Total fusion positioning system, method, apparatus, and storage medium

Abstract

The application discloses a full fusion positioning system, method, device and storage medium, wherein the system comprises: a data preprocessing module, a front fusion module, a data screening module and a rear fusion module which are sequentially connected in communication; the data preprocessing module is used for acquiring positioning data and visual data of a target vehicle, and performing first processing on the positioning data and the visual data to obtain first abnormal data and first normal data; the front fusion module is used for performing front fusion on the first normal data to obtain a front fusion result; the data screening module is used for performing second processing on the front fusion result to obtain second abnormal data and second normal data; and the rear fusion module is used for performing rear fusion on the second normal data to obtain a rear fusion result. The technical scheme of the application eliminates initial errors and environmental errors in the positioning data and the visual data of the target vehicle, and improves the robustness and the robustness of the full fusion positioning system.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to a fully integrated positioning system, method, device and storage medium. Background Technology

[0002] Currently, depending on the intervention stage of visual signal and map matching, map matching for high-precision positioning in autonomous driving mainly employs two methods: pre-fusion and post-fusion. Each method has its advantages and disadvantages: pre-fusion can retain more of the original observation information from each sensor and ensure a higher frequency of output positioning results, but it lacks control over sensor errors; post-fusion possesses the ability to detect and mitigate sensor errors, but its reliability is lower, and it faces the challenge of weight selection among sensors in different environments. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art. Therefore, one objective of this application is to provide a fully integrated positioning system, method, apparatus, and storage medium.

[0004] To address the aforementioned technical problems, embodiments of this application provide the following technical solutions:

[0005] A fully integrated positioning system, comprising:

[0006] The data preprocessing module, the pre-fusion module, the data filtering module, and the post-fusion module are connected in sequence via communication.

[0007] The data preprocessing module is used to acquire the positioning data and visual data of the target vehicle, and to perform a first processing on the positioning data and visual data to obtain a first abnormal data and a first normal data.

[0008] The pre-fusion module is used to perform pre-fusion on the first normal data to obtain the pre-fusion result;

[0009] The data filtering module is used to perform a second processing on the pre-fusion result to obtain second abnormal data and second normal data;

[0010] The post-fusion module is used to perform post-fusion on the second normal data to obtain the post-fusion result.

[0011] Optionally, the system further includes:

[0012] A matching module, comprising a first sub-matching module and a second sub-matching module;

[0013] The first sub-matching module is communicatively connected to both the pre-fusion module and the data filtering module; the second sub-matching module is communicatively connected to both the post-fusion module and the data filtering module.

[0014] The first sub-matching module is used to perform a first match between the data obtained from the front-view wide-angle camera and the side-view camera in the front fusion result and the map data to obtain a first matching result, and send the first matching result to the data filtering module;

[0015] The second sub-matching module is used to perform a second match between the data obtained from the second normal data based on the forward-looking narrow-angle camera and the data obtained based on the side-looking camera and the map data to obtain a second matching result.

[0016] Optionally, the data preprocessing module includes a sub-detection module;

[0017] The sub-detection module is used to obtain a positioning data threshold and a visual data threshold, compare the positioning data with the positioning data threshold to obtain a first comparison result, and compare the visual data with the visual data threshold to obtain a second comparison result.

[0018] Based on the first comparison result, a first sub-abnormal data is obtained, and based on the second comparison result, a second sub-abnormal data is obtained; wherein, the first abnormal data includes the first sub-abnormal data and the second sub-abnormal data.

[0019] Optionally, the data filtering module includes: a first sub-filtering module, a second sub-filtering module, and so on.

[0020] and the third sub-filter module;

[0021] The first sub-filtering module is used to detect the distribution state of the first matching result, obtain a first detection result, and obtain a third sub-abnormal data based on the first detection result; wherein, the second abnormal data includes the third sub-abnormal data;

[0022] The second sub-filtering module is used to detect the scene status of the first matching result, obtain a second detection result, and obtain a fourth sub-abnormal data based on the second detection result; wherein, the second abnormal data includes the fourth sub-abnormal data;

[0023] The third sub-filtering module is used to detect the trend state of the first matching result, obtain a third detection result, and obtain a fifth sub-abnormal data based on the third detection result; wherein, the trend state includes a continuous trend state and a slowly changing trend state, and the second abnormal data includes the fifth sub-abnormal data.

[0024] Optionally, the pre-fusion module includes a tightly coupled submodule; the tightly coupled submodule is used to perform pre-fusion on the first normal data based on a tightly coupled algorithm to obtain the pre-fusion result.

[0025] Optionally, the post-fusion module includes a loosely coupled submodule; the loosely coupled submodule is used to perform post-fusion on the second matching result based on a loosely coupled algorithm to obtain the post-fusion result.

[0026] Embodiments of this application also provide a fully fused localization method, including:

[0027] Acquire the positioning data and visual data of the target vehicle, and perform a first processing on the positioning data and visual data to obtain a first abnormal data and a first normal data;

[0028] Perform pre-fusion on the first normal data to obtain the pre-fusion result;

[0029] The pre-fusion result is subjected to a second processing to obtain second abnormal data and second normal data;

[0030] The second normal data is then fused to obtain the fused result.

[0031] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.

[0032] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.

[0033] The embodiments of this application have the following technical effects:

[0034] The above-described technical solution of this application, before performing pre-fusion of the positioning data and visual data of the target vehicle, performs anomaly detection on the positioning data and visual data based on a data preprocessing module, and obtains first abnormal data and first normal data; performs pre-fusion on the first normal data to obtain a pre-fusion result; performs a first matching on the pre-fusion result to obtain a first matching result; based on a data filtering module, performs anomaly detection on the first matching result to obtain second abnormal data and second normal data; performs a second matching on the second normal data to obtain a second matching result; and performs post-fusion on the second matching result to obtain a post-fusion result. This achieves the elimination of initial errors and environmental errors in the positioning data and visual data of the target vehicle, and realizes the fusion of the pre-fusion result and the post-fusion result, thereby improving the robustness and effectiveness of the fully fused positioning system.

[0035] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the structure of a fully fused positioning system provided in an embodiment of this application;

[0037] Figure 2 This is a schematic diagram of a fully fused localization method provided in an embodiment of this application. Detailed Implementation

[0038] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0039] To facilitate understanding of the embodiments by those skilled in the art, some terms are explained below:

[0040] (1) IMU: Inertial Measurement Unit, used to measure the three-axis attitude angles (or angular rates) and acceleration of an object.

[0041] (2) GNSS: Global Navigation Satellite System.

[0042] (3) RTU: Remote Terminal Unit.

[0043] like Figure 1As shown, an embodiment of this application provides a fully fused positioning system 10, comprising:

[0044] The data preprocessing module 11, the pre-fusion module 12, the data filtering module 13, and the post-fusion module 14 are connected in sequence via communication.

[0045] The data preprocessing module 11 is used to acquire the positioning data and visual data of the target vehicle, and to perform a first processing on the positioning data and visual data to obtain a first abnormal data and a first normal data.

[0046] The pre-fusion module 12 is used to perform pre-fusion on the first normal data to obtain a pre-fusion result;

[0047] The data filtering module 13 is used to perform a second processing on the pre-fusion result to obtain second abnormal data and second normal data.

[0048] The post-fusion module 14 is used to perform post-fusion on the second normal data to obtain the post-fusion result.

[0049] In an optional embodiment of this application, the positioning data and visual data of the target vehicle are first obtained; wherein, the positioning data of the target vehicle can be obtained based on wheel speed meters (for acquiring vehicle speed data), steering angle sensors (for acquiring steering angle data), IMU (for acquiring acceleration and angular velocity data), GNSS and RTU (for acquiring position data) installed on the target vehicle;

[0050] Visual data of the target vehicle can be obtained based on forward-facing wide-angle cameras, forward-facing narrow-angle cameras, and side-view cameras installed on the target vehicle.

[0051] The data preprocessing module 11 is used to search the positioning data and visual data of the target vehicle, respectively to obtain abnormal data in the positioning data and the visual data of the target vehicle. Based on the abnormal data in the positioning data and the visual data of the target vehicle, the first abnormal data is obtained. After the first abnormal data is determined, the data preprocessing module 11 removes the first abnormal data and retains the remaining first normal data, which is used for subsequent calculations based on the first normal data. The module filters out discontinuities, duplicate transmissions, time / order reversals, and numerical range exceeding limits in the positioning data and visual data of the target vehicle, and retains healthy observation data.

[0052] The data filtering module 13 is used to find abnormal data in the pre-fusion results, obtain second abnormal data based on the abnormal data found in the pre-fusion results, remove the second abnormal data in the pre-fusion results, and obtain second normal data based on the remaining data in the pre-fusion results excluding the second abnormal data.

[0053] In the embodiments of this application, before performing pre-fusion on the positioning data and visual data of the target vehicle, the data preprocessing module 11 performs anomaly detection on the positioning data and visual data to obtain first abnormal data and first normal data; the first normal data is then pre-fused to obtain a pre-fusion result; based on the data filtering module 13, the pre-fusion result is further anomaly detection to obtain second abnormal data and second normal data; the second normal data is then post-fused to obtain post-fused data. This process eliminates initial and environmental errors in the positioning data and visual data of the target vehicle, and integrates the pre-fusion result and the post-fusion result, thereby improving the robustness and effectiveness of the fully fused positioning system 10.

[0054] In an optional embodiment of this application, the data preprocessing module 11 includes a sub-detection module;

[0055] The sub-detection module is used to obtain a positioning data threshold and a visual data threshold, compare the positioning data with the positioning data threshold to obtain a first comparison result, and compare the visual data with the visual data threshold to obtain a second comparison result.

[0056] Based on the first comparison result, a first sub-abnormal data is obtained, and based on the second comparison result, a second sub-abnormal data is obtained; wherein, the first abnormal data includes the first sub-abnormal data and the second sub-abnormal data.

[0057] In an optional embodiment of this application, for the positioning data obtained by the wheel speed meter, the wheel speed meter data value at the previous moment and the current moment in the positioning data are compared to obtain the moment change value. The moment change value is then compared with the moment change value threshold. If the moment change value is greater than the moment change value threshold, the wheel speed meter data value at the current moment is determined as the first sub-abnormal data. Conversely, if the moment change value is not greater than the moment change value threshold, the wheel speed meter data value at the current moment is determined as the first sub-normal data. The first normal data includes the first sub-normal data. The positioning data threshold includes the moment change value threshold.

[0058] For example, if the target vehicle's speed is 10 km / s at 19s and 20 km / s at 20s, with a time change of 10 km / s, then the speed at 20s is considered the first sub-abnormal data if 10 km / s is greater than the time change threshold; otherwise, if 10 km / s is not greater than the time change threshold, then the speed at 20s is considered the first sub-normal data.

[0059] The threshold for time-varying changes can be adjusted according to actual needs, and the embodiments of this application do not impose specific limitations on it.

[0060] In an optional embodiment of this application, for an IMU, an acceleration threshold is obtained, and the acceleration at each moment in the positioning data is compared with the acceleration threshold. If the acceleration is greater than the acceleration threshold at a certain moment, the acceleration at that moment is determined as the first sub-abnormal data; conversely, if the acceleration is not greater than the acceleration threshold at a certain moment, the acceleration at that moment is determined as the first sub-normal data; wherein, the positioning data threshold includes the acceleration threshold.

[0061] For example, at the 10th second, the target vehicle's acceleration is 6.5. If 6.5 If the acceleration exceeds the acceleration threshold, the acceleration corresponding to the 10th second is considered the first sub-anomaly data; otherwise, if it is less than 6.5... If the acceleration is not greater than the threshold value of the change value at time, then the acceleration corresponding to the 10th second is the first normal data.

[0062] Similarly, visual data can be screened for abnormal data based on visual data thresholds, and a second sub-abnormal data and a second sub-normal data can be obtained; wherein, the first normal data includes the second sub-normal data.

[0063] Similarly, the sub-detection module in the data preprocessing module 11 can detect and remove abnormal data in the positioning data and visual data of the target vehicle, thereby avoiding interference from the initial errors in the positioning data and visual data during the subsequent pre-fusion process and improving the accuracy of the pre-fusion results.

[0064] In an optional embodiment of this application, the pre-fusion module 12 includes: a tightly coupled submodule; the tightly coupled submodule is used to perform pre-fusion on the first normal data based on a tightly coupled algorithm to obtain the pre-fusion result.

[0065] In the embodiments of this application, when performing pre-fusion on the first normal data, a tightly coupled algorithm is used to improve the accuracy of the pre-fusion result, thereby improving the reliability of the positioning result. Specifically, positioning calculation is performed in the carrier phase space, and the tightly coupled algorithm can be a Kalman filter or graph optimization (FGO) to obtain the three-dimensional coordinates (longitude, latitude, and altitude) of the absolute position.

[0066] It should be noted that tightly coupled algorithms can be obtained directly based on related technologies and are not within the scope of protection of this application, so they will not be described in detail here.

[0067] In an optional embodiment of this application, the data filtering module 13 includes: a first sub-filtering module, a second sub-filtering module, and a third sub-filtering module;

[0068] The first sub-filtering module is used to detect the distribution state of the first matching result, obtain a first detection result, and obtain a third sub-abnormal data based on the first detection result; wherein, the second abnormal data includes the third sub-abnormal data;

[0069] The second sub-filtering module is used to detect the scene status of the first matching result, obtain a second detection result, and obtain a fourth sub-abnormal data based on the second detection result; wherein, the second abnormal data includes the fourth sub-abnormal data;

[0070] The third sub-filtering module is used to detect the trend state of the first matching result, obtain a third detection result, and obtain a fifth sub-abnormal data based on the third detection result; wherein, the trend state includes a continuous trend state and a slowly changing trend state, and the second abnormal data includes the fifth sub-abnormal data.

[0071] In an optional embodiment of this application, for the first sub-screening module, the distribution state of the data from various sensors included in the first matching result is detected based on the chi-square test method;

[0072] Specifically, assuming that in the presence of thermal noise (i.e., the data measured by different sensors are only inconsistent in temperature data, while other data are consistent), the distribution of the data corresponding to each sensor conforms to a normal distribution; then, we can take the data of each first sensor included in the previous fusion result, and detect the distribution state of each first sensor data one by one based on the chi-square value test algorithm, and determine the distribution result of each first sensor data.

[0073] If, after the detection is completed, a certain type of first sensor data follows a normal distribution, then the first sensor data is identified as the third sub-normal data; wherein, the second normal data includes the third sub-normal data; conversely, if a certain type of first sensor data does not follow a normal distribution, it indicates that the first sensor not only has thermal noise during operation, but also other reasons that reduce data accuracy. Therefore, the first sensor data is identified as the third sub-abnormal data.

[0074] Furthermore, for data that follows a normal distribution, confidence level processing can be performed to obtain the confidence level corresponding to each data point. The calculated confidence level is between 1% and 99%. A confidence level threshold can be set, and the data that follows a normal distribution can be further filtered based on the confidence level threshold.

[0075] In an optional embodiment of this application, for the second sub-filtering module, the second sensor data corresponding to each sensor is obtained based on the first matching result, and the scene condition corresponding to each second sensor data is determined based on the second sensor data corresponding to each sensor; wherein, the scene condition may include road conditions, environmental conditions and weather conditions.

[0076] For example, 1) when it is determined that a certain second sensor data is obtained based on a camera working in a dimly lit environment, the second sensor data is identified as the fourth sub-abnormal data, and the second sub-filtering module reduces the weight corresponding to the second sensor data; for example, the initial value of the weight corresponding to the second sensor data is 0.5, and after it is determined that the second sensor data is based on a camera working in a dimly lit environment, the weight corresponding to the second sensor data is adjusted to 0.1.

[0077] 2) When it is determined that a certain second sensor data is obtained based on a camera operating in stormy weather, the second sensor data is identified as the fourth sub-abnormal data, and the second sub-filtering module reduces the weight corresponding to the second sensor data; for example, the initial value of the weight corresponding to the second sensor data is 0.8, and after it is determined that the second sensor data is based on a camera operating in stormy weather, the weight corresponding to the second sensor data is adjusted to 0.3.

[0078] 3) When it is determined that a certain second sensor data is obtained from a radar operating in sandstorm weather, the second sensor data is identified as the fourth sub-anomaly data, and the second sub-filtering module reduces the weight corresponding to the second sensor data; for example, the initial value of the weight corresponding to the second sensor data is 0.6, and after it is determined that the second sensor data is obtained from a radar operating in sandstorm weather, the weight corresponding to the second sensor data is adjusted to 0.2.

[0079] 3) When it is determined that a certain second sensor data is obtained based on a GNSS operating under tunnel conditions, the second sensor data is identified as the fourth sub-abnormal data, and the second sub-filtering module reduces the weight corresponding to the second sensor data; for example, the initial value of the weight corresponding to the second sensor data is 0.4, and after it is determined that the second sensor data is obtained based on a GNSS operating under tunnel conditions, the weight corresponding to the second sensor data is adjusted to 0.05.

[0080] Furthermore, the fourth sub-abnormal data found by the second sub-filtering module is removed, and the normal data is retained to obtain the fourth sub-normal data; wherein, the second normal data includes the fourth sub-normal data.

[0081] In an optional embodiment of this application, for the third sub-screening module, the third sensor data corresponding to each sensor is obtained based on the first matching result, and the trend state corresponding to each third sensor data is determined based on the third sensor data corresponding to each sensor; wherein, the trend state includes a continuous trend state and a slowly changing trend state.

[0082] Specifically, for continuous trend states, when the third sub-filtering module detects that the data of a certain third sensor is continuously abnormal within a certain period of time, it determines the third sensor data as the fifth sub-abnormal data; conversely, when the third sub-filtering module detects that the data of a certain third sensor is continuously normal, it determines the third sensor data as the fifth sub-normal data, wherein the second normal data includes the fifth sub-normal data.

[0083] For a slow-changing trend state, when the third sub-filtering module detects that a certain third sensor data has a slow-changing fault within a certain period of time, it determines that third sensor data as the fifth sub-abnormal data; conversely, when the third sub-filtering module detects that a certain third sensor data is continuously normal, it determines that third sensor data as the fifth sub-normal data. For example, if the data in the 1st second is 1, the data in the 2nd second is 3, the data in the 3rd second is 5, the data in the 4th second is 7, etc., then the third sensor data has a slow-changing fault, corresponding to a slow-changing trend state.

[0084] In the embodiments of this application, before post-fusion, the data filtering module 13, in conjunction with weather conditions, environmental conditions, and road conditions, checks for abnormal data in the pre-fusion results, thereby minimizing the interference of different scenario conditions on post-fusion.

[0085] In an optional embodiment of this application, the system further includes: the system further includes:

[0086] A matching module, comprising a first sub-matching module and a second sub-matching module;

[0087] The first sub-matching module is communicatively connected to both the pre-fusion module and the data filtering module; the second sub-matching module is communicatively connected to both the post-fusion module and the data filtering module.

[0088] The first sub-matching module is used to perform a first match between the data obtained from the front-view wide-angle camera and the side-view camera in the front fusion result and the map data to obtain a first matching result, and send the first matching result to the data filtering module;

[0089] The second sub-matching module is used to perform a second match between the data obtained from the second normal data based on the forward-looking narrow-angle camera and the data obtained based on the side-looking camera and the map data to obtain a second matching result.

[0090] In an optional embodiment of this application, for the second sub-matching module, the weight of the data X obtained based on the side-view camera is W = 1 - confidence level, and the weight of the data Y obtained based on the side-view camera in the obtained second matching result is the confidence level; wherein, the confidence level is consistent with the confidence level corresponding to the weight of the data Z obtained based on the side-view camera in the first matching data;

[0091] In the second matching result, for the data N obtained based on the side-view camera:

[0092] N = Z * confidence level + Y * confidence level.

[0093] In one optional embodiment of this application, the map data (including multiple map elements) can be obtained based on Amap or Baidu Map.

[0094] In the embodiments of this application, a front-view wide-angle camera (used to obtain lane line information) and a side-view camera (used to obtain road information around the vehicle) are grouped together; a front-view narrow-angle camera (used to obtain traffic sign information) and a side-view camera are grouped together. Through hardware redundancy and data heterogeneity, interference with the camera's visual judgment results is avoided due to common cause failure.

[0095] In the embodiments of this application, before performing pre-fusion on the positioning data and visual data of the target vehicle, an anomaly search is performed on the positioning data and visual data based on the data preprocessing module to obtain first anomaly data and first normal data; pre-fusion is performed on the first normal data to obtain a pre-fusion result; a first matching is performed on the pre-fusion result to obtain a first matching result; based on the data filtering module, anomaly search is performed on the first matching result to obtain second anomaly data and second normal data; a second matching is performed on the second normal data to obtain a second matching result; and post-fusion is performed on the second matching result to obtain a post-fusion result. This achieves the elimination of initial errors and environmental errors in the positioning data and visual data of the target vehicle, and realizes the fusion of the pre-fusion result and the post-fusion result, thereby improving the robustness and effectiveness of the fully fused positioning system.

[0096] In an optional embodiment of this application, the post-fusion module 14 includes: a loosely coupled submodule; the loosely coupled submodule is used to perform post-fusion on the second matching result based on a loosely coupled algorithm to obtain the post-fusion result.

[0097] In the embodiments of this application, when performing post-fusion on the second matching result, a loosely coupled algorithm is used to improve the accuracy of the post-fusion result, thereby improving the reliability of the positioning result. Specifically, the second matching result N is transformed into the vehicle coordinate system, and a cubic curve of the lane line in the vehicle coordinate system is fitted. The high-precision positioning result at the current moment in the vehicle coordinate system is calculated in the position coordinate space using the loosely coupled algorithm and used for the downstream planning and control module. The planning and control module is communicatively connected to the post-fusion module.

[0098] It should be noted that loosely coupled algorithms can be obtained directly based on related technologies and are not within the scope of protection of this application, so they will not be described in detail here.

[0099] like Figure 2 As shown, embodiments of this application also provide a fully fused localization method, applicable to, for example... Figure 1 The fully integrated positioning system 10 shown includes:

[0100] Step S21: Obtain the positioning data and visual data of the target vehicle, and perform a first processing on the positioning data and visual data to obtain a first abnormal data and a first normal data;

[0101] In an optional embodiment of this application, the step of acquiring the positioning data and visual data of the target vehicle, and performing a first process on the positioning data and visual data to obtain first abnormal data, includes:

[0102] Obtain a location data threshold and a visual data threshold; compare the location data with the location data threshold to obtain a first comparison result; compare the visual data with the visual data threshold to obtain a second comparison result.

[0103] Based on the first comparison result, a first sub-abnormal data is obtained, and based on the second comparison result, a second sub-abnormal data is obtained; wherein, the first abnormal data includes the first sub-abnormal data and the second sub-abnormal data.

[0104] Step S22: Perform pre-fusion on the first normal data to obtain the pre-fusion result;

[0105] In an optional embodiment of this application, the pre-fusion of the first normal data to obtain pre-fused data includes:

[0106] The first normal data is pre-fused based on a tightly coupled algorithm to obtain the pre-fusion result.

[0107] Step S23: Perform a second processing on the pre-fusion result to obtain second abnormal data and second normal data;

[0108] In an optional embodiment of this application, the second processing of the pre-fusion result to obtain second abnormal data includes:

[0109] The distribution state of the first matching result is detected to obtain a first detection result, and a third sub-anomaly data is obtained based on the first detection result; wherein, the second anomaly data includes the third sub-anomaly data;

[0110] The scene condition of the first matching result is detected to obtain a second detection result, and a fourth sub-anomaly data is obtained based on the second detection result; wherein, the second anomaly data includes the fourth sub-anomaly data;

[0111] The trend state of the first matching result is detected to obtain a third detection result, and a fifth sub-anomaly data is obtained based on the third detection result; wherein, the trend state includes a continuous trend state and a slowly changing trend state, and the second anomaly data includes the fifth sub-anomaly data.

[0112] Step S24: Perform post-fusion on the second normal data to obtain the post-fusion result.

[0113] In an optional embodiment of this application, the post-fusion of the second normal data to obtain the post-fusion result includes:

[0114] The second matching result is then fused using a loosely coupled algorithm to obtain the fused result.

[0115] In an optional embodiment of this application, the method further includes:

[0116] The data obtained from the front-view wide-angle camera and the side-view camera in the pre-fusion result are matched with the map data to obtain the first matching result.

[0117] The data obtained from the second normal data based on the forward-looking narrow-angle camera and the side-view camera are matched with the map data to obtain a second matching result.

[0118] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.

[0119] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.

[0120] Furthermore, other configurations and functions of the apparatus in the embodiments of this application are known to those skilled in the art, and will not be described in detail here to reduce redundancy.

[0121] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0122] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0123] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0124] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0125] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0126] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0127] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0128] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A fully integrated positioning system, characterized in that, include: The data preprocessing module, the pre-fusion module, the data filtering module, and the post-fusion module are connected in sequence via communication. The data preprocessing module is used to acquire the positioning data and visual data of the target vehicle, and to perform a first processing on the positioning data and visual data, comparing the positioning data with a positioning data threshold, comparing the visual data with a visual data threshold, and performing anomaly detection on the positioning data and visual data to obtain a first abnormal data and a first normal data. The pre-fusion module is used to perform pre-fusion on the first normal data to obtain the pre-fusion result; The data filtering module is used to perform a second processing on the pre-fusion result to obtain second abnormal data and second normal data; The post-fusion module is used to perform post-fusion on the second normal data to obtain the post-fusion result.

2. The system according to claim 1, characterized in that, The system also includes: A matching module, comprising a first sub-matching module and a second sub-matching module; The first sub-matching module is communicatively connected to both the pre-fusion module and the data filtering module; the second sub-matching module is communicatively connected to both the post-fusion module and the data filtering module. The first sub-matching module is used to perform a first match between the data obtained from the front-view wide-angle camera and the side-view camera in the front fusion result and the map data to obtain a first matching result, and send the first matching result to the data filtering module; The second sub-matching module is used to perform a second match between the data obtained from the second normal data based on the forward-looking narrow-angle camera and the data obtained based on the side-looking camera and the map data to obtain a second matching result.

3. The system according to claim 1, characterized in that, The data preprocessing module includes a sub-detection module; The sub-detection module is used to obtain a positioning data threshold and a visual data threshold, compare the positioning data with the positioning data threshold to obtain a first comparison result, and compare the visual data with the visual data threshold to obtain a second comparison result. Based on the first comparison result, a first sub-abnormal data is obtained, and based on the second comparison result, a second sub-abnormal data is obtained; wherein, the first abnormal data includes the first sub-abnormal data and the second sub-abnormal data.

4. The system according to claim 2, characterized in that, The data filtering module includes: a first sub-filtering module, a second sub-filtering module, and a third sub-filtering module; The first sub-filtering module is used to detect the distribution state of the first matching result, obtain a first detection result, and obtain a third sub-abnormal data based on the first detection result; wherein, the second abnormal data includes the third sub-abnormal data; The second sub-filtering module is used to detect the scene status of the first matching result, obtain a second detection result, and obtain a fourth sub-abnormal data based on the second detection result; wherein, the second abnormal data includes the fourth sub-abnormal data; The third sub-filtering module is used to detect the trend state of the first matching result, obtain a third detection result, and obtain a fifth sub-abnormal data based on the third detection result; wherein, the trend state includes a continuous trend state and a slowly changing trend state, and the second abnormal data includes the fifth sub-abnormal data.

5. The system according to any one of claims 1 to 4, characterized in that, The pre-fusion module includes a tightly coupled sub-module; the tightly coupled sub-module is used to perform pre-fusion on the first normal data based on a tightly coupled algorithm to obtain the pre-fusion result.

6. The system according to claim 2, characterized in that, The post-fusion module includes a loosely coupled submodule; the loosely coupled submodule is used to perform post-fusion on the second matching result based on a loosely coupled algorithm to obtain the post-fusion result.

7. A fully fusion localization method, characterized in that, include: The system acquires the positioning data and visual data of the target vehicle, performs a first processing on the positioning data and visual data, compares the positioning data with a positioning data threshold, compares the visual data with a visual data threshold, performs anomaly detection on the positioning data and visual data, and obtains a first abnormal data and a first normal data. Perform pre-fusion on the first normal data to obtain the pre-fusion result; The pre-fusion result is subjected to a second processing to obtain second abnormal data and second normal data; The second normal data is then fused to obtain the fused result.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method of claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method of claim 7.

Images