Location alarm methods, devices and electronic equipment for autonomous vehicles

By dynamically updating the location alarm time threshold for autonomous vehicles, the problem of a single threshold being unable to adapt to different vehicle models and scenarios is solved, improving the accuracy and security of location alarms, reducing false alarms, and enhancing passenger experience and driving safety.

CN118033707BActive Publication Date: 2026-11-10ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410184233.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-19
Publication Date
2026-11-10
Estimated Expiration
2044-02-19

AI Technical Summary

Technical Problem

In existing positioning solutions for autonomous vehicles, the alarm time thresholds provided by single integrated navigation devices cannot adapt to the differences in different vehicle models and operating scenarios, resulting in divergent positioning errors that affect passenger experience and safety.

Method used

By acquiring location alarm data from autonomous vehicles, and using preset statistical fields to perform statistical analysis on the real-time location alarm data, the alarm time threshold is dynamically updated. This includes statistics on dimensions such as vehicle type, driving scenario, vehicle speed, and RTK positioning status, and the positioning algorithm is optimized to adapt to different driving conditions.

Benefits of technology

It reduces the time and manpower costs of R&D testing and parameter calculation, avoids manual takeover or vehicle downgrade operations caused by false alarms, and improves passenger experience and driving safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118033707B_ABST
    Figure CN118033707B_ABST
Patent Text Reader

Abstract

This application discloses a location alarm method, device, and electronic device for autonomous vehicles. The method includes: acquiring location alarm data of the autonomous vehicle, including initial location alarm data and real-time location alarm data, wherein the initial location alarm data includes an initial alarm time threshold; determining whether the real-time location alarm data meets a preset threshold update condition; if so, performing statistics on the real-time location alarm data using a preset statistical field to obtain the current alarm time threshold under the preset statistical field; and updating the initial alarm time threshold using the current alarm time threshold. This application can automatically update the alarm time threshold based on the location alarm data reported in real time by the autonomous vehicle, reducing the time and manpower costs of developing a large number of tests and calculation parameters. By determining the corresponding alarm time threshold for different statistical dimensions, it avoids manual intervention due to false alarms caused by a single parameter, thereby improving passenger experience and safety.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a location alarm method, device and electronic equipment for autonomous vehicles. Background Technology

[0002] With the popularization of autonomous driving technology and the reduction of hardware costs, companies are putting more and more types of autonomous vehicles into operation, including: driverless trucks, driverless sweepers, driverless minibuses, driverless taxis, driverless patrol cars, etc. Most of these vehicles will be concentrated in specific parks or specific urban areas for operation.

[0003] As a fundamental module in the software framework of the entire autonomous vehicle, the positioning module directly impacts the operation of downstream modules through the stability, accuracy, confidence level, and positioning warning information it outputs. Positioning warnings are directly related to passenger comfort and safety; excessively frequent alarms and degraded operations may improve vehicle safety but significantly reduce passenger comfort, while conversely, insufficient warnings can lead to excessively high safety risks.

[0004] Currently, the mainstream positioning solution is to replace the traditional combined navigation positioning by integrating IMU, GNSS / RTK, vehicle data, laser positioning, and visual positioning information, in order to improve the problem of direct alarms after long-term interference with satellite signals in tunnels, urban canyons, and other areas.

[0005] Existing technologies mainly rely on statistical analysis of the relationship between the filter prediction time and the degree of error divergence when effective observations are lost (RTK, laser positioning, and visual positioning in differential states). A reasonable time threshold (a value provided by the integrated navigation equipment manufacturer) is selected, and an alarm is triggered when the threshold is exceeded.

[0006] However, due to differences in vehicle size among different models and differences in scenarios in different operating cities / parks, the alarm time threshold provided by a single integrated navigation device cannot adequately meet the above conditions, further affecting user experience and safety. Summary of the Invention

[0007] This application provides a location alarm method, device, and electronic device for autonomous vehicles to improve the accuracy of location alarms for autonomous vehicles, enhance passenger experience, and improve driving safety.

[0008] The embodiments of this application adopt the following technical solutions:

[0009] In a first aspect, embodiments of this application provide a location alarm method for an autonomous vehicle, wherein the method includes:

[0010] Acquire location alarm data of autonomous vehicles, the location alarm data including initial location alarm data and real-time location alarm data, the initial location alarm data including an initial alarm time threshold;

[0011] Determine whether the real-time location alarm data meets the preset threshold update conditions;

[0012] When the real-time location alarm data meets the preset threshold update conditions, the real-time location alarm data is statistically analyzed using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields.

[0013] The initial alarm time threshold is updated using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0014] Optionally, the preset statistical fields include basic statistical fields, the initial location alarm data includes an initial alarm time threshold, and the acquisition of location alarm data for autonomous vehicles includes:

[0015] The basic statistical fields are determined, and the basic statistical fields include at least one dimension among vehicle type, driving scenario, vehicle speed, and RTK positioning status;

[0016] The initial alarm time threshold for autonomous vehicles under basic statistical fields is determined based on a preset data source.

[0017] Optionally, the preset statistical fields include basic statistical fields, and determining whether the real-time location alarm data meets the preset threshold update conditions includes:

[0018] The number of times the target data in the real-time location alarm data is reported is counted. The target data refers to data in which the field values ​​of each basic statistical field are the same.

[0019] If the number of times the target data is reported reaches a preset threshold, then the target data is determined to meet the preset threshold update condition;

[0020] Otherwise, the condition is not met.

[0021] Optionally, the preset statistical fields further include additional statistical fields, which include the type of abnormal situation and the time of occurrence of the abnormal situation. The step of performing statistical analysis on the real-time location alarm data using the preset statistical fields when the real-time location alarm data meets the preset threshold update condition includes:

[0022] Determine the statistical weights corresponding to the types of anomalies based on the vehicle models contained in the target data;

[0023] By using the basic statistical fields and the statistical weights corresponding to the abnormal situation types, statistical analysis is performed on the occurrence time of abnormal situations contained in the target data to obtain the current alarm time threshold under the basic statistical fields.

[0024] Optionally, the abnormal situation types include takeover situations and shaking situations, the statistical weights include takeover weights and shaking weights, and the step of determining the statistical weights corresponding to the abnormal situation types based on the vehicle models included in the target data includes:

[0025] If the vehicle type included in the target data is a vehicle without passengers, then the takeover weight value corresponding to the takeover situation in the target data is assigned to 1, and the sway weight value corresponding to the sway situation in the target data is assigned to 0.

[0026] If the vehicle type included in the target data is a vehicle with passengers, then the takeover weight value corresponding to the takeover situation and the sway weight value corresponding to the sway situation in the target data are both assigned a value of 1.

[0027] Optionally, the step of using the basic statistical fields and the statistical weights corresponding to the anomaly types to perform statistical analysis on the occurrence time of anomalies in the target data includes:

[0028] Based on the statistical weights corresponding to the anomaly types, the occurrence times of the anomalies contained in the target data are sorted.

[0029] Based on the sorting results of the occurrence time of the abnormal situation and the field values ​​of the basic statistical fields contained in the target data, the current alarm time threshold under the basic statistical fields is determined.

[0030] Optionally, sorting the occurrence times of anomalies in the target data according to the statistical weights corresponding to the anomaly types includes:

[0031] If the statistical weight corresponding to the abnormal situation type is 1, then the occurrence time of the abnormal situation corresponding to the abnormal situation type is included in the sorting.

[0032] If the statistical weight corresponding to the abnormal situation type is 0, then the occurrence time of the abnormal situation corresponding to the abnormal situation type will not be included in the sorting.

[0033] Optionally, updating the initial alarm time threshold using the current alarm time threshold under a preset statistical field includes:

[0034] Determine whether the current alarm time threshold is an abnormal value;

[0035] If not, then update the initial alarm time threshold using the current alarm time threshold;

[0036] Otherwise, the localization algorithm for autonomous vehicles is optimized, and the updated alarm time threshold is determined based on the optimized localization algorithm.

[0037] Secondly, embodiments of this application also provide a positioning alarm device for an autonomous vehicle, wherein the device includes:

[0038] The acquisition unit is used to acquire the positioning alarm data of the autonomous vehicle. The positioning alarm data includes initial positioning alarm data and real-time positioning alarm data. The initial positioning alarm data includes an initial alarm time threshold.

[0039] The determining unit is used to determine whether the real-time positioning alarm data meets the preset threshold update conditions;

[0040] The statistical unit is used to perform statistical analysis on the real-time location alarm data using a preset statistical field when the real-time location alarm data meets the preset threshold update condition, and to obtain the current alarm time threshold under the preset statistical field.

[0041] The update unit is used to update the initial alarm time threshold using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0042] Thirdly, embodiments of this application also provide an electronic device, including:

[0043] Processor; and

[0044] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0045] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.

[0046] The above-mentioned technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The positioning alarm method for autonomous vehicles in the embodiments of this application first acquires positioning alarm data of autonomous vehicles, including initial positioning alarm data and real-time positioning alarm data, wherein the initial positioning alarm data includes an initial alarm time threshold; then it determines whether the real-time positioning alarm data meets the preset threshold update condition; then, if the real-time positioning alarm data meets the preset threshold update condition, it performs statistical analysis on the real-time positioning alarm data using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields; finally, it updates the initial alarm time threshold using the current alarm time threshold under the preset statistical fields, so that the autonomous vehicle performs positioning alarm based on the updated alarm time threshold. The positioning alarm method for autonomous vehicles in the embodiments of this application can automatically update the alarm time threshold parameter according to the positioning alarm data reported by the autonomous vehicle in real time, reducing the time and manpower costs of developing a large number of tests and calculating parameters, and determining the corresponding alarm time threshold for different statistical dimensions, avoiding manual takeover or other vehicle degradation operations caused by false alarms due to a single parameter, thereby improving passenger experience and driving safety. Attached Figure Description

[0047] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0048] Figure 1 This is a flowchart illustrating a positioning alarm method for an autonomous vehicle according to an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the structure of a positioning alarm device for an autonomous vehicle according to an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0053] This application provides a method for locating and alarming autonomous vehicles, such as... Figure 1 The diagram shows a flowchart of a location alarm method for an autonomous vehicle according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0054] Step S110: Obtain the location alarm data of the autonomous vehicle. The location alarm data includes initial location alarm data and real-time location alarm data. The initial location alarm data includes an initial alarm time threshold.

[0055] The core of the autonomous vehicle positioning alarm method in this application embodiment lies in dynamically calculating and updating the alarm time threshold of the autonomous vehicle based on the actual driving state. Here, the "alarm time threshold" can be understood as the maximum time the autonomous vehicle can continue driving when it enters a non-differential state due to RTK positioning. When the autonomous vehicle accumulates enough driving time in the non-differential state to reach the alarm time threshold, an alarm is triggered to ensure the driving safety and passenger comfort of the autonomous vehicle. The "non-differential state" mainly includes trajectory extrapolation state, single-point positioning state, floating-point positioning state, and no-output state.

[0056] When dynamically calculating the alarm time threshold for autonomous vehicles, it is necessary to first obtain the location alarm data of the autonomous vehicles. The location alarm data includes initial location alarm data and real-time location alarm data. The initial location alarm data refers to the location alarm data initially determined based on existing scene data and test data, mainly including the initial alarm time threshold, which serves as the basis for subsequent threshold updates.

[0057] Real-time location alarm data refers to location alarm data reported in real time by operating vehicles or test vehicles. Since location alarms are mainly warnings triggered by the divergence of positioning errors when autonomous vehicles are in a non-differential state, the conditions for real-time reporting of data by operating vehicles or test vehicles can be constrained. That is, operating vehicles or test vehicles can monitor their own positioning status in real time, and when the vehicle enters a non-differential state, they will report the data for the time period in which the non-differential positioning state occurs.

[0058] Step S120: Determine whether the real-time positioning alarm data meets the preset threshold update conditions.

[0059] To ensure the accuracy of threshold updates, the amount of real-time location alarm data corresponding to different driving states needs to be sufficient. Therefore, embodiments of this application can determine whether the currently accumulated data meets the preset threshold update conditions based on the location alarm data reported in real time by each autonomous vehicle.

[0060] Step S130: When the real-time location alarm data meets the preset threshold update conditions, the real-time location alarm data is statistically analyzed using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields.

[0061] If the accumulated real-time location alarm data meets the preset threshold update conditions, further statistical analysis of the real-time location alarm data is required based on predefined statistical fields to calculate the current alarm time threshold corresponding to a specific statistical field.

[0062] The aforementioned statistical fields can be defined based on the differences in positioning alarm thresholds for autonomous vehicles under different driving conditions. For example, different vehicle models, different driving scenarios, and different non-differential states may lead to different tolerance levels for positioning errors in autonomous vehicles. Therefore, different positioning alarm time thresholds need to be set for different vehicle models, different driving scenarios, and different non-differential states. Of course, it should be noted that those skilled in the art can flexibly set which statistical fields to define according to actual needs, and no specific limitations are made here.

[0063] Step S140: Update the initial alarm time threshold using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0064] After obtaining the current alarm time threshold under the preset statistical fields, the corresponding initial alarm time threshold can be updated using the current alarm time threshold. Thus, when an autonomous vehicle is in a specific driving state in a real-world scenario, it can trigger a location alarm according to the alarm time threshold corresponding to that driving state. Since the alarm time threshold for this driving state is based on statistical analysis of a large amount of actual driving data for that state, it is better suited to the location alarm requirements of that driving state, thereby reducing the need for manual intervention due to false alarms caused by using a single threshold parameter.

[0065] The location alarm method for autonomous vehicles in this application embodiment can automatically update the alarm time threshold parameter based on the location alarm data reported by the autonomous vehicle in real time. This reduces the time and manpower costs of developing a large number of tests and calculating parameters. Furthermore, it determines the corresponding alarm time threshold for different statistical dimensions, avoiding manual takeover or other vehicle degradation operations caused by false alarms due to a single parameter, thereby improving passenger experience and driving safety.

[0066] In some embodiments of this application, the preset statistical fields include basic statistical fields, the initial positioning alarm data includes an initial alarm time threshold, and the acquisition of positioning alarm data of autonomous vehicles includes: determining the basic statistical fields, wherein the basic statistical fields include at least one dimension among vehicle type, driving scenario, vehicle speed, and RTK positioning status; and determining the initial alarm time threshold of autonomous vehicles under the basic statistical fields based on a preset data source.

[0067] The aforementioned preset statistical fields may include basic statistical fields. The basic statistical fields defined in this application embodiment mainly include vehicle type, driving scenario, vehicle speed, RTK positioning status, etc., and may also include the duration of the non-differential state. Vehicle type can be divided into two main categories: commercial vehicles with passengers and work vehicles without passengers. Of course, those skilled in the art can flexibly classify other vehicle types according to actual needs. Driving scenario can be divided according to different cities / regions / areas. Vehicle speed can be a single point value or an interval range. RTK positioning status mainly includes 3-track extrapolation state, 1-single-point positioning state, 5-floating-point positioning state, and 0-no output state. It should be noted that the above statistical fields are the main dimensions affecting the positioning alarm threshold and can be flexibly configured according to actual needs.

[0068] The initial values ​​for each of the above fields can be assigned based on the data provided by the scenario and the data from the initial R&D tests. For example, {SWEEPER, Beijing, 20, 3, 15} indicates that the sweeper has a simulated flight path of 20 km / h for 15 seconds in Beijing. Based on the data provided by the scenario and the data from the initial R&D tests, the initial alarm time thresholds corresponding to each basic statistical field can be preliminarily determined. For example, the initial alarm time threshold corresponding to {SWEEPER, Beijing, 20, 3} is 15 seconds, and the initial alarm time threshold corresponding to {ROBOTAXI, Beijing, 60, 3} is 12 seconds.

[0069] In some embodiments of this application, the preset statistical fields include basic statistical fields, and determining whether the real-time location alarm data meets the preset threshold update condition includes: counting the number of times the target data in the real-time location alarm data is reported, where the target data refers to data in which the field values ​​of each basic statistical field are the same; if the number of times the target data is reported reaches the preset number threshold, then the target data is determined to meet the preset threshold update condition; otherwise, it is not met.

[0070] When determining whether real-time location alarm data meets the preset threshold update conditions, the number of reports of target data in the real-time location alarm data can be statistically analyzed. Target data here refers to data where the values ​​of all basic statistical fields are identical. For example, the cumulative data volume corresponding to the same vehicle model, the same scene, the same vehicle speed, and the same RTK positioning state can be statistically analyzed. If the cumulative data volume reaches a certain threshold, such as 1000 times, it indicates that the cumulative data volume in that state is sufficient for subsequent calculation of the alarm time threshold for that state, meaning the data under that basic statistical field is considered to meet the preset threshold update conditions. Of course, the size of this preset threshold can be flexibly set by those skilled in the art according to actual needs, and is not specifically limited here.

[0071] In some embodiments of this application, the preset statistical field further includes an additional statistical field, which includes an anomaly type and an anomaly occurrence time. The step of performing statistical analysis on the real-time location alarm data using the preset statistical field when the real-time location alarm data meets the preset threshold update condition includes: determining the statistical weight corresponding to the anomaly type based on the vehicle model contained in the target data; and performing statistical analysis on the anomaly occurrence time contained in the target data using the basic statistical field and the statistical weight corresponding to the anomaly type to obtain the current alarm time threshold under the basic statistical field.

[0072] The preset statistical fields in this application embodiment also include additional statistical fields. The additional statistical fields can be understood as data related to abnormal vehicle conditions collected after the actual driving of the operating vehicle or test vehicle. They mainly include the abnormal condition type and the abnormal condition occurrence time. The abnormal condition type refers to the abnormal condition caused by the autonomous vehicle after entering the non-differential state, such as takeover or shaking. The abnormal condition occurrence time refers to how long after the autonomous vehicle is taken over or shakes after entering the non-differential state, which is the basis for subsequent calculation of the alarm time threshold.

[0073] In this embodiment of the application, when performing statistical analysis on real-time location alarm data, the statistics are performed according to the dimensions of the target data, and the data under the additional statistical fields and the data under the basic statistical fields have a many-to-one relationship. Therefore, the data of multiple additional statistical fields under the same basic statistical field can be statistically analyzed separately to obtain the current alarm time threshold corresponding to the basic statistical field.

[0074] Regarding the aforementioned abnormal situations of takeover and shaking, from the perspective of user riding experience, the importance of takeover and shaking varies across different vehicle models. For example, in vehicles with passengers, shaking has a greater impact on the user's physical sensation, while in vehicles without passengers, vehicle shaking has no impact on physical sensation. Based on this, this application embodiment can determine the statistical weight corresponding to the abnormal situation type based on the specific vehicle model information contained in each target data. Here, the statistical weight mainly takes the value of 0 or 1. A value of 0 indicates that the abnormal situation has no impact on physical sensation, while a value of 1 indicates that the abnormal situation has an impact on physical sensation and safety. Based on the statistical weight corresponding to the abnormal situation type, statistical analysis is performed on the occurrence time of abnormal situations under the same basic statistical field to obtain the current alarm time threshold under the basic statistical field.

[0075] In some embodiments of this application, the abnormal situation types include takeover situations and swaying situations, the statistical weights include takeover weights and swaying weights, and determining the statistical weights corresponding to the abnormal situation types based on the vehicle models contained in the target data includes: if the vehicle models contained in the target data are passengerless vehicles, then the takeover weight corresponding to the takeover situation in the target data is assigned a value of 1, and the swaying weight corresponding to the swaying situation in the target data is assigned a value of 0; if the vehicle models contained in the target data are passenger-carrying vehicles, then both the takeover weight corresponding to the takeover situation and the swaying weight corresponding to the swaying situation in the target data are assigned a value of 1.

[0076] As mentioned above, the statistical weights defined in this application embodiment are mainly 0 or 1. If the vehicle type included in the current target data is a vehicle without passengers, then the vehicle takeover situation has an impact on the vehicle driving safety, but the vehicle shaking situation has no impact on the body sensation. Therefore, the takeover weight corresponding to the takeover situation can be assigned to 1, and the shaking weight corresponding to the shaking situation can be assigned to 0. That is, when calculating the alarm time threshold in the future, the relevant data of abnormal situations can be ignored, and only the takeover data can be considered.

[0077] If the vehicle is a passenger vehicle, then the vehicle's feel is just as important as the takeover. Passengers are more sensitive to vehicle shaking that causes discomfort. Therefore, the takeover weight and the shaking weight can both be set to 1. This means that when calculating the alarm time threshold, the relevant data of both the takeover and abnormal situations need to be considered simultaneously.

[0078] In some embodiments of this application, the step of statistically analyzing the occurrence time of abnormal situations in the target data using the basic statistical fields and the statistical weights corresponding to the abnormal situation types includes: sorting the occurrence times of abnormal situations in the target data according to the statistical weights corresponding to the abnormal situation types; and determining the current alarm time threshold under the basic statistical fields based on the sorting results of the occurrence times of abnormal situations and the field values ​​of the basic statistical fields in the target data.

[0079] When calculating the current alarm time threshold based on the occurrence time of an anomaly, all anomaly data participating in the calculation can be determined first according to the statistical weight corresponding to the anomaly type. Then, these data can be sorted according to the magnitude of the occurrence time of the anomaly. Based on the sorting result, the current alarm time threshold under the specific basic statistical field can be determined in combination with the field value of the specific basic statistical field.

[0080] For example, the sorting results can determine the minimum or nth minimum time of occurrence of abnormal situations (with an acceptable error rate of n per thousand). Assuming both the minimum and second minimum values ​​originate from the time of the shaking event, with the minimum being 15 seconds and the second minimum 18 seconds, further judgment can be made based on the values ​​of specific basic statistical fields. For instance, if it's a driverless taxi traveling at 60 km / h (highway) in the city, the high speed and noticeable shaking effect can be set to a minimum of 15 seconds; if it's a sightseeing vehicle traveling at 10 km / h in a scenic area, the shaking effect is less noticeable, and the second minimum could be set to 18 seconds. Since both the minimum and second minimum values ​​in the sorted data originate from takeover data, the minimum value can be directly selected to ensure driving safety.

[0081] Of course, it should be noted that the above is merely an exemplary description and does not constitute a limitation on the scope of protection of the embodiments of this application.

[0082] In some embodiments of this application, sorting the occurrence times of abnormal situations in the target data according to the statistical weights corresponding to the abnormal situation types includes: if the statistical weight corresponding to the abnormal situation type is 1, then the occurrence time of the abnormal situation corresponding to the abnormal situation type participates in the sorting; if the statistical weight corresponding to the abnormal situation type is 0, then the occurrence time of the abnormal situation corresponding to the abnormal situation type does not participate in the sorting.

[0083] When performing statistical analysis on the occurrence time of anomalies based on their corresponding statistical weights, if the statistical weight corresponding to the anomaly type is 1, it is included in the statistics; if the statistical weight is 0, it is not included. To facilitate understanding of the above embodiments, Table 1 below provides an example of the fields for real-time location alarm data:

[0084] Table 1

[0085]

[0086] Based on Table 1 above, under the same vehicle model, driving scenario, vehicle speed, and RTK positioning status, the shaking weight in the second and third data entries is 0, while the weights of the rest are 1. Therefore, the shaking occurrence times of 14s and 17s in these two data entries will not be included in the subsequent calculation of the alarm time threshold. The remaining data will be included in the calculation, which means that the remaining abnormal occurrence time data {15, 13, 16, 18, 17...} with all weights of 1 will be uniformly sorted.

[0087] In some embodiments of this application, updating the initial alarm time threshold using the current alarm time threshold under a preset statistical field includes: determining whether the current alarm time threshold is an outlier; if not, updating the initial alarm time threshold using the current alarm time threshold; otherwise, optimizing the positioning algorithm of the autonomous vehicle and redetermining the updated alarm time threshold based on the optimized positioning algorithm.

[0088] Considering that the statistical results obtained in the aforementioned embodiments may contain outliers, this application embodiment can determine whether the current alarm time threshold is an outlier based on a predefined outlier judgment strategy. For example, an outlier threshold can be set first, and the current alarm time threshold can be compared with the outlier threshold. If the difference between the current alarm time threshold and the outlier threshold is large, or if the minimum value of the outlier occurrence time after sorting in the above embodiments is too far from the second minimum value, the situation at that time can be further analyzed to determine whether it is caused by a positioning error. If not, the outlier is ignored; if so, the positioning algorithm is optimized, and a special case handling mechanism is added to prevent frequent alarms caused by excessively low thresholds.

[0089] This application also provides a positioning alarm device 200 for autonomous vehicles, such as... Figure 2 The diagram shows a schematic representation of a positioning alarm device for an autonomous vehicle according to an embodiment of this application. The device 200 includes: an acquisition unit 210, a determination unit 220, a statistics unit 230, and an update unit 240, wherein:

[0090] The acquisition unit 210 is used to acquire the positioning alarm data of the autonomous vehicle. The positioning alarm data includes initial positioning alarm data and real-time positioning alarm data. The initial positioning alarm data includes an initial alarm time threshold.

[0091] Determining unit 220 is used to determine whether the real-time positioning alarm data meets the preset threshold update condition;

[0092] The statistical unit 230 is used to perform statistical analysis on the real-time location alarm data using a preset statistical field when the real-time location alarm data meets the preset threshold update condition, and obtain the current alarm time threshold under the preset statistical field.

[0093] The update unit 240 is used to update the initial alarm time threshold using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0094] In some embodiments of this application, the preset statistical fields include basic statistical fields, the initial positioning alarm data includes an initial alarm time threshold, and the acquisition unit 210 is specifically used to: determine the basic statistical fields, which include at least one dimension among vehicle type, driving scenario, vehicle speed, and RTK positioning status; and determine the initial alarm time threshold of the autonomous vehicle under the basic statistical fields based on a preset data source.

[0095] In some embodiments of this application, the preset statistical fields include basic statistical fields, and the determining unit 220 is specifically used to: count the number of times the target data in the real-time positioning alarm data is reported, where the target data refers to data in which the field values ​​of each basic statistical field are the same; if the number of times the target data is reported reaches a preset number threshold, then the target data is determined to meet the preset threshold update condition; otherwise, it is not met.

[0096] In some embodiments of this application, the preset statistical field further includes an additional statistical field, which includes an abnormal situation type and an abnormal situation occurrence time. The statistical unit 230 is specifically used to: determine the statistical weight corresponding to the abnormal situation type based on the vehicle model contained in the target data; and use the basic statistical field and the statistical weight corresponding to the abnormal situation type to perform statistical analysis on the abnormal situation occurrence time contained in the target data to obtain the current alarm time threshold under the basic statistical field.

[0097] In some embodiments of this application, the abnormal situation types include takeover situations and swaying situations, the statistical weights include takeover weights and swaying weights, and the statistical unit 230 is specifically used to: if the vehicle models included in the target data are passengerless vehicles, then assign the takeover weight corresponding to the takeover situation in the target data to 1, and assign the swaying weight corresponding to the swaying situation in the target data to 0; if the vehicle models included in the target data are passenger-carrying vehicles, then assign both the takeover weight corresponding to the takeover situation and the swaying weight corresponding to the swaying situation in the target data to 1.

[0098] In some embodiments of this application, the statistics unit 230 is specifically used to: sort the occurrence times of abnormal situations contained in the target data according to the statistical weights corresponding to the abnormal situation types; and determine the current alarm time threshold under the basic statistical fields according to the sorting results of the occurrence times of abnormal situations and the field values ​​of the basic statistical fields contained in the target data.

[0099] In some embodiments of this application, the statistical unit 230 is specifically used to: if the statistical weight value corresponding to the abnormal situation type is 1, then the occurrence time of the abnormal situation corresponding to the abnormal situation type is included in the sorting; if the statistical weight value corresponding to the abnormal situation type is 0, then the occurrence time of the abnormal situation corresponding to the abnormal situation type is not included in the sorting.

[0100] In some embodiments of this application, the updating unit 240 is specifically used to: determine whether the current alarm time threshold is an abnormal value; if not, update the initial alarm time threshold using the current alarm time threshold; otherwise, optimize the positioning algorithm of the autonomous vehicle and redetermine the updated alarm time threshold according to the optimized positioning algorithm.

[0101] It is understood that the aforementioned location alarm device for autonomous vehicles can implement each step of the location alarm method for autonomous vehicles provided in the foregoing embodiments. The relevant explanations regarding the location alarm method for autonomous vehicles are applicable to the location alarm device for autonomous vehicles, and will not be repeated here.

[0102] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0103] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0104] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0105] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, logically forming the location alarm device for the autonomous vehicle. The processor executes the program stored in memory and specifically performs the following operations:

[0106] Acquire location alarm data of autonomous vehicles, the location alarm data including initial location alarm data and real-time location alarm data, the initial location alarm data including an initial alarm time threshold;

[0107] Determine whether the real-time location alarm data meets the preset threshold update conditions;

[0108] When the real-time location alarm data meets the preset threshold update conditions, the real-time location alarm data is statistically analyzed using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields.

[0109] The initial alarm time threshold is updated using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0110] The above is as stated in this application. Figure 1The method for the positioning alarm device of an autonomous vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0111] The electronic device can also perform Figure 1 The method for implementing the positioning alarm device of an autonomous vehicle, and realizing the positioning alarm device of an autonomous vehicle in... Figure 1 The functions of the embodiments shown are not described again in this application.

[0112] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the positioning alarm device of the autonomous vehicle in the illustrated embodiment is specifically used to perform:

[0113] Acquire location alarm data of autonomous vehicles, the location alarm data including initial location alarm data and real-time location alarm data, the initial location alarm data including an initial alarm time threshold;

[0114] Determine whether the real-time location alarm data meets the preset threshold update conditions;

[0115] When the real-time location alarm data meets the preset threshold update conditions, the real-time location alarm data is statistically analyzed using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields.

[0116] The initial alarm time threshold is updated using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold.

[0117] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0123] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0124] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0125] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A location alarm method for an autonomous vehicle, wherein, The method includes: Acquire location alarm data of autonomous vehicles, the location alarm data including initial location alarm data and real-time location alarm data, the initial location alarm data including an initial alarm time threshold; Determine whether the real-time location alarm data meets the preset threshold update conditions; When the real-time location alarm data meets the preset threshold update conditions, the real-time location alarm data is statistically analyzed using preset statistical fields to obtain the current alarm time threshold under the preset statistical fields. The initial alarm time threshold is updated using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold. The preset statistical fields include basic statistical fields and additional statistical fields. The additional statistical fields include the type of abnormal situation and the time of occurrence of the abnormal situation. The step of performing statistical analysis on the real-time location alarm data using the preset statistical fields when the real-time location alarm data meets the preset threshold update condition includes: Determine the statistical weights corresponding to the types of anomalies based on the vehicle models contained in the target data; By using the basic statistical fields and the statistical weights corresponding to the abnormal situation types, the occurrence time of abnormal situations contained in the target data is statistically analyzed to obtain the current alarm time threshold under the basic statistical fields; The abnormal situation types include takeover situations and shaking situations, the statistical weights include takeover weights and shaking weights, and the determination of the statistical weights corresponding to the abnormal situation types based on the vehicle models contained in the target data includes: If the vehicle type included in the target data is a vehicle without passengers, then the takeover weight value corresponding to the takeover situation in the target data is assigned to 1, and the sway weight value corresponding to the sway situation in the target data is assigned to 0. If the vehicle type included in the target data is a vehicle with passengers, then the takeover weight value corresponding to the takeover situation and the sway weight value corresponding to the sway situation in the target data are both assigned a value of 1. The step of statistically analyzing the occurrence time of abnormal situations in the target data using the basic statistical fields and the statistical weights corresponding to the abnormal situation types includes: Based on the statistical weights corresponding to the anomaly types, the occurrence times of the anomalies contained in the target data are sorted. Based on the sorting results of the occurrence time of the abnormal situation and the field values ​​of the basic statistical fields contained in the target data, the current alarm time threshold under the basic statistical fields is determined.

2. The method as described in claim 1, wherein, The preset statistical fields include basic statistical fields, the initial location alarm data includes an initial alarm time threshold, and the acquisition of location alarm data for autonomous vehicles includes: The basic statistical fields are determined, and the basic statistical fields include at least one dimension among vehicle type, driving scenario, vehicle speed, and RTK positioning status; The initial alarm time threshold for autonomous vehicles under basic statistical fields is determined based on a preset data source.

3. The method as described in claim 1, wherein, The preset statistical fields include basic statistical fields, and determining whether the real-time location alarm data meets the preset threshold update conditions includes: The number of times the target data in the real-time location alarm data is reported is counted. The target data refers to data in which the field values ​​of each basic statistical field are the same. If the number of times the target data is reported reaches a preset threshold, then the target data is determined to meet the preset threshold update condition; Otherwise, the condition is not met.

4. The method as described in claim 1, wherein, The step of sorting the occurrence times of abnormal situations in the target data according to the statistical weights corresponding to the abnormal situation types includes: If the statistical weight corresponding to the abnormal situation type is 1, then the occurrence time of the abnormal situation corresponding to the abnormal situation type is included in the sorting. If the statistical weight corresponding to the abnormal situation type is 0, then the occurrence time of the abnormal situation corresponding to the abnormal situation type will not be included in the sorting.

5. The method as described in claim 1, wherein, The step of updating the initial alarm time threshold using the current alarm time threshold under a preset statistical field includes: Determine whether the current alarm time threshold is an abnormal value; If not, then update the initial alarm time threshold using the current alarm time threshold; Otherwise, the localization algorithm for autonomous vehicles is optimized, and the updated alarm time threshold is determined based on the optimized localization algorithm.

6. A positioning alarm device for an autonomous vehicle, wherein, The device includes: The acquisition unit is used to acquire the positioning alarm data of the autonomous vehicle. The positioning alarm data includes initial positioning alarm data and real-time positioning alarm data. The initial positioning alarm data includes an initial alarm time threshold. The determining unit is used to determine whether the real-time positioning alarm data meets the preset threshold update conditions; The statistical unit is used to perform statistical analysis on the real-time location alarm data using a preset statistical field when the real-time location alarm data meets the preset threshold update condition, and to obtain the current alarm time threshold under the preset statistical field. The update unit is used to update the initial alarm time threshold using the current alarm time threshold under the preset statistical field, so that the autonomous vehicle can perform location alarm based on the updated alarm time threshold. The preset statistical fields include basic statistical fields and additional statistical fields. The additional statistical fields include the type of abnormal situation and the time of occurrence of the abnormal situation. The step of performing statistical analysis on the real-time location alarm data using the preset statistical fields when the real-time location alarm data meets the preset threshold update condition includes: Determine the statistical weights corresponding to the types of anomalies based on the vehicle models contained in the target data; By using the basic statistical fields and the statistical weights corresponding to the abnormal situation types, the occurrence time of abnormal situations contained in the target data is statistically analyzed to obtain the current alarm time threshold under the basic statistical fields; The abnormal situation types include takeover situations and shaking situations, the statistical weights include takeover weights and shaking weights, and the determination of the statistical weights corresponding to the abnormal situation types based on the vehicle models contained in the target data includes: If the vehicle type included in the target data is a vehicle without passengers, then the takeover weight value corresponding to the takeover situation in the target data is assigned to 1, and the sway weight value corresponding to the sway situation in the target data is assigned to 0. If the vehicle type included in the target data is a vehicle with passengers, then the takeover weight value corresponding to the takeover situation and the sway weight value corresponding to the sway situation in the target data are both assigned a value of 1. The step of statistically analyzing the occurrence time of abnormal situations in the target data using the basic statistical fields and the statistical weights corresponding to the abnormal situation types includes: Based on the statistical weights corresponding to the anomaly types, the occurrence times of the anomalies contained in the target data are sorted. Based on the sorting results of the occurrence time of the abnormal situation and the field values ​​of the basic statistical fields contained in the target data, the current alarm time threshold under the basic statistical fields is determined.

7. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 5.

Citation Information

Patent Citations

  • Vehicle driving early warning method and device

    CN111583713A

  • Positioning alarm method and device for autonomous vehicle, and electronic equipment

    CN114966794A