Vehicle positioning evaluation method and device

By acquiring and evaluating the data of the positioning components and evaluation modules of the vehicle's motion trajectory in an intelligent driving system, the problem of high-precision positioning evaluation relying on high-cost combined inertial navigation and GNSS errors is solved, and the reliability evaluation and iteration of the positioning components is achieved. guidance improves the accuracy and smoothness of positioning results.

CN119001769APending Publication Date: 2024-11-22RUILIAN XINGCHEN (BEIJING) TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310540685.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the existing intelligent driving system, high-precision positioning evaluation method relies on high-cost combined inertial navigation equipment, and there are errors accumulated over time and motion when there is no global GNSS observation, so it cannot be equipped on a large scale, and the smoothness of the positioning results and Important indicators such as uncertainty.

Method used

By obtaining the motion trajectory measured by the positioning component and the evaluation module on the vehicle, determining the reference truth value and positioning error, evaluating the reliability of the positioning uncertainty results of the positioning component, and realizing evaluation and iterative guidance for the positioning component.

Benefits of technology

Effectively evaluate the reliability of positioning uncertainty results of positioning components, guide the development iteration of positioning components, reduce the dependence on high-precision positioning equipment, improve the accuracy and smoothness of positioning results, and adapt to the needs of intelligent driving applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119001769A_ABST
    Figure CN119001769A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle positioning evaluation method and device. The method comprises the following steps: acquiring a first motion track of a vehicle measured by a positioning assembly; a reference truth value is determined on the basis of a second motion trail, measured by an evaluation module, of the vehicle, the evaluation module and the positioning assembly are both arranged on the vehicle, and the first motion trail and the second motion trail are motion trails obtained in the same time period; determining a positioning error of the positioning assembly according to the first motion track of the vehicle and the reference true value; and evaluating the reliability of the positioning uncertainty result of the positioning component based on the determined positioning error. According to the method and the device, the reliability of the positioning uncertainty result of the positioning component can be effectively evaluated, so that the development iteration of the positioning component can be guided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to a vehicle positioning evaluation method and device. Background Art

[0002] At present, high-precision positioning is the cornerstone of intelligent driving systems. The sensors widely used in mass-produced positioning algorithms usually include low-cost IMU, GNSS (with RTK differential positioning), and Odometry (wheel speed meter). IMU and GNSS are available in separate forms or low-cost combined inertial navigation box forms. The latter form is more common. At the same time, millimeter-wave radar, lidar, vision, high-precision map and other sensors can also be combined to provide positioning assistance.

[0003] The global positioning accuracy requirement of intelligent driving systems is usually lane-level (decimeter level). Lane-level positioning accuracy poses a huge challenge to the evaluation of positioning results. Generally speaking, the accuracy of the evaluation system needs to be more than an order of magnitude higher than the accuracy of the system to be evaluated. The current mainstream evaluation method is to equip a set of high-precision combined inertial navigation equipment as the positioning truth value, and compare the positioning results at the same time after time alignment to obtain the deviation.

[0004] However, the above evaluation method has the following problems: high-precision combined inertial navigation is expensive and cannot be deployed on a large scale. In addition, although high-precision combined inertial navigation can maintain positioning accuracy for a considerable period of time without relying on global GNSS positioning, there are still errors accumulated over time and movement when there is no global GNSS observation. The positioning "true value" it provides is not absolutely reliable in all scenarios. Summary of the invention

[0005] In view of this, the embodiments of the present application at least provide a vehicle positioning evaluation method and device, which can effectively evaluate the reliability of the positioning uncertainty results of the positioning component.

[0006] In a first aspect of the present application, a vehicle positioning evaluation method is provided, comprising: obtaining a first motion trajectory of the vehicle measured by a positioning component; determining a reference true value based on a second motion trajectory of the vehicle measured by an evaluation module, wherein the evaluation module and the positioning component are both arranged on the vehicle, and the first motion trajectory and the second motion trajectory are motion trajectories obtained in the same time period; determining a positioning error of the positioning component based on the first motion trajectory of the vehicle and the reference true value; and evaluating the reliability of a positioning uncertainty result of the positioning component based on the determined positioning error.

[0007] According to a second aspect of the present application, a vehicle positioning evaluation device is provided, the device comprising: a trajectory acquisition module, which acquires a first motion trajectory of the vehicle measured by a positioning component; a truth value determination module, which determines a reference truth value based on a second motion trajectory of the vehicle measured by the evaluation module, the evaluation module and the positioning component are both arranged on the vehicle, and the first motion trajectory and the second motion trajectory are motion trajectories obtained in the same time period; an error determination module, which determines a positioning error of the positioning component according to the first motion trajectory of the vehicle and the reference truth value; and a reliability evaluation module, which evaluates the reliability of a positioning uncertainty result of the positioning component based on the determined positioning error.

[0008] The vehicle positioning evaluation method and device provided in the embodiments of the present application can effectively evaluate the reliability of the positioning uncertainty results of the positioning component, so as to help guide the development iteration of the positioning component.

[0009] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 A flow chart showing a vehicle positioning evaluation method provided by an exemplary embodiment of the present application;

[0012] Figure 2 A flowchart showing the steps of determining the final state error of the first time period provided by an exemplary embodiment of the present application;

[0013] Figure 3 A flowchart showing the steps of determining the reliability of the positioning uncertainty result of the first time period provided by an exemplary embodiment of the present application;

[0014] Figure 4 A schematic diagram showing the structure of a vehicle positioning evaluation device provided by an exemplary embodiment of the present application is shown;

[0015] Figure 5 A schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0017] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0018] It should be understood that in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" is merely a way to describe the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "Including A, B and / or C" means including any one, any two, or any three of A, B, and C.

[0019] It should be understood that in the embodiments of the present application, "B corresponding to A", "B corresponding to A", "A corresponds to B", or "B corresponds to A" means that B is associated with A, and B can be determined according to A. Determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0020] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0021] At present, high-precision positioning is the cornerstone of intelligent driving systems. The sensors widely used in mass-produced positioning algorithms usually include low-cost IMU, GNSS (with RTK differential positioning), and Odometry. IMU and GNSS are available in separate forms or low-cost combined inertial navigation boxes. The latter is more common. At the same time, millimeter-wave radar, lidar, vision, high-precision maps and other sensors can also be combined to provide positioning assistance.

[0022] The global positioning accuracy requirement of intelligent driving systems is usually lane-level (decimeter level). Lane-level positioning accuracy poses a huge challenge to the evaluation of positioning results. Generally speaking, the accuracy of the evaluation system needs to be more than an order of magnitude higher than the accuracy of the system to be evaluated. The current mainstream evaluation method is to equip a set of high-precision combined inertial navigation equipment as the positioning truth value, and compare the positioning results at the same time after time alignment to obtain the deviation.

[0023] However, the above evaluation method has the following problems:

[0024] (1) High-precision integrated inertial navigation is expensive and cannot be deployed on a large scale. In addition, although high-precision integrated inertial navigation can maintain positioning accuracy for a considerable period of time without relying on global GNSS positioning, there are still errors accumulated over time and motion when there is no global GNSS observation. The positioning "truth" it provides is not absolutely reliable in all scenarios;

[0025] (2) For intelligent driving systems, in addition to evaluating positioning accuracy, indicators such as the smoothness and uncertainty of positioning results are often overlooked, while these indicators are equally important for the rational use of positioning results.

[0026] In response to at least one of the above-mentioned problems, the present application proposes a vehicle positioning evaluation method and device, which can determine a reference true value based on an evaluation module to effectively evaluate the reliability of the positioning uncertainty results of the positioning component, thereby helping to guide the development iteration of the positioning component.

[0027] To facilitate understanding of the present application, the vehicle positioning evaluation method, device, electronic device, storage medium, and program product provided in the embodiments of the present application are introduced in detail below.

[0028] Figure 1 A flow chart of a vehicle positioning evaluation method provided by an exemplary embodiment of the present application is shown.

[0029] Reference Figure 1 In step S101, a first motion trajectory of the vehicle measured by a positioning component is obtained.

[0030] Here, the positioning component may include a plurality of mass-produced, low-cost sensors, such as IMU, GNSS (with RTK differential positioning), Odometry, etc. For example, IMU (Inertial Measurement Unit) is used to measure the three-axis attitude angle (or angular rate) and acceleration of an object, GNSS (Global Navigation Satellite System) can output position information and satellite status information, RTK (Real-time kinematic, carrier phase differential technology), improves the GNSS positioning accuracy to centimeter level, Odometry - odometer, a device in the vehicle chassis system that infers the motion state of the vehicle body through the rotation of the tires, and can also be called a wheel speed meter.

[0031] In one application scenario, the positioning component may refer to a positioning system integrated in a vehicle, such as a positioning system equipped with a vehicle's intelligent driving system.

[0032] In an embodiment of the present application, the first motion trajectory of the vehicle acquired by the positioning component includes multiple trajectory points, and each trajectory point includes at least: a sampling time, a three-dimensional position, a three-dimensional speed, and a three-axis attitude angle and a standard deviation.

[0033] In step S102, a reference true value is determined based on the second motion trajectory of the vehicle measured by the evaluation module.

[0034] Here, the evaluation module and the positioning component are both arranged on the vehicle, and the second motion trajectory measured by the evaluation module and the first motion trajectory measured by the positioning component are measured during one movement of the vehicle, that is, during the movement of the vehicle, the motion trajectory of the vehicle is measured by the positioning component and the evaluation module respectively.

[0035] In the embodiment of the present application, the positioning component is the system to be evaluated, and the evaluation module is a module for evaluating the positioning component, which belongs to the evaluation system. The evaluation module also has related positioning functions, that is, the evaluation module and the positioning component belong to two independent positioning systems.

[0036] Exemplarily, in the application scenario where the above-mentioned vehicle is a vehicle, the positioning component is integrated in the vehicle, and the above-mentioned evaluation module can be temporarily installed on the vehicle when positioning evaluation is required, and then removed from the vehicle after the positioning evaluation is completed. In other words, the evaluation module may not be integrated in the vehicle, but the present application is not limited to this, and at least two positioning systems may also be integrated in the vehicle, and one of the positioning systems is selected as an evaluation module to perform positioning evaluation on the other positioning system.

[0037] In a preferred embodiment, the positioning accuracy of the evaluation module can be the same as the positioning accuracy of the positioning component. For example, the evaluation module can also be composed of multiple mass-produced, low-cost sensors. In this case, the vehicle positioning evaluation method based on the present application can realize the evaluation of positioning results without relying on high-precision positioning equipment (high-precision combined inertial navigation).

[0038] However, it should be understood that the present application is not limited to this, and the positioning accuracy of the evaluation module can also be higher than the positioning accuracy of the positioning component, that is, the vehicle positioning evaluation method of the present application is also applicable to the case of a high-precision positioning evaluation system.

[0039] In a preferred embodiment of the present application, the step of determining the reference truth value may include: determining the trajectory abnormal point in the second motion trajectory based on the continuous smoothness detection of the second motion trajectory; and determining the posture value corresponding to each trajectory point in the second motion trajectory except the trajectory abnormal point as the reference truth value. Exemplarily, the reference truth value may refer to the posture truth value.

[0040] Here, continuous smoothness detection may be performed on each trajectory point in the second motion trajectory one by one, wherein the trajectory abnormal point has no corresponding reference true value, and the non-trajectory abnormal point has a corresponding reference true value.

[0041] Here, the vehicle's motion trajectory must meet kinematic constraints, which are manifested in smooth posture, continuous curvature, and no sideslip in the positioning trajectory. At the same time, it should also meet dynamic constraints, which are manifested in the restrictions on the acceleration and deceleration, and the speed-curvature radius relationship. Through the above-mentioned tests, the rationality of the motion trajectory can be judged, so as to find out the abnormal change points of posture, that is, the abnormal points of the trajectory.

[0042] Exemplarily, the above-mentioned trajectory abnormal point is a trajectory point that satisfies at least one of the following items: abnormal reception of satellite positioning signal (GNSS signal), abnormal reception of positioning differential signal (RTK differential signal), and abnormal positioning offset of the trajectory point.

[0043] Here, when the GNSS signal and the RTK differential signal are normal, the positioning accuracy of the low-cost mass-produced combined inertial navigation module (i.e., the evaluation module) can also reach the centimeter level. At this time, the result output by the low-cost combined inertial navigation can be directly used as a reference true value.

[0044] As an example, the presence of abnormal positioning deviation of a trajectory point may include, but is not limited to, at least one of the following items: a posture jump, a curvature jump, a curvature that is too small, an acceleration that is too large, and a sideslip angle that is too large.

[0045] In the embodiment of the present application, the second motion trajectory of the vehicle collected by the evaluation module includes multiple trajectory points, each of which includes at least: sampling time, three-dimensional position, three-dimensional velocity, and three-axis attitude angle and standard deviation. Based on this, the curvature, acceleration and sideslip angle of each trajectory point can be calculated in the following way.

[0046] For example, the cumulative displacement s corresponding to each sampling moment can be calculated according to the horizontal position coordinates (x, y), and the curvature kappa can be calculated according to the following formula:

[0047]

[0048] For example, the acceleration can be obtained based on the differentiation of the velocity change with respect to time. The sideslip angle can be obtained based on the angle between the heading angle and the arc tangent of two horizontal velocities.

[0049] For example, considering that the differential operation will amplify the noise, and the original positioning output frequency can generally reach 100 Hz (Hertz), the time interval when calculating the curvature and acceleration can be 0.1 s (second).

[0050] After calculating the above parameter values, the thresholds of the position, speed, attitude angle, acceleration, and curvature changes between frames can be controlled. Situations such as excessive sideslip angle, too small curvature, and excessive curvature change rate can also be controlled to screen out abnormal points in the motion state.

[0051] In step S103, a positioning error of the positioning component is determined according to the first motion trajectory of the vehicle and a reference true value.

[0052] For example, the first motion trajectory of the vehicle includes trajectory points at each sampling moment, and the second motion trajectory of the vehicle includes trajectory anomaly points and non-trajectory anomaly points in multiple trajectory points at each sampling moment, that is, some sampling moments correspond to reference true values, while some sampling moments do not have corresponding reference true values.

[0053] In this case, for a moment with a reference true value, the positioning error of the positioning component may refer to the difference between the pose value of the first motion trajectory at the same sampling moment and the corresponding reference true value.

[0054] In step S104 , the reliability of the positioning uncertainty result of the positioning component is evaluated based on the determined positioning error.

[0055] Here, the above positioning uncertainty result is used to characterize the deviation given by the positioning component for the positioning result. In the embodiment of the present application, different evaluation methods are proposed for the time period lacking the reference true value and the time period having the reference true value, which will be described in detail below.

[0056] The first case is for the time period when the reference truth value is missing.

[0057] For each first time period lacking a reference true value, a final state error corresponding to each first time period is determined, and based on the error distribution of the final state errors of all first time periods, the reliability of the positioning uncertainty result of the positioning component is evaluated.

[0058] In the embodiment of the present application, in the absence of valid GNSS observations, although there is a lack of reference truth values, after the trajectory rationality constraint check, an overall evaluation can be performed based on the time interval without valid GNSS observations and the final-state error during this period to compare whether the final-state error and the standard deviation are self-consistent.

[0059] Figure 2 A flow chart showing steps of determining a final state error of a first time period provided by an exemplary embodiment of the present application.

[0060] Reference Figure 2 In step S201, the time with a true value closest to the end time of the first time period is determined.

[0061] For example, each first time period corresponds to a start time and an end time, and the time closest to the end time can be found from each second time period with a reference true value as the time with a true value. Exemplarily, the time with a true value is after the end time of the first time period, that is, the time with a true value is later than the end time in time.

[0062] In step S202, based on the positioning posture at the time when the true value is available and the reference true value, the positioning error at the time when the true value is available is determined.

[0063] For example, the difference between the positioning posture at the time when the true value is available and the reference true value can be determined as the positioning error at the time when the true value is available. Exemplarily, the positioning posture at the time when the true value is available can include the positioning posture measured by the positioning component.

[0064] In step S203, the positioning error at the time when the true value is obtained is determined as the final state error of the first time period.

[0065] In the embodiment of the present application, the reliability of the positioning uncertainty result for each first time period in which a reference true value is missing can be determined by comparing whether the final state error and the standard deviation are self-consistent.

[0066] Figure 3 A flow chart showing steps of determining the reliability of a positioning uncertainty result for a first time period provided by an exemplary embodiment of the present application.

[0067] Reference Figure 3 , in step S301, the standard deviation corresponding to the final state error of each first time period is determined.

[0068] Here, the standard deviation is the standard deviation corresponding to the true value moment closest to the end moment of the first time period. Exemplarily, the standard deviation can be directly output by the positioning component.

[0069] In step S302, the proportions of final state errors corresponding to all first time periods falling within a plurality of preset standard deviation intervals are counted.

[0070] Exemplarily, the plurality of preset standard deviation intervals may include: [-1σ, +1σ], [-2σ, +2σ], [-3σ, +3σ]. Here, σ represents the standard deviation, and the value of σ may be calculated from the standard deviation corresponding to each final state error, or may be determined based on experience.

[0071] In step S303, if the proportion values ​​falling into each preset standard deviation interval all meet the statistical characteristics, it is determined that the positioning uncertainty result of the positioning module is reliable.

[0072] In step S304, if the proportion of values ​​falling into any preset standard deviation interval does not satisfy the statistical characteristics, it is determined that the positioning uncertainty result of the positioning module is unreliable.

[0073] For example, it is possible to count whether the final state error falls within the above three preset standard deviation intervals and satisfies the statistical characteristics of approximately 0.6526, 0.9544, and 0.9974. It should be understood that the specific values ​​listed above are only examples, and the present application is not limited thereto. Those skilled in the art can make adjustments as needed.

[0074] The second case is for the time period when there is a reference true value.

[0075] For each second time period for which a reference true value exists, the reliability of the positioning uncertainty result of the positioning module is evaluated based on the positioning pose of each second time period without relying on the satellite positioning signal.

[0076] For example, you can select a time period with a true reference value, and feed the data offline to the mass production fusion positioning algorithm. At the same time, turn off the GNSS observation update and record the output positioning pose.

[0077] Specifically, all relevant parameters of the first motion trajectory of the vehicle measured by the above-mentioned positioning component can be recorded, and in the vehicle's positioning simulation system, the GNSS observation update can be manually turned off, and all the recorded relevant parameters can be fed back to the positioning simulation system offline, and the positioning posture output by the positioning simulation system in the time period with a reference true value and without GNSS observation update can be determined as the positioning posture in the second time period without relying on satellite positioning signals.

[0078] Exemplarily, the positioning simulation system can output position, speed, attitude and corresponding position standard deviation, speed standard deviation and heading angle standard deviation. Here, the sensors used in the positioning simulation system are consistent with the composition of the above positioning components.

[0079] In an embodiment of the present application, it is evaluated whether the divergence of the standard deviation is reasonable over time and motion when there is no GNSS observation. Here, the GNSS observation update can be manually turned off to determine whether the standard deviation output by the statistical positioning algorithm can truly reflect the positioning deviation.

[0080] In a preferred embodiment, the reliability of the positioning uncertainty result of the positioning component can be evaluated in the following manner: for each second time period in which a reference true value exists, based on the positioning posture and the reference true value of the second time period without relying on the satellite positioning signal, the actual error at each sampling moment in the second time period is determined; based on the error distribution of the actual error at each sampling moment of all second time periods, the reliability of the positioning uncertainty result of the positioning module is evaluated.

[0081] Here, the actual error (ie, posture error) at each sampling moment in the second time period may be the difference between the positioning posture at that moment without relying on the satellite positioning signal and the reference true value.

[0082] For example, the proportion of posture errors corresponding to all second time periods falling within multiple preset standard deviation intervals is counted.

[0083] Exemplarily, the plurality of preset standard deviation intervals may include: [-1σ, +1σ], [-2σ, +2σ], [-3σ, +3σ]. Here, the value of σ may be calculated from the standard deviation corresponding to each posture error, or may be determined based on experience.

[0084] If the proportion values ​​falling into each preset standard deviation interval meet the statistical characteristics, then the positioning uncertainty result of the positioning module is determined to be reliable. If the proportion values ​​falling into any preset standard deviation interval do not meet the statistical characteristics, then the positioning uncertainty result of the positioning module is determined to be unreliable.

[0085] After the above steps, it can be evaluated whether the posture output by the mass-produced positioning component is reasonable. On the premise of ensuring rationality, the positioning accuracy is statistically analyzed and the reliability of the positioning uncertainty results is evaluated to guide the development and iteration of the mass-produced positioning algorithm.

[0086] The positioning result evaluation method proposed in the embodiment of the present application does not rely on high-precision positioning equipment, mainly including a posture anomaly detection method based on vehicle kinematics and dynamic constraints, a method for screening out reliable true values ​​from the posture output by a low-cost combined inertial navigation device, and a method for evaluating the reliability of the uncertainty of the positioning result. The positioning results evaluated by the embodiment of the present application are more adapted to the needs of intelligent driving applications.

[0087] The vehicle positioning evaluation method of the embodiment of the present application is used to solve the problem that the positioning result evaluation is strongly dependent on high-precision positioning equipment. The accuracy, smoothness and uncertainty indicators of the positioning result are the cornerstones for the intelligent driving system to reasonably use the positioning result and thus work stably. The vehicle positioning evaluation method of the embodiment of the present application can effectively guide the development of the positioning algorithm and output the positioning result that meets the intelligent driving application.

[0088] Based on the same application concept, a vehicle positioning evaluation device corresponding to the method provided in the above embodiment is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the vehicle positioning evaluation method in the above embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0089] Figure 4 A schematic diagram of the structure of a vehicle positioning evaluation device provided in an exemplary embodiment of the present application.

[0090] like Figure 4 As shown, the vehicle positioning evaluation device 200 specifically includes:

[0091] A trajectory acquisition module 210, which acquires a first motion trajectory of the vehicle measured by the positioning component;

[0092] a truth value determination module 220, which determines a reference truth value based on a second motion trajectory of the vehicle measured by an evaluation module, wherein the evaluation module and the positioning component are both arranged on the vehicle;

[0093] The error determination module 230 determines the positioning error of the positioning component according to the first motion trajectory of the vehicle and the reference true value;

[0094] The reliability evaluation module 240 evaluates the reliability of the positioning uncertainty result of the positioning component based on the determined positioning error.

[0095] In a possible implementation manner of the present application, the positioning accuracy of the evaluation module is the same as the positioning accuracy of the positioning component, or the positioning accuracy of the evaluation module is higher than the positioning accuracy of the positioning component.

[0096] In a possible implementation of the present application, the true value determination module 220 is further used to: determine the trajectory abnormal points in the second motion trajectory based on the continuous smoothness detection of the second motion trajectory; and determine the posture values ​​corresponding to each trajectory point in the second motion trajectory except the trajectory abnormal points as the reference true value.

[0097] In a possible implementation manner of the present application, the abnormal trajectory point is a trajectory point that satisfies at least one of the following items: abnormal satellite positioning signal reception, abnormal positioning differential signal reception, and abnormal positioning offset of the trajectory point, wherein the abnormal positioning offset of the trajectory point includes at least one of the following items: posture jump, curvature jump, too small curvature, too large acceleration, and too large sideslip angle.

[0098] In a possible implementation manner of the present application, the positioning error of the positioning component is the difference between the posture value of the first motion trajectory at the same sampling time and the corresponding reference true value.

[0099] In a possible implementation manner of the present application, the reliability evaluation module 240 is further used to: determine, for each first time period in which a reference true value is missing, a final state error corresponding to each first time period, and evaluate the reliability of the positioning uncertainty result of the positioning component based on the error distribution of the final state errors of all first time periods.

[0100] In one possible implementation of the present application, the reliability assessment module 240 determines the final state error of each first time period in the following manner: determining the true value moment closest to the end moment of the first time period; determining the positioning error at the true value moment based on the positioning posture at the true value moment and the reference true value; and determining the positioning error at the true value moment as the final state error of the first time period.

[0101] In a possible implementation of the present application, the reliability assessment module 240 is also used to: count the proportion of final-state errors corresponding to all first time periods that fall into multiple preset standard deviation intervals; if the proportion values ​​that fall into each preset standard deviation interval all satisfy the statistical characteristics, then it is determined that the positioning uncertainty result of the positioning component is reliable; if the proportion values ​​that fall into any preset standard deviation interval do not satisfy the statistical characteristics, then it is determined that the positioning uncertainty result of the positioning component is unreliable.

[0102] In a possible implementation of the present application, the reliability assessment module 240 is further used to: for each second time period for which a reference true value exists, evaluate the reliability of the positioning uncertainty result of the positioning component based on the positioning posture of each second time period without relying on the satellite positioning signal.

[0103] In one possible implementation of the present application, the reliability assessment module 240 assesses the reliability of the positioning uncertainty result of the positioning component in the following manner: for each second time period for which a reference true value exists, based on the positioning posture of the second time period without relying on the satellite positioning signal and the corresponding reference true value, the actual error at each sampling moment in the second time period is determined; based on the error distribution of the actual error at each sampling moment of all second time periods, the reliability of the positioning uncertainty result of the positioning component is assessed.

[0104] See also Figure 5 , Figure 5 The schematic diagram of the structure of the electronic device provided by the exemplary embodiment of the present application. Figure 5 As shown, the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0105] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the steps of the vehicle positioning evaluation method in any of the above embodiments can be performed, which are specifically as follows:

[0106] A first motion trajectory of the vehicle measured by a positioning component is obtained; a reference truth value is determined based on a second motion trajectory of the vehicle measured by an evaluation module, wherein the evaluation module and the positioning component are both arranged on the vehicle; a positioning error of the positioning component is determined according to the first motion trajectory of the vehicle and the reference truth value; and the reliability of a positioning uncertainty result of the positioning component is evaluated based on the determined positioning error.

[0107] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle positioning evaluation method in the above method embodiment can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0108] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is executed, the above-mentioned product recommendation method can be executed.

[0109] The embodiment of the present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the vehicle positioning evaluation method in the above method embodiment. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0110] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0114] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A vehicle positioning evaluation method, characterized in that: include: Acquire a first motion trajectory of the vehicle measured by the positioning component; Determining a reference true value based on a second motion trajectory of the vehicle measured by an evaluation module, wherein the evaluation module and the positioning component are both arranged on the vehicle, and the first motion trajectory and the second motion trajectory are motion trajectories obtained in the same time period; Determining a positioning error of the positioning component according to a first motion trajectory of the vehicle and a reference true value; Based on the determined positioning error, the reliability of a positioning uncertainty result of the positioning component is evaluated, wherein the positioning uncertainty result is used to characterize the deviation given by the positioning component for the positioning result.

2. The method according to claim 1, characterized in that The positioning accuracy of the evaluation module is the same as the positioning accuracy of the positioning component, or the positioning accuracy of the evaluation module is higher than the positioning accuracy of the positioning component.

3. The method according to claim 1, characterized in that The step of determining a reference true value based on the second motion trajectory of the vehicle measured by the evaluation module includes: Based on the continuous smoothness detection of the second motion trajectory, determining the trajectory abnormal point in the second motion trajectory; The pose value corresponding to each trajectory point in the second motion trajectory except the trajectory abnormal point is determined as a reference true value.

4. The method according to claim 3, characterized in that The trajectory abnormal point is a trajectory point that satisfies at least one of the following items: Abnormal reception of satellite positioning signals, abnormal reception of positioning differential signals, and abnormal positioning offsets of trajectory points. Among them, the abnormal positioning deviation of the trajectory point includes at least one of the following items: there is a posture jump, there is a curvature jump, there is too small curvature, there is too large acceleration, and there is too large sideslip angle.

5. The method according to claim 1, characterized in that The positioning error of the positioning component is the difference between the pose value of the first motion trajectory at the same sampling time and the corresponding reference true value.

6. The method according to claim 3, characterized in that Based on the determined positioning error, the steps for evaluating the reliability of the positioning uncertainty result of the positioning assembly include: For each first time period lacking a reference true value, a final state error corresponding to each first time period is determined, and based on the error distribution of the final state errors of all first time periods, the reliability of the positioning uncertainty result of the positioning component is evaluated.

7. The method according to claim 6, characterized in that The final state error for each first time period is determined as follows: Determine the time with a true value closest to the end time of the first time period; Determine the positioning error at the time when the true value is available based on the positioning posture at the time when the true value is available and the reference true value; The positioning error at the time when the true value is obtained is determined as the final state error of the first time period.

8. The method according to claim 6, characterized in that The step of evaluating the reliability of the positioning uncertainty result of the positioning assembly based on the error distribution of the final state errors of all the first time periods comprises: Count the proportions of final state errors corresponding to all first time periods that fall within multiple preset standard deviation intervals; If the proportion values ​​falling into each preset standard deviation interval all meet the statistical characteristics, it is determined that the positioning uncertainty result of the positioning component is reliable; If the proportion of values ​​falling into any preset standard deviation interval does not satisfy the statistical characteristics, it is determined that the positioning uncertainty result of the positioning component is unreliable.

9. The method according to claim 1, characterized in that Based on the determined positioning error, the steps for evaluating the reliability of the positioning uncertainty result of the positioning assembly include: For each second time period for which a reference true value exists, the reliability of the positioning uncertainty result of the positioning component is evaluated based on the positioning pose of each second time period without relying on the satellite positioning signal.

10. The method according to claim 9, characterized in that The reliability of the positioning uncertainty results of the positioning components is evaluated by: For each second time period for which a reference true value exists, based on the positioning posture of the second time period without relying on the satellite positioning signal and the corresponding reference true value, determine the actual error of each sampling time in the second time period; Based on the error distribution of the actual errors at each sampling time of all the second time periods, the reliability of the positioning uncertainty result of the positioning component is evaluated.

11. A vehicle positioning evaluation device, characterized in that: include: A trajectory acquisition module, which acquires a first motion trajectory of the vehicle measured by the positioning component; a truth value determination module, which determines a reference truth value based on a second motion trajectory of the vehicle measured by an evaluation module, wherein the evaluation module and the positioning component are both arranged on the vehicle, and the first motion trajectory and the second motion trajectory are motion trajectories obtained in the same time period; an error determination module, determining a positioning error of the positioning component according to a first motion trajectory of the vehicle and a reference true value; The reliability evaluation module evaluates the reliability of the positioning uncertainty result of the positioning component based on the determined positioning error.