehicle journey and all the predicted data, the predicted coordinates of the vehicle at the end time of each preset time period are obtained.
[0054] In this embodiment, it is easy to understand that for each preset period, based on the corresponding predicted travel distance and predicted vehicle attitude angle, the change in the coordinates of the vehicle at the end of the preset period compared to the coordinates of the vehicle at the start of the preset period can be obtained. On this basis, combined with the real coordinates of the starting point of the vehicle trip, the predicted coordinates of the vehicle at the end of each preset period can be obtained.
[0055] Furthermore, in one embodiment, step S30 includes:
[0056] Step S301, obtaining the i-th coordinate variation based on the i-th predicted data, wherein the earlier the time sequence of the sampled data corresponding to the predicted data is, the smaller the value of i is;
[0057] Step S302, when i is 1, the predicted coordinates of the vehicle at the end of the i-th preset time period are obtained based on the real coordinates of the starting point of the vehicle journey and the i-th coordinate change;
[0058] Step S303, when i is greater than 1, the predicted coordinates of the vehicle at the end of the i-1 preset time period are obtained based on the predicted coordinates of the vehicle at the end of the i-1 preset time period and the i-th coordinate change.
[0059] In this embodiment, refer to Figure 2 , Figure 2 Schematic diagram of the scene for calculating the predicted coordinates. Figure 2 As shown, the first prediction data includes the predicted driving distance d1 and the predicted vehicle attitude angle θ1, and the first prediction data corresponds to the first sampling data at the front of the time series. The first coordinate change can be determined based on the following formula:
[0060] Δx1=d1*cosθ1
[0061] Δy1=d1*sinθ1
[0062] The second prediction data includes the predicted driving distance d2 and the predicted vehicle attitude angle θ2. The second prediction data corresponds to the second sampling data ranked second in time sequence.
[0063] The second coordinate change is:
[0064] Δx2=d2*cosθ2
[0065] Δy2=d2*sinθ2
[0066] P0 is the real coordinates of the starting point of the vehicle's journey (X0, Y0), then the predicted coordinates of the vehicle at the end of the first preset period are P1 = (X1, Y1) = (X0 + Δx1, Y0 + Δy1); the predicted coordinates of the vehicle at the end of the second preset period are P2 = (X2, Y2) = (X1 + Δx2, Y1 + Δy2). And so on, the predicted coordinates of the vehicle at the end of each preset period can be obtained.
[0067] It should be noted that, for the sake of ease of description, only the coordinate changes of the vehicle in two-dimensional coordinates are considered here. However, based on the current description, following the same principle, it is easy to think of analogy to consider the coordinate changes of the vehicle in three-dimensional coordinates.
[0068] In this embodiment, the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset time period in the vehicle journey are obtained, and the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset time period is the start time of the next preset time period; each sampling data and the preset duration corresponding to the preset time period are input into the prediction model to obtain the prediction data output by the prediction model for each input, and the prediction data includes the predicted driving distance and the predicted vehicle attitude angle; based on the real coordinates of the starting point of the vehicle journey and all the prediction data, the predicted coordinates of the vehicle at the end time of each preset time period are obtained. This embodiment uses the vehicle state parameters and the vehicle environment parameters as basic data, and the basic data has high stability, and basically will not have signal loss, data errors, etc., and combined with the prediction model to ensure the reliability of vehicle positioning.
[0069] Furthermore, in one embodiment, before step S10, the method further includes:
[0070] Step S01, obtaining a plurality of sets of training data from a training data set, wherein a set of training data includes a sample data and a true value data, wherein the sample data includes a vehicle state parameter corresponding to a preset driving time of a vehicle in a driving scenario and a vehicle environment parameter, and the true value data includes a real driving distance and a real vehicle attitude angle corresponding to a preset driving time of a vehicle in a driving scenario;
[0071] In this embodiment, the training data in the training data set is obtained based on historical trips. A driving scene is defined by vehicle speed and weather type, and there are differences in vehicle speed and / or weather type between different driving scenes. For example:
[0072] The vehicle is moving at a speed greater than or equal to a first preset speed V H The vehicle speed is greater than or equal to the first preset speed V H The vehicle speed is less than or equal to the second preset speed V L The vehicle speed is V in the snowy weather. N The vehicle speed in rainy day is a driving scene, and the vehicle speed V N Introduction H and V L between.
[0073] For explanations of the vehicle status parameters and the vehicle environment parameters, please refer to the above embodiments and will not be elaborated here.
[0074] Regarding true value data, the starting coordinates and ending coordinates of the preset driving time are determined through conventional positioning methods in the historical journey. These two coordinates can be used to determine the actual driving distance and the actual vehicle attitude angle corresponding to the preset driving time in a driving scenario.
[0075] Step S02, taking each sample data and the preset time length as a group of input samples, to obtain several groups of input samples;
[0076] Step S03, inputting a plurality of groups of input samples into a preset neural network model to obtain a plurality of sample prediction data output by the preset neural network model for the plurality of groups of input samples, wherein the sample prediction data includes a predicted driving distance and a predicted vehicle attitude angle;
[0077] In this embodiment, the preset neural network model includes an input layer, an output layer and three hidden layers.
[0078] For each group of input samples, they are input into the input layer, and the input layer passes them to the first hidden layer; the first hidden layer receives the input samples from the input layer, performs a linear transformation on them, and then inputs the result of the linear transformation into the activation function (such as ReLU) for nonlinear transformation; the second hidden layer receives the activation output from the first hidden layer, and this layer further learns a deeper level of nonlinear feature representation; the third hidden layer receives the activation output from the second hidden layer, and continues to perform linear transformation and nonlinear activation. This layer extracts more abstract and complex nonlinear features; the output layer receives the activation output from the third hidden layer, performs the final linear transformation, and outputs the sample prediction data, which includes the predicted driving distance and the predicted vehicle attitude angle.
[0079] Step S04, calculating the loss based on a number of sample prediction data and a number of true value data;
[0080] In this embodiment, a loss function for calculating the loss is selected based on actual needs, for example, a mean square error loss function is selected, that is, a number of predicted driving distances are compared with a number of corresponding real driving distances, a number of predicted vehicle attitude angles are compared with a number of corresponding real vehicle attitude angles, and the mean square error is calculated based on the comparison results to obtain the loss.
[0081] Step S05, detecting whether the loss has converged;
[0082] In this embodiment, in addition to detecting whether convergence has occurred, it is also possible to detect whether the number of model iterations has reached a threshold, and if the threshold has been reached, the iteration is also stopped.
[0083] Step S06, if the loss has not converged, update the parameters of the preset neural network model and return to step S01;
[0084] Step S07: if the loss converges, the current preset neural network model is used as the prediction model.
[0085] In this embodiment, if the loss has not converged, the iteration continues, that is, the parameters of the preset neural network model are updated, and the process returns to step S01. It should be emphasized here that the reacquired sets of training data are different from the previously acquired sets of training data.
[0086] If the loss converges, the iteration is stopped and the current (i.e., the latest) preset neural network model is used as the prediction model.
[0087] Furthermore, in one embodiment, the plurality of groups of training data include training data under multiple driving scenarios.
[0088] In this embodiment, considering that the driving scenarios of the vehicle are diverse in an actual vehicle journey, in order to ensure that the prediction model can have good prediction accuracy for a variety of driving scenarios, it is necessary to use training data under multiple driving scenarios during training, which can avoid the long tail effect and improve the prediction accuracy of the prediction model.
[0089] Furthermore, the several groups of training data acquired each time include training data under multiple driving scenarios, and the amount of training data under different driving scenarios tends to be consistent.
[0090] Furthermore, in one embodiment, after step S30, the method further includes:
[0091] The vehicle's travel trajectory is drawn based on the actual coordinates of the vehicle's starting point and all predicted coordinates.
[0092] In this embodiment, the vehicle travel trajectory can be drawn by connecting the real coordinates of the vehicle travel starting point and all the predicted coordinates in time sequence.
[0093] Furthermore, in one embodiment, after step S10, the method further includes:
[0094] Eliminate sampling data with zero speed.
[0095] In this embodiment, if the vehicle speed is zero, it can be considered that the vehicle has not moved within the corresponding preset time period, and its coordinates will not change. In order to save computing resources, the sampling data with a vehicle speed of zero can be eliminated, that is, the sampling data with a vehicle speed of zero is not input into the prediction model.
[0096] In a second aspect, an embodiment of the present application also provides a vehicle positioning device.
[0097] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of the vehicle positioning device of the present application. Figure 3 As shown, the vehicle positioning device includes:
[0098] The acquisition module 10 is used to acquire the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey and transmit them to the prediction module 20, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period;
[0099] The prediction module 20 is used to input each sampled data and the preset duration corresponding to the preset time period into the prediction model, so as to obtain the prediction data output by the prediction model for each input and transmit it to the positioning module 30, wherein the prediction data includes the predicted driving distance and the predicted vehicle attitude angle;
[0100] The positioning module 30 is used to obtain the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the starting point of the vehicle journey and all predicted data.
[0101] Furthermore, in one embodiment, the vehicle positioning device further includes a training module for:
[0102] Acquire a plurality of sets of training data from a training data set, wherein a set of training data includes a sample data and a true value data, wherein the sample data includes a vehicle state parameter corresponding to a preset driving time of a vehicle in a driving scenario and a vehicle environment parameter, and the true value data includes a real driving distance and a real vehicle attitude angle corresponding to a preset driving time of a vehicle in a driving scenario;
[0103] Taking each sample data and the preset duration as a group of input samples, a plurality of groups of input samples are obtained;
[0104] Inputting a plurality of groups of input samples into a preset neural network model to obtain a plurality of sample prediction data output by the preset neural network model for the plurality of groups of input samples, the sample prediction data including a predicted driving distance and a predicted vehicle attitude angle;
[0105] Calculate the loss based on some sample prediction data and some true value data;
[0106] Check if the loss converges;
[0107] If the loss has not converged, the parameters of the preset neural network model are updated, and the step of obtaining a plurality of training data from the training data set is returned;
[0108] If the loss converges, the current preset neural network model is used as the prediction model.
[0109] Furthermore, in one embodiment, the plurality of groups of training data include training data under multiple driving scenarios.
[0110] Furthermore, in one embodiment, the vehicle positioning device further includes a trajectory drawing module, which is used to:
[0111] The vehicle's travel trajectory is drawn based on the actual coordinates of the vehicle's starting point and all predicted coordinates.
[0112] Furthermore, in one embodiment, the positioning module 30 is used to:
[0113] The i-th coordinate change is obtained based on the i-th predicted data, wherein the earlier the time sequence of the sampled data corresponding to the predicted data is, the smaller the value of i is;
[0114] When i is 1, the predicted coordinates of the vehicle at the end of the i-th preset time period are obtained based on the real coordinates of the vehicle's starting point and the i-th coordinate change;
[0115] When i is greater than 1, the predicted coordinates of the vehicle at the end of the i-1th preset time period are obtained based on the predicted coordinates of the vehicle at the end of the i-1th preset time period and the i-th coordinate change.
[0116] Furthermore, in one embodiment, the vehicle state parameters include vehicle speed, tire pressure, and vehicle attitude angle change, and the vehicle environment parameters include weather type.
[0117] Furthermore, in one embodiment, the vehicle positioning device further includes a rejection module, which is used to:
[0118] Eliminate sampling data with zero speed.
[0119] Among them, the functional implementation of each module in the above-mentioned vehicle positioning device corresponds to each step in the above-mentioned vehicle positioning method embodiment, and its functions and implementation processes are no longer repeated here.
[0120] In a third aspect, an embodiment of the present application provides a vehicle positioning device, which may be a device with data processing capabilities, such as a driving computer, a personal computer, or a server.
[0121] Reference Figure 4 , Figure 4 The hardware structure diagram of the vehicle positioning device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle positioning device may include a processor, a memory, a communication interface, and a communication bus.
[0122] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0123] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle positioning device, and the interface used to realize the interconnection of the vehicle positioning device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0124] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0125] The processor may be a general-purpose processor, and the general-purpose processor may call the vehicle positioning program stored in the memory and execute the vehicle positioning method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle positioning program is called may refer to the various embodiments of the vehicle positioning method of the present application, and will not be repeated here.
[0126] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0127] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.
[0128] The computer-readable storage medium of the present application stores a vehicle positioning program, wherein when the vehicle positioning program is executed by a processor, the steps of the vehicle positioning method as described above are implemented.
[0129] Among them, the method implemented when the vehicle positioning program is executed can refer to the various embodiments of the vehicle positioning method of the present application, and will not be repeated here.
[0130] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0131] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0132] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0133] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0134] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0136] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A vehicle positioning method, characterized in that: The vehicle positioning method comprises: Acquire the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period; Input each sampled data and the preset duration corresponding to the preset time period into the prediction model to obtain the prediction data output by the prediction model for each input, wherein the prediction data includes the predicted driving distance and the predicted vehicle attitude angle; Based on the actual coordinates of the vehicle's starting point and all predicted data, the predicted coordinates of the vehicle at the end of each preset time period are obtained.
2. The vehicle positioning method according to claim 1, characterized in that: Before the step of inputting each sample data into the prediction model, the method further includes: Acquire a plurality of sets of training data from a training data set, wherein a set of training data includes a sample data and a true value data, wherein the sample data includes a vehicle state parameter corresponding to a preset driving time of a vehicle in a driving scenario and a vehicle environment parameter, and the true value data includes a real driving distance and a real vehicle attitude angle corresponding to a preset driving time of a vehicle in a driving scenario; Taking each sample data and the preset duration as a group of input samples, a plurality of groups of input samples are obtained; Inputting a plurality of groups of input samples into a preset neural network model to obtain a plurality of sample prediction data output by the preset neural network model for the plurality of groups of input samples, the sample prediction data including a predicted driving distance and a predicted vehicle attitude angle; Calculate the loss based on some sample prediction data and some true value data; Check if the loss converges; If the loss has not converged, the parameters of the preset neural network model are updated, and the step of obtaining a plurality of training data from the training data set is returned; If the loss converges, the current preset neural network model is used as the prediction model.
3. The vehicle positioning method according to claim 2, characterized in that: The several groups of training data include training data under multiple driving scenarios.
4. The vehicle positioning method according to claim 1, characterized in that: After the step of obtaining the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data, the method further includes: The vehicle's travel trajectory is drawn based on the actual coordinates of the vehicle's starting point and all predicted coordinates.
5. The vehicle positioning method according to claim 1, characterized in that: The step of obtaining the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data includes: The i-th coordinate change is obtained based on the i-th predicted data, wherein the earlier the time sequence of the sampled data corresponding to the predicted data is, the smaller the value of i is; When i is 1, the predicted coordinates of the vehicle at the end of the i-th preset time period are obtained based on the real coordinates of the starting point of the vehicle journey and the i-th coordinate change; When i is greater than 1, the predicted coordinates of the vehicle at the end of the i-1th preset time period are obtained based on the predicted coordinates of the vehicle at the end of the i-1th preset time period and the i-th coordinate change.
6. The vehicle positioning method according to any one of claims 1 to 5, characterized in that: The vehicle state parameters include vehicle speed, tire pressure, and vehicle attitude angle change, and the vehicle environment parameters include weather type.
7. The vehicle positioning method according to claim 6, characterized in that: After the step of obtaining the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset time period in the vehicle journey, the method further includes: Eliminate sampling data with zero speed.
8. A vehicle positioning device, characterized in that: The vehicle positioning device comprises: An acquisition module is used to acquire the real coordinates of the starting point of the vehicle journey and the sampling data corresponding to each preset period in the vehicle journey and transmit them to the prediction module, wherein the sampling data includes vehicle state parameters and vehicle environment parameters, wherein the end time of the previous preset period is the start time of the next preset period; A prediction module, used to input each sampled data and a preset duration corresponding to a preset time period into a prediction model, so as to obtain prediction data output by the prediction model for each input and transmit the prediction data to the positioning module, wherein the prediction data includes a predicted driving distance and a predicted vehicle attitude angle; The positioning module is used to obtain the predicted coordinates of the vehicle at the end of each preset time period based on the real coordinates of the vehicle's starting point and all predicted data.
9. A vehicle positioning device, characterized in that: The vehicle positioning device comprises a processor, a memory, and a vehicle positioning program stored in the memory and executable by the processor, wherein when the vehicle positioning program is executed by the processor, the steps of the vehicle positioning method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle positioning program, wherein when the vehicle positioning program is executed by a processor, the steps of the vehicle positioning method according to any one of claims 1 to 7 are implemented.