CN113011517A

CN113011517A - Positioning result detection method and device, electronic equipment and storage medium

Info

Publication number: CN113011517A
Application number: CN202110342234.4A
Authority: CN
Inventors: 何磊; 王潇峰; 刘余钱
Original assignee: Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Priority date: 2021-03-30
Filing date: 2021-03-30
Publication date: 2021-06-22

Abstract

The present disclosure provides a method, an apparatus, an electronic device and a storage medium for detecting a positioning result, wherein the method comprises: acquiring a positioning result of positioning equipment and first environment sensing information acquired by a sensor associated with the positioning equipment at a position indicated by the positioning result; acquiring second environment sensing information of a target scene corresponding to the positioning position indicated by the positioning result according to a pre-constructed map, wherein the map comprises the environment sensing information of a plurality of positioning positions; rasterizing the second environment sensing information, and determining an effectiveness detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterizing.

Description

Positioning result detection method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of positioning technologies, and in particular, to a method and an apparatus for detecting a positioning result, an electronic device, and a storage medium.

Background

With the development of science and technology, vehicles, robots and the like occupy an important position in the life of people. The accuracy of positioning and navigation of vehicles, robots and the like plays a crucial role in the intellectualization and automation of the vehicles, the robots and the like, and the effective identification of the uncertainty of the positioning result is the premise of ensuring the reliability of the positioning result.

Generally, the uncertainty of the positioning result can be determined through the difference between the current positioning result and the positioning result at the previous time, but the above method cannot accurately determine the positioning result in a scene with large positioning uncertainty, such as a scene in which the vehicle moves but the positioning result returns to the vehicle is still. Therefore, it is important to provide a method capable of determining uncertainty of positioning result in multiple directions and accurately.

Disclosure of Invention

In view of the above, the present disclosure at least provides a method and an apparatus for detecting a positioning result, an electronic device, and a storage medium.

In a first aspect, the present disclosure provides a method for detecting a positioning result, including:

acquiring a positioning result of positioning equipment and first environment sensing information acquired by a sensor associated with the positioning equipment at a position indicated by the positioning result;

acquiring second environment sensing information of a target scene corresponding to the positioning position indicated by the positioning result according to a pre-constructed map, wherein the map comprises the environment sensing information of a plurality of positioning positions;

rasterizing the second environment sensing information, and determining an effectiveness detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterizing.

By adopting the method, the positioning result of the positioning device and the first environment sensing information acquired by the sensor associated with the positioning device at the position indicated by the positioning result are obtained, the second environment sensing information of the target scene corresponding to the positioning position indicated by the positioning result is obtained according to the pre-constructed map, the second environment sensing information can be regarded as the standard environment sensing information corresponding to the positioning result, when the difference between the first environment sensing information and the second environment sensing information is small, the accuracy of the positioning result is high, the effectiveness of the positioning result is high, and the effectiveness detection result of the positioning result can be accurately determined by utilizing the second environment sensing information and the first environment sensing information after rasterization.

Meanwhile, under the scene with larger uncertainty, the difference between the positioning result at the previous moment and the positioning result at the current moment is larger, and compared with the scheme of determining the effectiveness of the current positioning result by using the historical positioning result, the scheme can accurately judge the positioning result under the scene with larger uncertainty.

In one possible embodiment, the first environmental sensing information includes a first sensing image, and the second environmental sensing information includes a second sensing image; and/or

The first environmental sensing information includes first point cloud data, and the second environmental sensing information includes second point cloud data.

In a possible implementation manner, the determining, based on the second environment sensing information and the first environment sensing information after the rasterizing process, a validity detection result of the positioning result includes:

determining evaluation data corresponding to the positioning result based on the second environment sensing information and the first environment sensing information after rasterization processing;

and determining the validity detection result of the positioning result based on the evaluation data.

In a possible implementation manner, the determining, based on the rasterized second environmental sensing information and the first environmental sensing information, evaluation data corresponding to the positioning result includes:

determining a score of a local area corresponding to each grid position in the second environment sensing information based on the second environment sensing information and the first environment sensing information after rasterization, wherein the score is used for representing similarity between the local area of the grid position and the corresponding local area in the first environment sensing information;

and determining evaluation data corresponding to the positioning result based on the scores of the local regions corresponding to the grid positions.

In a possible implementation manner, the determining, based on the scores of the local regions corresponding to the respective grid positions, evaluation data corresponding to the positioning result includes:

determining a similarity probability value between the local region corresponding to each grid position and the corresponding local region in the first environment sensing information based on the scores of the local regions corresponding to the grid positions respectively;

and determining evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position.

In a possible implementation manner, in a case that the evaluation data includes a location covariance, the determining, based on the similarity probability value of the local region corresponding to each grid location, the evaluation data corresponding to the positioning result includes:

selecting at least one target reference point from local areas corresponding to other grid positions except the grid position where the positioning result is located;

determining a position covariance corresponding to the positioning result based on the similarity probability value of the local region corresponding to each target reference point, the candidate position information corresponding to the target reference point and the target position information indicated by the positioning result;

wherein the location covariance is used to characterize an uncertainty of location information indicated in the positioning result;

the determining the validity detection result of the positioning result based on the evaluation data comprises:

and determining the positioning result as a valid positioning result when the position covariance is smaller than a set first threshold.

In a possible implementation manner, in a case that the evaluation data includes an angular variance, the determining, based on the similarity probability values of the local regions corresponding to the respective grid positions, the evaluation data corresponding to the positioning result includes:

determining a position covariance corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position;

determining the angle variance corresponding to the positioning result based on the target element value positioned on the main diagonal in the position covariance;

wherein the angular variance is used to characterize an uncertainty of orientation information indicated in the positioning result;

and determining the positioning result as a valid positioning result when the angular variance is smaller than a set second threshold.

In a possible implementation manner, in a case that the evaluation data includes similar entropy, the determining, based on the similarity probability value of the local region corresponding to each grid position, the evaluation data corresponding to the positioning result includes:

determining the similarity entropy corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position and the logarithm value of the similarity probability value corresponding to each grid position;

wherein the similar entropy is used for representing the uncertainty of the positioning result;

and determining the positioning result as a valid positioning result under the condition that the similarity entropy is smaller than a set third threshold value.

In a possible implementation manner, in a case that the evaluation data includes a matching score, the determining, based on the similarity probability values of the local regions corresponding to the respective grid positions, the evaluation data corresponding to the positioning result includes:

determining the ratio of the similarity probability value of the local regions corresponding to the grid positions except the grid position where the positioning result is located to the similarity probability value of the local region corresponding to the grid position where the positioning result is located;

selecting the maximum ratio from ratios corresponding to other grid positions as the matching score corresponding to the positioning result;

wherein the match score characterizes an uncertainty of the positioning result;

and under the condition that the matching score is smaller than a set fourth threshold value, determining the positioning result as an effective positioning result.

In a possible implementation manner, after determining the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization, the method further includes:

and controlling a traveling path of a traveling apparatus on which the positioning device and/or the sensor is mounted, based on the positioning result, when the validity detection result of the positioning result is a valid positioning result.

The following descriptions of the effects of the apparatus, the electronic device, and the like refer to the description of the above method, and are not repeated here.

In a second aspect, the present disclosure provides a positioning result detecting apparatus, including:

the acquisition module is used for acquiring a positioning result of positioning equipment and first environment sensing information acquired by a sensor associated with the positioning equipment at a position indicated by the positioning result;

the first determining module is used for acquiring second environment sensing information of a target scene corresponding to a positioning position indicated by the positioning result according to a pre-constructed map, wherein the map comprises environment sensing information of a plurality of positioning positions;

and the second determining module is used for rasterizing the second environment sensing information and determining the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterizing.

In a possible implementation manner, the second determining module is configured to determine the validity detection result of the positioning result as follows:

In a possible implementation manner, the second determining module is configured to determine the evaluation data corresponding to the positioning result according to the following manner:

In a possible implementation manner, the second determining module is further configured to determine the evaluation data corresponding to the positioning result according to the following manner:

In a possible implementation manner, in the case that the evaluation data includes a location covariance, the second determining module is further configured to determine the evaluation data corresponding to the positioning result as follows:

the second determining module is configured to determine the validity detection result of the positioning result as follows:

In a possible implementation manner, in the case that the evaluation data includes an angular variance, the second determining module is further configured to determine the evaluation data corresponding to the positioning result as follows:

In a possible implementation manner, in a case that the evaluation data includes similar entropy, the second determining module is further configured to determine the evaluation data corresponding to the positioning result as follows:

In a possible implementation manner, in a case that the evaluation data includes a matching score, the second determining module is further configured to determine the evaluation data corresponding to the positioning result as follows:

wherein the match score characterizes an uncertainty of the positioning result;

In a possible embodiment, the apparatus further comprises: a control module to:

after the second determining module determines the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization processing,

In a third aspect, the present disclosure provides an electronic device comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the positioning result detection method according to the first aspect or any one of the embodiments.

In a fourth aspect, the present disclosure provides a computer-readable storage medium, having a computer program stored thereon, where the computer program is executed by a processor to perform the steps of the positioning result detecting method according to the first aspect or any one of the embodiments.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 is a schematic flow chart illustrating a method for detecting a positioning result according to an embodiment of the present disclosure;

fig. 2a is a schematic diagram illustrating rasterized second environment sensing information in a method for detecting a positioning result according to an embodiment of the disclosure;

fig. 2b is a schematic diagram illustrating rasterized second environment sensing information in a method for detecting a positioning result according to an embodiment of the disclosure;

fig. 2c is a schematic diagram illustrating rasterized second environment sensing information in a method for detecting a positioning result according to an embodiment of the disclosure;

FIG. 3 is a flowchart illustrating a specific implementation manner of determining evaluation data corresponding to a positioning result according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram illustrating rasterized second environment sensing information in a method for detecting a positioning result according to an embodiment of the disclosure;

fig. 5 is a schematic diagram illustrating an architecture of a positioning result detection apparatus provided in an embodiment of the present disclosure;

fig. 6 shows a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

Generally, the uncertainty of the positioning result can be determined through the difference between the current positioning result and the positioning result at the previous time, but the above method cannot accurately determine the positioning result in a scene with large positioning uncertainty, such as a scene in which the vehicle moves but the positioning result returns to the vehicle is still. Therefore, in order to solve the above problems and accurately determine the uncertainty of the positioning result, embodiments of the present disclosure provide a method and an apparatus for detecting a positioning result, an electronic device, and a storage medium.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

The technical solutions in the present disclosure will be described clearly and completely with reference to the accompanying drawings in the present disclosure, and it is to be understood that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. The components of the present disclosure, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

For facilitating understanding of the embodiments of the present disclosure, a detailed description will be first given of a positioning result detection method disclosed in the embodiments of the present disclosure. An execution subject of the positioning result detection method provided by the embodiment of the present disclosure is generally a computer device with certain computing capability, and the computer device includes: a terminal device, which may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle mounted device, a wearable device, or a server or other processing device. In some possible implementations, the positioning result detection method may be implemented by a processor calling computer readable instructions stored in a memory.

Referring to fig. 1, a schematic flow chart of a positioning result detection method provided in the embodiment of the present disclosure is shown, where the method includes S101-S103, where:

s101, acquiring a positioning result of positioning equipment and first environment sensing information acquired by a sensor associated with the positioning equipment at a position indicated by the positioning result;

s102, acquiring second environment sensing information of a target scene corresponding to a positioning position indicated by the positioning result according to a pre-constructed map, wherein the map comprises the environment sensing information of a plurality of positioning positions;

s103, rasterizing the second environment sensing information, and determining a validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterizing.

According to the method, the positioning result of the positioning device and the first environment sensing information acquired by the sensor associated with the positioning device at the position indicated by the positioning result are obtained, the second environment sensing information of the target scene corresponding to the positioning position indicated by the positioning result is obtained according to the pre-constructed map, the second environment sensing information can be regarded as the standard environment sensing information corresponding to the positioning result, when the difference between the first environment sensing information and the second environment sensing information is small, the accuracy of the positioning result is high, the effectiveness of the positioning result is high, and the effectiveness detection result of the positioning result can be accurately determined by utilizing the second environment sensing information and the first environment sensing information after rasterization.

S101 to S103 will be specifically described below.

For S101 and S102:

here, the Positioning device may be any device capable of determining a Positioning result, for example, the Positioning device may be a Global Positioning System (GPS) or the like. Sensors associated with the positioning device include, but are not limited to, vision sensors, lidar, and the like.

In an application scenario, the positioning device and the sensor may be mounted on the traveling device, the positioning device may determine a positioning result of the traveling device, and the sensor acquires first environment sensing information collected at a position indicated by the positioning result.

The first environment sensing information may include a first sensing image and/or first point cloud data, for example, when the sensor is a visual sensor, the first environment sensing information may be the first sensing image; when the sensor is a lidar, the first environmental sensor may be first point cloud data.

After the positioning result of the positioning device is obtained, second environment sensing information of the target scene corresponding to the positioning position indicated by the positioning result can be obtained according to a pre-constructed map, wherein the pre-constructed map comprises environment sensing information of a plurality of positioning positions. When the first environment sensing information is a first sensing image, the second environment sensing information is a second sensing image; and when the second environment sensing information is the first point cloud data, the second environment sensing information is second point cloud data.

For example, the first environment sensing information may also include a first sensing image or first point cloud data within a range of 20 meters before, 20 meters behind, and 10 meters left and right from the positioning result of the positioning device as the center, wherein the first sensing image or first point cloud data extends forward by 10 meters, backward by 10 meters, leftward by 5 meters, and rightward by 5 meters, determines a target range, and obtains a second sensing image or second point cloud data within the target range from a pre-constructed map as the second environment sensing information of the target scene corresponding to the positioning result.

In specific implementation, the map can be constructed according to the following steps: the method includes the steps of obtaining multiple frames of scene images at different positioning positions, and building a map by using the multiple frames of scene images, for example, performing feature splicing on the multiple frames of scene images to build the map, wherein the map comprises environment sensing images of a plurality of positioning positions. Or, multiple frames of scene images at different positioning positions can be acquired, the feature information of the feature points in each frame of scene image is extracted, and a map is constructed by using the feature information of the feature points included in the multiple frames of scene images, wherein the map includes point cloud data of a plurality of positioning positions.

For S103:

here, the second environment sensing information may be rasterized to obtain rasterized second environment sensing information. For example, when the second environment sensing information is the second sensing image, the second sensing image may be uniformly rasterized according to the set number of the grids or the set size of the grids, so as to obtain a rasterized second sensing image with the same shape and size of each grid, as shown in fig. 2 a. Alternatively, the second sensing image may be subjected to non-uniform rasterization according to the number of the set grids or the set grid size, so as to obtain the rasterized second sensing image with different shapes and/or sizes of the grids, as shown in fig. 2 b.

When the second environment sensing information is the second point cloud data, the environment area corresponding to the second point cloud data may be rasterized to obtain local point cloud data located in the local area corresponding to each raster position. The rasterization process of the second point cloud data may refer to the rasterization process of the second sensing image, and is not described in detail here.

Considering that the accuracy of the environment sensing information at the position closer to the positioning result is higher, and the accuracy of the environment sensing information at the position farther from the positioning result is lower, the size of the grid may be set according to the distance from the positioning result, so that the size of the grid closer to the positioning result is smaller, and the size of the grid farther from the positioning result is larger, as shown in fig. 2 c.

In a possible implementation manner, determining a validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization processing includes: and determining the validity detection result of the positioning result based on the matching degree between the second environment sensing information and the first environment sensing information after rasterization processing. In a case where the degree of matching between the second environment sensing information and the first environment sensing information after the rasterization process exceeds a predetermined range, it may be determined that the positioning result is valid, otherwise, it may be determined that the positioning result is invalid.

In a possible implementation manner, the determining, based on the second environment sensing information and the first environment sensing information after the rasterizing process, a validity detection result of the positioning result includes: determining evaluation data corresponding to the positioning result based on the second environment sensing information and the first environment sensing information after rasterization processing; and determining the validity detection result of the positioning result based on the evaluation data.

The evaluation data can comprise one or more of the following data: position covariance, angle variance, similarity entropy, and matching score. Here, various evaluation data can be set, and the result to be detected can be evaluated in multiple directions through the set various evaluation data.

In an optional implementation manner, referring to fig. 3, the determining, based on the second environment sensing information and the first environment sensing information after rasterization, evaluation data corresponding to the positioning result includes:

s301, determining a score of a local area corresponding to each grid position in the second environment sensing information based on the second environment sensing information and the first environment sensing information after rasterization, wherein the score is used for representing similarity between the local area of the grid position and the corresponding local area in the first environment sensing information;

s302, determining evaluation data corresponding to the positioning result based on the scores of the local regions corresponding to the grid positions.

In the above embodiment, by determining the score of the local region corresponding to each grid position in the second environment sensing information, the similarity between the local region of the grid position and the corresponding local region in the first environment sensing information can be represented by the score. Generally, if the accuracy of the positioning result is high, the similarity should be high, that is, the score corresponding to each grid position is high, and it can be known that there is a relationship between the score corresponding to the grid position and the accuracy of the positioning result, so that the evaluation data corresponding to the result can be determined more accurately by determining the score of the local region corresponding to each grid position.

In S301, a score of a local area corresponding to each grid position in the second environment sensing information may be determined based on the second environment sensing information and the first environment sensing information that are rasterized. In specific implementation, when the second environment sensing information is the second sensing image, for each grid position, the similarity between the second local sensing image at the grid position and the corresponding first local sensing image in the first environment sensing information is calculated, and the similarity is determined as the score of the grid position, so that the score of the local area corresponding to each grid position can be obtained.

For example, the trained neural network may calculate a matching degree between the second local sensing image corresponding to the grid position and the first local sensing image corresponding to the first environmental sensing information, and determine the calculated matching degree as a score corresponding to the grid position. Or the cosine similarity between the second local sensing image corresponding to the grid position and the first local sensing image corresponding to the first environmental sensing information may be calculated, and the calculated cosine similarity is determined as the score corresponding to the grid position.

Referring to fig. 4, in a positioning result detection method, a score of each grid position may be obtained according to a schematic diagram of rasterized second environment sensing information, that is, a score corresponding to a grid position at a 00 th position, a score corresponding to a grid position at a-10 th position, a score corresponding to a grid position at a 01 th position, and the like may be obtained, where the grid position at the 00 th position may be the grid position where the positioning result is located.

In S302, evaluation data corresponding to the positioning result may be determined based on the score of the local region corresponding to each grid position.

s3021, determining a similarity probability value between the local region corresponding to each grid position and the corresponding local region in the first environmental sensing information based on the score of the local region corresponding to each grid position;

s3022, determining evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position.

During implementation, the scores of the local regions respectively corresponding to the grid positions can be normalized to generate a similarity probability value of the local region corresponding to each grid position; and determining evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position.

In an optional embodiment, in a case that the evaluation data includes a location covariance, in S3022, determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid location includes:

a1, selecting at least one target reference point from local areas corresponding to grid positions except the grid position where the positioning result is located;

step A2, determining a position covariance corresponding to the positioning result based on the similarity probability value of the local region corresponding to each target reference point, the candidate position information corresponding to the target reference point and the target position information indicated by the positioning result;

wherein the location covariance is used to characterize an uncertainty of the location information indicated in the positioning result.

Determining the validity detection result of the positioning result based on the evaluation data, wherein the validity detection result comprises the following steps: and determining the positioning result as a valid positioning result under the condition that the position covariance is smaller than the set first threshold value.

Here, at least one target reference point may be selected from the local scene images corresponding to the grid positions other than the grid position where the positioning result is located, for example, a central point of a local area corresponding to each other grid position may be determined as a target reference point, and candidate position information of each target reference point may be obtained. Wherein, the target reference point can be selected according to the requirement.

The position covariance can then be calculated according to the following equation (1):

Ω＝∑^i,jP(i,j)(a(i,j)-a)(a(i,j)-a)^T；(1)

where Ω is the position covariance, and P (i, j) is the similarity probability value of the local region of the grid position at the ijth position, for example, P (1,1) is the similarity probability value of the local region of the grid position at the 11 th position; a (i, j) is candidate position information of a target reference point on the local area of the grid position at the ij-th position, and a (1,1) is candidate position information of a target reference point on the local area of the grid position at the 11-th position; and a is target position information indicated by the positioning result.

Here, when determining the position covariance corresponding to the positioning result using the scores of the local regions corresponding to the respective grid positions, P (i, j) may be the score of the local region of the grid position at the ij-th position.

As can be seen from fig. 4, a (0,0) is the target location information indicated by the positioning result, so i, j is an integer other than zero, that is, P (i, j) is the similarity probability value of the local region corresponding to the grid location other than the grid location where the positioning result is located, and the maximum value of i, j can be determined according to the number of the divided grids.

Here, the location covariance may be used to characterize the uncertainty of the location information indicated in the positioning result, i.e. the location covariance may be used to characterize whether the location information indicated in the positioning result is usable or not. When the target position information indicated in the positioning result is a two-dimensional position, the generated position covariance is a two-dimensional matrix. For example, the location covariance may be:

in specific implementation, a first threshold value may be set, and when the position covariance is smaller than the set first threshold value, the positioning result is determined to be an effective positioning result; and when the position covariance is larger than or equal to the set first threshold value, determining the positioning result as an invalid positioning result.

For example, it may be determined whether the target element on the main diagonal of the position covariance is larger than a set first threshold, i.e., the target element may be d₀₀、d₁₁The first threshold may comprise d₀₀Corresponding first position threshold, and d₁₁Corresponding second position threshold at d₀₀Less than a set first position threshold, and d₁₁When the position is smaller than the set second position threshold value, determining the positioning result as an effective positioning result; at d₀₀Greater than or equal to a set first position threshold, and/or, d₁₁And when the position is greater than or equal to the set second position threshold value, determining the positioning result as an invalid positioning result. The first position threshold and the second position threshold may be the same or different.

In the above embodiment, when the evaluation data includes the location covariance, the determined location covariance may be used to characterize uncertainty of location information indicated in the positioning result, and further, the validity detection result of the positioning result may be determined more accurately by using the determined location covariance.

In an optional embodiment, in a case that the evaluation data includes an angle variance, determining the evaluation data corresponding to the positioning result based on the similarity probability values of the local regions corresponding to the respective grid positions includes:

step B1, determining a position covariance corresponding to the positioning result based on the similarity probability value of the local area corresponding to each grid position;

step B2, determining the angle variance corresponding to the positioning result based on the target element value on the main diagonal in the position covariance;

wherein the angular variance is used to characterize the uncertainty of the orientation information indicated in the positioning result.

Determining the validity detection result of the positioning result based on the evaluation data, wherein the validity detection result comprises the following steps: and determining the positioning result as a valid positioning result under the condition that the angle variance is smaller than a set second threshold value.

Here, the location covariance corresponding to the positioning result may be determined first, where the process of determining the location covariance may refer to the above location covariance determination process, and details are not repeated here.

The angular variance may be determined according to the following equation (2):

σ＝k×(Ω(0,0)+Ω(1,1))；(2)

where σ is an angular variance, Ω (0,0) and Ω (1,1) are target element values located on the main diagonal in the position covariance, that is, Ω (0,0) may be a target element value located on the 0 th row and 0 th column in the position covariance, and Ω (0,0) ═ d₀₀(ii) a Ω (1,1) may be a target element value located at row 1 and column 1 in the position covariance, and Ω (1,1) ═ d₁₁(ii) a k is a set parameter.

Here, the angular variance is used to characterize the uncertainty of the orientation information indicated in the positioning result, i.e. the angular variance is used to characterize whether the orientation information indicated in the positioning result is usable or not. When the angular variance is smaller than the set second threshold, the positioning result is determined to be a valid positioning result, and the positioning result can be used. And when the angle variance is larger than or equal to the set second threshold, determining that the positioning result is an invalid positioning result, and then the positioning result cannot be used.

In the above embodiment, when the evaluation data includes the angle variance, the determined angle variance may be used to characterize uncertainty of the orientation information indicated in the positioning result, and further, the validity detection result of the positioning result may be determined more accurately by using the determined angle variance.

In an optional embodiment, in a case that the evaluation data includes similar entropy, determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position includes: determining a similarity entropy corresponding to a positioning result based on the similarity probability value of the local region corresponding to each grid position and the logarithm value of the similarity probability value corresponding to each grid position;

determining the validity detection result of the positioning result based on the evaluation data, wherein the validity detection result comprises the following steps: and determining the positioning result as a valid positioning result under the condition that the similarity entropy is smaller than a set third threshold value.

In specific implementation, the similarity entropy can be calculated according to the following formula (3):

F_entropy＝-∑P(i,j)log(P(i,j))；(3)

wherein, F_entropyFor similarity entropy, P (i, j) is the similarity probability value of the local region at the grid position at the ijth position. Similar entropy can be used to characterize the uncertainty of the positioning result.

When the similarity entropy is smaller than a set third threshold value, determining the positioning result as an effective positioning result; and when the similarity entropy is greater than or equal to the set third threshold, determining the positioning result as an invalid positioning result.

In the above embodiment, the validity detection result of the positioning result can be determined more accurately by determining the similar entropy, representing the uncertainty of the positioning result by using the similar entropy, and then using the determined similar entropy.

In an optional embodiment, in a case that the evaluation data includes a matching score, determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position includes:

step C1, determining the ratio between the similarity probability value of the local area corresponding to the grid position except the grid position where the positioning result is located and the similarity probability value of the local area corresponding to the grid position where the positioning result is located;

step C2, selecting the maximum ratio from the ratios corresponding to other grid positions as the matching score corresponding to the positioning result;

wherein the matching score represents the uncertainty of the positioning result;

determining the validity detection result of the positioning result based on the evaluation data, wherein the validity detection result comprises the following steps: and under the condition that the matching score is smaller than a set fourth threshold value, determining the positioning result as a valid positioning result.

In particular implementations, the match score can be calculated according to the following equation (4):

factor＝max(P(i,j)/P(0,0))；(4)

the factor is a matching score, P (0,0) is a similarity probability value of a grid position where the positioning result is located, and P (i, j) is a similarity probability value of a local region corresponding to other grid positions, that is, i, j is an integer which is not 0.

Here, the matching score may be used to characterize the difference between the score of the grid position where the localization result is located and the scores corresponding to other grid positions, by which the uncertainty of the localization result is characterized. When the matching score is smaller than a set fourth threshold value, determining the positioning result as an effective positioning result; and when the matching score is greater than or equal to a set fourth threshold value, determining the positioning result as an invalid positioning result.

For example, when the evaluation data includes the position covariance, the angle variance, the similarity entropy, and the matching score, the position covariance corresponding to the positioning result may be determined first, and when a value of a target element on the main diagonal in the determined position covariance is greater than or equal to a set first threshold, the positioning result is determined to be an invalid positioning result, and the angle covariance, the similarity entropy, and the matching score are no longer determined.

And when the determined angle variance is larger than or equal to a set second threshold, determining the positioning result as an invalid positioning result, and not determining the similarity entropy and the matching score.

And when the determined angle variance is smaller than a set second threshold, determining the similarity entropy corresponding to the positioning result, and when the determined similarity entropy is larger than or equal to a set third threshold, determining the positioning result as an invalid positioning result and not determining the matching score.

When the determined similarity entropy is smaller than a set third threshold, determining a matching score corresponding to the positioning result, and when the determined matching score is smaller than a set fourth threshold, determining the positioning result as an effective positioning result; and when the determined matching score is greater than or equal to the set fourth threshold, determining the positioning result as an invalid positioning result.

In specific implementation, the selection of the evaluation data and the calculation sequence of the evaluation data may be determined according to needs, and this is only an exemplary illustration.

In the above embodiment, the matching score is determined, and the matching score is used for representing the uncertainty of the positioning result based on the difference between the score of the grid position where the positioning result is located and the scores corresponding to other grid positions, and the validity detection result of the positioning result can be determined more accurately by using the determined matching score.

In an optional implementation manner, after determining the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization, the method further includes: and controlling a travel path of a travel device on which the positioning device and/or the sensor is mounted, based on the positioning result, when the validity detection result of the positioning result is a valid positioning result.

Here, when the result of the detection of the validity of the positioning result is a valid positioning result, the travel path of the travel apparatus on which the positioning device and/or the sensor is mounted may be controlled based on the positioning result, for example, acceleration, deceleration, steering, braking, etc. of the travel apparatus may be controlled, or voice prompt information may be played to prompt the driver to control acceleration, deceleration, steering, braking, etc. of the travel apparatus.

For example, when the driving device is an autonomous vehicle, the road identifier included in the scene where the driving device is located may be determined according to the positioning result, and the driving device may be controlled according to the road identifier, for example, if the road identifier indicates that there is a traffic light within 10 meters ahead and the traffic light is a red light, the driving device may be controlled to slow down.

In specific implementation, a plurality of positioning devices can be arranged on the running device, each positioning device can obtain a positioning result corresponding to the running device, and the evaluation data and the validity detection result corresponding to each positioning result can be obtained by the positioning result detection method. And sending the positioning result with the effective detection result as the effective positioning result and the corresponding evaluation data to the fusion positioning system, and determining the positioning result corresponding to the target equipment from the positioning results with the effective detection results as the effective positioning results by the fusion positioning system according to the received evaluation data.

When the validity detection result of the positioning result is an invalid positioning result, the positioning result can be not used and the next positioning result can be determined again, or the positioning result and/or the evaluation data can be returned to the running device, so that an operator on the running device can manually control the running device; alternatively, the positioning result and/or the evaluation data can also be returned to the running gear, so that an operator on the running gear can determine the cause of positioning failure and the like according to the positioning result.

By adopting the method, when the validity detection result of the positioning result is determined to be the valid positioning result, the driving device can be controlled more accurately based on the positioning result; when the validity detection result of the positioning result is an invalid positioning result, the positioning result is not used, so that the condition that the running device is in failure when the running device is controlled by using the positioning result of which the validity detection result is the invalid positioning result is avoided, and the safety of the running device is improved.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same concept, an embodiment of the present disclosure further provides a positioning result detection apparatus, as shown in fig. 5, which is an architecture schematic diagram of the positioning result detection apparatus provided in the embodiment of the present disclosure, and includes an obtaining module 501, a first determining module 502, and a second determining module 503, specifically:

an obtaining module 501, configured to obtain a positioning result of a positioning device and first environment sensing information acquired by a sensor associated with the positioning device at a position indicated by the positioning result;

a first determining module 502, configured to obtain, according to a pre-constructed map, second environment sensing information of a target scene corresponding to a positioning location indicated by the positioning result, where the map includes environment sensing information of multiple positioning locations;

a second determining module 503, configured to perform rasterization on the second environment sensing information, and determine a validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after the rasterization.

In a possible implementation manner, the second determining module 503 is configured to determine the validity detection result of the positioning result as follows:

In a possible implementation manner, the second determining module 503 is configured to determine the evaluation data corresponding to the positioning result according to the following manner:

In a possible implementation manner, the second determining module 503 is further configured to determine the evaluation data corresponding to the positioning result according to the following manner:

In a possible implementation manner, in the case that the evaluation data includes a location covariance, the second determining module 503 is further configured to determine the evaluation data corresponding to the positioning result as follows:

the second determining module 503 is configured to determine the validity detection result of the positioning result as follows:

In a possible implementation manner, in the case that the evaluation data includes an angular variance, the second determining module 503 is further configured to determine the evaluation data corresponding to the positioning result as follows:

In a possible implementation manner, in the case that the evaluation data includes similar entropy, the second determining module 503 is further configured to determine the evaluation data corresponding to the positioning result as follows:

In a possible implementation manner, in the case that the evaluation data includes a matching score, the second determining module 503 is further configured to determine the evaluation data corresponding to the positioning result as follows:

wherein the match score characterizes an uncertainty of the positioning result;

In a possible embodiment, the apparatus further comprises: a control module 504 configured to:

In some embodiments, the functions of the apparatus provided in the embodiments of the present disclosure or the included templates may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, no further description is provided here.

Based on the same technical concept, the embodiment of the disclosure also provides an electronic device. Referring to fig. 6, a schematic structural diagram of an electronic device provided in the embodiment of the present disclosure includes a processor 601, a memory 602, and a bus 603. The memory 602 is used for storing execution instructions and includes a memory 6021 and an external memory 6022; the memory 6021 is also referred to as an internal memory, and is configured to temporarily store the operation data in the processor 601 and the data exchanged with the external memory 6022 such as a hard disk, the processor 601 exchanges data with the external memory 6022 through the memory 6021, and when the electronic device 600 operates, the processor 601 communicates with the memory 602 through the bus 603, so that the processor 601 executes the following instructions:

In addition, the embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the positioning result detection method described in the above method embodiments are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The embodiments of the present disclosure also provide a computer program product, where the computer program product carries a program code, and instructions included in the program code may be used to execute the steps of the positioning result detection method in the foregoing method embodiments, which may be referred to specifically in the foregoing method embodiments, and are not described herein again.

The computer program product may be implemented by hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above are only specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present disclosure, and shall be covered by the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method for detecting a positioning result is characterized by comprising the following steps:

2. The method of claim 1, wherein the first environmental sensory information comprises a first sensory image and the second environmental sensory information comprises a second sensory image; and/or

3. The method according to claim 1 or 2, wherein the determining the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization comprises:

4. The method according to claim 3, wherein the determining evaluation data corresponding to the positioning result based on the second environment sensing information and the first environment sensing information after rasterization comprises:

5. The method according to claim 4, wherein the determining the evaluation data corresponding to the positioning result based on the score of the local region corresponding to each grid position comprises:

6. The method according to claim 5, wherein in a case that the evaluation data includes a location covariance, the determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid location includes:

determining the position covariance corresponding to the positioning result based on the similarity probability value of the local region corresponding to each target reference point, the candidate position information corresponding to the target reference point and the target position information indicated by the positioning result;

7. The method according to claim 5, wherein in a case that the evaluation data includes an angular variance, the determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position includes:

8. The method according to claim 5, wherein in a case that the evaluation data includes similar entropy, the determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position includes:

9. The method according to claim 5, wherein in a case that the evaluation data includes a matching score, the determining the evaluation data corresponding to the positioning result based on the similarity probability value of the local region corresponding to each grid position includes:

wherein the match score characterizes an uncertainty of the positioning result;

10. The method according to any one of claims 1 to 9, wherein after determining the validity detection result of the positioning result based on the second environment sensing information and the first environment sensing information after rasterization, the method further comprises:

11. A positioning result detecting apparatus, comprising:

12. An electronic device, comprising: processor, memory and bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions when executed by the processor performing the steps of the positioning result detecting method according to any one of claims 1 to 10.

13. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the positioning result detection method according to any one of claims 1 to 10.