Vehicle integrated positioning method, device, electronic device, and storage medium

Abstract

The present application discloses a method, apparatus, electronic device, and storage medium for integrated positioning of a vehicle. The method includes: obtaining sensor data of the vehicle, specifically including observation data at the current moment and prediction data at the previous moment; determining an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the vehicle's sensor, where the preset sliding window stores threshold data of a preset time length; determining whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment; if it is normal, performing integrated positioning according to the observation data at the current moment to obtain an integrated positioning result of the vehicle. The present application determines the abnormal data threshold interval of the sensor in the current scenario based on the preset sliding window corresponding to different sensors, and realizes the dynamic calculation of the thresholds of different sensors in different scenarios by continuously updating the threshold data in the preset sliding window during the positioning process, improving the integrated positioning effect.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and particularly to a method and device for integrated positioning of a vehicle, an electronic device, and a storage medium. Background Art

[0002] Integrated positioning is the most important positioning technology in the field of autonomous driving. In the field of autonomous driving, multiple sensors are usually used to position a vehicle. For example, GPS (Global Positioning System), odometer, lidar, and camera, etc. Each type of sensor has its advantages and disadvantages and can only play an active role in a suitable environment. Therefore, the most commonly used method is to make up for the deficiencies of different types of sensors, and fuse their observation data or calculation results to obtain a more robust vehicle positioning result.

[0003] Performing integrated positioning based on different types of sensors is still a challenging research. One of the most important challenges is how to handle the problem of outliers of sensors. For example, how to avoid affecting the observation results of other sensors during the process of integrated positioning when a sensor generates incorrect information.

[0004] Existing solutions usually set a fixed threshold for the measurement results of different types of sensors according to empirical values, and discard the measurement values that exceed the threshold, so as to ensure the stability of the integrated positioning algorithm. For small-scale scenarios, the scenarios are relatively fixed, and most outliers can be filtered out by the above method of fixed threshold. However, for large-scale scenarios such as urban areas, the scenarios in different regions change significantly. If the threshold is too large, it is easy to introduce measurement errors and may discard valid measurement values. Therefore, filtering outliers by the method of fixed threshold will result in poor integrated positioning effect. Summary of the Invention

[0005] Embodiments of the present application provide a method and device for integrated positioning of a vehicle, an electronic device, and a storage medium, so as to realize dynamic calculation of the abnormal data threshold of different sensors in different scenarios and improve the integrated positioning accuracy.

[0006] Embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for integrated positioning of a vehicle, where the method includes:

[0008] Obtain sensor data of the vehicle, where the sensor data includes observation data at the current moment and prediction data at the previous moment;

[0009] Determine the abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle, where the threshold data of a preset time length is stored in the preset sliding window;

[0010] Determine whether the observed data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment;

[0011] When the observed data at the current moment is normal, perform fusion positioning according to the observed data at the current moment to obtain the fusion positioning result of the vehicle.

[0012] Optionally, the observed data at the current moment includes the observed position at the current moment, the predicted data at the previous moment includes the pose data at the previous moment, and the obtaining of the sensor data of the vehicle includes:

[0013] Obtain the pose data at the previous moment and the sensor measurement value at the current moment;

[0014] Determine the pose data at the current moment according to the pose data at the previous moment and the sensor measurement value at the current moment, and the pose data at the current moment includes the observed position at the current moment.

[0015] Optionally, the threshold data of the preset time length includes the relative distances between multiple observed positions and the corresponding predicted positions, and the determining of the abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle includes:

[0016] Determine the average value of the relative distances according to the relative distances between each observed position and the corresponding predicted position;

[0017] Determine the variance of the relative distances according to the relative distances between each observed position and the corresponding predicted position and the average value of the relative distances;

[0018] Determine the lower limit of the abnormal data threshold interval according to the difference between the average value of the relative distances and the variance of the relative distances;

[0019] Determine the upper limit of the abnormal data threshold interval according to the sum of the average value of the relative distances and the variance of the relative distances.

[0020] Optionally, the preset sliding window includes a buffer area, and the determining of the abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle includes:

[0021] Sort the multiple frames of threshold data stored in the preset sliding window;

[0022] Determine the threshold data in the buffer and the threshold data outside the buffer according to the sorting result;

[0023] Determine the abnormal data threshold interval at the current moment according to the threshold data outside the buffer.

[0024] Optionally, the observation data at the current moment includes the observation position at the current moment, the prediction data at the previous moment includes the prediction position at the previous moment, and determining whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment includes:

[0025] Determine the relative distance between the observation position at the current moment and the prediction position at the previous moment;

[0026] If the relative distance between the observation position at the current moment and the prediction position at the previous moment is within the abnormal data threshold interval, determine that the observation position at the current moment is normal;

[0027] Otherwise, determine that the observation position at the current moment is abnormal.

[0028] Optionally, after obtaining the sensor data of the vehicle, the method further includes:

[0029] Use the relative distance between the observation position at the current moment and the prediction position at the previous moment as a frame of threshold data and store it in the preset sliding window.

[0030] Optionally, using the relative distance between the observation position at the current moment and the prediction position at the previous moment as a frame of threshold data and storing it in the preset sliding window includes:

[0031] Determine whether the number of frames of the threshold data stored in the preset sliding window reaches the frame number threshold corresponding to the preset sliding window;

[0032] If so, delete the earliest frame of threshold data stored in the preset sliding window, and use the relative distance between the observation position at the current moment and the prediction position at the previous moment as the latest frame of threshold data and store it in the preset sliding window.

[0033] In a second aspect, an embodiment of the present application further provides a fusion positioning device for a vehicle, where the device includes:

[0034] An acquisition unit, configured to acquire sensor data of the vehicle, where the sensor data includes observation data at the current moment and prediction data at the previous moment;

[0035] A first determination unit, configured to determine an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to a sensor of the vehicle, where threshold data with a preset time length is stored in the preset sliding window;

[0036] A second determination unit, configured to determine whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment;

[0037] A fusion positioning unit, configured to perform fusion positioning according to the observation data at the current moment to obtain a fusion positioning result of the vehicle when the observation data at the current moment is normal.

[0038] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0039] A processor; and

[0040] A memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute any one of the foregoing methods.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute any one of the foregoing methods.

[0042] At least one of the foregoing technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: In the fusion positioning method of the vehicle in the embodiments of the present application, first, sensor data of the vehicle is acquired, where the sensor data includes observation data at the current moment and prediction data at the previous moment; then, an abnormal data threshold interval at the current moment is determined by using a preset sliding window corresponding to a sensor of the vehicle, and threshold data with a preset time length is stored in the preset sliding window; then, according to the sensor data and the abnormal data threshold interval at the current moment, it is determined whether the observation data at the current moment is abnormal; finally, when the observation data at the current moment is normal, fusion positioning is performed according to the observation data at the current moment to obtain a fusion positioning result of the vehicle. The fusion positioning method of the vehicle in the embodiments of the present application determines the abnormal data threshold interval of the sensor in the current scenario based on the preset sliding window corresponding to different sensors. During the positioning process, the threshold data in the preset sliding window is continuously updated, so as to realize the dynamic calculation of the thresholds of different sensors in different scenarios, ensure that the fusion positioning algorithm can run in the full scenario, and effectively improve the accuracy and robustness of the fusion positioning algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings described herein are used to provide a further understanding of the present application and form 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 to the present application. In the drawings:

[0044] Figure 1 is a schematic flow chart of a method for integrated positioning of a vehicle in an embodiment of the present application;

[0045] Figure 2 is a schematic structural diagram of an integrated positioning device for a vehicle in an embodiment of the present application;

[0046] Figure 3 is a schematic structural diagram of an electronic device in an embodiment of the present application. Detailed Description of the Embodiments

[0047] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0048] The following will describe in detail the technical solutions provided by each embodiment of the present application with reference to the drawings.

[0049] An embodiment of the present application provides a method for integrated positioning of a vehicle. As Figure 1 shown, a schematic flow chart of a method for integrated positioning of a vehicle in an embodiment of the present application is provided. The method at least includes the following steps S110 to S140:

[0050] Step S110: Obtain the sensor data of the vehicle. The sensor data includes the observation data at the current moment and the prediction data at the previous moment.

[0051] In an embodiment of the present application, it is necessary to first obtain the sensor data of the vehicle, specifically including the observation data of the sensors installed on the vehicle at the current moment and the prediction data at the previous moment. Here, the observation data can be regarded as the measurement data obtained by the sensors after calculating the real-time collected data according to a certain observation model, and the prediction data can be regarded as the integrated positioning result output after integrated positioning at the previous moment.

[0052] Step S120: Use a preset sliding window corresponding to the sensors of the vehicle to determine the abnormal data threshold interval at the current moment. The preset sliding window stores threshold data of a preset time length.

[0053] It should be noted that the sensors in the embodiments of the present application can refer to any type of sensor installed in a vehicle, such as GPS, odometer, lidar, or camera, etc. The processes of the embodiments of the present application can be respectively executed for the data of each sensor.

[0054] Since the data collection frequencies of sensors of different modalities are different, the embodiments of the present application define independent sliding window sizes W for sensors of different modalities. m , and there is no specific standard for setting the sliding window size. The number of data frames collected by the sensor within a certain time length, such as 1 s, can be used as its sliding window size. For example, if a lidar can collect 10 frames within 1 s, then the sliding window size W of the lidar sensor of this modality lidar can be set to 10; while a commonly used camera can collect 30 frame image data within 1 s, then the sliding window size W of the camera sensor of this modality cam can be set to 30, and so on.

[0055] The preset sliding window corresponding to the sensor defined in the embodiments of the present application is mainly used to store the threshold data of the sensor within a period of time. The threshold data can be specifically calculated according to the observation data and the corresponding prediction data output by the sensor in real time, so as to measure whether the data currently collected by the sensor is abnormal. Since the data stored in the preset sliding window is updated in real time according to the actual driving scenario, the dynamic calculation of the abnormal data threshold interval of the sensor in different scenarios can be realized, improving the fusion positioning accuracy.

[0056] Step S130, determine whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment.

[0057] It should be noted that the "abnormal data threshold interval" defined in the embodiments of the present application can be a threshold range, or of course a specific value, which can be flexibly determined according to different driving scenarios. For example, in a scenario where the road is smooth and the data fluctuation is very small, then a specific value can be used as the threshold for judgment. While in a bumpy road section, the data fluctuation is also large, then using a threshold range for judgment is more in line with the actual scenario.

[0058] In specific judgment, the above sensor data can be compared with the abnormal data threshold interval at the corresponding current moment, so as to determine whether the observation data output by the sensor at the current moment is abnormal data according to the comparison result, that is, whether it can be used for subsequent fusion positioning.

[0059] Step S140, when the observation data at the current moment is normal, perform fusion positioning according to the observation data at the current moment to obtain the fusion positioning result of the vehicle.

[0060] If the observation data at the current moment is determined to be normal in the foregoing steps, indicating that it can be used for fusion positioning processing, then at this time, the observation data of this sensor can be fused with the data output by other sensors to obtain the fusion positioning result of the vehicle at the current moment.

[0061] The above fusion positioning method can adopt, for example, the Extended Kalman Filter (EKF) or other fusion positioning methods, which are not specifically limited herein.

[0062] The fusion positioning method of the vehicle in the embodiments of the present application determines the abnormal data threshold interval of this sensor in the current scenario based on the preset sliding window corresponding to different sensors. During the positioning process, by continuously updating the threshold data in the preset sliding window, the dynamic calculation of the thresholds of different sensors in different scenarios is realized, ensuring that the fusion positioning algorithm can operate in the full scenario and effectively improving the accuracy and robustness of the fusion positioning algorithm.

[0063] In an embodiment of the present application, the observation data at the current moment includes the observed position at the current moment, the predicted data at the previous moment includes the pose data at the previous moment, and the obtaining of the sensor data of the vehicle includes: obtaining the pose data at the previous moment and the sensor measurement value at the current moment; determining the pose data at the current moment according to the pose data at the previous moment and the sensor measurement value at the current moment, and the pose data at the current moment includes the observed position at the current moment.

[0064] The observation data at the current moment in the embodiments of the present application may specifically include the observed position p at the current moment t k The predicted data at the previous moment specifically refers to the pose data T at the previous moment t m including the predicted position p and the rotation matrix R at the previous moment. k-1 k-1 k-1 According to the predicted positioning pose T of the vehicle at time t

[0065] k-1 and the sensor measurement value V at time t k-1 k-1 k k m m the pose T of the vehicle at time t k m m m m k-1 k-1 k k m m k-1 k-1 k k k-1 k-1from 0 to t k The relative position up to t is calculated to obtain t k The observed position p at time t m .

[0066] The above sensor measurement values can be regarded as the data actually collected by sensors of each modality. For example, the image data collected by a camera, the position coordinates collected by GPS, etc.

[0067] In an embodiment of the present application, the threshold data of the preset time length includes the relative distances between multiple observed positions and the corresponding predicted positions. The determining of the abnormal data threshold interval at the current moment by using the corresponding preset sliding window of the vehicle's sensors includes: determining the average value of the relative distances according to the relative distances between each observed position and the corresponding predicted position; determining the variance of the relative distances according to the relative distances between each observed position and the corresponding predicted position and the average value of the relative distances; determining the lower limit of the abnormal data threshold interval according to the difference between the average value of the relative distances and the variance of the relative distances; determining the upper limit of the abnormal data threshold interval according to the sum of the average value of the relative distances and the variance of the relative distances.

[0068] The threshold data in the embodiment of the present application may specifically include multiple observed positions p m and the relative distance d between the corresponding predicted positions p m , for example, the Euclidean distance can be used for calculation:

[0069] d m = ||p m - p|| 2 , (1)

[0070] After that, according to the magnitudes of multiple relative distances, the average value of the relative distances can be calculated and the variance δ m , which can be specifically expressed in the following form:

[0071]

[0072]

[0073] where

[0074] Finally, according to the difference between the average value of the relative distances and the variance δ of the relative distances m the lower limit of the abnormal data threshold interval can be calculated , that is According to the average value of the relative distances and the variance δ of the relative distances mThe sum can be calculated to obtain the abnormal data threshold range. The upper limit of If the relative distance calculated at the current moment is within the above abnormal data threshold range it can be considered that the observation data of the sensor at the current moment is normal data. That is to say, this calculation method indicates that the fluctuation of the relative distance is relatively normal within one variance range above and below the average value.

[0075] The above calculation method can also be expressed as:

[0076]

[0077] In an embodiment of the present application, the preset sliding window includes a buffer area. The method for determining the abnormal data threshold range at the current moment by using the preset sliding window corresponding to the sensor of the vehicle includes: sorting multiple frames of threshold data stored in the preset sliding window; determining the threshold data in the buffer area and the threshold data outside the buffer area according to the sorting result; and determining the abnormal data threshold range at the current moment according to the threshold data outside the buffer area.

[0078] A buffer area is also set in the preset sliding window of the embodiment of the present application, and the threshold data falling into the buffer area will not participate in the calculation of the abnormal data threshold range. Specifically, multiple frames of threshold data stored in the current preset sliding window, such as the relative distance in the above embodiment, are sorted in ascending or descending order. Normally, the data sizes of the calculated multiple frames of relative distances should be relatively close. At this time, if there are individual abnormal relative distance data, then after the above sorting, the relatively large relative distance data will be screened out. Therefore, the buffer area can be set at one end of the preset sliding window to store these extremely individual abnormal relative distance data, avoiding these abnormal relative distance data from participating in the calculation of the abnormal data threshold range, and further avoiding the problem that abnormal data collected by the sensor cannot be effectively filtered out subsequently.

[0079] The size of the buffer area can be flexibly set according to the actual scenario. For example, assuming the size of the preset sliding window is W m then the size of the buffer area can be set to C m = 0.2×W m When the size of the preset sliding window is 10, the size of the buffer area is 2, that is, 2 frames of data fall into the buffer area and do not participate in the calculation of the abnormal data threshold range. Among them, 0.2 is an empirical value and can be flexibly adjusted according to the actual scenario. Therefore, for N in the above formula (3) m it can be determined as:

[0080] N m = Wm -C m , (5)

[0081] For ease of understanding of the embodiments of the present application, further examples are given. Assume that the current vehicle has been driving on a relatively smooth section of the road, and the fluctuation of the relative distance data is small. Then, the abnormal data threshold interval calculated therefrom will also be within a very small fluctuation range. At this time, if a frame of data with a relatively large relative distance suddenly appears, this data will be stored in the preset sliding window and re-sorted with the previous relative distance data. Obviously, this data will fall into the buffer due to a large deviation from other data, thereby avoiding the influence of this single outlier on the calculation of the abnormal data threshold interval.

[0082] In addition, it should be noted that for the observation data obtained in real time by the sensor in the embodiments of the present application, the corresponding relative distance data will be calculated and stored in the preset sliding window, that is, the storage operation does not need to distinguish whether the data is abnormal.

[0083] Specifically, consider such a scenario. When the vehicle suddenly drives from a smooth section of the road to a bumpy section, the data fluctuation will become larger. At this time, based on the abnormal data threshold interval determined from the previous data, the current observation data will be considered abnormal data. If this data is directly filtered out, that is, the corresponding relative distance data is not calculated and stored in the preset sliding window, although it may not affect the processing of a few frames of data, but if accumulated for a long time, since each observation data obtained in this bumpy section may be considered abnormal data and filtered out, the abnormal data threshold interval will never be effectively updated. And because the abnormal data threshold interval cannot be updated, it will continue to affect the storage of the relative distance data. In this way, a cycle will occur, resulting in the inability to effectively filter abnormal data in the bumpy section, thereby affecting the fusion positioning accuracy.

[0084] Considering the above scenario, the present application provides a buffer in the preset sliding window. When only one or a few frames of relative distance data have a large deviation from the previous data, these data will fall into the buffer through sorting, thus not affecting the calculation of the abnormal data threshold interval. And if, over time, the amount of data with a large deviation from the previous data increases, then after re-sorting, these data will fall into the non-buffer area, so that they can participate in the calculation of the abnormal data threshold interval, thus meeting the requirement of dynamically calculating the abnormal data threshold interval in scenarios such as bumpy sections. Therefore, the setting of the buffer in the embodiments of the present application can realize the dynamic calculation of the abnormal data threshold interval in different scenarios.

[0085] In an embodiment of the present application, the observation data at the current moment includes the observed position at the current moment, and the prediction data at the previous moment includes the predicted position at the previous moment. Determining whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment includes: determining the relative distance between the observed position at the current moment and the predicted position at the previous moment; if the relative distance between the observed position at the current moment and the predicted position at the previous moment is within the abnormal data threshold interval, it is determined that the observed position at the current moment is normal; otherwise, it is determined that the observed position at the current moment is abnormal.

[0086] As described above, the abnormal data threshold interval in the embodiment of the present application is determined based on the relative distance between the observed position and the predicted position. Therefore, when determining whether the observation data at the current moment is abnormal data, the relative distance between the observed position at the current moment and the predicted position at the previous moment can be calculated first. Then judge this relative distance whether it falls into the abnormal data threshold interval If it falls into this interval, it means that the relative distance corresponding observed position is within the normal fluctuation range and can be used for the current fusion positioning. Otherwise, it is abnormal data and cannot be used for the current fusion positioning process.

[0087] In an embodiment of the present application, after obtaining the sensor data of the vehicle, the method further includes: storing the relative distance between the observed position at the current moment and the predicted position at the previous moment as a frame of threshold data into the preset sliding window.

[0088] As described above, after obtaining the observation data of the vehicle at the current moment in the embodiment of the present application, it is not necessary to pay attention to whether the observation data is abnormal, and the corresponding threshold data can be directly stored into the preset sliding window. Because if compared with the data previously stored in the preset sliding window, the threshold data corresponding to this observation is only a single abnormal data, then this threshold data will fall into the buffer zone set in the preset sliding window and will not affect the calculation of the abnormal data threshold interval. And if compared with the data previously stored in the preset sliding window, multiple abnormal threshold data are continuously obtained, then these data will also be readjusted to the abnormal data threshold interval due to the existence of the buffer zone, so as to flexibly adapt to different scenarios.

[0089] In one embodiment of the present application, storing the relative distance between the observed position at the current moment and the predicted position at the previous moment as a frame of threshold data in the preset sliding window includes: determining whether the number of frames of the threshold data stored in the preset sliding window reaches the frame number threshold corresponding to the preset sliding window; if so, deleting the earliest frame of threshold data stored in the preset sliding window, and storing the relative distance between the observed position at the current moment and the predicted position at the previous moment as the latest frame of threshold data in the preset sliding window.

[0090] Since the size of the preset sliding window is predefined in advance, that is, the storage space is limited. Therefore, when storing the threshold data corresponding to the current moment in the preset sliding window, it can be first determined whether the amount of the threshold data stored in the preset sliding window reaches the frame number threshold corresponding to the preset sliding window. For example, the preset sliding window corresponding to the lidar is 10. If the number of frames of the threshold data already stored in the current preset sliding window has reached 10 frames, then when storing the new threshold data in the preset sliding window, the earliest frame of threshold data previously stored can be deleted from the preset sliding window first, and then the latest threshold data can be stored. This is similar to the processing logic of a queue, so as to ensure that the latest data is always stored in the preset sliding window.

[0091] An embodiment of the present application further provides a fusion positioning device 200 for a vehicle, as Figure 2 shown, which provides a structural schematic diagram of a fusion positioning device for a vehicle in an embodiment of the present application. The device 200 includes: an acquisition unit 210, a first determination unit 220, a second determination unit 230, and a fusion positioning unit 240, where:

[0092] The acquisition unit 210 is configured to acquire sensor data of the vehicle, and the sensor data includes observed data at the current moment and predicted data at the previous moment;

[0093] The first determination unit 220 is configured to determine an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the vehicle's sensor, and the preset sliding window stores threshold data with a preset time length;

[0094] The second determination unit 230 is configured to determine whether the observed data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment;

[0095] The fusion positioning unit 240 is configured to perform fusion positioning according to the observed data at the current moment to obtain a fusion positioning result of the vehicle when the observed data at the current moment is normal.

[0096] In an embodiment of the present application, the observation data at the current moment includes the observed position at the current moment, and the prediction data at the previous moment includes the pose data at the previous moment. The obtaining unit 210 is specifically configured to: obtain the pose data at the previous moment and the sensor measurement value at the current moment; determine the pose data at the current moment according to the pose data at the previous moment and the sensor measurement value at the current moment, and the pose data at the current moment includes the observed position at the current moment.

[0097] In an embodiment of the present application, the threshold data of the preset time length includes the relative distances between multiple observed positions and the corresponding predicted positions. The first determining unit 220 is specifically configured to: determine the average value of the relative distances according to the relative distances between each observed position and the corresponding predicted position; determine the variance of the relative distances according to the relative distances between each observed position and the corresponding predicted position and the average value of the relative distances; determine the lower limit of the abnormal data threshold interval according to the difference between the average value of the relative distances and the variance of the relative distances; determine the upper limit of the abnormal data threshold interval according to the sum of the average value of the relative distances and the variance of the relative distances.

[0098] In an embodiment of the present application, the preset sliding window includes a buffer area. The first determining unit 220 is specifically configured to: sort the multiple frames of threshold data stored in the preset sliding window; determine the threshold data in the buffer area and the threshold data outside the buffer area according to the sorting result; determine the abnormal data threshold interval at the current moment according to the threshold data outside the buffer area.

[0099] In an embodiment of the present application, the observation data at the current moment includes the observed position at the current moment, and the prediction data at the previous moment includes the predicted position at the previous moment. The second determining unit 230 is specifically configured to: determine the relative distance between the observed position at the current moment and the predicted position at the previous moment; if the relative distance between the observed position at the current moment and the predicted position at the previous moment is within the abnormal data threshold interval, determine that the observed position at the current moment is normal; otherwise, determine that the observed position at the current moment is abnormal.

[0100] In an embodiment of the present application, the device further includes: a storage unit, configured to store the relative distance between the observed position at the current moment and the predicted position at the previous moment as a frame of threshold data into the preset sliding window.

[0101] In one embodiment of the present application, the storage unit is specifically configured to: determine whether the number of frames of the threshold data stored in the preset sliding window reaches the frame number threshold corresponding to the preset sliding window; if so, delete the earliest frame of threshold data stored in the preset sliding window, and use the relative distance between the observed position at the current moment and the predicted position at the previous moment as the latest frame of threshold data, and store it in the preset sliding window.

[0102] It can be understood that the above-mentioned vehicle fusion positioning device can implement each step of the vehicle fusion positioning method provided in the foregoing embodiment. The relevant explanations regarding the vehicle fusion positioning method are applicable to the vehicle fusion positioning device and will not be elaborated here.

[0103] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to 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. Among them, the memory may include internal memory, such as high-speed random access memory (Random-Access Memory, RAM), and may also include non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0104] 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, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 3 only a bidirectional arrow is used in [diagram] for illustration, but it does not mean that there is only one bus or one type of bus.

[0105] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provide instructions and data to the processor.

[0106] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, and forms a vehicle fusion positioning device at the logical level. The processor executes the program stored in the memory and is specifically configured to perform the following operations:

[0107] Obtain sensor data of a vehicle, where the sensor data includes observation data at the current moment and prediction data at the previous moment;

[0108] Use a preset sliding window corresponding to the sensors of the vehicle to determine the abnormal data threshold interval at the current moment, where the preset sliding window stores threshold data of a preset time length;

[0109] Determine whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment;

[0110] When the observation data at the current moment is normal, perform fusion positioning according to the observation data at the current moment to obtain the fusion positioning result of the vehicle.

[0111] The method executed by the vehicle fusion positioning device disclosed in the above embodiments of the present application Figure 1 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 the integrated logic circuit in the hardware of the processor or by instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium 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. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0112] The electronic device can also execute Figure 1 the method executed by the vehicle fusion positioning device inFigure 1 The functions of the illustrated embodiments will not be elaborated herein for the embodiments of this application.

[0113] The embodiments of this application also propose a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 1 the method executed by the vehicle's fusion positioning device in the illustrated embodiments, and specifically used to execute:

[0114] Obtain the sensor data of the vehicle, where the sensor data includes the observation data at the current moment and the prediction data at the previous moment;

[0115] Use the preset sliding window corresponding to the vehicle's sensors to determine the abnormal data threshold interval at the current moment, and the preset sliding window stores threshold data with a preset time length;

[0116] Determine whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment;

[0117] When the observation data at the current moment is normal, perform fusion positioning according to the observation data at the current moment to obtain the fusion positioning result of the vehicle.

[0118] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0119] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0120] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0122] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0123] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0124] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The 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 technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0125] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

[0126] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can 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.

[0127] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A fusion positioning method for a vehicle, wherein, The method includes: Obtaining sensor data of the vehicle, where the sensor data includes observation data at the current moment and prediction data at the previous moment; Determining an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle, and threshold data of a preset time length is stored in the preset sliding window; Determining whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment; When the observation data at the current moment is normal, performing fusion positioning according to the observation data at the current moment to obtain a fusion positioning result of the vehicle; The threshold data of the preset time length includes relative distances between multiple observation positions and corresponding prediction positions, and the determining an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle includes: Determining an average value of the relative distances according to the relative distances between each observation position and the corresponding prediction position; Determining a variance of the relative distances according to the relative distances between each observation position and the corresponding prediction position and the average value of the relative distances; Determining a lower limit of the abnormal data threshold interval according to a difference between the average value of the relative distances and the variance of the relative distances; Determining an upper limit of the abnormal data threshold interval according to a sum of the average value of the relative distances and the variance of the relative distances.

2. The method according to claim 1, wherein The observation data at the current moment includes an observation position at the current moment, and the prediction data at the previous moment includes pose data at the previous moment. The obtaining sensor data of the vehicle includes: Obtaining the pose data at the previous moment and sensor measurement values at the current moment; Determining pose data at the current moment according to the pose data at the previous moment and the sensor measurement values at the current moment, and the pose data at the current moment includes the observation position at the current moment.

3. The method according to claim 1, wherein The preset sliding window includes a buffer area, and the determining an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the sensors of the vehicle includes: Sorting multiple frames of threshold data stored in the preset sliding window; Determining threshold data in the buffer area and threshold data outside the buffer area according to the sorting result; Determining the abnormal data threshold interval at the current moment according to the threshold data outside the buffer area.

4. The method according to claim 1, wherein The observation data at the current moment includes an observation position at the current moment, and the prediction data at the previous moment includes a prediction position at the previous moment. The determining whether the observation data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment includes: Determining a relative distance between the observation position at the current moment and the prediction position at the previous moment; If the relative distance between the observation position at the current moment and the prediction position at the previous moment is within the abnormal data threshold interval, determining that the observation position at the current moment is normal; Otherwise, determining that the observation position at the current moment is abnormal.

5. The method according to claim 4, wherein After obtaining the sensor data of the vehicle, the method further includes: Take the relative distance between the observed position at the current moment and the predicted position at the previous moment as a frame of threshold data, and store it in the preset sliding window.

6. The method according to claim 5, wherein, The step of taking the relative distance between the observed position at the current moment and the predicted position at the previous moment as a frame of threshold data and storing it in the preset sliding window includes: Determine whether the number of frames of threshold data stored in the preset sliding window reaches the frame number threshold corresponding to the preset sliding window; If so, delete the earliest frame of threshold data stored in the preset sliding window, and take the relative distance between the observed position at the current moment and the predicted position at the previous moment as the latest frame of threshold data, and store it in the preset sliding window.

7. An integrated positioning device for a vehicle, wherein, The device includes: An acquisition unit, configured to acquire sensor data of a vehicle, where the sensor data includes observed data at the current moment and predicted data at the previous moment; A first determination unit, configured to determine an abnormal data threshold interval at the current moment by using a preset sliding window corresponding to the vehicle's sensor, and the preset sliding window stores threshold data with a preset time length; A second determination unit, configured to determine whether the observed data at the current moment is abnormal according to the sensor data and the abnormal data threshold interval at the current moment; A fusion positioning unit, configured to perform fusion positioning according to the observed data at the current moment to obtain a fusion positioning result of the vehicle when the observed data at the current moment is normal; The threshold data with the preset time length includes relative distances between multiple observed positions and corresponding predicted positions, and the first determination unit is specifically configured to: Determine the average value of the relative distances according to the relative distances between each observed position and the corresponding predicted position; Determine the variance of the relative distances according to the relative distances between each observed position and the corresponding predicted position and the average value of the relative distances; Determine the lower limit of the abnormal data threshold interval according to the difference between the average value of the relative distances and the variance of the relative distances; Determine the upper limit of the abnormal data threshold interval according to the sum of the average value of the relative distances and the variance of the relative distances.

8. An electronic device, comprising: A processor; And A memory arranged to store computer-executable instructions, and when the executable instructions are executed, the processor executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the method according to any one of claims 1 to 6.

Images