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

Abstract

The present application discloses a positioning alarm method, device and electronic device for an autonomous driving vehicle, the method comprising: obtaining first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device; based on the second positioning data, processing the first positioning data to obtain processed data of the combined navigation device, the processed data including a positioning state and a corresponding positioning error, the positioning state including a differential state and a non-differential state; determining an alarm condition corresponding to a preset positioning error threshold according to the processed data and a preset positioning error threshold; and performing a positioning alarm for the autonomous driving vehicle based on the alarm condition corresponding to the preset positioning error threshold. The present application determines the positioning error of the combined navigation device based on the true value device, and determines the corresponding alarm conditions in combination with the positioning state and the positioning accuracy requirements of different scenarios, thereby improving the accuracy of the positioning alarm, reducing the false alarm rate, and ensuring positioning stability.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a positioning alarm method, device and electronic equipment for an autonomous driving vehicle. Background Art

[0002] The gradual development of autonomous driving technology has led to an increasing demand for combined navigation devices such as GNSS (Global Navigation Satellite System) / RTK (Real Time Kinematic) + IMU (Inertial Measurement Unit). The built-in hardware and algorithms of these devices can fuse the high-frequency relative positioning results of IMU with the low-frequency absolute positioning results of GNSS / RTK, thereby outputting high-frequency, high-precision positioning results. At the same time, according to the built-in algorithm of the device, the positioning status and confidence of the current positioning result can be output simultaneously for subsequent modules to make decisions. Commonly used positioning states include fixed solution, floating point solution, single point solution, and track deduction solution (without considering the initialization state).

[0003] However, the confidence level of the integrated navigation device output is not always reliable due to the following reasons, or the positioning status output by the integrated navigation device cannot provide sufficient information to the subsequent modules to a certain extent:

[0004] 1) Due to the requirements of mass production costs, the cost of the integrated navigation modules of many autonomous driving vehicles is low, so the hardware equipment is noisy;

[0005] 2) Due to the limitations of the algorithm itself, for example, when the Kalman filter cannot obtain effective observations for a long time and only relies on track deduction, the cumulative error will become larger and larger.

[0006] When the positioning result output by the integrated navigation device no longer meets the positioning accuracy requirement due to the above reasons, a positioning alarm needs to be issued in time to ensure positioning stability, but the prior art does not provide a suitable alarm condition to control the triggering of the positioning alarm. For example, the current result output by the integrated navigation device is a floating point solution, but the floating point solution error will be unstable for a long time, and the prior art does not provide a suitable time threshold to trigger the alarm. Summary of the invention

[0007] The embodiments of the present application provide a positioning alarm method, device and electronic device for an autonomous driving vehicle to improve the accuracy of positioning alarms for autonomous driving vehicles, reduce the false alarm rate, and thus improve positioning stability.

[0008] The present application embodiment adopts the following technical solutions:

[0009] In a first aspect, an embodiment of the present application provides a positioning alarm method for an autonomous driving vehicle, wherein the method comprises:

[0010] Acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device;

[0011] Based on the second positioning data collected by the true value device, the first positioning data collected by the integrated navigation device is processed to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state;

[0012] Determining an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value;

[0013] Based on the alarm condition corresponding to the preset positioning error threshold, a positioning alarm of the autonomous driving vehicle is performed.

[0014] Optionally, the processed data of the integrated navigation device further includes a positioning timestamp corresponding to the positioning state, and determining, according to the processed data of the integrated navigation device and a preset positioning error threshold, an alarm condition corresponding to the preset positioning error threshold includes:

[0015] Determine a time series set corresponding to the non-differential state according to the positioning state and a positioning timestamp corresponding to the positioning state;

[0016] According to the time series set corresponding to the non-differential state, the state type of the non-differential state and the preset positioning error threshold, an alarm condition corresponding to the preset positioning error threshold is determined.

[0017] Optionally, the determining, according to the positioning state and the positioning timestamp corresponding to the positioning state, a time series set corresponding to the non-differential state includes:

[0018] Determine whether the time interval between any two adjacent positioning timestamps of the differential state is greater than a preset time interval;

[0019] If so, it is determined that there is processed data of a non-differential state between the two adjacent differential states, and the processed data corresponding to the non-differential state between the two adjacent differential states is recorded in a time series to obtain a time series set corresponding to the non-differential state.

[0020] Optionally, the state type of the non-differential state includes a track derivation state, and determining the alarm condition corresponding to the preset positioning error threshold according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold includes:

[0021] Based on the time series set corresponding to the non-differential state, determining a first time series subset in which the track derivation state does not exist;

[0022] A first alarm condition is determined according to the first time series subset and the preset positioning error threshold.

[0023] Optionally, the determining the first alarm condition according to the first time series subset and the preset positioning error threshold comprises:

[0024] Based on the positioning errors of each time series in the first time series subset, determining a plurality of maximum time series points at which the positioning errors in each time series do not exceed the preset positioning error threshold;

[0025] A time alarm threshold is determined according to a plurality of maximum time series points as the first alarm condition.

[0026] Optionally, the state type of the non-differential state includes a track derivation state, and determining the alarm condition corresponding to the preset positioning error threshold according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold includes:

[0027] Based on the time series set corresponding to the non-differential state, determining a second time series subset of the track derivation state;

[0028] A second alarm condition is determined according to the second time series subset and the preset positioning error threshold.

[0029] Optionally, the processed data of the integrated navigation device further includes the number of satellites corresponding to the positioning state, and the determining the second alarm condition according to the second time series subset and the preset positioning error threshold includes:

[0030] Determine, according to the second time series subset and the preset positioning error threshold, an optimal parameter combination among a satellite quantity threshold, a number threshold for satisfying the satellite quantity threshold, and a track deduction state quantity threshold;

[0031] The second alarm condition is determined according to the optimal parameter combination.

[0032] Optionally, the performing positioning alarm of the autonomous driving vehicle based on the alarm condition corresponding to the preset positioning error threshold comprises:

[0033] Determining a current driving scenario of the autonomous vehicle;

[0034] Acquire the corresponding alarm condition according to the above;

[0035] According to the alarm conditions corresponding to the current driving scene, a positioning alarm of the autonomous driving vehicle is performed.

[0036] In a second aspect, an embodiment of the present application further provides a positioning alarm device for an autonomous driving vehicle, wherein the device comprises:

[0037] An acquisition unit, used to acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device;

[0038] a processing unit, configured to process the first positioning data collected by the integrated navigation device based on the second positioning data collected by the true value device to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state;

[0039] a determination unit, configured to determine an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value;

[0040] An alarm unit is used to perform a positioning alarm for the autonomous driving vehicle based on an alarm condition corresponding to the preset positioning error threshold.

[0041] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0042] Processor; and

[0043] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.

[0044] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes any of the aforementioned methods.

[0045] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the positioning alarm method of the autonomous driving vehicle in the embodiments of the present application first obtains the first positioning data collected by the combined navigation device of the autonomous driving vehicle and the second positioning data collected by the true value device; then, based on the second positioning data collected by the true value device, the first positioning data collected by the combined navigation device is processed to obtain the processed data of the combined navigation device, the processed data of the combined navigation device includes the positioning state and the corresponding positioning error, and the positioning state includes the differential state and the non-differential state; then, according to the processed data of the combined navigation device and the preset positioning error threshold, the alarm condition corresponding to the preset positioning error threshold is determined; finally, based on the alarm condition corresponding to the preset positioning error threshold, the positioning alarm of the autonomous driving vehicle is performed. The positioning alarm method of the autonomous driving vehicle in the embodiments of the present application determines the positioning error of the combined navigation device based on the positioning data of the true value device, and further determines the corresponding alarm conditions in combination with the positioning state and the positioning accuracy requirements of different scenarios, thereby improving the accuracy of the positioning alarm of the autonomous driving vehicle, reducing the false alarm rate, and ensuring the positioning stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0047] Figure 1 A flowchart of a positioning alarm method for an autonomous driving vehicle in an embodiment of the present application;

[0048] Figure 2 This is a structural schematic diagram of a positioning alarm device for an autonomous driving vehicle in an embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0051] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0052] The present application embodiment provides a positioning alarm method for an autonomous driving vehicle, such as Figure 1 As shown, a flow chart of a method for positioning and alarming an autonomous driving vehicle in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S140:

[0053] Step S110, obtaining first positioning data collected by the combined navigation device of the autonomous driving vehicle and second positioning data collected by the true value device.

[0054] When performing a positioning alarm for an autonomous vehicle, the embodiment of the present application needs to first obtain first positioning data collected by a combined navigation device on the autonomous vehicle, and simultaneously obtain second positioning data collected by a true value device on the autonomous vehicle. The first positioning data here may specifically include data such as positioning timestamp, positioning posture, number of satellites, and positioning status. Since the second positioning data is positioning data collected by a high-precision true value device, it mainly includes data such as positioning timestamp and positioning posture.

[0055] Step S120, based on the second positioning data collected by the true value device, the first positioning data collected by the combined navigation device is processed to obtain processed data of the combined navigation device, the processed data of the combined navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state.

[0056] After obtaining two sets of positioning data collected by two devices, a series of processing needs to be performed on the first positioning data collected by the combined navigation device. Specifically, the two sets of positioning data can be aligned according to the positioning timestamps in the two sets of positioning data, that is, time synchronization processing can be performed, and then the positioning error of the positioning position collected by the combined navigation device is calculated based on the high-precision positioning position collected by the true value device. After the above processing, the processed data of the combined navigation device can be obtained, which may include data in dimensions such as positioning timestamp, positioning error, number of satellites, and positioning status.

[0057] The positioning state of the embodiment of the present application can be divided into a differential state and a non-differential state. The differential state can be understood as a fixed solution state. When positioning using carrier phase observations, ambiguity will be generated. The ambiguity is theoretically an integer. After the integer ambiguity is solved by the algorithm, that is, the fixed solution, the positioning accuracy will be greatly improved. The non-differential state is a non-fixed solution state, for example, it can include states such as floating point solution, single point solution, and track deduction solution. The positioning accuracy of these states is lower than the positioning accuracy of the fixed solution.

[0058] Step S130: determining an alarm condition corresponding to the preset positioning error threshold according to the processed data of the integrated navigation device and the preset positioning error threshold.

[0059] Different positioning scenarios have different requirements for positioning accuracy, and the allowable positioning errors are different, which leads to different conditions for triggering alarms. Therefore, after obtaining the processed data of the integrated navigation device, the embodiment of the present application needs to further determine the corresponding preset positioning error threshold, which can be set in advance based on the actual application scenario. Then, the alarm condition corresponding to the preset positioning error threshold is determined by combining the processed data of the integrated navigation device and the preset positioning error threshold.

[0060] Since the embodiment of the present application comprehensively considers the size of the positioning error corresponding to different positioning states and the size of the positioning error allowed by different positioning scenarios, it is possible to determine appropriate alarm conditions for subsequent positioning alarms, thereby improving the correct alarm rate while reducing the false alarm rate.

[0061] Step S140: Based on the alarm condition corresponding to the preset positioning error threshold, a positioning alarm of the automatic driving vehicle is performed.

[0062] After determining the corresponding alarm conditions in different positioning scenarios, the positioning alarm of the autonomous driving vehicle can be implemented according to the alarm conditions.

[0063] The positioning alarm method for the autonomous driving vehicle in the embodiment of the present application determines the positioning error of the combined navigation device based on the positioning data of the true value device, and further determines the corresponding alarm conditions in combination with the positioning status and the positioning accuracy requirements of different scenarios, thereby improving the accuracy of the positioning alarm of the autonomous driving vehicle, reducing the false alarm rate, and ensuring positioning stability.

[0064] In one embodiment of the present application, the processed data of the combined navigation device also includes a positioning timestamp corresponding to the positioning state, and determining the alarm condition corresponding to the preset positioning error threshold based on the processed data of the combined navigation device and a preset positioning error threshold includes: determining a time series set corresponding to the non-differential state based on the positioning state and the positioning timestamp corresponding to the positioning state; and determining the alarm condition corresponding to the preset positioning error threshold based on the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold.

[0065] As mentioned above, the differential state of the embodiment of the present application is a fixed solution state, so the positioning accuracy can be guaranteed at the centimeter level. The positioning error existing in this state is tolerable by the autonomous driving vehicle, while the non-differential state is a non-fixed solution state. The positioning accuracy varies according to the specific type of non-differential state, but is lower than the positioning accuracy in the differential state. The positioning error in the non-differential state will change with the accumulation of time. When the resulting positioning error exceeds the limit that the autonomous driving vehicle can tolerate, an alarm needs to be triggered.

[0066] Based on this, the embodiment of the present application focuses on the impact of the positioning results of the non-differential state on the positioning stability of the autonomous driving vehicle. Therefore, here, according to the various positioning states and their corresponding positioning timestamps in the processed data of the aforementioned embodiment, the time series set corresponding to the non-differential state can be determined. The reason why it is in the form of a time series set is that the appearance of the non-differential state may not always be continuous, such as the situation where the GNSS positioning signal is sometimes present and sometimes not. In addition, the different specific state types of the non-differential state will also affect the determination of the alarm condition. For example, there are differences in the size and change rules of the positioning error of the floating point solution, the single point solution and the track deduction solution. Therefore, based on the time series set corresponding to the non-differential state and the preset positioning error threshold, the corresponding alarm condition can be comprehensively determined in combination with the specific state type of the non-differential state.

[0067] In one embodiment of the present application, determining the time series set corresponding to the non-differential state based on the positioning state and the positioning timestamp corresponding to the positioning state includes: determining whether the time interval between the positioning timestamps of any two adjacent differential states is greater than a preset time interval; if so, determining that there is processed data of the non-differential state between the two adjacent differential states, and recording the processed data corresponding to the non-differential state between the two adjacent differential states into a time series to obtain the time series set corresponding to the non-differential state.

[0068] When determining the time series set corresponding to the non-differential state, the embodiment of the present application can be judged based on the positioning timestamps of any two adjacent differential states. Here, it is necessary to consider the frequency of the combined navigation device outputting positioning data. For example, the output frequency is 100HZ, that is, one positioning data is output every 0.01s. If the time interval between the positioning timestamps of two adjacent differential states is not greater than the preset time interval, that is, 0.01s, it means that there is no other non-differential state positioning data between the two adjacent differential states. If the time interval between the positioning timestamps of two adjacent differential states is greater than the preset time interval, it means that there must be non-differential state positioning data between the two adjacent differential states.

[0069] Since in the entire positioning process, once the positioning data in the differential state appears, a sufficiently high positioning accuracy can be guaranteed, the embodiment of the present application can record the processed data corresponding to all non-differential states between any two adjacent differential states into a time series, thereby obtaining a time series set Set, and the positioning data in each independent time series are numbered separately, for example, the positioning data in the time series Set-a are numbered a1, a2, a3... in chronological order, and the positioning data in the time series Set-b are numbered b1, b2, b3... in chronological order, and so on.

[0070] In order to facilitate the understanding of the embodiments of the present application, a group of processed data of the combined navigation device is provided, which can be specifically expressed in the form of the following Table 1:

[0071] Table 1

[0072]

[0073] It can be seen that there is no non-differential state between the T1 and T2 moments corresponding to two adjacent differential states, so there is no need to process the time series, and two non-differential states appear between the T2 and T5 moments corresponding to two adjacent differential states, and the corresponding moments are T3 and T4. At this time, the positioning data corresponding to T3 and T4 can be recorded in a time queue for storage. Similarly, a differential state appears between the T5 and T7 moments corresponding to two adjacent differential states, and the corresponding moment is T6. Then the positioning data corresponding to T6 can be recorded in another time queue for storage.

[0074] In one embodiment of the present application, the state type of the non-differential state includes a track deduction state, and determining the alarm condition corresponding to the preset positioning error threshold according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold includes: determining a first time series subset in which the track deduction state does not exist based on the time series set corresponding to the non-differential state; and determining a first alarm condition according to the first time series subset and the preset positioning error threshold.

[0075] As mentioned above, the state types of non-differential states may include track extrapolation states. Track extrapolation uses the position at a certain moment to extrapolate the current position based on the heading and speed information. That is, the position and driving trajectory of the autonomous driving vehicle are calculated based on the measured driving distance and heading of the autonomous driving vehicle. It is generally not affected by the external environment, but because its own error is accumulated over time, it cannot maintain high accuracy for a long time when working alone.

[0076] Therefore, the embodiments of the present application can adopt different strategies to determine the alarm condition according to whether there is positioning data of the track deduction state in the time series corresponding to the non-differential state. One strategy is to find a first time series subset in the time series set in which there is no track deduction state. The non-differential state contained in the time series in the first time series subset can be any type of state other than the track deduction state, such as a floating point solution or a single point solution. Finally, the first alarm condition is determined based on the first time series subset and a preset positioning error threshold. The first alarm condition here is mainly used to characterize the maximum time that the non-differential state can be allowed to exist under the set positioning error threshold.

[0077] In one embodiment of the present application, determining the first alarm condition based on the first time series subset and the preset positioning error threshold includes: based on the positioning errors of each time series in the first time series subset, determining multiple maximum time series points at which the positioning errors in each time series do not exceed the preset positioning error threshold; and determining a time alarm threshold based on the multiple maximum time series points as the first alarm condition.

[0078] The first time series subset obtained based on the aforementioned embodiment only includes positioning data of other types of non-differential states other than the track deduction state, such as floating-point solution or single-point solution state. Since the error of the floating-point solution or single-point solution will be unstable for a long time, the embodiment of the present application can determine the maximum time corresponding to the floating-point solution or single-point solution state within the allowable positioning error.

[0079] Specifically, based on the positioning errors of each time series in the first time series subset, multiple maximum time series points at which the positioning error in each time series does not exceed a preset positioning error threshold can be determined, and the time alarm threshold can be determined based on the multiple maximum time series points.

[0080] For example, assuming that there are three time series Set-a, Set-b, and Set-c in the first time series subset, the maximum time series point that does not exceed the preset positioning error threshold Thre_err in Set-a is the 10th time series point a10, the maximum time series point that does not exceed Thre_err in Set-b is the 12th time series point b12, and the maximum time series point that does not exceed Thre_err in Set-c is the 15th time series point c15. In order to improve the correct alarm rate and reduce the false alarm rate, the time alarm threshold can be determined based on the 10th time series point a10 in Set-a, the 12th time series point b12 in Set-b, and the 15th time series point c15 in Set-c.

[0081] Of course, the specific time series point to be selected to determine the time alarm threshold can be calculated and selected by those skilled in the art according to the actual required correct alarm rate and false alarm rate. For example, if the maximum time series point a10 in Set-a is selected to determine the time alarm threshold, then the corresponding cumulative time of a10 in the Set-a time series can be used as the time alarm threshold. When the cumulative time of the current positioning data being continuously in the floating point solution or single point solution state reaches the time alarm threshold, an alarm is triggered.

[0082] In one embodiment of the present application, the state type of the non-differential state includes a track deduction state, and determining the alarm condition corresponding to the preset positioning error threshold according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold includes: determining that a second time series subset of the track deduction state exists based on the time series set corresponding to the non-differential state; and determining a second alarm condition according to the second time series subset and the preset positioning error threshold.

[0083] Based on the aforementioned embodiments, different strategies can be adopted to determine the alarm condition according to whether there is positioning data of the track deduction state in the time series corresponding to the non-differential state. Therefore, another strategy adopted in the embodiment of the present application is to find a second time series subset in the time series set where the track deduction state exists. The non-differential state contained in the time series in the second time series subset may only contain the track deduction state, and of course, it may also contain any other type of non-differential state at the same time, such as a floating point solution or a single point solution. Finally, the second alarm condition is determined based on the second time series subset and the preset positioning error threshold.

[0084] In one embodiment of the present application, the processed data of the combined navigation device also includes the number of satellites corresponding to the positioning state, and determining the second alarm condition based on the second time series subset and the preset positioning error threshold includes: determining the optimal parameter combination among the satellite number threshold, the number threshold for satisfying the satellite number threshold, and the track deduction state number threshold based on the second time series subset and the preset positioning error threshold; and determining the second alarm condition based on the optimal parameter combination.

[0085] The processed data of the combined navigation device in the embodiment of the present application also includes information on the number of satellites. The more satellites there are and the longer the state of having a large number of satellites lasts, the better the quality of the positioning signal and the higher the positioning accuracy. The more track deduction states there are, the greater the cumulative error of the track deduction over time and the lower the positioning accuracy.

[0086] Based on this, an embodiment of the present application can construct an error model for the positioning data contained in the second time series subset and the preset positioning error threshold. The error model is used to measure the changing relationship between the positioning error and various parameters that affect the positioning error. The parameters here may include, for example, a satellite number threshold sat_num, a number threshold thre_sat that meets the satellite number threshold, and a track deduction state number threshold thre_dr, etc. Of course, the specific parameters that can be set can be flexibly defined by technicians in this field according to actual needs, and they are not listed here one by one.

[0087] For the threshold parameters of each of the above dimensions, an optimal parameter combination can be learned through the model training process. The purpose of this optimal parameter combination is to achieve a higher correct alarm rate and a lower false alarm rate. Therefore, the learned parameter combination can be used for verification and optimization on other data sets to achieve the required correct alarm rate and false alarm rate.

[0088] For example, assuming that in the optimal parameter combination, the satellite number threshold sat_num is 15, the number threshold thre_sat that meets the satellite number threshold is 100, and the track deduction state number threshold thre_dr is 600, then within a time series, if the number of times the number of satellites is less than 15 exceeds 100 cumulatively, or the number of track deduction states exceeds 600 cumulatively, the second alarm condition is met.

[0089] The process of determining the alarm condition in the above embodiment adopts a method of combining improving the correct alarm rate and reducing the false alarm rate, finds the optimal parameter threshold combination, minimizes the randomness of the combined navigation device error, and further improves the stability of the positioning output and its related outputs.

[0090] In one embodiment of the present application, the positioning alarm of the autonomous driving vehicle based on the alarm condition corresponding to the preset positioning error threshold includes: determining the current driving scene of the autonomous driving vehicle; obtaining the corresponding alarm condition; and performing a positioning alarm of the autonomous driving vehicle based on the alarm condition corresponding to the current driving scene.

[0091] The above-mentioned embodiments of the present application can collect relevant positioning data for different positioning scenarios, for example, it can cover common application scenarios of autonomous driving vehicles such as cities, canyons, tunnels, and under bridges, and define different preset positioning error thresholds according to the different requirements for positioning accuracy in different positioning scenarios, and then determine the alarm conditions for different positioning scenarios, and store these alarm conditions in advance in the configuration center of the autonomous driving system for subsequent calls.

[0092] In actual application, different alarm conditions can be selected according to different needs or scenarios. For example, the speed of an autonomous driving vehicle in an urban area is low and the scene is complex, so the subsequent modules have high requirements for positioning accuracy. At this time, the alarm conditions corresponding to a smaller positioning error threshold can be adaptively selected. On the other hand, the speed of an autonomous driving vehicle on an urban highway is high and the scene is simple, so the subsequent modules have relatively low requirements for positioning accuracy. At this time, the alarm conditions corresponding to a relatively larger positioning error threshold can be adaptively selected, thereby achieving adaptive and flexible adjustment of the alarm conditions according to the actual positioning scenario and needs.

[0093] The present application also provides a positioning alarm device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a schematic diagram of the structure of a positioning alarm device for an autonomous driving vehicle in an embodiment of the present application is provided, wherein the device 200 includes: an acquisition unit 210, a processing unit 220, a determination unit 230, and an alarm unit 240, wherein:

[0094] An acquisition unit 210 is used to acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device;

[0095] The processing unit 220 is used to process the first positioning data collected by the integrated navigation device based on the second positioning data collected by the true value device to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state;

[0096] A determination unit 230, configured to determine an alarm condition corresponding to a preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value;

[0097] The alarm unit 240 is used to perform a positioning alarm for the autonomous driving vehicle based on the alarm condition corresponding to the preset positioning error threshold.

[0098] In one embodiment of the present application, the processed data of the combined navigation device also includes a positioning timestamp corresponding to the positioning state, and the determination unit 230 is specifically used to: determine a time series set corresponding to the non-differential state according to the positioning state and the positioning timestamp corresponding to the positioning state; determine an alarm condition corresponding to the preset positioning error threshold according to the time series set corresponding to the non-differential state, the state type of the non-differential state and the preset positioning error threshold.

[0099] In one embodiment of the present application, the determination unit 230 is specifically used to: determine whether the time interval between the positioning timestamps of any two adjacent differential states is greater than a preset time interval; if so, determine that there is processed data of a non-differential state between the two adjacent differential states, and record the processed data corresponding to the non-differential state between the two adjacent differential states into a time series to obtain a time series set corresponding to the non-differential state.

[0100] In one embodiment of the present application, the state type of the non-differential state includes a track deduction state, and the determination unit 230 is specifically used to: determine a first time series subset in which the track deduction state does not exist based on a time series set corresponding to the non-differential state; and determine a first alarm condition based on the first time series subset and the preset positioning error threshold.

[0101] In one embodiment of the present application, the determination unit 230 is specifically used to: determine, based on the positioning errors of each time series in the first time series subset, multiple maximum time series points at which the positioning errors in each time series do not exceed the preset positioning error threshold; determine a time alarm threshold based on the multiple maximum time series points as the first alarm condition.

[0102] In one embodiment of the present application, the state type of the non-differential state includes a track deduction state, and the determination unit 230 is specifically used to: determine the existence of a second time series subset of the track deduction state based on the time series set corresponding to the non-differential state; and determine a second alarm condition based on the second time series subset and the preset positioning error threshold.

[0103] In one embodiment of the present application, the processed data of the combined navigation device also includes the number of satellites corresponding to the positioning status, and the determination unit 230 is specifically used to: determine the optimal parameter combination between the satellite number threshold, the number threshold for meeting the satellite number threshold, and the track deduction state number threshold based on the second time series subset and the preset positioning error threshold; and determine the second alarm condition based on the optimal parameter combination.

[0104] In one embodiment of the present application, the alarm unit 240 is specifically used to: determine the current driving scene of the autonomous driving vehicle; obtain the corresponding alarm conditions; and perform positioning alarm of the autonomous driving vehicle according to the alarm conditions corresponding to the current driving scene.

[0105] It can be understood that the positioning alarm device of the above-mentioned autonomous driving vehicle can implement the various steps of the positioning alarm method of the autonomous driving vehicle provided in the aforementioned embodiments. The relevant explanations about the positioning alarm method of the autonomous driving vehicle are applicable to the positioning alarm device of the autonomous driving vehicle and will not be repeated here.

[0106] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0107] The processor, network interface and memory can be interconnected through 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. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0108] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0109] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a positioning alarm device for the autonomous driving vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0110] Acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device;

[0111] Based on the second positioning data collected by the true value device, the first positioning data collected by the integrated navigation device is processed to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state;

[0112] Determining an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value;

[0113] Based on the alarm condition corresponding to the preset positioning error threshold, a positioning alarm of the autonomous driving vehicle is performed.

[0114] The above application Figure 1 The method performed by the positioning alarm device of the autonomous driving 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. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0115] The electronic device may also perform Figure 1 A method for executing a positioning alarm device of an autonomous driving vehicle in the present invention, and realizing a positioning alarm device of an autonomous driving vehicle in the present invention Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0116] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method performed by the positioning alarm device of the autonomous driving vehicle in the illustrated embodiment is specifically used to perform:

[0117] Acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device;

[0118] Based on the second positioning data collected by the true value device, the first positioning data collected by the integrated navigation device is processed to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state;

[0119] Determining an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value;

[0120] Based on the alarm condition corresponding to the preset positioning error threshold, a positioning alarm of the autonomous driving vehicle is performed.

[0121] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0122] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0126] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0127] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0128] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0130] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A positioning alarm method for an autonomous driving vehicle, wherein: The method comprises: Acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device; Based on the second positioning data collected by the true value device, the first positioning data collected by the integrated navigation device is processed to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state; Determining an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value; Based on the alarm condition corresponding to the preset positioning error threshold, performing a positioning alarm for the autonomous driving vehicle; The processed data of the integrated navigation device also includes a positioning timestamp corresponding to the positioning state, and the determining, based on the processed data of the integrated navigation device and a preset positioning error threshold, an alarm condition corresponding to the preset positioning error threshold includes: Determine a time series set corresponding to the non-differential state according to the positioning state and a positioning timestamp corresponding to the positioning state; According to the time series set corresponding to the non-differential state, the state type of the non-differential state and the preset positioning error threshold, an alarm condition corresponding to the preset positioning error threshold is determined.

2. The method of claim 1, wherein: The step of determining the time series set corresponding to the non-differential state according to the positioning state and the positioning timestamp corresponding to the positioning state includes: Determine whether the time interval between any two adjacent positioning timestamps of the differential state is greater than a preset time interval; If so, it is determined that there is processed data of a non-differential state between the two adjacent differential states, and the processed data corresponding to the non-differential state between the two adjacent differential states is recorded in a time series to obtain a time series set corresponding to the non-differential state.

3. The method of claim 1, wherein: The state type of the non-differential state includes a track deduction state, and the determining, according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold, the alarm condition corresponding to the preset positioning error threshold includes: Based on the time series set corresponding to the non-differential state, determining a first time series subset in which the track derivation state does not exist; A first alarm condition is determined according to the first time series subset and the preset positioning error threshold.

4. The method of claim 3, wherein: The determining of the first alarm condition according to the first time series subset and the preset positioning error threshold comprises: Based on the positioning errors of each time series in the first time series subset, determining a plurality of maximum time series points at which the positioning errors in each time series do not exceed the preset positioning error threshold; A time alarm threshold is determined according to a plurality of maximum time series points as the first alarm condition.

5. The method of claim 1, wherein: The state type of the non-differential state includes a track deduction state, and the determining, according to the time series set corresponding to the non-differential state, the state type of the non-differential state, and the preset positioning error threshold, the alarm condition corresponding to the preset positioning error threshold includes: Based on the time series set corresponding to the non-differential state, determining a second time series subset containing the track derivation state; A second alarm condition is determined according to the second time series subset and the preset positioning error threshold.

6. The method of claim 5, wherein: The processed data of the integrated navigation device also includes the number of satellites corresponding to the positioning state, and the determining the second alarm condition according to the second time series subset and the preset positioning error threshold includes: Determine, according to the second time series subset and the preset positioning error threshold, an optimal parameter combination among a satellite quantity threshold, a number threshold for satisfying the satellite quantity threshold, and a track deduction state quantity threshold; The second alarm condition is determined according to the optimal parameter combination.

7. The method according to any one of claims 1 to 6, wherein: The performing of the positioning alarm of the automatic driving vehicle based on the alarm condition corresponding to the preset positioning error threshold comprises: Determining a current driving scenario of the autonomous vehicle; Acquire corresponding alarm conditions according to the current driving scene; According to the alarm conditions corresponding to the current driving scene, a positioning alarm of the autonomous driving vehicle is performed.

8. A positioning alarm device for an autonomous driving vehicle, wherein: The device comprises: An acquisition unit, used to acquire first positioning data collected by a combined navigation device of the autonomous driving vehicle and second positioning data collected by a true value device; a processing unit, configured to process the first positioning data collected by the integrated navigation device based on the second positioning data collected by the true value device to obtain processed data of the integrated navigation device, wherein the processed data of the integrated navigation device includes a positioning state and a corresponding positioning error, and the positioning state includes a differential state and a non-differential state; a determination unit, configured to determine an alarm condition corresponding to the preset positioning error threshold value according to the processed data of the integrated navigation device and the preset positioning error threshold value; An alarm unit, configured to perform a positioning alarm of the autonomous driving vehicle based on an alarm condition corresponding to the preset positioning error threshold; The processed data of the integrated navigation device also includes a positioning timestamp corresponding to the positioning state, and the determining unit is specifically used for: Determine a time series set corresponding to the non-differential state according to the positioning state and a positioning timestamp corresponding to the positioning state; According to the time series set corresponding to the non-differential state, the state type of the non-differential state and the preset positioning error threshold, an alarm condition corresponding to the preset positioning error threshold is determined.

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

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.

Images