A vehicle positioning method, system, positioning terminal and storage medium
By employing time alignment and digital map constraints, the problems of GPS signal obstruction and data asynchrony in complex scenarios were solved for vehicle positioning systems, achieving high-precision vehicle positioning, especially maintaining lane-level positioning accuracy when GPS fails.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JIANGSU BDSTAR AUTOMOTIVE ELECTRONICS CO LTD
- Filing Date
- 2026-03-18
- Publication Date
- 2026-05-29
AI Technical Summary
Existing vehicle positioning systems suffer from inaccurate positioning in complex scenarios due to GPS signal obstruction, and the asynchronous data from multiple sources introduces additional errors, making it difficult to meet lane-level accuracy requirements.
By acquiring multi-source fusion data and performing time alignment processing, vehicle status is predicted using inertial measurement data and vehicle speed, and observation errors are provided by digital maps. Combined with filters, fusion positioning is performed to reduce data asynchrony errors, especially when GPS fails, relying on high-precision maps to constrain vehicle trajectories.
It improves the reliability and accuracy of vehicle positioning in complex environments, especially when GPS fails, it can control positioning errors at the lane level and reduce over-reliance on GPS data.
Smart Images
Figure CN122108172A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle positioning technology, and in particular to a vehicle positioning method, system, positioning terminal and storage medium. Background Technology
[0002] In existing high-precision vehicle positioning technologies, navigation systems based on a combination of Global Positioning System (GPS) and Inertial Measurement Unit (IMU) are widely used. This system utilizes the absolute position information provided by GPS and the high-frequency inertial data output by the IMU to achieve pose fusion estimation, achieving good positioning performance in open environments. However, in complex scenarios such as tunnels and urban canyons, GPS signals are easily blocked, leading to prolonged failures. The system is forced to enter a pure inertial navigation mode, where IMU errors accumulate over time, causing the positioning results to diverge rapidly and failing to meet lane-level accuracy requirements. Furthermore, time asynchrony issues exist between multiple sensor sources, introducing additional errors during data fusion and affecting system stability. Summary of the Invention
[0003] In view of this, embodiments of this application provide a vehicle positioning method, system, positioning terminal, and storage medium, which can effectively solve the problem of inaccurate vehicle positioning caused by the failure of the Global Positioning System or data time synchronization.
[0004] In a first aspect, embodiments of this application provide a vehicle positioning method, including: Acquire multi-source fusion data, and perform time alignment processing on the multi-source fusion data based on the target clock source to obtain time-aligned data. The time-aligned data includes time-aligned GPS positioning data, inertial measurement data, and vehicle speed. The predicted state of the vehicle at the current moment is predicted based on the inertial measurement data, the vehicle speed, and the positioning data of the previous moment. The predicted state includes the predicted position and the predicted heading. Using the predicted location as the center, search for multiple roads within a preset range in the digital map, and determine the observation error between the predicted state and each of the roads; The minimum observation error is input into the filter to obtain the fused positioning result based on the positioning data, the inertial measurement data, and the minimum observation error.
[0005] In a first possible embodiment of the first aspect, it further includes: When the positioning data of the Global Positioning System cannot be obtained, the weight of the minimum observation error in the filter is adjusted to a first weight, and the weight of the positioning data in the filter is adjusted to a second weight, wherein the first weight is greater than the second weight.
[0006] In a second possible embodiment of the first aspect, it further includes: In the absence of location data from the Global Positioning System, multiple candidate states for vehicles at the current moment are generated based on the fused positioning results. Based on the current first candidate states, the inertial measurement data, and the vehicle speed, predict multiple second candidate states for the vehicle in the next moment; Determine the matching degree between each second candidate state and a road in the digital map, and determine the weight of each second candidate state based on the matching degree, wherein the matching degree and the weight are directly proportional. The target positioning state of the vehicle at the next moment is obtained by weighting and summing the weights of each second candidate state.
[0007] In a third possible embodiment of the first aspect, the target clock source is the clock source of the inertial measurement unit, and the time alignment processing of the multi-source fused data based on the target clock source includes: A first delay time is determined for transmission by the Global Positioning System receiver, the first delay time including a first fixed delay time and a first variable delay time; The first fixed delay time is the fixed delay time for the global positioning system receiver to receive satellite signals, and the first variable delay time is the deviation increment of the positioning data received by the global positioning system receiver at different times relative to the ideal time; A second delay time for the communication bus is determined, the second delay time including a second fixed delay time and a second variable delay time; The second fixed delay time is the fixed delay for receiving the vehicle speed from the communication bus, and the second variable delay time is the deviation increment of the vehicle speed received by the communication bus at different times relative to the ideal time; The positioning data, vehicle speed, and measurement data are aligned in the time dimension based on the first delay time and the second delay time.
[0008] In a fourth possible embodiment of the first aspect, aligning the positioning data, the vehicle speed, and the measurement data in a time dimension according to the first delay time and the second delay time includes: Based on the actual reception time of the positioning data and the first delay time, the theoretical reception time of the positioning data is determined; Based on the actual reception time of the vehicle speed and the second delay time, the theoretical generation time of the vehicle speed is determined; Using the time of the inertial measurement data as the system time reference, the theoretical reception time, the theoretical generation time, and the inertial measurement data time are aligned to the same time series to obtain the time-aligned data.
[0009] In a fifth possible embodiment of the first aspect, the inertial measurement data includes acceleration and heading angle, the positioning data includes vehicle position, and the prediction of the vehicle's predicted state at the current moment based on the inertial measurement data, the vehicle speed, and the positioning data from the previous moment includes: The predicted position of the vehicle is calculated from the vehicle's position at the previous moment to the current moment, based on the acceleration and the vehicle speed. The heading angle at the current moment is taken as the predicted heading of the vehicle at the current moment.
[0010] In a sixth possible embodiment of the first aspect, determining the matching degree between each of the second candidate states and roads in the digital map includes: The distance from the vehicle's position to the road when the vehicle is in the second candidate state is determined, and the matching degree is determined based on the distance, wherein the distance and the matching degree are inversely proportional.
[0011] Secondly, embodiments of this application provide a vehicle positioning system, including: The time alignment module is used to acquire multi-source fused data and perform time alignment processing on the multi-source fused data based on the target clock source to obtain time-aligned data. The time-aligned data includes time-aligned GPS positioning data, inertial measurement data, and vehicle speed. The prediction module is used to predict the vehicle's predicted state at the current moment based on the inertial measurement data, the vehicle speed, and the positioning data of the previous moment. The predicted state includes the predicted position and the predicted heading. An error calculation module is used to search for multiple candidate roads within a preset range in a digital map with the predicted location as the center, and to determine the observation error between the predicted state and each of the candidate roads. The fusion positioning module is used to input the minimum observation error into the filter to obtain the fusion positioning result of the filter based on the positioning data, the inertial measurement data and the minimum observation error.
[0012] Thirdly, embodiments of this application provide a positioning terminal, including a memory and a processor. The memory stores a computer program, and the computer program executes the above-described vehicle positioning method when it runs on the processor.
[0013] Thirdly, embodiments of this application provide a readable storage medium storing a computer program that executes the vehicle positioning method described above when run on a processor.
[0014] The embodiments of this application have the following beneficial effects: This embodiment of a vehicle positioning method includes: acquiring multi-source fusion data; performing time alignment processing on the multi-source fusion data based on a target clock source to obtain time-aligned data, the time-aligned data including time-aligned GPS positioning data, inertial measurement data, and vehicle speed; predicting the vehicle's predicted state at the current moment based on the inertial measurement data, vehicle speed, and positioning data from the previous moment, the predicted state including predicted position and predicted heading; searching multiple roads within a preset range on a digital map centered on the predicted position, determining the observation error between the predicted state and each road; inputting the minimum observation error into a filter to obtain a fusion positioning result based on the positioning data, inertial measurement data, and the minimum observation error. Based on the above scheme, time alignment processing reduces fusion errors caused by data asynchrony. The digital map, as a continuous and reliable observation source, can optimize and constrain the positioning results in any environment, reducing over-reliance on GPS positioning data, especially when GPS fails, thus improving the reliability of vehicle positioning in complex urban environments. Attached Figure Description
[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 A schematic flowchart of a first embodiment of the vehicle positioning method of this application is shown; Figure 2 A second flowchart of the vehicle positioning method according to an embodiment of this application is shown; Figure 3 A third flowchart of the vehicle positioning method according to an embodiment of this application is shown; Figure 4 A schematic diagram of a vehicle positioning system according to an embodiment of this application is shown.
[0017] Explanation of key component symbols: 200 - Vehicle positioning system; 210 - Time alignment module; 220 - Prediction module; 230 - Error calculation module; 240 - Fusion positioning module. Detailed Implementation
[0018] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.
[0019] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0020] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0021] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in a generally used dictionary) shall be interpreted as having the same meaning as in the context of the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.
[0022] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0023] Traditional vehicle positioning schemes based on a GPS / IMU combination typically include a GPS receiver and an IMU module. GPS provides absolute position and velocity information, but its update frequency is low and it fails when the signal is blocked; the IMU provides high-frequency attitude and acceleration information, but its errors accumulate over time. The system fuses the data from both using a Kalman filter, using GPS to correct IMU drift and the IMU to provide continuous pose estimation within the GPS update intervals. When GPS fails, the system enters a pure inertial navigation mode, and the positioning error gradually increases.
[0024] Especially in scenarios where GPS is completely unavailable, such as long tunnels or underground parking lots, the system relies solely on the IMU for dead reckoning. Due to the inherent drift characteristics of the IMU, vehicle position errors can accumulate to unacceptable levels within a short period (tens of seconds to minutes), rendering the positioning function essentially ineffective. Moreover, existing solutions often simply feed sensor data from different timestamps directly into the filter, lacking a high-precision time synchronization mechanism, leading to decreased fusion performance, especially when the vehicle is moving at high speeds, which introduces additional errors.
[0025] To address the aforementioned issues, this application provides a vehicle positioning method, system, positioning terminal, and storage medium. High-precision digital map information is used as an observation source and deeply integrated into a combined GPS / IMU / odometer navigation filter to constrain the vehicle's trajectory. This is particularly effective in suppressing inertial navigation solution drift when the Global Navigation Satellite System (GPS) signal fails. Time alignment processing of GPS positioning data, inertial measurement data, and vehicle speed achieves low-cost, high-precision data synchronization.
[0026] The vehicle positioning method will be explained below with reference to some specific embodiments.
[0027] Figure 1 A flowchart of a vehicle positioning method according to an embodiment of this application is shown. Exemplarily, the vehicle positioning method includes the following steps: S110: Acquire multi-source fusion data, perform time alignment processing on the multi-source fusion data based on the target clock source to obtain time-aligned data, which includes time-aligned GPS positioning data, inertial measurement data and vehicle speed.
[0028] Exemplary, the multi-source fusion data includes GPS positioning data, inertial measurement data, and vehicle speed. GPS positioning data can be acquired through a GPS receiver, which receives GNSS satellite signals to obtain the vehicle's position (latitude and longitude), speed, and time in a global coordinate system. Inertial measurement data can be acquired through an inertial measurement unit (IMU), which provides high-frequency raw data on the vehicle's acceleration and angular velocity. Based on the initial state, the IMU can quickly calculate the vehicle's displacement, attitude (pitch / roll / heading), and velocity changes, enabling dead reckoning. Inertial measurement data includes, but is not limited to, vehicle heading (heading angle) and acceleration. Vehicle speed can be acquired through a communication bus interface, which can be a CAN (Controller Area Network) bus.
[0029] In one embodiment, the target clock source is the clock source of the inertial measurement unit, such as... Figure 2 As shown, the time alignment process for multi-source fused data specifically includes the following steps: S111, determine a first delay time for transmission by the global positioning system receiver, the first delay time including a first fixed delay time and a first variable delay time.
[0030] Exemplary, the first fixed delay time is the fixed delay of the GPS receiver receiving satellite signals. This first fixed delay time is a relatively constant time delay determined by the hardware structure and processing flow. The sources of the first fixed delay time include, but are not limited to, satellite signal acquisition and demodulation time, and the average computation time of the PVT (Position, Velocity, Time) calculation algorithm itself. The first variable delay time is the increment of deviation between the GPS receiver's received positioning data at different times and the ideal time. This first variable delay time is the periodic or random jitter delay caused by changes in the external environment or internal state during the operation of the same GPS receiver.
[0031] S112, determine the second delay time of the communication bus, the second delay time includes a second fixed delay time and a second variable delay time.
[0032] Exemplary, the second fixed delay time is the fixed delay for receiving vehicle speed from the communication bus. This second fixed delay time is a relatively constant data transmission delay determined by the physical structure and protocol stack of the onboard network. Sources of the second fixed delay time include, but are not limited to, the time required for the ECU (Electronic Control Unit) to acquire wheel speed sensor signals and calculate vehicle speed, and the processing delay for writing the vehicle speed value into the CAN message and entering the transmission queue. The second variable delay time is the incremental deviation of the vehicle speed received by the communication bus at different times relative to an ideal time. This second variable delay time is a periodic or random change in transmission delay caused by bus load fluctuations, priority contention, or scheduling jitter.
[0033] S113, Align the positioning data, vehicle speed, and measurement data in the time dimension according to the first delay time and the second delay time.
[0034] In one embodiment, the theoretical reception time of the positioning data is determined based on the actual reception time and the first delay time; the theoretical generation time of the vehicle speed is determined based on the actual reception time and the second delay time. Using the time of the inertial measurement data as the system time reference, the theoretical reception time, the theoretical generation time, and the inertial measurement data time are aligned to the same time series to obtain time-aligned data.
[0035] In this embodiment, the theoretical reception time of the positioning data is the difference between the actual reception time and the first delay time, thus obtaining the actual moment when the positioning data occurs. The theoretical generation time of the vehicle speed is the difference between the actual reception time and the second delay time; the theoretical generation time is the starting moment when the vehicle speed value is calculated in its respective electronic control unit and enters the communication queue. Since inertial measurement data has the highest sampling frequency, the output time series of the inertial measurement data is used as the unified time reference for the system. The theoretical sampling time of the positioning data and the theoretical generation time of the vehicle speed are aligned to the time series of the inertial measurement data, forming time-synchronized time-aligned data. This eliminates errors caused by asynchronous acquisition times from different sensors, achieving microsecond-level data alignment.
[0036] S120 predicts the vehicle's current state based on inertial measurement data, vehicle speed, and positioning data from the previous moment. The predicted state includes the predicted position and the predicted heading.
[0037] In one embodiment, the predicted vehicle position is calculated from the vehicle's position at the previous moment to the current moment based on acceleration and vehicle speed; the heading angle at the current moment is used as the predicted heading of the vehicle at the current moment. In this embodiment, the eastward displacement increment can be calculated using the cosine component of the vehicle speed and the heading at the previous moment, and the northward displacement increment can be calculated using the sine component, and these are accumulated to the previous position to obtain the current predicted position. The yaw angle change within the time interval can be integrated based on the angular velocity data output by the inertial measurement unit and superimposed on the heading angle at the previous moment to obtain the predicted heading at the current moment.
[0038] S130: Search for multiple roads within a preset range on the map with the predicted location as the center, and determine the predicted state and the observation error of each road.
[0039] For example, the observation error includes position observation error and heading observation error. For each searched road segment, the shortest geometric distance from the predicted position to the centerline of the road is calculated as the position observation error; at the same time, the angle difference between the predicted heading and the tangent direction of the road at the corresponding position is calculated as the heading observation error; the position observation error and the heading observation error can be normalized separately to obtain dimensionless error components; the normalized error components are weighted and summed using preset weighting coefficients to generate the observation error, which is used for subsequent filter state updates.
[0040] S140, input the minimum observation error into the filter to obtain the fused positioning result based on the positioning data, inertial measurement data and the minimum observation error.
[0041] In this embodiment, the filter includes, but is not limited to, an Extended Kalman Filter (EKF) and an Unscented Kalman Filter (UKF). This filter achieves fusion localization through two steps: state prediction and observation update. First, it performs high-frequency prediction of vehicle position and attitude based on inertial measurement data. Then, it uses GPS-provided positioning data as the primary observation to correct accumulated errors, while using the minimum observation error obtained from map matching as the virtual observation input to provide road geometric constraints and suppress lateral drift. When GPS is available, the filter primarily uses the fusion of inertial measurement and positioning data, with map assistance correcting minor deviations. By dynamically adjusting the weights (i.e., covariance) of each source observation, high-confidence data has a greater impact on the result. Finally, the filter outputs a continuous, smooth fusion localization result with higher accuracy than any single source.
[0042] As an example, when the Global Positioning System is available, positioning data and inertial measurement data have lower observation noise and therefore dominate the fusion process with a larger weight, while map matching serves only as an auxiliary constraint with a smaller weight to suppress slight lateral drift. The guiding filter pulls the final estimated position back onto the road.
[0043] In one embodiment, when GPS positioning data is unavailable, the weight of the minimum observation error in the filter is adjusted to a first weight, and the weight of the positioning data in the filter is adjusted to a second weight, wherein the first weight is greater than the second weight. In this embodiment, when positioning data is lost or its quality degrades, the weight of positioning data observation is reduced, and the weight of the virtual minimum observation error for map matching is increased, making it the main source of correction for maintaining positioning accuracy, thereby effectively suppressing error accumulation in pure inertial navigation mode.
[0044] In another embodiment, such as Figure 3 As shown, the vehicle positioning method also includes the following steps: S150, under the condition that the positioning data of the Global Positioning System cannot be obtained, generates the first candidate state of multiple vehicles at the current moment based on the fused positioning results.
[0045] In this embodiment, each first candidate state represents a possible pose hypothesis of the vehicle at the current moment, constituting a discrete probability distribution sample used to express the state uncertainty of the system in the absence of absolute observations. Guided by the road topology provided by a high-precision digital map, a set of candidate states can be generated along multiple possible driving paths and path directions; each candidate state contains the vehicle's position and heading. For example, initially there are 100 particles distributed within ±5 meters of the current position, with a heading deviation of ±3°, simulating possible drift paths.
[0046] S160, based on the current first candidate states, inertial measurement data and vehicle speed, predict multiple second candidate states of the vehicle at the next moment.
[0047] As an example, the eastward displacement increment can be calculated using the cosine component of the vehicle speed and the vehicle heading in the first candidate state, and the northward displacement increment can be calculated using the sine component. These are then added to the vehicle position in the first candidate state to obtain the vehicle position in the second candidate state. Alternatively, based on the angular velocity data output by the inertial measurement unit, the change in vehicle heading in the first candidate state over a time interval can be integrated and superimposed onto the vehicle heading in the first candidate state to obtain the vehicle heading in the second candidate state.
[0048] S170, determine the matching degree between each second candidate state and the road in the map, and determine the weight of each second candidate state based on the matching degree, wherein the matching degree and the weight are directly proportional.
[0049] In one embodiment, the distance from the vehicle's position to the road in the second candidate state is determined to establish a matching degree, where distance and matching degree are inversely proportional. In this embodiment, for each second candidate state, its position information is matched with a pre-loaded high-precision digital map. The distance from the vehicle's position to the nearest road centerline is calculated, and the angle difference between the vehicle's heading and the road tangent is obtained. The distance and angle difference can be normalized to obtain dimensionless error components. These normalized error components are then weighted and summed using preset weighting coefficients to generate the error for the second candidate state. A smaller error for the second candidate state indicates a higher matching degree.
[0050] S180, based on the weights of each second candidate state, perform a weighted summation of each second candidate state to obtain the target positioning state of the vehicle at the next moment.
[0051] In one implementation, the position and heading of each second candidate state are multiplied by their corresponding weights and then summed to obtain the final weighted position and weighted heading, i.e., the target positioning state. This second candidate state serves as the candidate state for the next moment, and the vehicle's candidate state can continue to be predicted based on inertial measurement data and vehicle speed until the Global Positioning System (GPS) recovers and positioning data can be obtained. This achieves the goal of locking the vehicle trajectory onto a limited and reasonable road path, rather than allowing inertial errors to diverge freely, greatly suppressing the drift of pure inertial navigation.
[0052] In this embodiment, the vehicle is traveling on a highway and briefly enters a tunnel, causing GPS to completely fail. Based solely on IMU / odometer calculations, the positional error could reach tens of meters within a few minutes. At this point, a high-precision map provides a crucial constraint: the filter strongly tends to constrain the vehicle's position to the centerline of the road where the tunnel is located and aligns its heading with the tunnel's direction. Thus, even without GPS, the system can control the positioning error at the lane level until the vehicle exits the tunnel and re-receives positioning data.
[0053] Figure 4 A schematic diagram of a vehicle positioning system 200 according to an embodiment of this application is shown. Exemplarily, the vehicle positioning system 200 includes: The time alignment module 210 is used to acquire multi-source fusion data and perform time alignment processing on the multi-source fusion data based on the target clock source to obtain time-aligned data. The time-aligned data includes the time-aligned positioning data of the global positioning system, inertial measurement data, and vehicle speed.
[0054] The prediction module 220 is used to predict the vehicle's current state based on inertial measurement data, vehicle speed, and positioning data from the previous moment. The predicted state includes the predicted position and the predicted heading.
[0055] The error calculation module 230 is used to search for multiple candidate roads within a preset range on the map with the predicted location as the center, and to determine the observation error between the predicted state and each candidate road.
[0056] The fusion positioning module 240 is used to input the minimum observation error into the filter to obtain the fusion positioning result based on the positioning data, inertial measurement data and the minimum observation error.
[0057] It is understood that the system in this embodiment corresponds to the vehicle positioning method in the above embodiments, and the options in the above embodiments are also applicable to this embodiment, so they will not be described again here.
[0058] This application also provides a positioning terminal, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the positioning terminal to perform the functions of the vehicle positioning method described above or the various modules in the vehicle positioning system 200 described above. This positioning terminal includes, but is not limited to, on-board computing units, domain controllers, and other on-board positioning devices.
[0059] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.
[0060] Memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM). Memory is used to store computer programs, and the processor can execute these programs upon receiving execution instructions.
[0061] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned positioning terminal. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0062] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0063] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0064] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.
[0065] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A vehicle positioning method, characterized in that, include: Acquire multi-source fusion data, and perform time alignment processing on the multi-source fusion data based on the target clock source to obtain time-aligned data. The time-aligned data includes time-aligned GPS positioning data, inertial measurement data, and vehicle speed. The predicted state of the vehicle at the current moment is predicted based on the inertial measurement data, the vehicle speed, and the positioning data of the previous moment. The predicted state includes the predicted position and the predicted heading. Using the predicted location as the center, search for multiple roads within a preset range in the digital map, and determine the observation error between the predicted state and each of the roads; The minimum observation error is input into the filter to obtain the fused positioning result based on the positioning data, the inertial measurement data, and the minimum observation error.
2. The vehicle positioning method according to claim 1, characterized in that, Also includes: When the positioning data of the Global Positioning System cannot be obtained, the weight of the minimum observation error in the filter is adjusted to a first weight, and the weight of the positioning data in the filter is adjusted to a second weight, wherein the first weight is greater than the second weight.
3. The vehicle positioning method according to claim 1, characterized in that, Also includes: In the absence of location data from the Global Positioning System, multiple candidate states for vehicles at the current moment are generated based on the fused positioning results. Based on the current first candidate states, the inertial measurement data, and the vehicle speed, predict multiple second candidate states for the vehicle in the next moment; Determine the matching degree between each second candidate state and a road in the digital map, and determine the weight of each second candidate state based on the matching degree, wherein the matching degree and the weight are directly proportional. The target positioning state of the vehicle at the next moment is obtained by weighting and summing the weights of each second candidate state.
4. The vehicle positioning method according to claim 1, characterized in that, The target clock source is the clock source of the inertial measurement unit. The step of performing time alignment processing on the multi-source fused data based on the target clock source includes: A first delay time is determined for transmission by the Global Positioning System receiver, the first delay time including a first fixed delay time and a first variable delay time; The first fixed delay time is the fixed delay time for the global positioning system receiver to receive satellite signals, and the first variable delay time is the deviation increment of the positioning data received by the global positioning system receiver at different times relative to the ideal time; A second delay time for the communication bus is determined, the second delay time including a second fixed delay time and a second variable delay time; The second fixed delay time is the fixed delay for receiving the vehicle speed from the communication bus, and the second variable delay time is the deviation increment of the vehicle speed received by the communication bus at different times relative to the ideal time; The positioning data, vehicle speed, and measurement data are aligned in the time dimension based on the first delay time and the second delay time.
5. The vehicle positioning method according to claim 4, characterized in that, Aligning the positioning data, vehicle speed, and measurement data in the time dimension according to the first delay time and the second delay time includes: Based on the actual reception time of the positioning data and the first delay time, the theoretical reception time of the positioning data is determined; Based on the actual reception time of the vehicle speed and the second delay time, the theoretical generation time of the vehicle speed is determined; Using the time of the inertial measurement data as the system time reference, the theoretical reception time, the theoretical generation time, and the inertial measurement data time are aligned to the same time series to obtain the time-aligned data.
6. The vehicle positioning method according to claim 1, characterized in that, The inertial measurement data includes acceleration and heading angle, and the positioning data includes vehicle position. The step of predicting the vehicle's current state based on the inertial measurement data, vehicle speed, and positioning data from the previous moment includes: The predicted position of the vehicle is calculated from the vehicle's position at the previous moment to the current moment, based on the acceleration and the vehicle speed. The heading angle at the current moment is taken as the predicted heading of the vehicle at the current moment.
7. The vehicle positioning method according to claim 3, characterized in that, Determining the matching degree between each second candidate state and a road in the digital map includes: The distance from the vehicle's position to the road in the second candidate state is determined, and the matching degree is determined based on the distance, wherein the distance and the matching degree are inversely proportional.
8. A vehicle positioning system, characterized in that, include: The time alignment module is used to acquire multi-source fused data and perform time alignment processing on the multi-source fused data based on the target clock source to obtain time-aligned data. The time-aligned data includes time-aligned GPS positioning data, inertial measurement data, and vehicle speed. The prediction module is used to predict the vehicle's predicted state at the current moment based on the inertial measurement data, the vehicle speed, and the positioning data of the previous moment. The predicted state includes the predicted position and the predicted heading. An error calculation module is used to search for multiple candidate roads within a preset range in a digital map with the predicted location as the center, and to determine the observation error between the predicted state and each of the candidate roads. The fusion positioning module is used to input the minimum observation error into the filter to obtain the fusion positioning result of the filter based on the positioning data, the inertial measurement data and the minimum observation error.
9. A positioning terminal, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed on the processor, performs the vehicle positioning method according to any one of claims 1 to 7.
10. A readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the vehicle positioning method according to any one of claims 1 to 7.