Map evaluation method and device

Abstract

A map evaluation method and device are used for evaluating the availability of a high-precision map so as to improve the vehicle positioning performance and improve the driving safety. In the method, n frames of scene images of a map to be evaluated can be acquired, and n is an integer greater than 1; map matching is carried out based on the n frames of scene images, first pose information and second pose information are obtained, the first pose information comprises pose information of a target object output by an inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information comprises pose information of the target object output by a fusion positioning system; and based on the difference information of the first pose information and the second pose information, obtaining the confidence of the to-be-evaluated map, the confidence being used for representing the accuracy of map matching based on the to-be-evaluated map.

Description

Technical Field

[0001] This application relates to the field of map technology, and in particular to a map evaluation method and apparatus. Background Technology

[0002] Intelligent vehicle autonomous driving technology is of great significance for improving driving efficiency and safety. In vehicles with autonomous driving functions, the vehicle is endowed with advanced perception, decision-making and control performance.

[0003] High-definition maps (HD maps) serve as a crucial data foundation for autonomous driving technology, providing intelligent vehicles with accurate prior road environment information and playing a vital role in the vehicle's perception, decision-making, and control functions. HD map data is often fused with data from other sensors in the perception layer to provide accurate vehicle pose information, making it a key technology in intelligent connected vehicles.

[0004] Currently, fusion positioning systems based on high-precision maps and sensors such as cameras, lidar, Global Navigation Satellite System (GNSS), and inertial measurement units (IMUs) have become crucial components of intelligent connected vehicles. The accuracy and real-time performance of this fusion positioning system are indispensable for correct subsequent decision-making and control. However, changes in the road environment inevitably lead to deviations and outdated information in high-precision maps. For example, extreme weather and road construction can cause changes or disappearance of map elements used for matching and positioning, such as lane lines and light poles. These changes or disappearances have a significant impact on matching and positioning, and even on the entire fusion positioning system; incorrect pose information can trigger vehicle safety issues. Summary of the Invention

[0005] This application provides a map evaluation method and apparatus for evaluating the usability of high-precision maps, so as to improve vehicle positioning performance and enhance driving safety.

[0006] In a first aspect, this application provides a map evaluation method, which may include: acquiring n frames of scene images of a map to be evaluated, where n is an integer greater than 1; performing map matching based on the n frames of scene images to obtain first pose information and second pose information, wherein the first pose information includes pose information of a target object output by an inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information includes pose information of the target object output by a fusion positioning system; and obtaining a confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, wherein the confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

[0007] In one possible implementation, the step of performing map matching based on the n frames of scene images to obtain first pose information and second pose information includes: performing map matching based on the n frames of scene images to obtain first pose information, a first covariance associated with the first pose information, second pose information, and a second covariance associated with the second pose information; the step of obtaining the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information includes: obtaining the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance.

[0008] In one possible implementation, obtaining the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance, includes: for each frame of the n-frame scene images, calculating a state chi-square value using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance; generating a frequency distribution histogram based on the n state chi-square values ​​associated with the n-frame scene images; and fitting a probability density function to the frequency distribution histogram to obtain the confidence level of the map to be evaluated.

[0009] In one possible implementation, the target object includes at least one map element in the map to be evaluated.

[0010] In one possible implementation, prior to performing map matching based on the n frames of scene images, the method further includes:

[0011] The positions of at least one map element in the map to be evaluated are modified to obtain at least one simulated map of the map to be evaluated; the step of performing map matching based on the n frames of scene images to obtain first pose information and second pose information includes: performing a simulation test of map matching based on the n frames of scene images and the at least one simulated map to obtain at least one set of first pose information and second pose information; the confidence level of the map to be evaluated is obtained based on the difference information between the first pose information and the second pose information, including: obtaining the confidence level of the map to be evaluated based on the difference information between the at least one set of first pose information and second pose information.

[0012] In one possible implementation, the map to be evaluated is an elevation-free map, and the step of modifying the position of at least one map element in the map to be evaluated to obtain at least one simulated map of the map to be evaluated includes: for a target map element among the at least one map elements, obtaining at least one moving distance and / or moving angle of the target map element in the XY plane; modifying the map to be evaluated based on the at least one moving distance and / or moving angle to obtain at least one simulated map of the map to be evaluated.

[0013] Secondly, this application provides a map evaluation apparatus, comprising: an acquisition unit, configured to acquire n frames of scene images of a map to be evaluated, where n is an integer greater than 1; a map matching unit, configured to perform map matching based on the n frames of scene images to obtain first pose information and second pose information, wherein the first pose information includes pose information of a target object output by an inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information includes pose information of the target object output by a fusion positioning system; and an evaluation unit, configured to obtain a confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, wherein the confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

[0014] In one possible implementation, the map matching unit is specifically used to: perform map matching based on the n frames of scene images to obtain the first pose information, the first covariance associated with the first pose information, the second pose information, and the second covariance associated with the second pose information; the evaluation unit is specifically used to: obtain the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance.

[0015] In one possible implementation, the evaluation unit is specifically used to: for each frame of the n-frame scene images, calculate a state chi-square value using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance; generate a frequency distribution histogram based on the n state chi-square values ​​associated with the n-frame scene images; and perform probability density function fitting based on the frequency distribution histogram to obtain the confidence level of the map to be evaluated.

[0016] In one possible implementation, the target object includes at least one map element in the map to be evaluated.

[0017] In one possible implementation, the apparatus further includes: a simulation unit for modifying the position of at least one map element in the map to be evaluated to obtain at least one simulated map of the map to be evaluated; the map matching unit is specifically used for: performing a simulation test of map matching based on the n-frame scene images and the at least one simulated map to obtain at least one set of first pose information and second pose information; the evaluation unit is specifically used for: obtaining the confidence level of the map to be evaluated based on the difference information between the at least one set of first pose information and second pose information.

[0018] In one possible implementation, the map to be evaluated is an elevation-free map, and the simulation unit is specifically used to: for a target map element among the at least one map elements, obtain at least one moving distance and / or moving angle of the target map element in the XY plane; modify the map to be evaluated based on the at least one moving distance and / or moving angle to obtain at least one simulated map of the map to be evaluated.

[0019] Thirdly, this application provides a communication device including at least one processor and an interface circuit, wherein the interface circuit is used to provide data or code instructions to the at least one processor, and the at least one processor is used to implement the method as described in the first aspect and any possible implementation thereof through logic circuits or executing code instructions.

[0020] Fourthly, this application provides a computing device including a processor and a memory, the processor being coupled to the memory, the processor being configured to execute a computer program stored in the memory such that the computing device performs the method as described in the first aspect and any possible implementation thereof.

[0021] Fifthly, this application provides a chip including at least one processor and an interface, wherein the at least one processor is configured to read instructions through the interface to execute the method as described in the first aspect and any possible implementation thereof.

[0022] Sixthly, this application provides a computer-readable storage medium storing a computer program that, when executed, implements the method described in the first aspect and any possible implementation thereof.

[0023] In a seventh aspect, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to perform the method described in the first aspect and any possible implementation thereof.

[0024] Based on the implementations provided in the above aspects, the embodiments of this application can be further combined to provide more implementations.

[0025] The technical effects that can be achieved by any possible implementation of any of the second to seventh aspects mentioned above can be described with reference to the technical effects that can be achieved by any possible implementation of the first aspect mentioned above, and the repetitions will not be discussed. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of a possible system architecture applicable to the embodiments of this application;

[0027] Figure 2 This is a flowchart illustrating the map evaluation method according to an embodiment of this application;

[0028] Figure 3 This is a schematic diagram of the probability density function of ξ(k) under a specific prior map in an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of the map confidence model under different mapping errors of a map feature in a priori map, according to an embodiment of this application.

[0030] Figure 5 This is a schematic diagram of the map confidence model under different mapping errors of another map element in the prior map, according to an embodiment of this application.

[0031] Figure 6 This is a schematic diagram of the structure of a communication device according to an embodiment of this application;

[0032] Figure 7 This is a schematic diagram of the structure of another communication device according to an embodiment of this application. Detailed Implementation

[0033] This application provides a map evaluation method and apparatus for evaluating the usability of high-precision maps to improve vehicle positioning performance and enhance driving safety. The method and apparatus are based on the same technical concept. Since the principles by which the method and apparatus solve problems are similar, their implementations can be mutually referenced, and repeated details will not be repeated. Furthermore, in the various embodiments of this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0034] It should be noted that in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0035] Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the priority or importance of multiple objects. For example, "first pose information" and "second pose information" are only used to distinguish pose information obtained in different ways, and do not indicate that the two pose information are different in priority or importance.

[0036] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0037] Before introducing the map evaluation method provided in the embodiments of this application, the system architecture applicable to the embodiments of this application will be described in detail first.

[0038] Figure 1 This is a schematic diagram of a possible system architecture applicable to the embodiments of this application, such as... Figure 1 The system architecture shown may include acquisition device 110, server 120 and electronic device 130.

[0039] Data acquisition device 110 refers to a device capable of acquiring environmental information in a real traffic network, which may include, but is not limited to, the following types of devices:

[0040] Third-party server 111 refers to a server set up in a third-party organization that is independent of server 120 and electronic device 130 and has shared functions. In the field of vehicle networking, the third-party organization can typically be a manager of the transportation system, such as the Ministry of Transport, or urban transportation management offices or management stations at various levels. The managers of the transportation system have the ability to monitor various traffic routes in the transportation system in real time. They can not only obtain timely information on the traffic conditions of each route, but also make certain changes to the traffic patterns, such as changing the speed limit of a particular route. Road environment information can also be obtained through the server set up in the third-party organization. For example, this server can be a vehicle networking server. The vehicle networking server can provide planning and control services for vehicle networking terminals by maintaining and updating high-definition map (HD MAP) information, and can also maintain and update map information to provide navigation services for vehicle networking terminals.

[0041] A roadside unit (RSU) 112 refers to a communication-enabled device installed on one or both sides of a road. Typically, the RSU establishes a connection with the onboard unit (OBU) of a vehicle when it passes by, enabling vehicle identification. In this embodiment, the RSU may also encapsulate functional modules such as cameras, radar, or laser emitters. These modules allow the RSU to monitor the road in real time and promptly obtain environmental information when changes occur.

[0042] Vehicle 113 has data acquisition functions such as camera and sensor capabilities, enabling it to collect environmental information around the vehicle. The vehicle's camera device can be a monocular camera, a binocular camera, etc. The camera's field of view can be the vehicle's external environment. The vehicle's sensor devices can include radar such as lidar, millimeter-wave radar, and ultrasonic radar for acquiring environmental information, and may also include an inertial navigation system (e.g., a global navigation satellite system (GNSS)) and an inertial measurement unit (IMU) for acquiring the vehicle's attitude. (e.g., IMU, etc.) GNSS can be used to estimate a vehicle's geographic location. For this purpose, GNSS can include transceivers that estimate the vehicle's position relative to the Earth based on satellite positioning data. In an example, the vehicle's computer system can use GNSS in conjunction with map data to estimate the road the vehicle is traveling on. An IMU can sense changes in the vehicle's position and orientation based on inertial acceleration and any combination thereof. In some examples, the combination of sensors in the IMU may include, for example, accelerometers and gyroscopes. The positioning information obtained based on GNSS and information obtained based on other technologies (e.g., IMU) is fused, and the fused result is used as the vehicle's global pose at the current moment. This method of fusing information obtained based on GNSS and information obtained based on other technologies (e.g., sensors such as IMUs) to achieve positioning can be called combined positioning or fusion positioning. However, combined positioning can also match data collected by other sensors with corresponding sensor data stored in a high-precision map to achieve lane-level positioning of the vehicle. For example, millimeter-wave radar sensors can use radio signals to sense targets in the vehicle's surrounding environment. In some embodiments, in addition to sensing targets, millimeter-wave radar can also be used to sense the speed and / or direction of travel of targets. LiDAR can use lasers to sense targets in the environment in which the vehicle is located. Sensors can be used to capture multiple images of the vehicle's surrounding environment. In addition, each vehicle can be equipped with one or more sensors, and the number of each type of sensor can be one or more. Sensors can be installed on the top of the vehicle (e.g., in the middle of the top of the vehicle), the front of the vehicle, etc. The embodiments of this application do not limit the installation location and number of sensors in each vehicle.

[0043] Here, server 120 can refer to a single server or a server cluster consisting of multiple servers. In the field of connected vehicles, server 120 can specifically be a cloud server, also known as cloud, cloud-based server, cloud controller, or connected vehicle server, etc. Cloud server is a general term for devices or components with data processing capabilities, which may include physical devices such as hosts or processors, virtual devices such as virtual machines or containers, and chips or integrated circuits.

[0044] The electronic device 130 can be a smart terminal with map evaluation capabilities or any vehicle, including but not limited to cars, buses, and even trucks. The electronic device 130 can also typically register with the server 120 to access various services provided by the server 120, such as voice services, map evaluation services, autonomous driving services, flight search services, or voice broadcast services.

[0045] It should be understood that the embodiments of this application do not limit the types and quantities of data collection devices, the number of servers, or the number of user vehicles in the system architecture. For example, one server can interact with only one type of data collection device (such as third-party server 111) and one user vehicle, or it can interact with multiple data collection devices (such as roadside unit 112 and vehicle 113) and one user vehicle, or it can interact with multiple data collection devices and multiple user vehicles. Information interaction between two devices can refer to direct interaction via wired or wireless means, or indirect interaction via one or more other devices. Furthermore, the system architecture applicable to the embodiments of this application may include other devices besides data collection devices, servers, and user vehicles, such as terminal devices, network devices, core network devices, etc., and the embodiments of this application do not limit this. Also, any device in the embodiments of this application can integrate its functions on a single physical unit or distribute its functions across multiple independent physical units, and the embodiments of this application do not limit this.

[0046] based on Figure 1 The illustrated system architecture allows electronic device 130 to acquire environmental information from the real traffic network via data acquisition device 110, which in turn uploads this information to server 120. Server 120 can then construct a map to be evaluated based on this environmental information. Electronic device 130 can also pre-obtain the map to be evaluated from server 120 and perform an evaluation on it.

[0047] The above describes the system architecture applicable to the embodiments of this application. The map evaluation method provided by the embodiments of this application is described below with reference to the specific accompanying drawings.

[0048] Figure 2 This is a flowchart illustrating a map evaluation method provided in an embodiment of this application. This method is applicable to electronic devices with map evaluation capabilities (e.g., such as...). Figure 1 The electronic device 130 shown is an example. Figure 2 As shown, the method may include the following steps:

[0049] S210: The electronic device acquires n frames of scene images of the map to be evaluated, where n is an integer greater than 1.

[0050] In this embodiment, the map to be evaluated can be a high-precision map of a certain area or region, used to provide prior road environment information. The map to be evaluated can also be called a priori map. Electronic devices can download this high-precision map from a server in advance to implement navigation or positioning functions based on it.

[0051] In one example, the electronic device itself can have a camera, which can capture images or videos of the real-world scene corresponding to the map being evaluated, thereby obtaining the n frames of scene images. In another example, the electronic device can acquire the n frames of scene images from other devices via wired or wireless communication technology. For example, in... Figure 1 In this embodiment, the electronic device can download n frames of scene images of the map to be evaluated from the server. Alternatively, the electronic device can acquire n frames of scene images of the map to be evaluated from roadside units. In another example, the electronic device can play back a recorded real scene and read n frames of scene images. This application does not specifically limit the method of acquiring these multiple frames of images.

[0052] It should be understood that the above is merely an example using a single map and does not constitute any limitation. In other embodiments, there can be multiple maps to be evaluated in S210. For example, if there are m prior maps, when implementing S210, prior map i is used as the map to be evaluated, and the electronic device can obtain n of the prior map i. i A frame of scene image. Where m is an integer greater than or equal to 1, i = 1, 2, ..., m, n i It is an integer greater than 1.

[0053] S220: The electronic device performs map matching based on n frames of scene images to obtain the first pose information and the second pose information.

[0054] In this embodiment of the application, the electronic device can implement S220 through its own fusion positioning system. The first pose information may include the pose information of the target object output by the IMU associated with n frames of scene images, and the second pose information may include the pose information of the target object output by the fusion positioning system.

[0055] Specifically, when the fusion localization system matches the map features extracted from the k-th frame scene image of the n-th frame scene image of the prior map i with the prior map i, it can output the pose state variables and covariance recursively derived by the IMU, as well as the pose state variables and covariance of the fused pose. The pose is represented by 3 position degrees of freedom (x, y, z) and 3 orientation degrees of freedom (α, γ, β), and the covariance matrix is ​​represented by the covariance between each degree of freedom, satisfying the following expression (1):

[0056]

[0057] For ease of distinction, in this embodiment, the pose state quantity recursively derived by the IMU is referred to as the first pose information, denoted as x1(k), and the corresponding covariance is referred to as the first covariance, denoted as P1(k). The pose state quantity of the fused pose is referred to as the second pose information, denoted as x2(k), and the corresponding covariance is referred to as the second covariance P2(k).

[0058] S230: The electronic device obtains the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information. The confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

[0059] For example, the greater the difference between the first pose information and the second pose information, the smaller the similarity and the lower the confidence level, indicating lower accuracy of map matching based on the map to be evaluated. If the map's confidence level is lower than a preset first threshold, it will affect vehicle positioning performance and driving safety, requiring map optimization.

[0060] For example, the greater the difference between the first pose information and the second pose information, the smaller the similarity and the higher the confidence level, indicating a lower accuracy in map matching based on the map being evaluated. If the map's confidence level is higher than a preset second threshold, it will affect vehicle positioning performance and driving safety, requiring map optimization.

[0061] The embodiments of this application do not limit the correspondence between the confidence level and the accuracy.

[0062] Optionally, in implementing S220, the electronic device can use a fusion positioning system to perform map matching based on n frames of scene images to obtain the first pose information, the first covariance associated with the first pose information, the second pose information, and the second covariance associated with the second pose information. In implementing S230, the electronic device can obtain the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, as well as the difference information between the first covariance and the second covariance.

[0063] For example, for each frame of scene images in n frames, the electronic device can calculate the state chi-square value using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance. The electronic device can calculate n state chi-square values ​​associated with the n frames of scene images using the same method. The smaller the state chi-square value, the higher the similarity between the fused localization result and the IMU recursive result; the larger the value, the lower the similarity. Based on the n state chi-square values ​​associated with the n frames of scene images, a frequency distribution histogram can be generated, and a probability density function can be fitted according to the frequency distribution histogram to obtain the confidence level of the map to be evaluated.

[0064] For the k-th scene image in n-frame scene images, the electronic device can calculate the difference b(k) of pose information and the difference B(k) of covariance using the following expressions (2) and (3):

[0065] b(k)=x1(k)-x2(k) (2);

[0066] B(k)=P1(k)-P2(k) (3);

[0067] Then, substituting into the following expression (4), we obtain the chi-square value ξ(k) of the state corresponding to the scene image of the kth frame:

[0068] ξ(k)=bT(k)B-1(k)b(k) (4);

[0069] It should be understood that the above expressions (2)-(4) are general expressions. For the k-th frame scene image of the prior map i, each parameter can be represented as bi(k), Bi(k), and ξi(k), respectively. If the prior map is represented as j, then for the k-th frame scene image of the prior map j, each parameter can be represented as bj(k), Bj(k), and ξj(k), respectively.

[0070] Then, the electronic device can statistically analyze the ξi(k) values ​​of the fused localization results obtained from map matching each time under the prior map i, generate a frequency distribution histogram, and fit a probability density function based on this frequency distribution histogram to obtain the probability density function of ξi(k) for the prior map i. This probability density function includes the difference between the pose result obtained from map matching under the current prior map i and the IMU recursive pose result. Therefore, this probability density function can be used as the confidence model for the prior map i. Under correct observation conditions, the smaller the expectation and variance obtained from solving this probability density function, the higher the accuracy of map matching and the higher the confidence of the prior map i.

[0071] Through the gamma distribution:

[0072]

[0073] To fit the probability density function of ξ(k) on the map to be evaluated, we determine its shape parameter α and inverse scaling parameter β, thus obtaining the distribution of ξ. The fitted curve is shown below. Figure 3 As shown, the curves showing the distribution of ξ differ when the values ​​of the shape parameter α and the inverse scaling parameter β are different.

[0074] Understandably, in practical implementation, abnormal data is difficult to obtain. To obtain more test data, in an optional implementation, before S220, the position of at least one map element in the map to be evaluated can be modified to obtain at least one simulated map of the map to be evaluated, thereby simulating mapping errors. Then, based on at least one simulated map of the map to be evaluated, S220 and S230 are performed to conduct simulation tests to obtain a confidence model of the map to be evaluated and obtain more accurate evaluation results. For example, S220 can be replaced by: performing a map matching simulation test based on the n frames of scene images and the at least one simulated map to obtain at least one set of first pose information and second pose information. S230 can be replaced by: obtaining the confidence of the map to be evaluated based on the difference information between the at least one set of first pose information and second pose information.

[0075] In specific implementation, the map to be evaluated can be a map without elevation data, and at least one map element in the map to be evaluated can include lane lines, light poles, etc. When obtaining the simulated map, for a target map element among at least one map element, at least one moving distance and / or moving angle of the target map element in the XY plane can be obtained, and the map to be evaluated can be modified based on the at least one moving distance and / or moving angle to obtain at least one simulated map of the map to be evaluated. The method of obtaining this information can be configured by the user in the interface, or it can be obtained by obtaining relevant configuration information through a configuration file; this application embodiment does not specifically limit this.

[0076] For example, taking the simulated mapping offset error of light poles in a map as an example, an abnormal data simulation method for light pole elements can be designed: The coordinates (X,Y) of the constituent elements of the light pole are offset globally on the XY plane, including offsets based on the movement angle θ and / or offsets based on the movement distance. Since the error has a random nature, the movement angle θ can be designed to be uniformly distributed, with θp belonging to U(0,360°). Alternatively, based on the actual error magnitude, the movement distance sp(k) can be designed as {sp,min,……,sp,max}, where p represents the light pole. For example, the movement distance sp can be {0.1m,0.2m,0.3m,0.4m}.

[0077] Taking the simulated mapping offset error of lane lines in a map as an example, an abnormal data simulation method for lane line elements can be designed: The coordinates (X, Y) of the lane line elements are offset globally on the XY plane, including offsets based on the movement angle θ and / or offsets based on the movement distance. Similarly, due to the randomness of the error, the movement angle θ is designed to be uniformly distributed, with θl belonging to U(0, 360°). Alternatively, based on the actual error magnitude, the movement distance sl(k) can be designed as {sl, min, ..., sl, max}, where 1 represents the lane line. For example, the movement distance sl can be {0.1m, 0.2m, 0.3m, 0.4m}.

[0078] Then, in S220, the electronic device can perform a map matching simulation test based on the n frames of scene images and the at least one simulated map to obtain at least one set of first pose information and second pose information. And in S230, based on the difference information between the at least one set of first pose information and second pose information, the confidence level of the map to be evaluated is obtained, including the map confidence level of the map to be evaluated under different mapping errors.

[0079] For example, the prior map of the lamppost offset sp = {0.1m, 0.2m, 0.3m, 0.4m} was tested and its ξ value was obtained as {ξsp = 0.1(k), ξsp = 0.2(k), ξsp = 0.3(k), ξsp = 0.4(k)}.

[0080] The prior map with lane offset sl = {0.1m, 0.2m, 0.3m, 0.4m} was tested and the results were obtained as {ξsl = 0.1(k), ξsl = 0.2(k), ξsl = 0.3(k), ξsl = 0.4(k)}.

[0081] The probability distribution of ξ(k) values ​​under different mapping errors is fitted to obtain their probability density functions and then compared.

[0082] The probability density function curve of the ξ value under the pole offset sp = {0.1m, 0.2m, 0.3m, 0.4m} is given by... Figure 4 As shown, the expected values ​​E(ξ) are {0.0432, 0.0443, 0.0510, 0.0562}, and the variances D(ξ) are {0.0013, 0.0014, 0.0020, 0.0024}. Within the range of 0.1-0.4m of pole offset, the expected and variance of ξ(k) values ​​increase with the increase of pole offset.

[0083] The probability density function curve of ξ(k) for lane offset sp = {0.1m, 0.2m, 0.3m, 0.4m} is given by... Figure 5As shown, the expected values ​​E(ξ) are {0.0482, 0.0549, 0.0701, 0.0816}, and the variances D(ξ) are {0.0017, 0.0021, 0.0039, 0.0049}. Within the lane line offset range of 0.1-0.4m, the expected value and variance of ξ(k) increase with the increase of the lamppost offset.

[0084] In summary, regardless of whether it is a light pole or a lane line element, when the positional error increases, the expected value and variance of the prior map ξ(k) obtained from the probability density function both increase. This means that the fused positioning result and the IMU recursive result are significantly different, which indicates that the accuracy and stability of the map matching process are reduced, and the confidence of the corresponding prior map is reduced.

[0085] It should be understood that the above methods are merely examples using light poles or lane lines as map elements and do not constitute any limitation. In actual implementation, map elements can also include other static elements, such as traffic lights and traffic signs, which will not be elaborated here.

[0086] According to the aforementioned method, Figure 6 This is a schematic diagram of the structure of a map evaluation device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device can be an electronic device, or it can be a chip or circuit, such as a chip or circuit that can be disposed in an electronic device. The electronic device can be a device with processing capabilities, for example, such as... Figure 1 The aforementioned electronic device 130.

[0087] Furthermore, the map evaluation device 601 may further include a bus system, wherein the processor 602, memory 604, and transceiver 603 can be connected through the bus system.

[0088] It should be understood that the processor 602 described above can be a chip. For example, the processor 602 can be a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0089] In implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware in the processor 602 or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly implemented by the hardware processor, or by a combination of hardware and software modules in the processor 602. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 604, and the processor 602 reads the information in memory 604 and, in conjunction with its hardware, completes the steps of the above method.

[0090] It should be noted that the processor 602 in this application embodiment can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this application embodiment. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in this application embodiment can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0091] It is understood that the memory 604 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0092] In the case of an electronic device, the map evaluation device 601 may include a processor 602, a transceiver 603, and a memory 604. The memory 604 is used to store instructions, and the processor 602 is used to execute the instructions stored in the memory 604 to implement the relevant scheme of the electronic device in the above method embodiment.

[0093] When the map evaluation device 601 is an electronic device and performs Figure 2 The map evaluation method shown is as follows:

[0094] The processor 602 can acquire n frames of scene images of the map to be evaluated, where n is an integer greater than 1; perform map matching based on the n frames of scene images to obtain first pose information and second pose information. The first pose information includes the pose information of the target object output by the inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information includes the pose information of the target object output by the fused positioning system; based on the difference information between the first pose information and the second pose information, obtain the confidence level of the map to be evaluated, which is used to characterize the accuracy of map matching based on the map to be evaluated. For specific implementation details, please refer to the preceding text. Figure 2 The relevant information will not be repeated here.

[0095] Based on the above embodiments and the same concept, Figure 7 A schematic diagram of the map evaluation device provided in the embodiments of this application, such as Figure 7 As shown, the map evaluation device 700 can be an electronic device, or a chip or circuit within an electronic device. The map evaluation device 700 can implement the steps performed by the aforementioned electronic device. The map evaluation device 700 may include: an acquisition unit 701, used to acquire n frames of scene images of the map to be evaluated, where n is an integer greater than 1; a map matching unit 702, used to perform map matching based on the n frames of scene images to obtain first pose information and second pose information, wherein the first pose information includes the pose information of a target object output by an inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information includes the pose information of the target object output by a fusion positioning system; and an evaluation unit 703, used to obtain the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, wherein the confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

[0096] In one possible design, the map matching unit 702 is specifically used to: perform map matching based on the n frames of scene images to obtain the first pose information, the first covariance associated with the first pose information, the second pose information, and the second covariance associated with the second pose information; the evaluation unit is specifically used to: obtain the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance.

[0097] In one possible design, the evaluation unit 703 is specifically used to: for each frame of the n-frame scene images, calculate the state chi-square value using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance; generate a frequency distribution histogram based on the n state chi-square values ​​associated with the n-frame scene images; and perform probability density function fitting based on the frequency distribution histogram to obtain the confidence level of the map to be evaluated.

[0098] In one possible design, the target object includes at least one map element from the map to be evaluated.

[0099] In one possible design, the apparatus further includes: a simulation unit for modifying the position of at least one map element in the map to be evaluated to obtain at least one simulated map of the map to be evaluated; the map matching unit is specifically used for: performing a simulation test of map matching based on the n-frame scene images and the at least one simulated map to obtain at least one set of first pose information and second pose information; the evaluation unit is specifically used for: obtaining the confidence level of the map to be evaluated based on the difference information between the at least one set of first pose information and second pose information.

[0100] In one possible design, the map to be evaluated is an elevation-free map, and the simulation unit is specifically used to: for a target map element among the at least one map elements, obtain at least one moving distance and / or moving angle of the target map element in the XY plane; modify the map to be evaluated based on the at least one moving distance and / or moving angle to obtain at least one simulated map of the map to be evaluated.

[0101] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to perform the method of any one of the above method embodiments.

[0102] This application also provides an electronic device for performing the method of any one of the above method embodiments.

[0103] The terms “component,” “module,” “system,” etc., used in this specification are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0104] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0105] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0109] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A map evaluation method, characterized in that, include: Obtain n frames of scene images of the map to be evaluated, where n is an integer greater than 1; Map matching is performed based on the n-frame scene images to obtain first pose information and second pose information. The first pose information includes the pose information of the target object output by the inertial measurement unit (IMU) associated with the n-frame scene images, and the second pose information includes the pose information of the target object output by the fusion positioning system. Based on the difference between the first pose information and the second pose information, the confidence level of the map to be evaluated is obtained, and the confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

2. The method according to claim 1, characterized in that, The step of performing map matching based on the n frames of scene images to obtain the first pose information and the second pose information includes: Map matching is performed based on the n frames of scene images to obtain the first pose information, the first covariance associated with the first pose information, the second pose information, and the second covariance associated with the second pose information. The process of obtaining the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information includes: Based on the difference between the first pose information and the second pose information, as well as the difference between the first covariance and the second covariance, the confidence level of the map to be evaluated is obtained.

3. The method according to claim 2, characterized in that, The process of obtaining the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance, includes: For each scene image in the n-frame scene images, the state chi-square value is calculated using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance. A frequency distribution histogram is generated based on the n state chi-square values ​​associated with the n frame scene images; The confidence level of the map to be evaluated is obtained by fitting a probability density function to the frequency distribution histogram.

4. The method according to any one of claims 1-3, characterized in that, The target object includes at least one map element in the map to be evaluated.

5. The method according to claim 4, characterized in that, Before performing map matching based on the n frames of scene images, the method further includes: The position of at least one map element in the map to be evaluated is modified to obtain at least one simulated map of the map to be evaluated; The step of performing map matching based on the n frames of scene images to obtain the first pose information and the second pose information includes: Based on the n frames of scene images and the at least one simulated map, a map matching simulation test is performed to obtain at least one set of first pose information and second pose information. Based on the difference between the first pose information and the second pose information, the confidence level of the map to be evaluated is obtained, including: The confidence level of the map to be evaluated is obtained based on the difference information between the first pose information and the second pose information.

6. The method according to claim 5, characterized in that, The map to be evaluated is a map without elevation data. Modifying the position of at least one map element in the map to be evaluated to obtain at least one simulated map of the map to be evaluated includes: For a target map element among the at least one map element, obtain at least one moving distance and / or moving angle of the target map element in the XY plane; Based on the at least one movement distance and / or movement angle, the map to be evaluated is modified to obtain at least one simulated map of the map to be evaluated.

7. A map evaluation device, characterized in that, include: The acquisition unit is used to acquire n frames of scene images of the map to be evaluated, where n is an integer greater than 1; The map matching unit is used to perform map matching based on the n frames of scene images to obtain first pose information and second pose information. The first pose information includes the pose information of the target object output by the inertial measurement unit (IMU) associated with the n frames of scene images, and the second pose information includes the pose information of the target object output by the fusion positioning system. An evaluation unit is used to obtain the confidence level of the map to be evaluated based on the difference information between the first pose information and the second pose information. The confidence level is used to characterize the accuracy of map matching based on the map to be evaluated.

8. The apparatus according to claim 7, characterized in that, The map matching unit is specifically used for: Map matching is performed based on the n frames of scene images to obtain the first pose information, the first covariance associated with the first pose information, the second pose information, and the second covariance associated with the second pose information. The evaluation unit is specifically used for: Based on the difference between the first pose information and the second pose information, as well as the difference between the first covariance and the second covariance, the confidence level of the map to be evaluated is obtained.

9. The apparatus according to claim 8, characterized in that, The evaluation unit is specifically used for: For each scene image in the n-frame scene images, the state chi-square value is calculated using the state chi-square test theory, the difference information between the first pose information and the second pose information, and the difference information between the first covariance and the second covariance. A frequency distribution histogram is generated based on the n state chi-square values ​​associated with the n frame scene images; The confidence level of the map to be evaluated is obtained by fitting a probability density function to the frequency distribution histogram.

10. The apparatus according to any one of claims 7-9, characterized in that, The target object includes at least one map element in the map to be evaluated.

11. The apparatus according to claim 10, characterized in that, The device further includes: A simulation unit is used to modify the position of at least one map element in the map to be evaluated to obtain at least one simulated map of the map to be evaluated. The map matching unit is specifically used for: Based on the n frames of scene images and the at least one simulated map, a map matching simulation test is performed to obtain at least one set of first pose information and second pose information. The evaluation unit is specifically used for: The confidence level of the map to be evaluated is obtained based on the difference information between the first pose information and the second pose information.

12. The apparatus according to claim 11, characterized in that, The map to be evaluated is a map without elevation data, and the simulation unit is specifically used for: For a target map element among the at least one map element, obtain at least one moving distance and / or moving angle of the target map element in the XY plane; Based on the at least one movement distance and / or movement angle, the map to be evaluated is modified to obtain at least one simulated map of the map to be evaluated.

13. A computing device, characterized in that, The device includes a processor and a memory, the processor being coupled to the memory, the processor being configured to execute a computer program stored in the memory such that the computing device performs the method as described in any one of claims 1-6.

14. A chip, characterized in that, It includes at least one processor and an interface, wherein the at least one processor is configured to read instructions through the interface to perform the method as described in any one of claims 1-6.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1-6.

16. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method as described in any one of claims 1-6.

Images