Vehicle positioning method, system, device and storage medium

Abstract

The present invention provides a vehicle positioning method, system, device and storage medium. Among them, an RTK positioning system and a UWB positioning system are deployed on the vehicle-mounted side. The method includes: obtaining RTK positioning observations of the vehicle where it is located by using the RTK positioning system, obtaining UWB positioning observations of the vehicle where it is located by using the UWB positioning system, obtaining the confidence levels of the RTK positioning system and the UWB positioning system respectively, selecting target positioning observations whose system confidence levels meet the set conditions from the RTK positioning observations and the UWB positioning observations, and using the target positioning observations as the vehicle-end positioning result. The present invention can achieve integrated positioning based on RTK-UWB technology. In this case, even when system errors are caused by scene switching, positioning observations with smaller errors and higher accuracy can be selected in a timely manner according to the system confidence level as the vehicle positioning result, improving the vehicle positioning accuracy.

Description

Background Art

[0002] An autonomous vehicle, also known as a driverless vehicle, a computer-driven vehicle, a self-driving vehicle, is a vehicle that requires driver assistance or no operation at all. As an automated vehicle, an autonomous vehicle can sense its environment and navigate without human operation.

[0003] How to more accurately perform self-positioning during the autonomous driving process of a vehicle is an issue that the industry needs to consider.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present invention, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] Aiming at the problems in the prior art, the purpose of the present invention is to provide a vehicle positioning method, system, device and storage medium, which overcome the difficulties of the prior art, can select a target positioning observation value with lower error and higher credibility from RTK positioning observation values and UWB positioning observation values according to the system confidence, and realize fusion positioning based on RTK-UWB technology to improve the vehicle positioning accuracy.

[0006] An embodiment of the present invention provides a vehicle positioning method, which is applied to the vehicle-mounted terminal. An RTK positioning system and a UWB positioning system are deployed at the vehicle-mounted terminal. The vehicle positioning method includes:

[0007] Obtain the RTK positioning observation value of the vehicle using the RTK positioning system;

[0008] Obtain the UWB positioning observation value of the vehicle using the UWB positioning system;

[0009] Obtain the confidence of each of the RTK positioning system and the UWB positioning system, select a target positioning observation value whose system confidence meets the set conditions from the RTK positioning observation value and the UWB positioning observation value, and use the target positioning observation value as the vehicle terminal positioning result;

[0010] Control the vehicle to perform corresponding driving behaviors using the vehicle terminal positioning result.

[0011] Optionally, selecting a target positioning observation value whose system confidence meets the set conditions from the RTK positioning observation value and the UWB positioning observation value includes:

[0012] When the system confidence of each of the RTK positioning system and the UWB positioning system is within the set confidence interval, select a target positioning observation value with a relatively larger system confidence from the RTK positioning observation value and the UWB positioning observation value.

[0013] Optionally, a target positioning observation value whose system confidence satisfies a set condition is selected from the RTK positioning observation value and the UWB positioning observation value, including:

[0014] When one of the system confidences of the RTK positioning system and the UWB positioning system is within a set confidence interval, a target positioning observation value whose system confidence is within the set confidence interval is selected from the RTK positioning observation value and the UWB positioning observation value.

[0015] Optionally, the vehicle positioning method further includes:

[0016] When the system confidence of the RTK positioning system and the UWB positioning system are both not within the set confidence interval, the vehicle positioning estimate at the second moment obtained based on the vehicle-side positioning result at the first moment is used as the vehicle-side positioning result;

[0017] The first moment is the moment before the second moment, and the RTK positioning observation value and the UWB positioning observation value are both positioning observation values at the second moment.

[0018] Optionally, before selecting a target positioning observation value whose system confidence satisfies a set condition from among the RTK positioning observation value and the UWB positioning observation value, the vehicle positioning method further includes:

[0019] Time synchronization is performed on RTK positioning observations and UWB positioning observations.

[0020] Optionally, the vehicle positioning method further includes:

[0021] Before using the target positioning observation value as the vehicle-side positioning result, obtaining a vehicle positioning estimate value at a second moment estimated based on the vehicle-side positioning result at a first moment, wherein the first moment is a moment before the second moment, and the vehicle positioning estimate value and the target positioning observation value are synchronized in time;

[0022] Using an extended Kalman filter, a preset error covariance matrix is used to converge the error between the vehicle positioning estimate at the second moment and the target positioning observation value;

[0023] When converged, the target positioning observation value is used as the vehicle-side positioning result.

[0024] Optionally, the vehicle positioning method further includes:

[0025] The Kalman gain is calculated using the vehicle-side positioning result and the vehicle positioning estimate at the second moment;

[0026] The error covariance matrix is updated using the Kalman gain.

[0027] Optionally, the vehicle positioning method further includes:

[0028] Upload the RTK positioning observation values, UWB positioning observation values, and vehicle - end positioning results to the cloud.

[0029] In the case of receiving an alarm from the cloud regarding the error of the vehicle - end positioning result, respond to the alarm and control the vehicle to execute the regulation behavior corresponding to the alarm.

[0030] An embodiment of the present invention further provides a vehicle positioning method, which is applied to the cloud corresponding to the vehicle - mounted terminal. The vehicle positioning method includes:

[0031] Receive, from the vehicle - mounted terminal, the first RTK positioning observation values of the vehicle, the first UWB positioning observation values, and the first target positioning observation values selected from the first RTK positioning observation values and the first UWB positioning observation values, where the system confidence meets the set conditions.

[0032] Use the CORS network data to calculate the second RTK positioning observation values of the vehicle, and use the UWB network data to calculate the second UWB positioning observation values of the vehicle, and select the second target positioning observation values whose system confidence meets the set conditions from the second RTK positioning observation values and the second UWB positioning observation values.

[0033] In the case where the error between the first target positioning observation values and the second target positioning observation values exceeds the error threshold, send an alarm message to the vehicle - mounted terminal.

[0034] Optionally, before using the CORS network data to calculate the second RTK positioning observation values of the vehicle, using the UWB network data to calculate the second UWB positioning observation values of the vehicle, and selecting the second target positioning observation values whose system confidence meets the set conditions from the second RTK positioning observation values and the second UWB positioning observation values, the vehicle positioning method further includes:

[0035] Receive, from the vehicle - mounted terminal, the system confidence of the reported first RTK positioning observation values as the system confidence of the second RTK positioning observation values.

[0036] In the case of deploying the UWB positioning system in the cloud, extract the system confidence of the UWB positioning system from the storage location in the cloud.

[0037] An embodiment of the present invention further provides a vehicle positioning system, including:

[0038] A vehicle - mounted terminal, which obtains the first RTK positioning observation values of the vehicle, the first UWB positioning observation values, and the first target positioning observation values selected from the first RTK positioning observation values and the first UWB positioning observation values, where the system confidence meets the set conditions.

[0039] The cloud receives the first RTK positioning observation value, the first UWB positioning observation value, and the first target positioning observation value from the vehicle-mounted terminal, calculates the second RTK positioning observation value of the vehicle using the CORS network data, and calculates the second UWB positioning observation value of the vehicle using the UWB network data, and selects the second target positioning observation value whose system confidence level meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value. When the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold, an alarm message is sent to the vehicle-mounted terminal.

[0040] An embodiment of the present invention further provides a vehicle positioning system, which is applied to the vehicle-mounted terminal. An RTK positioning system and a UWB positioning system are deployed at the vehicle-mounted terminal. The vehicle positioning system includes:

[0041] A first positioning module that obtains the RTK positioning observation value of the vehicle where it is located using the RTK positioning system;

[0042] A second positioning module that obtains the UWB positioning observation value of the vehicle where it is located using the UWB positioning system;

[0043] A first fusion positioning module that obtains the confidence levels of the RTK positioning system and the UWB positioning system respectively, selects the target positioning observation value whose system confidence level meets the set conditions from the RTK positioning observation value and the UWB positioning observation value, and uses the target positioning observation value as the vehicle-end positioning result;

[0044] A control module that controls the vehicle to perform corresponding driving behaviors using the vehicle-end positioning result.

[0045] An embodiment of the present invention further provides a vehicle positioning system, which is applied to the cloud corresponding to the vehicle-mounted terminal. The vehicle positioning system includes:

[0046] A receiving module that receives the first RTK positioning observation value, the first UWB positioning observation value, and the first target positioning observation value selected from the first RTK positioning observation value and the first UWB positioning observation value and whose system confidence level meets the set conditions of the vehicle from the vehicle-mounted terminal;

[0047] A second fusion positioning module that calculates the second RTK positioning observation value of the vehicle using the CORS network data, and calculates the second UWB positioning observation value of the vehicle using the UWB network data, and selects the second target positioning observation value whose system confidence level meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value;

[0048] A sending module that sends an alarm message to the vehicle-mounted terminal when the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold.

[0049] An embodiment of the present invention further provides a vehicle positioning device, including:

[0050] A processor;

[0051] A memory in which executable instructions of the processor are stored;

[0052] Wherein, the processor is configured to execute the steps of the above vehicle positioning method by executing the executable instructions.

[0053] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, and when the program is executed, the steps of the above vehicle positioning method are implemented.

[0054] The purpose of the present invention is to provide a vehicle positioning method, system, device and storage medium, which can deploy an RTK positioning system and a UWB positioning system on the vehicle side at the same time, and select a target positioning observation value with lower error and higher credibility from the RTK positioning observation value and the UWB positioning observation value according to the system confidence, so as to realize fusion positioning based on RTK-UWB technology. In this case, even if the system error is caused by scene switching, the positioning observation value with smaller error and higher accuracy can be selected in a timely manner according to the system confidence as the vehicle positioning result, thereby improving the vehicle positioning accuracy. Description of the Drawings

[0055] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious.

[0056] Figure 1 is a flowchart of one of the embodiments of the vehicle positioning method of the present invention;

[0057] Figure 2 is a flowchart of the second embodiment of the vehicle positioning method of the present invention;

[0058] Figure 3 is a timing diagram of the third embodiment of the vehicle positioning method of the present invention;

[0059] Figure 4 is a structural diagram of an embodiment of the vehicle positioning system of the present invention;

[0060] Figure 5 is a schematic diagram of an application scenario of the vehicle positioning method of the present invention;

[0061] Figure 6 is a block diagram of one of the embodiments of the vehicle positioning system of the embodiments of the present invention;

[0062] Figure 7 is a block diagram of the second embodiment of the vehicle positioning system of the embodiments of the present invention;

[0063] Figure 8 It is a schematic diagram of the modules of the third embodiment of the vehicle positioning system according to the embodiments of the present invention;

[0064] Figure 9 It is a schematic diagram of the modules of the fourth embodiment of the vehicle positioning system according to the embodiments of the present invention;

[0065] Figure 10 It is a schematic diagram of the operation of the vehicle positioning system of the present invention. Specific Embodiments

[0066] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0067] The accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware forwarding modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0068] In addition, the processes shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all steps. For example, some steps can be decomposed, some steps can be combined or partially combined, and the actual execution order may be changed according to the actual situation. The "first", "second" and similar terms used in the specific description do not denote any order, quantity or importance, but are only used to distinguish different components. It should be noted that, without conflict, the features in the embodiments of the present invention and those in different embodiments can be combined with each other.

[0069] In the prior art, high-precision positioning technology is an important basis for realizing vehicle autonomous driving. The commonly used high-precision positioning solutions in the field of autonomous driving include:

[0070] A high-precision positioning system based on the real-time kinematic (RTK) technology and the inertial measurement unit (IMU); and

[0071] A high-precision positioning system based on the ultra-wideband (UWB) technology and the IMU.

[0072] Among them, RTK is the abbreviation of Real-Time Kinematic carrier-phase differential technology, which is a differential measurement technology that realizes fast and high-precision positioning functions by using carrier-phase observation values through synchronous observations of a reference station and a rover station.

[0073] Among them, RTK is realized based on the Continuously Operating Reference Stations (CORS) system. Usually, multiple (generally three or more) Global Navigation Satellite System (GNSS) reference stations (CORS stations) are established in a region to form a network coverage (CORS network) for this region.

[0074] During operation, one receiver is installed on a known high-level point as a reference station to continuously observe GPS satellites, and the observation data and station information are transmitted to the rover station in real time through a radio transmission device. While the rover station receiver receives GPS satellite signals and collects satellite data, it receives the data link from the reference station through a wireless receiving device, and performs carrier-phase differential processing on the two sets of collected and received data in the system to calculate the three-dimensional coordinates and their accuracy of the rover station in real time. Using RTK technology, by utilizing the spatial correlation of observation errors between the reference station and the rover station, most of the errors in the rover station's observation data are removed through the differential method, thereby achieving high-precision positioning.

[0075] IMU is a device that measures the vehicle's three-axis attitude angle (or angular rate) and acceleration

[0076] UWB is a carrierless communication technology that uses non-sinusoidal narrow pulses in the nanosecond to picosecond range to transmit data. The positioning principle of UWB is that by arranging several positioning base stations with known coordinates, the vehicle emits pulses at a certain frequency, continuously measures distances with several base stations, and determines the position of the tag through a certain precise algorithm.

[0077] UWB can achieve a data transmission rate of several hundred Mbit / s to several Gbit / s within a range of about 10 meters. Applying this technology can achieve a positioning accuracy of up to 10 cm.

[0078] During the process of using the above two solutions for autonomous driving tests, the inventors of this case found that in an environmental scenario where the vehicle has both RTK positioning and UWB positioning results at the vehicle end, when the scenario changes continuously, the vehicle will introduce a certain degree of system error due to the switching of its own different positioning systems.

[0079] At this time, how to reduce the positioning error and obtain a high-precision vehicle positioning result is the technical problem to be solved in this case.

[0080] Embodiments of the present invention provide a vehicle positioning method, system, device, and storage medium. The inventive concept is that by deploying an RTK-UWB integrated positioning solution, when the vehicle-mounted terminal obtains two positioning observations based on the RTK and UWB positioning engines, the two positioning observations are selected based on the observation confidence levels of the two positioning systems, and the observation with the higher observation confidence level is adopted.

[0081] Figure 1 This is a flowchart of an embodiment of the vehicle positioning method of the present invention. The execution node of this method is the vehicle-mounted terminal, where an RTK positioning system and a UWB positioning system are deployed. As Figure 1 shown, the vehicle positioning method provided by the embodiments of the present invention includes the following steps:

[0082] Step 110: Obtain the RTK positioning observation of the vehicle using the RTK positioning system;

[0083] Step 120: Obtain the UWB positioning observation of the vehicle using the UWB positioning system;

[0084] Step 130: Obtain the system confidence levels of the RTK positioning system and the UWB positioning system respectively, select the target positioning observation whose system confidence level meets the set conditions from the RTK positioning observation and the UWB positioning observation, and use the target positioning observation as the vehicle-end positioning result;

[0085] Step 140: Control the vehicle to perform corresponding driving behaviors using the vehicle-end positioning result.

[0086] Embodiments of the present invention can select the target positioning observation with lower error and higher credibility from the RTK positioning observation and the UWB positioning observation according to the system confidence level, and achieve integrated positioning based on the RTK-UWB technology. In this case, even when the system error is caused by scene switching, the positioning observation with smaller error and higher accuracy can be selected in a timely manner according to the system confidence level as the vehicle-end positioning result, improving the vehicle positioning accuracy.

[0087] In an application scenario, even when the RTK positioning technology is restricted by a road environment scene with strong interference and strong occlusion, such as when the vehicle enters / leaves a tunnel or the vehicle is driving in an environment with many viaducts, using the embodiments of the present invention, it is also possible to use the UWB positioning technology to achieve high-precision vehicle positioning.

[0088] In this case, the system confidence levels of the UWB positioning system and the RTK positioning system in the face of these scenarios can evaluate the accuracy of each positioning result in the corresponding scenario, so that it is possible to automatically switch to the appropriate positioning system and adopt the positioning observation of the selected positioning system as the vehicle-end positioning result.

[0089] In an alternative embodiment, the system confidence of the RTK positioning system and the system confidence of the UWB positioning system are specifically in the form of an observation noise variance matrix.

[0090] In an alternative embodiment, selecting target positioning observations with system confidence meeting the set conditions from the RTK positioning observations and the UWB positioning observations specifically includes the following steps:

[0091] When the system confidence of each of the RTK positioning system and the UWB positioning system is within the set confidence interval, select the target positioning observation with relatively higher system confidence from the RTK positioning observations and the UWB positioning observations.

[0092] That is, the set condition here is to adopt the positioning observation with higher confidence.

[0093] In an alternative embodiment, selecting target positioning observations with system confidence meeting the set conditions from the RTK positioning observations and the UWB positioning observations specifically includes the following steps:

[0094] When one of the system confidences of the RTK positioning system and the UWB positioning system is within the set confidence interval, select the target positioning observation with system confidence within the set confidence interval from the RTK positioning observations and the UWB positioning observations.

[0095] In this case, first make an initial judgment on the system confidence set for the RTK positioning system and the UWB positioning system according to the confidence interval to determine their credibility, thereby improving the accuracy of the positioning result.

[0096] In an alternative embodiment, the vehicle positioning method further includes the following steps:

[0097] When the system confidence of each of the RTK positioning system and the UWB positioning system is not within the set confidence interval, use the predicted value of vehicle positioning at the second moment as the vehicle terminal positioning result;

[0098] Wherein, the predicted value of vehicle positioning at the second moment is predicted based on the vehicle terminal positioning result at the first moment with earlier time sequence, and both the RTK positioning observation and the UWB positioning observation are the positioning observations at the second moment.

[0099] In an alternative embodiment, before selecting target positioning observations with system confidence meeting the set conditions from the RTK positioning observations and the UWB positioning observations, the vehicle positioning method further includes:

[0100] Synchronize the time of the RTK positioning observations and the UWB positioning observations.

[0101] In an alternative embodiment, the vehicle positioning method further includes the following steps:

[0102] Before using the target positioning observation value as the vehicle-end positioning result, obtain a vehicle positioning prediction value at a second moment estimated based on the vehicle-end positioning result at a first moment, where the first moment is a moment before the second moment, and the vehicle positioning prediction value is time-synchronized with the target positioning observation value;

[0103] Use a Kalman filter to converge the error between the vehicle positioning prediction value at the second moment and the target positioning observation value using a preset error covariance matrix;

[0104] In the case of convergence, use the target positioning observation value as the vehicle-end positioning result.

[0105] The Kalman filter is an optimal linear state estimation method (equivalent to "the best linear filter under the minimum mean square error criterion"). State estimation is to find the state vector that best fits the observed data through mathematical methods.

[0106] The error covariance matrix characterizes the relative weight between the vehicle positioning prediction value at the second moment and the target positioning observation value. Convergence means that the relative weight of the two approaches 1, that is, the target positioning observation value and the vehicle positioning prediction value tend to be consistent, and then the target positioning observation value is credible.

[0107] In an alternative embodiment, the vehicle positioning method further includes the following steps:

[0108] Calculate the Kalman gain using the vehicle-end positioning result and the vehicle positioning prediction value at the second moment;

[0109] Update the error covariance matrix using the Kalman gain.

[0110] The updated error covariance matrix is used for vehicle positioning at the next moment.

[0111] The Kalman gain is the relative weight assigned to the vehicle positioning observation value and the estimated value, and can be "adjusted" to obtain specific performance. When the gain is high, the filter focuses more on the latest observation value, so the response speed is faster. When the gain is low, the filter follows the predicted estimated value more closely.

[0112] In an alternative embodiment, Figure 1 The execution subject of the vehicle positioning method shown is the vehicle-mounted end. At this time, the vehicle positioning method further includes:

[0113] Upload the RTK positioning observation value, UWB positioning observation value, and vehicle-end positioning result to the cloud;

[0114] When receiving an alarm about the error of the vehicle positioning result from the cloud, respond to the alarm and control the vehicle to execute the regulation behavior corresponding to the alarm.

[0115] Figure 2 The figure is a flowchart of the vehicle positioning method provided by the embodiment of the present invention. The execution subject of this method is the cloud corresponding to the in-vehicle terminal. The vehicle positioning method includes:

[0116] Step 210: Obtain the first RTK positioning observation value, the first UWB positioning observation value of the vehicle from the in-vehicle terminal, and the first target positioning observation value whose system confidence level selected from the first RTK positioning observation value and the first UWB positioning observation value meets the set condition;

[0117] Step 220: Use the CORS station network data to calculate the second RTK positioning observation value of the vehicle, and use the UWB station network data to calculate the second UWB positioning observation value of the vehicle, and select the second target positioning observation value whose system confidence level meets the set condition from the second RTK positioning observation value and the second UWB positioning observation value;

[0118] Step 230: When the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold, send an alarm message to the in-vehicle terminal.

[0119] For step 220, reference can be made to step 120 above, and details will not be elaborated here.

[0120] In possible application scenarios, the positions of the base stations in the CORS station network may be offset, and there may be system errors in the base station equipment itself. Similarly, the UWB station network may also have these problems. However, for the in-vehicle terminal, it is insensitive to these problems. The cloud can obtain the possible defective problems of the CORS station network or the UWB station network. Therefore, it is considered that the RTK positioning observation value, the UWB observation value and the fusion positioning result of the two calculated by it are relatively accurate, and can be used to evaluate the error of the vehicle positioning result calculated by the in-vehicle terminal, and can give an alarm in time when there is a large error in the vehicle positioning result measured by the in-vehicle terminal.

[0121] In the embodiment of the present invention, the RTK-UWB fusion positioning algorithm engines are respectively deployed at the in-vehicle terminal and the cloud. The cloud establishes an effective cloud monitoring operation analysis system through strong computing power, and real-time identifies the error of the positioning result of the in-vehicle terminal according to the CORS station network and UWB station network data. When the positioning error exceeds the error threshold, an alarm message is sent to the in-vehicle terminal to prompt the in-vehicle terminal to make corresponding response actions, so as to meet the safety requirements of the autonomous driving function.

[0122] In an alternative embodiment, the CORS station network data and UWB station network data on which cloud positioning is based can be actual station network data pre - stored in the cloud, which is consistent with the CORS station network data set and UWB station network data on which the vehicle - mounted terminal is based under normal circumstances.

[0123] In special circumstances, the CORS station network data and UWB station network data on which cloud positioning is based are the latest station network data.

[0124] In an alternative embodiment, before calculating the second RTK positioning observation value of the vehicle using the CORS station network data, calculating the second UWB positioning observation value of the vehicle using the UWB station network data, and selecting a second target positioning observation value whose system confidence meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value, the vehicle positioning method further includes the following steps:

[0125] Receiving, from the vehicle - mounted terminal, the system confidence of the reported first RTK positioning observation value as the system confidence of the second RTK positioning observation value;

[0126] In the case where the UWB positioning system is deployed in the cloud, extracting the system confidence of the UWB positioning system from the storage location in the cloud.

[0127] In this embodiment, the vehicle - mounted terminal reports the first RTK positioning observation value and the system confidence of the corresponding RTK positioning system. The vehicle - mounted terminal may not deploy the RTK positioning system. In this case, the reported first RTK positioning observation value of the vehicle - mounted terminal is directly used as the second RTK positioning observation value.

[0128] In this embodiment, the UWB positioning system is deployed in the cloud and the system confidence of the UWB positioning system is stored, so that the cloud can calculate the second UWB positioning observation value using the UWB positioning system deployed by itself.

[0129] In an alternative embodiment, a VRS algorithm engine based on the virtual reference station technology VRS (Virtual Reference Station) is deployed in the cloud. The virtual reference station technology, also known as the virtual base station technology, is a network real - time kinematic measurement technology. By establishing multiple GPS reference stations that form a network - like coverage in a certain area and establishing a virtual reference station near the rover station, the virtual observation value of the virtual reference station is calculated based on the actual observation values on each surrounding reference station to achieve high - precision positioning of the user station.

[0130] The VRS algorithm engine is used to send differential correction information to the vehicle - mounted terminal according to the position reported by the vehicle - mounted terminal, so that the vehicle - mounted terminal can calculate the RTK positioning observation value with dynamic sub - meter and centimeter - level accuracy through the RTK positioning system based on the differential correction information and the GNSS raw observation information.

[0131] Figure 3 This is a timing diagram of the vehicle positioning method provided by an embodiment of the present invention. This method includes:

[0132] The in-vehicle RTK positioning system calculates the RTK positioning result by observing the original observation information of the Global Navigation Satellite System (GNSS) and receiving differential correction information.

[0133] The in-vehicle UWB positioning system calculates the UWB positioning result by receiving the message information broadcast by the UWB base station.

[0134] The in-vehicle terminal sets the confidence levels for the RTK and UWB positioning results respectively through a preset fusion positioning algorithm engine, selects the positioning system by confidence level judgment, and outputs the corresponding fusion positioning result, that is, the RTK-UWB positioning result, which is the vehicle terminal positioning result.

[0135] The in-vehicle terminal uploads the RTK positioning result, UWB positioning result, and fusion positioning result to the cloud fusion positioning supervision system.

[0136] The cloud fusion positioning supervision system calls the RTK-UWB fusion positioning algorithm engine in the cloud and calculates the fusion positioning result using the same fusion positioning algorithm as the in-vehicle terminal.

[0137] The platform fusion positioning supervision system automatically alarms the vehicle terminal when the error exceeds the preset error threshold according to the alarm evaluation accuracy it sets.

[0138] The cloud respectively performs real-time quality analysis on the CORS network, UWB network, differential service, and the reported RTK and UWB positioning results of the vehicle terminal through its own analysis ability, evaluates the differential service, UWB site, and vehicle terminal positioning status and results. If it exceeds the alarm threshold defined by the cloud monitoring system, the cloud can broadcast quality alarm information to the vehicle terminal CAN bus through the mobile communication network, and the vehicle combines its own management system to decelerate and turn on the indicator light to ensure vehicle safety.

[0139] In this case, referring to Figure 4 , the vehicle positioning system provided by the embodiment of the present invention may include:

[0140] An in-vehicle terminal 410, which obtains the first RTK positioning observation value, the first UWB positioning observation value of the vehicle, and the first target positioning observation value whose system confidence level selected from the first RTK positioning observation value and the first UWB positioning observation value meets the set conditions.

[0141] The cloud 420 receives the first RTK positioning observation value, the first UWB positioning observation value, and the first target positioning observation value from the vehicle-mounted terminal 410, calculates the second RTK positioning observation value of the vehicle using the CORS network data, and calculates the second UWB positioning observation value of the vehicle using the UWB network data, and selects the second target positioning observation value whose system confidence meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value. When the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold, an alarm message is sent to the vehicle-mounted terminal.

[0142] Reference Figure 5 , the vehicle positioning method specifically includes the following application scenarios:

[0143] In an open environment (GNSS signal environment), the GNSS signal is strong, and the vehicle-mounted terminal uses the CORS base station network for self-vehicle positioning;

[0144] In a closed environment (UWB signal environment), the GNSS signal is weak or there is no GNSS signal. At this time, the UWB signal existing in the tunnel is used for self-vehicle positioning;

[0145] In the multi-path environment (GNSS / UWB signal environment) switching scenario, when the GNSS / UWB signal switches, the vehicle-mounted terminal uses the RTK-UWB fusion positioning technology provided by the embodiments of the present invention for self-vehicle positioning, and the cloud is responsible for evaluating the error of the vehicle-end positioning result.

[0146] This effectively solves the problem of achieving high-precision positioning in the scenario of no / weak GNSS signal.

[0147] From Figure 5 It can be seen that a VRS algorithm engine and a UWB positioning system are deployed in the cloud. For the functions of the two, reference can be made to the above text and will not be elaborated here.

[0148] Specifically, the RTK-UWB fusion positioning algorithm deployed on the vehicle-mounted terminal or the cloud in the embodiments of the present invention is specifically described as follows.

[0149] First, vehicle coordinate modeling.

[0150] The vehicle moves approximately in a two-dimensional plane. Since the vehicle centroid point, GNSS antenna, and UWB antenna cannot be strictly aligned, there is the concept of lever arms, which are L(G) and L(U) respectively. Two coordinate systems are defined, the vehicle body coordinate system (v system) and the navigation coordinate system (n system).

[0151] Among them, in the vehicle body coordinate system, the longitudinal direction (front of the vehicle) is the Y axis, the transverse direction (vehicle body) is the X axis, and the origin is the reference point (centroid) of the vehicle body. The navigation coordinate system is set as the longitude and latitude coordinate system, with the due east as the X axis and the due north as the Y axis.

[0152] Among them, the velocity and position of the reference point in the navigation system (n - system) are V n and P n , the velocity and position of the GNSS antenna in the navigation system (n - system) are V Gn and P Gn , the position of the UWB antenna in the navigation system (n - system) is P un .

[0153] The relationship between the vehicle body coordinate system and the navigation coordinate system, that is, the attitude of the vehicle body, is usually represented by . Since the vehicle movement is approximately in a two - dimensional plane, is a 2×2 matrix and can be expressed as and there is only one degree of freedom, the heading angle θ, where θ is the angle between the vehicle body coordinate system and the navigation coordinate system.

[0154] The RTK - UWB fusion positioning algorithm is mainly applicable to the scenario where there are both RTK and UWB positioning results when entering / leaving the tunnel, reducing the large system error caused by system switching. Generally, during the vehicle driving process, in the scenario of entering / leaving the tunnel, the speed of the vehicle remains basically unchanged, and a uniform motion model is used for modeling.

[0155] Using the uniform motion model for modeling, the vehicle dynamic equation can be expressed as:

[0156] P n =V n +n v

[0157] V n =0 + n a

[0158] where n v and n a are Gaussian white noises with zero mean. Here, the fusion problem can be regarded as estimating the state vector X = [P gn V gn P un through the observation quantities V n V n T .

[0159] Among them, for the RTK - UWB fusion positioning algorithm based on the Extended Kalman Filter (EKF), based on the KF filter theoretical framework, the state vector of the system is defined as X = [P n V n θ] T , V n ​Let \(v\) and \(\theta\) be the scalar speed and heading angle of the reference point respectively, and the heading angle is defined as the deflection angle with respect to due north.

[0160] The system state transition equation is established as:

[0161]

[0162] \(Q\) is the system noise covariance matrix, and \(g(X n )\) is a non - linear function. To perform the Extended Kalman Filter (EKF), partial derivatives are needed to linearize it:

[0163] \(X n+1 =AX n

[0164] +Q

[0165]

[0166] Among them, the RTK observation equation is:

[0167]

[0168] \(w n \) is the angular velocity of the reference point. When the angular velocity is small enough or the lever - arm value is small enough, the \(w n \cdot L G \) term can be ignored.

[0169] Write the RTK observation as the form of a state vector:

[0170]

[0171] The RTK observation vector is not a linear function of the state vector, and partial derivatives are needed to linearize it:

[0172] \(Z G =H G x + R G

[0173]

[0174] The UWB observation equation:

[0175]

[0176] The UWB observation equation is a non - linear equation, so it needs to be linearized:

[0177] \(Z U =H u \cdot x+R u

[0178]

[0179] R G and R U are the observation noise variance matrices of RTK and UWB respectively, corresponding to the confidence levels of RTK and UWB observations. The positioning system is switched according to the confidence level results of each system.

[0180] The system state transition equation, RTK and UWB observation equations are established respectively above, and the standard EKF filter can be used for data fusion.

[0181] EKF system dynamic model: X k = f(X k-1 , t) + G(t)·w k

[0182] EKF system observation model: Z(t) = h(X k , t) + w k

[0183] Predicted state model:

[0184] Predicted error covariance matrix model:

[0185] Observation innovation update:

[0186] KF gain:

[0187] State vector update:

[0188] Error covariance update:

[0189] According to the data reported by the RTK and UWB positioning systems, time synchronization is performed, and the respective observation noise covariances are evaluated. The system can automatically switch each positioning result. When the data of both have not converged or the confidence level is low, the predicted data can be output as the output of the current system.

[0190] The embodiment of the present invention solves the system error (≥30CM) introduced by the switching of different positioning systems in the vehicle RTK-UWB high-precision positioning solution covering all road environment scenarios. The embodiment of this aspect proposes an RTK-UWB fusion positioning algorithm to realize data fusion in the scenario where each system outputs positioning results, and reduce the system error (<20CM).

[0191] By establishing a cloud-based RTK-UWB positioning monitoring and operation management system, when a system error occurs, the cloud can broadcast an alarm message to the vehicle-mounted fusion positioning system according to the preset error threshold, so that the vehicle can turn on the alarm light in time to alert other vehicles and decelerate. This effectively solves the problem that the reliability of the fusion positioning is affected due to the limited computing power of the vehicle itself.

[0192] Figure 6 It is a schematic diagram of modules of an embodiment of the vehicle positioning system of the present invention. The vehicle positioning system of the present invention is applied to the vehicle-mounted terminal, and an RTK positioning system and a UWB positioning system are deployed at the vehicle-mounted terminal. As Figure 6 shown, the vehicle positioning system includes but is not limited to:

[0193] The first positioning module 610 obtains the RTK positioning observation value of the vehicle where it is located by using the RTK positioning system;

[0194] The second positioning module 620 obtains the UWB positioning observation value of the vehicle where it is located by using the UWB positioning system;

[0195] The first fusion positioning module 630 obtains the confidence levels of the RTK positioning system and the UWB positioning system respectively, selects the target positioning observation value whose system confidence level meets the set conditions from the RTK positioning observation value and the UWB positioning observation value, and uses the target positioning observation value as the vehicle-terminal positioning result;

[0196] The control module 640 controls the vehicle to perform corresponding driving behaviors by using the vehicle-terminal positioning result.

[0197] For the implementation principles of the above modules, refer to the relevant introductions in the vehicle positioning method, which will not be elaborated here.

[0198] The vehicle positioning system of the present invention can deploy an RTK positioning system and a UWB positioning system at the vehicle-mounted terminal simultaneously, select the target positioning observation value with lower error and higher credibility from the RTK positioning observation value and the UWB positioning observation value according to the system confidence level, and realize the fusion positioning based on the RTK-UWB technology. In this case, even if a system error occurs due to scene switching, the positioning observation value with smaller error and higher accuracy can be selected in a timely manner according to the system confidence level as the vehicle positioning result, improving the vehicle positioning accuracy.

[0199] Optionally, the first fusion positioning module 630 is specifically used for:

[0200] When the system confidence levels of both the RTK positioning system and the UWB positioning system are within the set confidence interval, select the target positioning observation value with a relatively larger system confidence level from the RTK positioning observation value and the UWB positioning observation value.

[0201] Optionally, the first fusion positioning module 630 is specifically used for:

[0202] When one of the system confidence levels of the RTK positioning system and the UWB positioning system is within the set confidence interval, a target positioning observation value with the system confidence level within the set confidence interval is selected from the RTK positioning observation value and the UWB positioning observation value.

[0203] Optionally, the first fusion positioning module 630 is specifically configured to:

[0204] When the system confidence levels of both the RTK positioning system and the UWB positioning system are not within the set confidence interval, the vehicle positioning prediction value at the second moment estimated based on the vehicle end positioning result at the first moment is used as the vehicle end positioning result;

[0205] Wherein, the first moment is a moment before the second moment, and both the RTK positioning observation value and the UWB positioning observation value are positioning observation values at the second moment.

[0206] Optionally, the first fusion positioning module 630 is further specifically configured to:

[0207] Before using the target positioning observation value as the vehicle end positioning result, obtain the vehicle positioning prediction value at the second moment estimated based on the vehicle end positioning result at the first moment, wherein the first moment is a moment before the second moment, and the vehicle positioning prediction value is time-synchronized with the target positioning observation value;

[0208] Use a Kalman filter to converge the error between the vehicle positioning prediction value at the second moment and the target positioning observation value using a preset error covariance matrix;

[0209] When the convergence is achieved, use the target positioning observation value as the vehicle end positioning result.

[0210] Optionally, the first fusion positioning module 630 is further specifically configured to:

[0211] Calculate the Kalman gain using the vehicle end positioning result and the vehicle positioning prediction value at the second moment;

[0212] Update the error covariance matrix using the Kalman gain.

[0213] Optionally, compared with Figure 6 compared with Figure 7 The vehicle positioning system shown further includes:

[0214] A time synchronization module 710 that synchronizes the RTK positioning observation value and the UWB positioning observation value in time before selecting a target positioning observation value with the system confidence level meeting the set conditions from the RTK positioning observation value and the UWB positioning observation value.

[0215] Optionally, compared with Figure 6Compared with Figure 8 The vehicle positioning system shown also includes:

[0216] An upload module 810 that uploads RTK positioning observations, UWB positioning observations, and vehicle-end positioning results to the cloud;

[0217] A regulation module 820 that, in the case of receiving an alarm from the cloud regarding the error of the vehicle-end positioning result, responds to the alarm and controls the vehicle to perform the regulation behavior corresponding to the alarm.

[0218] Figure 9 FIG. is a schematic diagram of modules of another embodiment of the vehicle positioning system of the present invention. The vehicle positioning system is applied to the cloud corresponding to the vehicle-mounted terminal. The vehicle positioning system includes:

[0219] A receiving module 910 that receives, from the vehicle-mounted terminal, the first RTK positioning observations of the vehicle, the first UWB positioning observations, and the first target positioning observations whose system confidence level selected from the first RTK positioning observations and the first UWB positioning observations meets the set conditions;

[0220] A second fusion positioning module 920 that calculates the second RTK positioning observations of the vehicle using CORS network data, and calculates the second UWB positioning observations of the vehicle using UWB network data, and selects the second target positioning observations whose system confidence level meets the set conditions from the second RTK positioning observations and the second UWB positioning observations;

[0221] A sending module 930 that, in the case where the error between the first target positioning observations and the second target positioning observations exceeds the error threshold, sends an alarm message to the vehicle-mounted terminal.

[0222] Optionally, the receiving module 910 is further specifically configured to:

[0223] Before calculating the second RTK positioning observations of the vehicle using CORS network data, calculating the second UWB positioning observations of the vehicle using UWB network data, and selecting the second target positioning observations whose system confidence level meets the set conditions from the second RTK positioning observations and the second UWB positioning observations, receive the system confidence level of the reported first RTK positioning observations from the vehicle-mounted terminal as the system confidence level of the second RTK positioning observations;

[0224] The second fusion positioning module 920 is specifically configured to:

[0225] In the case where a UWB positioning system is deployed in the cloud, extract the system confidence level of the UWB positioning system from the storage location in the cloud.

[0226] For the implementation principle of the above-mentioned module, please refer to the relevant introduction in the vehicle positioning method, which will not be elaborated here.

[0227] In the embodiments of the present invention, RTK-UWB fusion positioning algorithm engines are respectively deployed at the vehicle-mounted end and the cloud end. The cloud end establishes an effective monitoring and operation analysis system of the cloud end with strong computing power, and real-time identifies the errors of the vehicle-end positioning results according to the data of the CORS station network and the UWB station network. When the positioning error exceeds the error threshold, an alarm message is sent to the vehicle-mounted end to prompt the vehicle-mounted end to make corresponding response behaviors, so as to meet the functional safety requirements of autonomous driving.

[0228] The embodiments of the present invention also provide a vehicle positioning device, including a processor and a memory, in which executable instructions of the processor are stored. Among them, the processor is configured to execute the steps of the vehicle positioning method via executing the executable instructions.

[0229] As shown above, the vehicle positioning device of this embodiment can deploy an RTK positioning system and a UWB positioning system at the vehicle-mounted end at the same time, and select a target positioning observation value with lower error and higher credibility from the RTK positioning observation value and the UWB positioning observation value according to the system confidence, so as to realize fusion positioning based on RTK-UWB technology. In this case, even if the system error is caused by scene switching, the positioning observation value with smaller error and higher accuracy can be timely selected according to the system confidence as the vehicle positioning result, improving the vehicle positioning accuracy.

[0230] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module" or "platform" here.

[0231] Figure 10 is a schematic structural diagram of the vehicle positioning device of the present invention. The following will refer to Figure 10 to describe the electronic device 1000 according to this embodiment of the present invention. Figure 10 The electronic device 1000 shown is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention.

[0232] As Figure 10 shown, the electronic device 1000 is presented in the form of a general-purpose computing device. The components of the electronic device 1000 may include but are not limited to: at least one processing unit 1010, at least one storage unit 1020, a bus 1030 connecting different platform components (including the storage unit 1020 and the processing unit 1010), a display unit 1040, etc.

[0233] Among them, the storage unit stores program code, which can be executed by the processing unit 1010, so that the processing unit 1010 executes the steps according to various exemplary embodiments of the present invention described in the above vehicle positioning method part of this specification. For example, the processing unit 1010 can execute steps as shown in Figure 1 or 2.

[0234] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 1021 and / or a cache storage unit 1022, and may further include a read-only storage unit (ROM) 1023.

[0235] The storage unit 1020 may also include a program / utility 1024 having a set (at least one) of program modules 1025. Such program modules 1025 include but are not limited to: a processing system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0236] The bus 1030 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area bus using any bus structure in a variety of bus structures.

[0237] The electronic device 1000 can also communicate with one or more external devices 1070 (such as a keyboard, a pointing device, a Bluetooth device, etc.), can also communicate with one or more devices that enable a user to interact with the electronic device 1000, and / or can communicate with any device that enables the electronic device 1000 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 1050.

[0238] Moreover, the electronic device 1000 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 1060. The network adapter 1060 can communicate with other modules of the electronic device 1000 through the bus 1030. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0239] Embodiments of the present invention also provide a computer-readable storage medium for storing a program, and the steps of the vehicle positioning method are implemented when the program is executed. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above vehicle positioning method section of this specification.

[0240] The program product for implementing the above method according to an embodiment of the present invention can be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0241] The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0242] The computer-readable storage medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than the readable storage medium, and this readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code included on the readable storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0243] The program code for performing the processing of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0244] In summary, the object of the present invention is to provide a vehicle positioning method, system, device and storage medium, which can deploy an RTK positioning system and a UWB positioning system on the vehicle side at the same time, and select a target positioning observation value with lower error and higher credibility from the RTK positioning observation value and the UWB positioning observation value according to the system confidence, so as to realize integrated positioning based on RTK-UWB technology. In this case, even when the system error is caused by scene switching, the positioning observation value with smaller error and higher accuracy can be selected in a timely manner according to the system confidence as the vehicle positioning result, improving the vehicle positioning accuracy.

[0245] The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention belongs, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A vehicle positioning method, characterized in that, Applied to the vehicle side, an RTK positioning system and a UWB positioning system are deployed on the vehicle side. The vehicle positioning method includes: Obtaining RTK positioning observations of the vehicle using the RTK positioning system; Obtaining UWB positioning observations of the vehicle using the UWB positioning system; Obtaining the confidence levels of the RTK positioning system and the UWB positioning system respectively, selecting a target positioning observation whose system confidence level meets the set conditions from the RTK positioning observations and the UWB positioning observations, and using the target positioning observation as the vehicle-side positioning result; Controlling the vehicle to perform corresponding driving behaviors using the vehicle-side positioning result; Uploading the RTK positioning observations, the UWB positioning observations, and the vehicle-side positioning result to the cloud; In the case of receiving an alarm from the cloud regarding the error of the vehicle-side positioning result, responding to the alarm and controlling the vehicle to perform the regulation behavior corresponding to the alarm, where the alarm is obtained by the cloud through the following method: Selecting a first target positioning observation whose system confidence level meets the set conditions from the RTK positioning observations and the UWB positioning observations; Calculating a second RTK positioning observation of the vehicle using CORS network data, and calculating a second UWB positioning observation of the vehicle using UWB network data, and selecting a second target positioning observation whose system confidence level meets the set conditions from the second RTK positioning observation and the second UWB positioning observation; In the case where the error between the first target positioning observation and the second target positioning observation exceeds the error threshold, sending the alarm to the vehicle side.

2. The vehicle positioning method according to claim 1, wherein, Selecting a target positioning observation whose system confidence level meets the set conditions from the RTK positioning observations and the UWB positioning observations includes: In the case where the system confidence levels of the RTK positioning system and the UWB positioning system are both within the set confidence interval, selecting a target positioning observation with a relatively larger system confidence level from the RTK positioning observations and the UWB positioning observations.

3. The vehicle positioning method according to claim 1, characterized in that, Selecting a target positioning observation whose system confidence level meets the set conditions from the RTK positioning observations and the UWB positioning observations includes: In the case where one of the system confidence levels of the RTK positioning system and the UWB positioning system is within the set confidence interval, selecting a target positioning observation whose system confidence level is within the set confidence interval from the RTK positioning observations and the UWB positioning observations.

4. The vehicle positioning method according to claim 1, characterized in that The vehicle positioning method further includes: In the case where the system confidence levels of the RTK positioning system and the UWB positioning system are both not within the set confidence interval, using the vehicle positioning prediction value at the second moment estimated based on the vehicle-side positioning result at the first moment as the vehicle-side positioning result; Wherein, the first moment is a moment before the second moment, and both the RTK positioning observation and the UWB positioning observation are the positioning observations at the second moment.

5. The vehicle positioning method according to claim 1, characterized in that, Before selecting target positioning observations with system confidence levels meeting set conditions from the RTK positioning observations and UWB positioning observations, the vehicle positioning method further includes: Performing time synchronization on the RTK positioning observations and UWB positioning observations.

6. The vehicle positioning method according to claim 1, characterized in that The vehicle positioning method further includes: Before using the target positioning observations as the vehicle-end positioning result, obtaining a vehicle positioning prediction value at a second moment estimated based on the vehicle-end positioning result at a first moment, where the first moment is a moment before the second moment, and the vehicle positioning prediction value is time-synchronized with the target positioning observations; Using an extended Kalman filter to converge the error between the vehicle positioning prediction value at the second moment and the target positioning observations using a preset error covariance matrix; In the case of convergence, using the target positioning observations as the vehicle-end positioning result.

7. The vehicle positioning method according to claim 6, wherein The vehicle positioning method further includes: Calculating a Kalman gain using the vehicle-end positioning result and the vehicle positioning prediction value at the second moment; Updating the error covariance matrix using the Kalman gain.

8. A vehicle positioning method, characterized in that, Applied to the cloud corresponding to the vehicle-mounted terminal, the vehicle positioning method includes: Receiving from the vehicle-mounted terminal the first RTK positioning observations, the first UWB positioning observations, and the first target positioning observations selected from the first RTK positioning observations and the first UWB positioning observations with system confidence levels meeting set conditions; Calculating the second RTK positioning observations of the vehicle using CORS network data and calculating the second UWB positioning observations of the vehicle using UWB network data, and selecting second target positioning observations with system confidence levels meeting set conditions from the second RTK positioning observations and the second UWB positioning observations; In the case where the error between the first target positioning observations and the second target positioning observations exceeds an error threshold, sending an alarm message to the vehicle-mounted terminal.

9. The vehicle positioning method according to claim 8, wherein Before calculating the second RTK positioning observations of the vehicle using CORS network data and calculating the second UWB positioning observations of the vehicle using UWB network data, and selecting second target positioning observations with system confidence levels meeting set conditions from the second RTK positioning observations and the second UWB positioning observations, the vehicle positioning method further includes: Receiving from the vehicle-mounted terminal the system confidence level of the reported first RTK positioning observations as the system confidence level of the second RTK positioning observations; In the case of deploying a UWB positioning system in the cloud, extracting the system confidence level of the UWB positioning system from the storage location in the cloud.

10. A vehicle positioning system, characterized in that, Including: A vehicle-mounted terminal that obtains the first RTK positioning observations, the first UWB positioning observations, and the first target positioning observations selected from the first RTK positioning observations and the first UWB positioning observations with system confidence levels meeting set conditions; The cloud receives the first RTK positioning observation value, the first UWB positioning observation value, and the first target positioning observation value from the vehicle-mounted terminal, calculates the second RTK positioning observation value of the vehicle using CORS network data, and calculates the second UWB positioning observation value of the vehicle using UWB network data, and selects a second target positioning observation value whose system confidence level meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value. When the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold, an alarm message is sent to the vehicle-mounted terminal.

11. A vehicle positioning system, characterized in that, Applied to the vehicle-mounted terminal, an RTK positioning system and a UWB positioning system are deployed on the vehicle-mounted terminal. The vehicle positioning system includes: A first positioning module that obtains the RTK positioning observation value of the vehicle where it is located using the RTK positioning system; A second positioning module that obtains the UWB positioning observation value of the vehicle where it is located using the UWB positioning system; A first fusion positioning module that obtains the confidence levels of the RTK positioning system and the UWB positioning system respectively, selects a target positioning observation value whose system confidence level meets the set conditions from the RTK positioning observation value and the UWB positioning observation value, and uses the target positioning observation value as the vehicle-end positioning result; A control module that controls the vehicle to perform corresponding driving behaviors using the vehicle-end positioning result; An upload module that uploads the RTK positioning observation value, the UWB positioning observation value, and the vehicle-end positioning result to the cloud; A regulation module that, when receiving an alarm about the error of the vehicle-end positioning result from the cloud, responds to the alarm and controls the vehicle to perform the regulation behavior corresponding to the alarm; Wherein the alarm is obtained by the cloud through the following method: Select a first target positioning observation value whose system confidence level meets the set conditions from the RTK positioning observation value and the UWB positioning observation value; Calculate the second RTK positioning observation value of the vehicle using CORS network data, and calculate the second UWB positioning observation value of the vehicle using UWB network data, and select a second target positioning observation value whose system confidence level meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value; When the error between the first target positioning observation value and the second target positioning observation value exceeds the error threshold, send the alarm to the vehicle-mounted terminal.

12. A vehicle positioning system, characterized in that, Applied to the cloud corresponding to the vehicle-mounted terminal, the vehicle positioning system includes: A receiving module that receives the first RTK positioning observation value, the first UWB positioning observation value, and the first target positioning observation value selected from the first RTK positioning observation value and the first UWB positioning observation value of the vehicle from the vehicle-mounted terminal; A second fusion positioning module that calculates the second RTK positioning observation value of the vehicle using CORS network data, and calculates the second UWB positioning observation value of the vehicle using UWB network data, and selects a second target positioning observation value whose system confidence level meets the set conditions from the second RTK positioning observation value and the second UWB positioning observation value; The sending module sends an alarm message to the vehicle-mounted terminal when the error between the first target positioning observation value and the second target positioning observation value exceeds an error threshold.

13. A detection device for abnormal behaviors of network users, characterized in that, It includes: A processor; A memory that stores executable instructions of the processor; Wherein, the processor is configured to execute the steps of the vehicle positioning method according to any one of claims 1 to 9 by executing the executable instructions.

14. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it realizes the steps of the vehicle positioning method according to any one of claims 1 to 9.

Images