Unmanned vehicle positioning anomaly detection method, device, storage medium and electronic equipment

Abstract

The present disclosure relates to a method, device, storage medium and electronic device for detecting anomalies in positioning of an unmanned vehicle, and relates to the technical field of unmanned vehicles. The method comprises: calculating a first driving trajectory of the unmanned vehicle within a preset time period based on the vehicle status information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle, wherein the vehicle status information is used to characterize the vehicle status of the unmanned vehicle at the initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period; obtaining a second driving trajectory recorded by the positioning module of the unmanned vehicle within the preset time period; and determining whether the positioning module of the unmanned vehicle has an anomaly based on the first driving trajectory and the second driving trajectory. The beneficial effects of the present disclosure are: not only is the degree of automation high, reducing the labor cost of determining anomalies in the positioning module, but also being able to monitor in real time whether the positioning module of the unmanned vehicle has an anomaly, thereby adjusting the automatic driving strategy of the unmanned vehicle in a timely manner.

Description

Technical Field

[0001] The present disclosure relates to the technical field of unmanned vehicles, and in particular to a method, device, storage medium, and electronic device for detecting positioning anomalies of an unmanned vehicle. Background Art

[0002] Unmanned vehicles generally include functional modules such as perception, positioning, high-precision maps, prediction, decision-making, path planning, and control. Among them, the positioning module is responsible for outputting information such as the current position and posture of the unmanned vehicle. The control module calculates the vehicle's throttle, brake, steering wheel angle and other vehicle control variables based on the received information such as the current position and posture of the unmanned vehicle, thereby controlling the unmanned vehicle to track the desired trajectory.

[0003] However, during the operation of autonomous vehicles, the positioning module's output often deviates from the vehicle's actual value, or the positioning module's output suddenly deviates from the vehicle's actual value. These anomalies can cause the vehicle to swerve, stray from its planned trajectory, and other issues that affect its safe and stable operation. Due to the high degree of coupling between the various functional modules in the autonomous driving system, when a positioning module anomaly occurs, it is extremely difficult to determine the cause, often requiring extensive analysis and troubleshooting.

[0004] In typical technical solutions, identifying positioning module anomalies primarily relies on observing the alignment of the curb point cloud lines scanned by the LiDAR with the curb lines on the high-precision map. A significant deviation indicates a positioning module anomaly. However, this detection method relies on visual inspection by human inspectors, which is labor-intensive and incapable of real-time detection of positioning module anomalies. When an unmanned vehicle drives based on erroneous information output by the positioning module, safety issues are highly likely to arise. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a method, device, storage medium and electronic device for detecting anomalies in positioning of an unmanned vehicle, which can partially solve the above-mentioned problems existing in the related art.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for detecting positioning anomalies of an unmanned vehicle is provided, comprising:

[0007] Calculating a first driving trajectory of the unmanned vehicle within a preset time period based on vehicle state information of the unmanned vehicle and a vehicle control amount of the unmanned vehicle, wherein the vehicle state information is used to represent the vehicle state of the unmanned vehicle at an initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period;

[0008] Obtaining a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period;

[0009] According to the first driving trajectory and the second driving trajectory, it is determined whether a positioning module of the unmanned vehicle has an abnormality.

[0010] In some embodiments, determining whether a positioning module of the unmanned vehicle is abnormal based on the first driving trajectory and the second driving trajectory includes:

[0011] calculating a trajectory error between the first driving trajectory and the second driving trajectory;

[0012] When the trajectory error is greater than a preset threshold, it is determined that an abnormality occurs in the positioning module of the unmanned vehicle.

[0013] In some embodiments, calculating the trajectory error between the first driving trajectory and the second driving trajectory includes:

[0014] Calculating the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time;

[0015] A trajectory error between the first driving trajectory and the second driving trajectory is obtained by calculating the distances between a plurality of trajectory points at the same time.

[0016] In some embodiments, calculating the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time includes:

[0017] calculating a longitudinal distance between a projection of a first trajectory point in the first driving trajectory in a tangential direction of the second driving trajectory at the second trajectory point and the second trajectory point, and / or calculating a lateral distance between a projection of the first trajectory point in a normal direction of the second driving trajectory at the second trajectory point and the second trajectory point, wherein the second trajectory point is a trajectory point in the second driving trajectory at the same time as the first trajectory point;

[0018] The calculating the trajectory error between the first driving trajectory and the second driving trajectory according to the distances between the plurality of trajectory points at the same time includes:

[0019] A trajectory error between the first driving trajectory and the second driving trajectory is obtained according to the longitudinal distances and / or the lateral distances between the plurality of pairs of first trajectory points and the second trajectory points.

[0020] In some embodiments, the preset threshold is obtained by the following steps:

[0021] Obtaining a third driving trajectory of the unmanned vehicle during a historical period, calculated based on vehicle state information at an initial moment of the historical period and a vehicle control amount during the historical period;

[0022] Obtaining positioning data collected by the unmanned vehicle through the positioning module during the historical period;

[0023] Correcting the positioning data to obtain real positioning data of the unmanned vehicle in the historical period, and determining a fourth driving trajectory of the unmanned vehicle in the historical period based on the real positioning data;

[0024] The preset threshold is determined based on a difference between the third driving trajectory and the fourth driving trajectory.

[0025] In some embodiments, calculating a first driving trajectory of the unmanned vehicle within a preset time period based on the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle includes:

[0026] Inputting the vehicle state information and the vehicle control variable into a vehicle motion model to obtain the first driving trajectory output by the vehicle motion model;

[0027] In which, the vehicle control quantity includes the vehicle control quantity sampled at multiple sampling moments within the preset time length, and the vehicle motion model is used to calculate the vehicle state from the adoption moment to the next sampling moment of the adoption moment based on the vehicle control quantity collected at the adoption moment and the vehicle state of the unmanned vehicle at the sampling moment.

[0028] In some embodiments, the vehicle status information includes the position information, posture information, and speed information of the unmanned vehicle, and the vehicle control quantity includes the steering information and acceleration information of the unmanned vehicle.

[0029] According to a second aspect of an embodiment of the present disclosure, a device for detecting positioning anomalies of an unmanned vehicle is provided, comprising:

[0030] a trajectory prediction module configured to calculate a first driving trajectory of the unmanned vehicle within a preset time period based on vehicle state information of the unmanned vehicle and a vehicle control amount of the unmanned vehicle, wherein the vehicle state information is used to represent the vehicle state of the unmanned vehicle at an initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period;

[0031] a trajectory recording module, configured to obtain a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period;

[0032] The detection module is configured to determine whether an abnormality occurs in the positioning module of the unmanned vehicle based on the first driving trajectory and the second driving trajectory.

[0033] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the method described in any one of the above embodiments are implemented.

[0034] According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic device, including:

[0035] a memory having a computer program stored thereon;

[0036] A processor is used to execute the computer program in the memory to implement the steps of the method in any one of the above embodiments.

[0037] Based on the above technical solution, a first driving trajectory of the unmanned vehicle is generated according to the vehicle state of the unmanned vehicle at the initial moment of a preset time and the vehicle control amount of the unmanned vehicle within the preset time, and then the positioning module of the unmanned vehicle is judged to see whether there is an abnormality based on the first driving trajectory and the second driving trajectory recorded by the positioning module. This not only has a high degree of automation and reduces the manpower cost of judging abnormalities of the positioning module, but also can monitor in real time whether the positioning module of the unmanned vehicle is abnormal, thereby adjusting the automatic driving strategy of the unmanned vehicle in a timely manner.

[0038] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0040] Figure 1 is a schematic diagram showing a conventional method of detecting whether an abnormality occurs in a positioning module according to an exemplary embodiment;

[0041] Figure 2 This is a flow chart showing a method for detecting positioning anomalies of an unmanned vehicle according to an exemplary embodiment;

[0042] Figure 3 is a flow chart illustrating a method for detecting positioning anomalies of an unmanned vehicle according to another exemplary embodiment;

[0043] Figure 4 is a schematic diagram showing a trajectory error according to an exemplary embodiment;

[0044] Figure 5is a flow chart showing a method for calculating a trajectory error according to an exemplary embodiment;

[0045] Figure 6 is a schematic diagram showing calculation of a horizontal distance and / or a vertical distance according to an exemplary embodiment;

[0046] Figure 7 is a flowchart showing a method for calculating a preset threshold according to an exemplary embodiment;

[0047] Figure 8 is a schematic diagram showing a longitudinal preset threshold and a lateral preset threshold according to an exemplary embodiment;

[0048] Figure 9 is a block diagram of a device for detecting positioning anomalies of an unmanned vehicle according to an exemplary embodiment;

[0049] Figure 10 is a block diagram of an electronic device 700 according to an exemplary embodiment;

[0050] Figure 11 is a block diagram of an electronic device 1900 according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0052] At present, the main way to detect whether there is any abnormality in the positioning module of the unmanned vehicle is by staff observing whether the curb point cloud line scanned by the lidar is aligned with the curb line on the high-precision map. Figure 1 FIG. 1 is a schematic diagram showing a conventional method for detecting whether an abnormality occurs in a positioning module according to an exemplary embodiment. Figure 1 As shown in the figure, the lidar line is the curb point cloud line scanned by the lidar, and the map line is the curb line on the high-precision map. When the curb point cloud line scanned by the lidar deviates from the curb line on the high-precision map, it can be determined that the unmanned vehicle's positioning module has an anomaly. However, this detection method not only requires a large amount of human resources, but also cannot detect positioning anomalies in real time during the operation of the unmanned vehicle, resulting in the unmanned vehicle being unable to adjust its driving strategy in a timely manner. Furthermore, this detection method relies on high-precision maps and lidar, making it unsuitable for unmanned vehicles that lack lidar and high-precision maps.

[0053] Based on the above technical problems, the present disclosure proposes a method, device, storage medium and electronic device for detecting abnormalities in the positioning of an unmanned vehicle. The method generates a first driving trajectory of the unmanned vehicle based on the vehicle state of the unmanned vehicle at the initial moment of a preset time period and the vehicle control amount of the unmanned vehicle within the preset time period, and then judges whether the positioning module of the unmanned vehicle has abnormalities based on the first driving trajectory and the second driving trajectory recorded by the positioning module. This method not only has a high degree of automation and reduces the manpower cost of judging abnormalities in the positioning module, but also can monitor whether the positioning module of the unmanned vehicle has abnormalities in real time, thereby adjusting the automatic driving strategy of the unmanned vehicle in a timely manner.

[0054] The following describes in detail a method for detecting anomalies in positioning of an unmanned vehicle proposed in the present disclosure with reference to the accompanying drawings.

[0055] Figure 2 This is a flow chart of a method for detecting anomalies in positioning of an unmanned vehicle according to an exemplary embodiment. The disclosed embodiment provides a method for detecting anomalies in positioning of an unmanned vehicle, which can be applied to electronic devices such as unmanned vehicles, servers, mobile terminals, etc. Figure 2 As shown, the unmanned vehicle positioning anomaly detection method may include:

[0056] In step 110, based on the vehicle status information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle, the first driving trajectory of the unmanned vehicle within a preset time length is calculated, wherein the vehicle status information is used to characterize the vehicle status of the unmanned vehicle at the initial moment of the preset time length, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time length.

[0057] Here, the first driving trajectory is generated based on the vehicle state information of the unmanned vehicle at the initial moment within a preset duration and the vehicle control variables of the unmanned vehicle within the preset duration. This first driving trajectory represents the actual driving trajectory of the unmanned vehicle under the control of the autonomous driving system. For example, if the current time is 13:17:00 and the preset duration is 8 seconds, the vehicle state information at 13:16:52 can be obtained, and the vehicle state information of the unmanned vehicle at each sampling moment from 13:16:52 to 13:17:00 can be generated based on the vehicle control variables collected at each sampling moment, thereby obtaining the unmanned first driving trajectory. The vehicle state information includes the unmanned vehicle's position, posture, and speed information, and the vehicle control variables include the unmanned vehicle's steering information and acceleration information. It should be understood that the unmanned vehicle's steering information refers to the steering wheel angle of the unmanned vehicle, which is used to control the unmanned vehicle's steering. Acceleration information refers to information such as the unmanned vehicle's throttle signal and brake signal that controls the unmanned vehicle's speed. Acceleration information can be positive or negative.

[0058] In some implementations, the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle can be used as inputs of the vehicle motion model to obtain a first driving trajectory.

[0059] It is worth noting that in the above embodiment, the generation process of the first driving trajectory is illustrated using the current time as an example, but this is not intended to limit the generation process of the first driving trajectory. The first driving trajectory can be generated based on the vehicle status information and vehicle control amount of the unmanned vehicle within any preset time period in a historical time period, or it can be a driving trajectory generated in real time based on the vehicle status information of the unmanned vehicle at the current time and the vehicle control amount of the unmanned vehicle collected within a preset time period in the future. For example, if the current time is 13:17:00 and the preset time period is 8 seconds, the vehicle status information of the unmanned vehicle at 13:17:00 can be obtained, and the vehicle control amount of the unmanned vehicle can be collected during the time period from 13:17:00 to 13:17:08, to generate the driving trajectory of the unmanned vehicle during the time period from 13:17:00 to 13:17:08.

[0060] In step 120, a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period is obtained.

[0061] Here, while the unmanned vehicle is driving, the positioning module records the positioning data of the unmanned vehicle in real time, and then generates a second driving trajectory based on the recorded positioning data. The second driving trajectory represents the driving trajectory of the unmanned vehicle determined by the positioning data. The positioning module can be a GPS (Global Positioning System), a BDS (BeiDou Navigation Satellite System), or a GNSS (Global Navigation Satellite System).

[0062] It should be understood that the second driving trajectory can also be calculated based on data collected by GNSS, IMU (Inertial Measurement Unit) data, and laser point cloud data. Different unmanned vehicle positioning solutions can use different positioning modules, and the type of positioning module is not limited in this disclosure.

[0063] It is worth noting that step 120 and step 110 can be performed simultaneously, that is, while the first driving trajectory is being generated, the second driving trajectory of the unmanned vehicle can also be recorded by the positioning module.

[0064] In step 130, it is determined whether an abnormality occurs in the positioning module of the unmanned vehicle based on the first driving trajectory and the second driving trajectory.

[0065] Here, the first driving trajectory is the actual driving trajectory of the unmanned vehicle generated based on the vehicle status information and vehicle control quantity of the unmanned vehicle, and the second driving trajectory is the driving trajectory recorded by the positioning module based on the positioning data. When there is a deviation between the first driving trajectory and the second driving trajectory, it can be determined that there is an abnormality in the positioning module of the unmanned vehicle.

[0066] It should be understood that after determining that the positioning module of the unmanned vehicle has an abnormality, the positioning strategy of the positioning module of the unmanned vehicle can be corrected so that the positioning data obtained by the positioning module of the unmanned vehicle can return to normal.

[0067] Thus, determining whether the unmanned vehicle's positioning module has an anomaly based on the first and second driving trajectories not only achieves a high degree of automation, reducing the labor cost of determining positioning module anomalies, but also enables real-time monitoring of the unmanned vehicle's positioning module for anomalies, thereby enabling timely adjustments to the unmanned vehicle's autonomous driving strategy. Furthermore, the unmanned vehicle positioning anomaly detection method proposed in this disclosure has a wide range of applications, including for vehicles lacking high-precision maps or lidar.

[0068] Figure 3 FIG. 1 is a flow chart showing a method for detecting anomalies in positioning of an unmanned vehicle according to another exemplary embodiment. Figure 3 As shown, a method for detecting anomaly in positioning of an unmanned vehicle may include:

[0069] In step 210, based on the vehicle status information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle, the first driving trajectory of the unmanned vehicle within the preset time length is calculated, wherein the vehicle status information is used to characterize the vehicle status of the unmanned vehicle at the initial moment of the preset time length, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time length.

[0070] Here, the process of generating the first driving trajectory has been described in detail in the above embodiment, and will not be repeated here.

[0071] In step 220, a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period is obtained.

[0072] Here, the process of generating the second driving trajectory has been described in detail in the above embodiment and will not be repeated here.

[0073] In step 230 , a trajectory error between the first driving trajectory and the second driving trajectory is calculated.

[0074] Here, the trajectory error refers to the distance deviation between the first driving trajectory and the second driving trajectory. The distance deviation can be the distance deviation between the first driving trajectory and the second driving trajectory in the longitude direction or the distance deviation between the first driving trajectory and the second driving trajectory in the latitude direction. Figure 4 is a schematic diagram of a trajectory error according to an exemplary embodiment. Figure 4 As shown, Figure 4 The X-axis is the latitude direction, and the Y-axis is the longitude direction. The trajectory error can be the distance deviation between one or more trajectory points between the first and second driving trajectories. For example, the trajectory error can be the average of the distance deviations between multiple trajectory points at the same time when the line connecting the first and second driving trajectories is connected. The trajectory error can also be the distance deviation between the first and second driving trajectories as a whole.

[0075] In step 240 , when the trajectory error is greater than a preset threshold, it is determined that an abnormality occurs in the positioning module of the unmanned vehicle.

[0076] Here, when the trajectory error is greater than the preset threshold, it means that the positioning data recorded by the positioning module has exceeded the allowable error range, and it can be determined that the positioning module of the unmanned vehicle has an abnormality. This abnormality may be caused by the positioning strategy of the positioning module, or it may be a positioning failure caused by the lack of positioning data. When the trajectory error is equal to the preset threshold, it can be determined that the positioning module is operating normally. When the trajectory error is less than the preset threshold, it can be determined that the trajectory error is caused by the calculation strategy of the first driving trajectory of the unmanned vehicle within a preset time period, which is calculated based on the vehicle status information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle. If it is determined that the trajectory error is caused by the vehicle motion model, the calculation strategy of the vehicle motion model can be optimized.

[0077] Among them, the preset threshold can be the maximum error value of the positioning module determined based on historical positioning data and historical vehicle trajectories. It can include the maximum error value of the unmanned vehicle in the longitude direction, the maximum error value of the unmanned vehicle in the latitude direction, or the maximum error value in other directions. The size of the preset threshold can be set according to the accuracy of different positioning modules or the actual operation of the unmanned vehicle.

[0078] Figure 5 FIG. 1 is a flow chart showing a method for calculating a trajectory error according to an exemplary embodiment. Figure 5 As shown, calculating the trajectory error between the first driving trajectory and the second driving trajectory may include:

[0079] In step 231 , the distance between the trajectory points at the same time in the first driving trajectory and the second driving trajectory is calculated.

[0080] Here, when calculating the trajectory error, the distance between the trajectory points at the same time in the first driving trajectory and the second driving trajectory may be calculated. The distance between the trajectory points at the same time may be the distance between the trajectory points in the longitude direction and / or the latitude direction. Of course, the distance between the trajectory points at the same time may also be calculated by other means, such as projecting the trajectory points at the same time onto a coordinate system to further calculate the distance between the trajectory points at the same time.

[0081] In step 232 , a trajectory error between the first driving trajectory and the second driving trajectory is obtained by calculating the distances between a plurality of trajectory points at the same time.

[0082] Here, the first and second driving trajectories include multiple trajectory points at the same time. The trajectory error between the first and second driving trajectories is calculated by calculating the distances between the multiple trajectory points at the same time. The trajectory error can be calculated as the average of the distances between the multiple trajectory points at the same time, or the distances between trajectory points that meet specific conditions can be selected as the trajectory error.

[0083] In some possible implementations, in step 231, calculating the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time includes:

[0084] calculating a longitudinal distance between a projection of a first trajectory point in the first driving trajectory in a tangential direction of the second driving trajectory at the second trajectory point and the second trajectory point, and / or calculating a lateral distance between a projection of the first trajectory point in a normal direction of the second driving trajectory at the second trajectory point and the second trajectory point, wherein the second trajectory point is a trajectory point in the second driving trajectory at the same time as the first trajectory point;

[0085] In step 232, the trajectory error between the first driving trajectory and the second driving trajectory is calculated based on the distances between the multiple trajectory points at the same time, including:

[0086] A trajectory error between the first driving trajectory and the second driving trajectory is obtained according to the longitudinal distances and / or the lateral distances between the plurality of pairs of first trajectory points and the second trajectory points.

[0087] here, Figure 6 FIG. 1 is a schematic diagram showing a method of calculating a horizontal distance and / or a vertical distance according to an exemplary embodiment. Figure 6As shown, the first trajectory point in the first driving trajectory and the second trajectory point in the second driving trajectory are trajectory points at the same time. When calculating the longitudinal distance, the tangent direction of the second trajectory point on the second driving trajectory is determined, and then the first trajectory point is projected onto this tangent direction to obtain the projection of the first trajectory point in the tangent direction. The distance between the projection of the first trajectory point in the tangent direction and the second trajectory point is then calculated, which is the longitudinal distance. When calculating the lateral distance, the normal direction of the second trajectory point on the second driving trajectory is determined, and then the first trajectory point is projected onto this normal direction. The distance between the projection of the first trajectory point in the normal direction and the second trajectory point is then calculated, which is the longitudinal distance. In step 232, the average of the calculated longitudinal distances and / or lateral errors of multiple pairs of first and second trajectory points can be used as the trajectory error, or the maximum value of the calculated longitudinal distances and / or lateral errors of multiple pairs of first and second trajectory points can be used as the trajectory error. In actual application scenarios, this can be set according to actual needs.

[0088] It is worth noting that the first and second in the first trajectory point and the second trajectory point are not used to distinguish the order of the trajectory points. They are only used to distinguish and understand the trajectory points in the first driving trajectory and the second driving trajectory at the same time. There can be multiple pairs of trajectory points at the same time in the first driving trajectory and the second driving trajectory.

[0089] When the trajectory error includes the lateral distance and / or the longitudinal distance, in step 240, when the trajectory error is greater than a preset threshold, determining that the positioning module of the unmanned vehicle is abnormal may include:

[0090] When the longitudinal distance between the first driving track and the second driving track is greater than a longitudinal preset threshold, it is determined that an abnormality occurs in the positioning module of the unmanned vehicle;

[0091] When the lateral distance between the first driving track and the second driving track is greater than a preset lateral threshold, it is determined that an abnormality occurs in the positioning module of the unmanned vehicle.

[0092] Among them, the setting of the preset threshold can be determined based on one or more judgment conditions of the selected longitudinal distance and / or lateral distance. For example, when the lateral distance is used as the judgment condition, the preset threshold corresponds to the lateral preset threshold; when the longitudinal distance is used as the judgment condition, the preset threshold corresponds to the longitudinal preset threshold; when the longitudinal distance and the lateral distance are used as the judgment conditions, the preset threshold includes the lateral preset threshold and the longitudinal preset threshold.

[0093] Figure 7 FIG. 1 is a flow chart showing a method for calculating a preset threshold value according to an exemplary embodiment. Figure 7 As shown, in some feasible implementations, the preset threshold value can be obtained by the following steps:

[0094] In step 201, a third driving trajectory of the unmanned vehicle is obtained in a historical period, which is calculated based on the vehicle state information at the initial moment of the historical period and the vehicle control amount in the historical period.

[0095] Here, the third driving trajectory is the driving trajectory of the unmanned vehicle during the historical period, calculated based on the vehicle state information of the unmanned vehicle at the initial moment in the historical period and the vehicle control information collected by the unmanned vehicle during the historical period. For example, if the historical period is from 15:14:01 to 15:15:01, the vehicle state information of the unmanned vehicle at 15:14:01 is obtained, and the vehicle state information includes the position information, posture information, and speed information of the unmanned vehicle. At the same time, the vehicle control information sampled by the unmanned vehicle at each sampling moment in the period from 15:14:01 to 15:15:01 is obtained, where the vehicle control information includes the steering information and acceleration information of the unmanned vehicle, thereby generating the driving trajectory of the unmanned vehicle during the period from 15:14:01 to 15:15:01.

[0096] It should be understood that, in some embodiments, the third driving trajectory can be generated by using the vehicle state information at the initial moment of the historical period and the vehicle control amount in the historical period as inputs to the vehicle motion model.

[0097] In step 202, the positioning data collected by the unmanned vehicle through the positioning module during the historical period is obtained.

[0098] Here, the positioning module of the unmanned vehicle can obtain the positioning data collected by the positioning module during the historical period. This positioning data reflects the positioning trajectory of the unmanned vehicle during the historical period. For example, if the historical period is from 15:14:01 to 15:15:01, the positioning data of the unmanned vehicle's positioning module during the period from 15:14:01 to 15:15:01 can be obtained.

[0099] In step 203, the positioning data is corrected to obtain the real positioning data of the unmanned vehicle in the historical period, and the fourth driving trajectory of the unmanned vehicle in the historical period is determined based on the real positioning data.

[0100] Correcting the positioning data can involve utilizing offline post-processing techniques to obtain the true positioning data of the unmanned vehicle during the historical period. For example, the original positioning data can be supplemented with base station data collected by the unmanned vehicle during the historical period, and the positioning data acquired by the positioning module can be corrected to obtain the true positioning data. A fourth driving trajectory is then generated based on the true positioning data. This fourth driving trajectory is obtained by correcting the positioning data from the positioning module and reflects the true driving trajectory of the unmanned vehicle.

[0101] In step 204 , the preset threshold is determined based on the difference between the third driving trajectory and the fourth driving trajectory.

[0102] Here, the difference between the trajectory points of the third and fourth driving trajectories at the same time can be used as the preset threshold. For example, the maximum value of the difference between the trajectory points of the third and fourth driving trajectories at the same time can be used as the preset threshold. Alternatively, the average value of the difference between all trajectory points of the third and fourth driving trajectories at the same time can be used as the preset threshold.

[0103] It should be understood that the difference between the trajectory points of the third driving trajectory and the fourth driving trajectory at the same time may include the distance difference in the longitude direction and / or the distance difference in the latitude direction, and the preset threshold may include a horizontal preset threshold and / or a longitudinal preset threshold. Figure 8 FIG. 1 is a schematic diagram showing a longitudinal preset threshold value and a transverse preset threshold value according to an exemplary embodiment. Figure 8 As shown, the lateral preset threshold value calculated using the third driving trajectory and the fourth driving trajectory of a large number of historical periods converges to 15 cm, and the longitudinal preset threshold value converges to 20 cm.

[0104] In some feasible implementations, calculating a first driving trajectory of the unmanned vehicle within a preset time period based on the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle includes:

[0105] Inputting the vehicle state information and the vehicle control variable into a vehicle motion model to obtain the first driving trajectory output by the vehicle motion model;

[0106] In which, the vehicle control quantity includes the vehicle control quantity sampled at multiple sampling moments within the preset time length, and the vehicle motion model is used to calculate the vehicle state from the adoption moment to the next sampling moment of the adoption moment based on the vehicle control quantity collected at the adoption moment and the vehicle state of the unmanned vehicle at the sampling moment.

[0107] Here, the vehicle state collected at the initial moment of a preset duration and the vehicle control variables sampled within the preset duration serve as inputs to a vehicle motion model to generate a first driving trajectory for the unmanned vehicle. The vehicle motion model predicts the vehicle state information at each sampling moment under certain input control, thereby generating a driving trajectory. This vehicle motion model may include a vehicle kinematic model, a bicycle model, a dynamic bicycle model, and the like.

[0108] For example, the preset duration is 13:17:00 to 13:17:08, and the sampling times are 13:17:03 and 13:17:07 respectively. The vehicle status information and vehicle control amount at 13:17:00 are used to obtain the driving trajectory of the unmanned vehicle in the time period from 13:17:00 to 13:17:03. When the unmanned vehicle samples a new vehicle control amount at 13:17:03, the vehicle motion model is based on the vehicle status information and vehicle control amount at 13:17:03. The vehicle state and the new vehicle control quantity sampled at 13:17:03 generate the driving trajectory of the unmanned vehicle from 13:17:03 to 13:17:07. When the unmanned vehicle samples the new vehicle control quantity at 13:17:07, the vehicle motion model generates the driving trajectory of the unmanned vehicle from 13:17:07 to 13:17:08 based on the vehicle state of the unmanned vehicle at 13:17:07 and the new vehicle control quantity sampled at 13:17:07.

[0109] It's worth noting that the third driving trajectory can also be generated using a vehicle motion model. This can be obtained by using the vehicle state information of the unmanned vehicle at the initial moment of a historical period and the vehicle control variables during that period as inputs to the vehicle motion model. The generation process for the third driving trajectory is identical to that for the first, and will not be repeated here.

[0110] Figure 9 FIG. 1 is a block diagram of a device for detecting positioning anomalies of an unmanned vehicle according to an exemplary embodiment. Figure 9 As shown, an embodiment of the present disclosure provides a device for detecting positioning anomalies of an unmanned vehicle, the device 1300 including:

[0111] The trajectory prediction module 1301 is configured to calculate a first driving trajectory of the unmanned vehicle within a preset time period based on vehicle state information of the unmanned vehicle and a vehicle control amount of the unmanned vehicle, wherein the vehicle state information is used to represent the vehicle state of the unmanned vehicle at the initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period;

[0112] The trajectory recording module 1302 is configured to obtain a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period;

[0113] The detection module 1303 is configured to determine whether there is an abnormality in the positioning module of the unmanned vehicle based on the first driving trajectory and the second driving trajectory.

[0114] In some embodiments, the detection module 1303 includes:

[0115] a trajectory error calculation unit, configured to calculate a trajectory error between the first driving trajectory and the second driving trajectory;

[0116] The determination unit is configured to determine that an abnormality occurs in the positioning module of the unmanned vehicle when the trajectory error is greater than a preset threshold.

[0117] In some embodiments, the trajectory error calculation unit includes:

[0118] a distance calculation unit configured to calculate the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time;

[0119] The error determination unit is configured to calculate a trajectory error between the first driving trajectory and the second driving trajectory based on distances between multiple trajectory points at the same time.

[0120] In some embodiments, the distance calculation unit is specifically configured to: calculate a longitudinal distance between a projection of a first trajectory point in the first driving trajectory in a tangential direction of the second driving trajectory at the second trajectory point and the second trajectory point, and / or calculate a lateral distance between a projection of the first trajectory point in a normal direction of the second driving trajectory at the second trajectory point and the second trajectory point, wherein the second trajectory point is a trajectory point in the second driving trajectory at the same time as the first trajectory point;

[0121] The error determination unit is specifically configured to obtain a trajectory error between the first driving trajectory and the second driving trajectory based on longitudinal distances and / or lateral distances between multiple pairs of first trajectory points and second trajectory points.

[0122] In some embodiments, the apparatus further comprises:

[0123] an acquisition module configured to acquire a third driving trajectory of the unmanned vehicle during a historical period, calculated based on vehicle state information at an initial moment of the historical period and a vehicle control amount during the historical period;

[0124] a collection module configured to obtain positioning data collected by the unmanned vehicle through the positioning module during the historical period;

[0125] a correction module configured to correct the positioning data to obtain real positioning data of the unmanned vehicle in the historical period, and determine a fourth driving trajectory of the unmanned vehicle in the historical period based on the real positioning data;

[0126] The threshold calculation module is configured to determine the preset threshold based on a difference between the third driving trajectory and the fourth driving trajectory.

[0127] In some embodiments, the trajectory prediction module 1301 is specifically configured as follows:

[0128] Inputting the vehicle state information and the vehicle control variable into a vehicle motion model to obtain the first driving trajectory output by the vehicle motion model;

[0129] In which, the vehicle control quantity includes the vehicle control quantity sampled at multiple sampling moments within the preset time length, and the vehicle motion model is used to calculate the vehicle state from the adoption moment to the next sampling moment of the adoption moment based on the vehicle control quantity collected at the adoption moment and the vehicle state of the unmanned vehicle at the sampling moment.

[0130] In some embodiments, the vehicle status information includes the position information, posture information, and speed information of the unmanned vehicle, and the vehicle control quantity includes the steering information and acceleration information of the unmanned vehicle.

[0131] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0132] Figure 10 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 10 As shown, the electronic device 700 may include: a processor 701 , a memory 702 , and may further include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0133] Among them, the processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned unmanned vehicle positioning anomaly detection method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. These data may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as the second driving trajectory recorded by the positioning module of the unmanned vehicle, a preset threshold, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or transmitted via the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices.

[0134] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned unmanned vehicle positioning anomaly detection method.

[0135] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the above-mentioned unmanned vehicle positioning anomaly detection method. For example, the computer-readable storage medium may be the above-mentioned memory 702 including the program instructions. The above-mentioned program instructions may be executed by the processor 701 of the electronic device 700 to implement the above-mentioned unmanned vehicle positioning anomaly detection method.

[0136] Figure 11 1 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 11 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing a computer program executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 1922 may be configured to execute the computer program to perform the above-mentioned unmanned vehicle positioning anomaly detection method.

[0137] In addition, the electronic device 1900 may further include a power supply component 1926 and a communication component 1950. The power supply component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to implement communication of the electronic device 1900, for example, wired or wireless communication. In addition, the electronic device 1900 may further include an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM , Linux TMetc.

[0138] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the unmanned vehicle positioning anomaly detection method described above. For example, the computer-readable storage medium may be the aforementioned memory 1932 including the program instructions. The program instructions may be executed by the processor 1922 of the electronic device 1900 to implement the unmanned vehicle positioning anomaly detection method described above.

[0139] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned unmanned vehicle positioning anomaly detection method when executed by the programmable device.

[0140] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0141] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0142] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for detecting anomaly in positioning of an unmanned vehicle, characterized in that: include: Calculating a first driving trajectory of the unmanned vehicle within a preset time period based on vehicle state information of the unmanned vehicle and a vehicle control amount of the unmanned vehicle, wherein the vehicle state information is used to represent the vehicle state of the unmanned vehicle at an initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period; Obtaining a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period; Determining whether a positioning module of the unmanned vehicle has an abnormality according to the first driving trajectory and the second driving trajectory; The calculating, based on the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle, a first driving trajectory of the unmanned vehicle within a preset time period includes: Inputting the vehicle state information and the vehicle control variable into a vehicle motion model to obtain the first driving trajectory output by the vehicle motion model; In which, the vehicle control quantity includes the vehicle control quantity sampled at multiple sampling moments within the preset time length, and the vehicle motion model is used to calculate the vehicle state from the sampling moment to the next sampling moment based on the vehicle control quantity collected at each sampling moment and the vehicle state of the unmanned vehicle at the sampling moment.

2. The method according to claim 1, characterized in that The determining, based on the first driving trajectory and the second driving trajectory, whether a positioning module of the unmanned vehicle is abnormal includes: calculating a trajectory error between the first driving trajectory and the second driving trajectory; When the trajectory error is greater than a preset threshold, it is determined that an abnormality occurs in the positioning module of the unmanned vehicle.

3. The method according to claim 2, characterized in that The calculating a trajectory error between the first driving trajectory and the second driving trajectory includes: Calculating the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time; A trajectory error between the first driving trajectory and the second driving trajectory is obtained by calculating the distances between a plurality of trajectory points at the same time.

4. The method according to claim 3, characterized in that The calculating the distance between trajectory points in the first driving trajectory and the second driving trajectory at the same time includes: calculating a longitudinal distance between a projection of a first trajectory point in the first driving trajectory in a tangential direction of the second driving trajectory at the second trajectory point and the second trajectory point, and / or calculating a lateral distance between a projection of the first trajectory point in a normal direction of the second driving trajectory at the second trajectory point and the second trajectory point, wherein the second trajectory point is a trajectory point in the second driving trajectory at the same time as the first trajectory point; The calculating the trajectory error between the first driving trajectory and the second driving trajectory according to the distances between the plurality of trajectory points at the same time includes: A trajectory error between the first driving trajectory and the second driving trajectory is obtained according to the longitudinal distances and / or the lateral distances between the plurality of pairs of first trajectory points and the second trajectory points.

5. The method according to claim 2, characterized in that The preset threshold is obtained by the following steps: Obtaining a third driving trajectory of the unmanned vehicle during a historical period, calculated based on vehicle state information at an initial moment of the historical period and a vehicle control amount during the historical period; Obtaining positioning data collected by the unmanned vehicle through the positioning module during the historical period; Correcting the positioning data to obtain real positioning data of the unmanned vehicle in the historical period, and determining a fourth driving trajectory of the unmanned vehicle in the historical period based on the real positioning data; The preset threshold is determined based on a difference between the third driving trajectory and the fourth driving trajectory.

6. The method according to claim 1, characterized in that The vehicle state information includes the position information, posture information and speed information of the unmanned vehicle, and the vehicle control amount includes the steering information and acceleration information of the unmanned vehicle.

7. An unmanned vehicle positioning anomaly detection device, characterized in that: include: The trajectory prediction module is configured to calculate a first driving trajectory of the unmanned vehicle within a preset time period based on the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle, wherein the vehicle state information is used to represent the vehicle state of the unmanned vehicle at the initial moment of the preset time period, and the vehicle control amount includes the driving control amount of the unmanned vehicle within the preset time period. The calculation of the first driving trajectory of the unmanned vehicle within the preset time period based on the vehicle state information of the unmanned vehicle and the vehicle control amount of the unmanned vehicle includes: Inputting the vehicle state information and the vehicle control variable into a vehicle motion model to obtain the first driving trajectory output by the vehicle motion model; The vehicle control amount includes the vehicle control amount sampled at multiple sampling moments within the preset time period, and the vehicle motion model is used to calculate the vehicle state from the sampling moment to the next sampling moment based on the vehicle control amount collected at each sampling moment and the vehicle state of the unmanned vehicle at the sampling moment; a trajectory recording module, configured to obtain a second driving trajectory of the unmanned vehicle recorded by the positioning module within the preset time period; The detection module is configured to determine whether an abnormality occurs in the positioning module of the unmanned vehicle based on the first driving trajectory and the second driving trajectory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

Images