Simultaneous positioning and mapping method and device, equipment and medium

Abstract

The invention relates to the technical field of positioning and mapping, in particular to a simultaneous positioning and mapping method and device, equipment and a medium. According to the observation coordinates, the reflection intensity and the local point cloud information, anomaly detection is carried out on the reflector, and an anomaly detection result of the reflector is determined; according to the abnormal detection result of the reflector, determining the weight value of the reflector, calculating the reflector error of each reflector according to the observation coordinate and the fixed coordinate of the reflector, and calculating the target error of the pose of the positioning equipment at the current moment according to the weight value of the reflector, the reflector error and a preset optimization function. And optimizing the pose of the positioning equipment according to the target error to obtain an optimized pose, and constructing a target map based on the optimized pose. According to the method, cross validation is carried out according to the multi-dimensional anomaly detection result, the anomaly detection result of the reflector is determined, misjudgment and missing detection of the reflector are avoided, and therefore the corresponding positioning precision is improved in the positioning optimization process based on the reflector.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of positioning and mapping, and in particular to a simultaneous localization and mapping method, device, equipment and medium. BACKGROUND

[0002] In the fields of automatic driving, industrial mobile robots (AGV), intelligent warehousing and precision measurement, a reflector plate, as a high-reflectivity positioning reference, becomes a core "anchor point" component for realizing centimeter-level or even millimeter-level high-precision positioning, by virtue of its stable signal feedback characteristics. The reflector plate provides an accurate position reference for the system by reflecting the detection signals of laser radar, vision sensor and other devices, directly determining the precision and reliability of the positioning system, and the position stability of the reflector plate is a prerequisite for ensuring the effectiveness of measurement data.

[0003] However, the reflector plate is prone to various abnormal states in long-term use or complex environments. If these abnormalities are not detected in time, it will cause the accumulation of positioning errors, which may cause path deviation, industrial robot operation failure, or even cause the positioning failure of an automatic driving vehicle and the distortion of precision measurement data, resulting in safety hazards and economic losses. To solve the above problems, the prior art generally uses a single sensor threshold detection scheme, in which the laser radar selects reflector plate point clouds based on a fixed reflectivity threshold. When the environment light changes or the reflector plate is slightly aged, false positives or false negatives may occur, resulting in low positioning accuracy. Therefore, how to improve the positioning accuracy in the process of positioning only with the reflector plate becomes a problem to be solved. SUMMARY

[0004] In view of this, the embodiments of the present application provide a simultaneous localization and mapping method, device, equipment and medium to solve the problem of low positioning accuracy in the process of positioning the reflector plate.

[0005] In a first aspect, the embodiments of the present application provide a simultaneous localization and mapping method, which comprises: acquiring laser radar point cloud data, extracting reflector plate observation information in the laser radar point cloud data, the reflector plate observation information at least including observation coordinates, reflection intensity and local point cloud information of the reflector plate, and the laser radar point cloud data being data collected by a positioning device carrying a laser radar; performing abnormality detection on the reflector plate according to the observation coordinates, reflection intensity and local point cloud information, and determining an abnormality detection result of the reflector plate; iterating through all reflector plates observed by the positioning device at the current position to obtain an abnormality detection result of each reflector plate, determining the number of abnormal reflector plates and the number of normal reflector plates according to the abnormality detection result of each reflector plate, and determining a weight value of the reflector plate according to the ratio of the number of abnormal reflector plates to the number of normal reflector plates; The fixed coordinates of each reflector plate are obtained, the reflector plate error of each reflector plate is calculated according to the observation coordinates and the fixed coordinates of each reflector plate, and the target error of the pose of the positioning device at the current moment is calculated according to the weight value of the reflector plate, the reflector plate error and a preset optimization function. The pose of the positioning device is optimized according to the target error to obtain an optimized pose, and a target map is constructed based on the optimized pose.

[0006] In a second aspect, an embodiment of the present application provides a simultaneous localization and mapping device, which comprises: An extraction module is configured to obtain laser radar point cloud data, and extract reflector plate observation information in the laser radar point cloud data, wherein the reflector plate observation information at least comprises observation coordinates, reflection intensity and local point cloud information of the reflector plate, and the laser radar point cloud data is data collected by a laser radar carried by a positioning device; A first determination module is configured to perform abnormality detection on the reflector plate according to the observation coordinates, the reflection intensity and the local point cloud information, and determine an abnormality detection result of the reflector plate; A second determination module is configured to obtain the abnormality detection result of each reflector plate by traversing all reflector plates observed by the positioning device at a current position, determine the number of abnormal reflector plates and the number of normal reflector plates according to the abnormality detection result of each reflector plate, and determine the weight value of the reflector plate according to the ratio of the number of abnormal reflector plates to the number of normal reflector plates; A calculation module is configured to obtain fixed coordinates of each reflector plate, calculate the reflector plate error of each reflector plate according to the observation coordinates and the fixed coordinates of each reflector plate, and calculate the target error of the pose of the positioning device at the current moment according to the weight value of the reflector plate, the reflector plate error and a preset optimization function; An optimization module is configured to optimize the pose of the positioning device according to the target error to obtain an optimized pose, and construct a target map based on the optimized pose.

[0007] In a third aspect, an embodiment of the present application provides a computer device, which comprises a processor, a memory and a computer program stored in the memory and executable on the processor, and the processor implements the simultaneous localization and mapping method of the first aspect when executing the computer program.

[0008] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the simultaneous localization and mapping method of the first aspect.

[0009] Compared with the prior art, the present application has the following beneficial effects: The application performs abnormality detection on the reflector plate according to the observation coordinates, the reflection intensity and the local point cloud information, determines an abnormality detection result of the reflector plate, determines a weight value of the reflector plate according to the abnormality detection result of the reflector plate, obtains a fixed coordinate of each reflector plate, calculates a reflector plate error of each reflector plate according to the observation coordinates and the fixed coordinates, calculates a target error of the pose of the positioning device at the current moment according to the weight value of the reflector plate, the reflector plate error and a preset optimization function, optimizes the pose of the positioning device according to the target error, obtains an optimized pose, and constructs a target map based on the optimized pose. The abnormality detection result of the reflector plate is determined through cross verification according to the multi-dimensional abnormality detection result, and misjudgment and missed detection of the reflector plate are avoided, so that the corresponding positioning accuracy is improved in the positioning optimization process based on the reflector plate. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0011] Figure 1 is a flow diagram of a simultaneous localization and mapping method provided by an embodiment of the present application; Figure 2 is a structural diagram of a simultaneous localization and mapping device provided by an embodiment of the present application; Figure 3 is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0013] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application, but it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0014] It will be understood that the term “includes,” “comprises,” “comprising,” “has,” “contains” and / or “including,” when used in the specification and / or the claims of this application, specifies the presence of stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0015] It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items, and that the term “at least one of’ denotes one, or a combination of two or more items.

[0016] As used in the description of the application and the appended claims, the term “if’ can be interpreted to mean “when” or “upon” or “in response to determining” or “in response to detecting” depending on the context. Similarly, the phrase “if it is determined” or “if [a described condition or event] is detected” can be interpreted to mean “upon determining” or “in response to determining” or “upon [the described condition or event] being detected” or “in response to [the described condition or event] being detected,” depending on the context.

[0017] In addition, the terms “first,” “second,” “third,” etc. as used in the description of embodiments herein and throughout the claims (if any) are not used to connote or imply a relative importance or a relational or chronological sequence.

[0018] Reference throughout this specification to “one embodiment” or “an embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in additional embodiments,” and so on, in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms “including,” “comprising,” “having,” and variations thereof, are meant to encompass the item listed and variations thereof as well as their equivalents to the extent permitted by law.

[0019] In order to illustrate the technical solutions of the present application, the following will be described by specific embodiments.

[0020] Referring to Figure 1 , Fig. 1 is a flow diagram of a simultaneous localization and mapping method according to an embodiment of the present application, which can include the following steps. Figure 1

[0021] ​S101: Obtain laser radar point cloud data, extract retroreflective panel observation information in the laser radar point cloud data, and the retroreflective panel observation information at least includes observation coordinates of the retroreflective panel, reflection intensity, and local point cloud information. The laser radar point cloud data is data collected by a laser radar carried by a positioning device.

[0022] In step S101, the retroreflective panel is a pre-set artificial marker point, and the high-reflective characteristic thereof is used to realize rapid and accurate positioning, so as to assist the system in determining the position thereof or correcting a map coordinate. The retroreflective panel observation information in the laser radar point cloud data at least includes observation coordinates of the retroreflective panel, reflection intensity, and local point cloud information. The observation coordinates are coordinate information of the retroreflective panel observed based on the laser radar. The reflection intensity is the ability of the surface to reflect the laser radar emission signal, and is usually quantified by reflectivity or reflection signal intensity value. The local point cloud information is point cloud data at the retroreflective panel, and the positioning device is a mobile device, such as a robot.

[0023] In this embodiment, the corresponding point cloud is collected by using a vehicle-mounted positioning device to obtain laser radar point cloud data, and the target scene is scanned according to the preset collection parameters (including but not limited to laser emission frequency, scanning angle range, point cloud density threshold, and data collection time length) of the vehicle-mounted positioning device to collect original laser radar point cloud data. The target scene is a scene containing a retroreflective panel. The original laser radar point cloud data contains at least one group of point cloud data points, each of which carries three-dimensional space coordinate information, reflection intensity information, and timestamp information. The three-dimensional space coordinate information is usually based on the coordinate system of the positioning device, including X-axis, Y-axis, and Z-axis coordinates. The reflection intensity information represents the intensity of the reflection signal after the laser beam is irradiated to the surface of the object, and the unit is dB or gray value. The timestamp information represents the collection time of the point cloud data point.

[0024] In order to reduce the influence of environmental noise on subsequent processing, the original laser radar point cloud data can be preprocessed to obtain preprocessed point cloud data, that is, laser radar point cloud data. For example, a statistical filtering algorithm or a radius filtering algorithm is used to remove isolated noise points caused by air suspensions, raindrops, dust, and the like.

[0025] In this embodiment, reflector observation information is extracted from the lidar point cloud data. This information includes at least the reflector's observation coordinates, reflection intensity, and local point cloud information. Specifically, based on the high reflectivity of the reflector, the lidar point cloud data is filtered using a reflection intensity threshold. A threshold range is set, pre-calibrated according to the reflector's material properties, the observation distance between the lidar and the reflector, and ambient lighting conditions. Point cloud data points with reflection intensities within the threshold range are retained, resulting in a candidate set of reflective points. Since some non-reflector objects may also have high reflection intensities, further geometric morphology filtering is needed to eliminate false candidate points. For example, cluster analysis is performed on the candidate reflective point set, aggregating point cloud data with spatial distances less than a preset clustering threshold into multiple point cloud clusters. For each point cloud cluster, its geometric morphology parameters are calculated and matched against a preset reflector geometric feature template, retaining the successfully matched clusters.

[0026] For each reflector point cloud cluster, the mean 3D coordinates of all point cloud data points within the cluster are calculated, and this mean is used as the observed coordinates of the reflector. For each reflector point cloud cluster, the arithmetic mean of the reflection intensity of all point cloud data points within the cluster is calculated, which is the reflection intensity of the corresponding reflector. For each reflector point cloud cluster, the 3D coordinate range, point cloud density, and distance between adjacent point cloud clusters are calculated as local point cloud information for the reflector.

[0027] In this embodiment, reflector observation information is extracted from the lidar point cloud data. This reflector observation information includes at least the reflector's observation coordinates, reflection intensity, and local point cloud information. Features from point cloud data of different dimensions are extracted to facilitate anomaly detection of the reflector based on these features, thereby improving detection accuracy.

[0028] S102: Based on the observed coordinates, reflection intensity, and local point cloud information, perform anomaly detection on the reflector and determine the anomaly detection result of the reflector.

[0029] In step S102, the abnormal detection result of the reflector is determined based on the observed coordinates, reflection intensity and local point cloud information. The abnormal detection result of the reflector includes abnormal reflectors and normal reflectors.

[0030] In this embodiment, based on the observed coordinates, reflection intensity, and local point cloud information, the geometric anomaly detection results, reflection anomaly detection results, and matching anomaly detection results of the reflector are determined. The geometric anomaly detection result refers to anomalies in the reflector's coordinates; the reflection intensity anomaly detection result refers to anomalies in the reflective lidar signal of the reflector; and the matching anomaly detection result refers to matching anomalies in the local point cloud of the reflector. This facilitates the determination of the reflector's anomaly detection results based on these three assessments.

[0031] In this embodiment, anomaly detection of the reflector is performed based on the observed coordinates, reflection intensity, and local point cloud information. The anomaly detection result of the reflector is determined by taking into account the detection results of anomalies in different dimensions and fusing the detection results of anomalies in different dimensions to determine the anomaly detection result of the reflector, thereby improving the accuracy of the anomaly detection result of the reflector.

[0032] Optionally, based on the observed coordinates, reflection intensity, and local point cloud information, anomaly detection is performed on the reflector to determine the anomaly detection results, including: Obtain the fixed coordinates of the reflector, and based on the observed coordinates and fixed coordinates of the reflector, detect the geometric anomalies of the reflector and determine the results of the geometric anomaly detection. Obtain the preset reflection intensity of the reflector, and detect the reflection anomaly of the reflector based on the reflection intensity and the preset reflection intensity to determine the reflection anomaly detection result of the reflector; Based on the local point cloud information, the point cloud matching score of the local point cloud information in point cloud matching is calculated. Based on the point cloud matching score, the matching anomaly of the reflector is detected, and the detection result of the matching anomaly of the reflector is determined. Based on the results of geometric anomaly detection, reflection anomaly detection, matching anomaly detection, and the preset detection mechanism, the anomaly detection results of the reflector are determined.

[0033] In this embodiment, the observed coordinates are local coordinates in a coordinate system with the positioning device as the origin. The observed coordinates are transformed to a global coordinate system, and it is determined whether the transformed global coordinates are consistent with the fixed coordinates. If they are consistent, it is determined that there is no geometric anomaly; otherwise, it is determined that there is a geometric anomaly. The positioning device can be a robot, etc. Fixed coordinates (Xg, Yg, Zg) are obtained, where Xg, Yg, and Zg represent the coordinate values ​​of the reflector in the X, Y, and Z axes of the global coordinate system, respectively. There is a certain spatial relationship between the positioning device coordinate system and the global coordinate system, which can be represented by a coordinate transformation matrix. The positioning device coordinate system is a coordinate system with the positioning device as the origin. The transformation relationship between the two coordinate systems includes translation and rotation. First, the translation parameters (Tx, Ty, Tz) of the positioning device in the global coordinate system are obtained through the positioning module of the positioning device itself (such as an IMU inertial measurement unit and a GPS combined positioning module). Tx, Ty, and Tz represent the translation amounts of the origin of the positioning device's coordinate system in the X, Y, and Z axes of the global coordinate system, respectively. Simultaneously, the pose parameters of the positioning device are obtained, including roll, pitch, and yaw angles. These pose parameters are used to determine the rotation relationship between the positioning device's coordinate system and the global coordinate system. Based on the obtained translation and pose parameters, a transformation matrix from the positioning device's coordinate system to the global coordinate system is constructed. Using the transformation matrix and the observed coordinates, the global coordinates of the reflector in the global coordinate system are calculated. Geometric anomalies of the reflector are detected using global and fixed coordinates. The result of the geometric anomaly detection is determined by whether the global and fixed coordinates are consistent. If they are inconsistent, the corresponding geometric anomaly detection result is considered geometrically abnormal; if they are consistent, the reflector is considered normal, and the corresponding geometric anomaly detection result is considered geometrically normal. The fixed coordinates are the coordinates of the center point of the reflector.

[0034] In this embodiment, the geometric anomalies of the reflector are detected based on the observed coordinates and fixed coordinates. The results of the geometric anomaly detection are determined so that the position of the corresponding reflector can be judged based on the corresponding geometric anomaly detection results, thus preventing the use of incorrect reflector positions for subsequent positioning correction.

[0035] In this embodiment, the preset reflection intensity is the average reflection intensity of the background or the initial intensity of the reflector. Based on the reflection intensity and the preset reflection intensity, the reflection anomaly of the reflector is detected, that is, whether the reflector can reflect the corresponding laser normally, so as to ensure that the positioning device can receive the reflection information of the reflector normally.

[0036] In this embodiment, a preset reflection intensity of the reflector is obtained, wherein the preset reflection intensity is the initial intensity of the reflector. Based on the reflection intensity and the preset reflection intensity, the reflection anomaly of the reflector is detected. When determining the reflection anomaly detection result of the reflector, the judgment can be made based on the intensity difference between the reflection intensity and the preset reflection intensity. When the intensity difference is greater than the preset intensity threshold, it is considered that the reflection intensity of the reflector is significantly different from the initial reflection intensity of the reflector, and the corresponding reflection anomaly detection result is a reflection anomaly. When the intensity difference is not greater than the preset intensity threshold, it is considered that the reflection intensity of the reflector is relatively small compared with the initial reflection intensity of the reflector, and the corresponding reflection anomaly detection result is a normal reflection.

[0037] In this embodiment, the reflection anomaly of the reflector is detected based on the reflection intensity and the preset reflection intensity to determine the abnormal result of the reflector in terms of the reflection dimension, so as to ensure that the reflector can reflect the laser emitted by the lidar normally and ensure the accuracy of the point cloud data.

[0038] In this embodiment, based on the local point cloud information, a point cloud matching score is calculated for the local point cloud information in point cloud matching. This score characterizes the overlap accuracy between the reflector point cloud and the source point cloud (reference model or previous frame point cloud). A higher point cloud matching score indicates higher overlap accuracy, and a lower score indicates lower overlap accuracy.

[0039] In this embodiment, the ICP iterative method is used for point cloud matching. The corresponding point cloud matching score is determined based on the matching accuracy index in the ICP iterative method. For example, the RMSE (Root Mean Square Error) matching accuracy index reflects the average distance deviation between the local point cloud information and the corresponding point pair in the previous frame; the smaller the value, the higher the matching score. The matching accuracy index is evaluated for all local point clouds corresponding to the reflector, and the corresponding point cloud matching score is determined based on the mean of all RMSE values ​​for all local point clouds.

[0040] It should be noted that local point cloud information also includes the corresponding point cloud density and the distance between adjacent point cloud clusters. The point cloud matching score can also be determined based on the point cloud density and the distance between adjacent point cloud clusters. For example, the ratio of the point cloud density to the preset point cloud density of the corresponding reflector is calculated, and the ratio of the distance between the reflector in this local point cloud information and the reflectors corresponding to adjacent point cloud clusters to a preset distance is calculated. The preset distance is the actual distance between the corresponding reflector and adjacent reflectors. These ratios are then normalized to obtain normalized ratios. All normalized ratios are summed to obtain the corresponding sum. The point cloud matching score is determined based on the magnitude of the sum. The larger the sum, the larger the point cloud matching score; the smaller the sum, the smaller the point cloud matching score.

[0041] Based on the point cloud matching score, the matching anomalies of the reflector are detected, and the detection results of the matching anomalies of the reflector are determined. The larger the point cloud matching score, the more normal the corresponding reflector is, and the smaller the matching score, the more abnormal the corresponding reflector is.

[0042] Based on the geometric anomaly detection results, reflection anomaly detection results, matching anomaly detection results, and the preset detection mechanism, the anomaly detection result of the reflector is determined. The preset detection mechanism is that when the geometric anomaly detection result is geometrically normal, the reflection detection result is reflection normal, and the matching detection result is matching normal, the anomaly detection result of the reflector is determined to be normal; otherwise, it is anomaly.

[0043] In this embodiment, the anomaly detection result of the reflector is determined based on the geometric anomaly detection result, the reflection anomaly detection result, the matching anomaly detection result, and the preset detection mechanism. The detection results of anomalies in different dimensions are taken into account and fused to determine the anomaly detection result of the reflector, thereby improving the accuracy of the anomaly detection result of the reflector.

[0044] Optionally, the geometric anomaly detection results include geometrically normal and geometrically abnormal; Based on the observed and fixed coordinates of the reflector, geometric anomalies of the reflector are detected, and the results of the geometric anomaly detection are determined, including: The pose of the positioning device is obtained, and the global coordinates of the reflector are calculated based on the pose of the positioning device and the observed coordinates. Calculate the distance between the global coordinates and the fixed coordinates to obtain the distance difference; If the distance difference is greater than the preset distance threshold, the geometric anomaly detection result of the reflector is a geometric anomaly; If the distance difference is not greater than the preset distance threshold, the geometric anomaly detection result of the reflector is geometrically normal.

[0045] In this embodiment, the pose of the positioning device is acquired, and the global coordinates of the reflector are calculated based on the pose of the positioning device and the observed coordinates. Specifically, the observed coordinates are transformed using a coordinate transformation matrix between the positioning device coordinate system and the global coordinate system to obtain the global coordinates. The coordinate transformation matrix is ​​a pre-prepared transformation matrix. The distance between the global coordinates and the fixed coordinates is calculated to obtain the distance difference. If the distance difference is greater than a preset distance threshold, the geometric anomaly detection result of the reflector is geometrically abnormal. If the distance difference is not greater than the preset distance threshold, the geometric anomaly detection result of the reflector is geometrically normal. The preset distance threshold is set in advance based on actual conditions, such as 0.2 times the historical average.

[0046] In this embodiment, geometric anomaly detection is performed by measuring the distance between global coordinates and fixed coordinates, which can quickly locate the corresponding abnormal reflectors and improve the efficiency of mapping.

[0047] Optionally, the results of abnormal reflection detection include normal reflection and abnormal reflection; Based on the reflection intensity and a preset reflection intensity, the reflection anomalies of the reflector are detected, and the detection results of the reflection anomalies of the reflector are determined, including: Calculate the ratio of the reflected intensity to the preset reflected intensity, and obtain the ratio result; If the ratio result is less than the preset ratio threshold, the geometric anomaly detection result of the reflector is determined to be a reflection anomaly. If the ratio result is not less than the preset ratio threshold, then the geometric anomaly detection result of the reflector is determined to be normal reflection.

[0048] In this embodiment, the ratio of the reflected intensity to a preset reflected intensity is calculated to obtain the ratio result. The reflection anomaly detection result is determined based on the ratio result. If the ratio result is less than a preset ratio threshold, the reflection anomaly detection result of the reflector is determined to be a reflection anomaly. If the ratio result is not less than the preset ratio threshold, the reflection anomaly detection result of the reflector is determined to be normal. The preset ratio threshold is a pre-set threshold value.

[0049] In this embodiment, the reflection anomaly detection result is determined based on the ratio of the reflection intensity to the preset reflection intensity. If the ratio is small, it is considered that the damage to the reflector is large, which may cause the positioning device to not receive the corresponding reflection signal after emitting the corresponding laser. The reflection anomaly detection result of the corresponding reflector is determined to be a reflection anomaly, which improves the accuracy of mapping.

[0050] Optionally, the anomaly detection results include normal matches and abnormal matches; Based on the point cloud matching score, the matching anomalies of the reflector are detected, and the detection results of the matching anomalies of the reflector are determined, including: If the point cloud matching score is less than the preset matching threshold, the matching anomaly detection result of the reflector is determined to be a matching anomaly. If the point cloud matching score is not less than the preset matching threshold, then the matching anomaly detection result of the reflector is determined to be a normal match.

[0051] In this embodiment, the point cloud matching score is compared with a preset matching threshold, where the preset matching threshold is a pre-set threshold. If the point cloud matching score is less than the preset matching threshold, the reflector's matching anomaly detection result is determined to be a matching anomaly. If the point cloud matching score is not less than the preset matching threshold, the reflector's matching anomaly detection result is determined to be a normal matching.

[0052] In this embodiment, the matching result in the corresponding matching dimension is determined by judging the difference between the point cloud matching score and the preset matching threshold. This ensures that the matching result in the matching dimension can be taken into account when detecting whether the reflector is abnormal, thereby improving the accuracy of anomaly detection.

[0053] Optionally, based on the geometric anomaly detection results, reflection anomaly detection results, matching anomaly detection results, and a preset detection mechanism, the anomaly detection results of the reflector are determined, including: If the abnormal detection results of the reflector are normal in geometry, normal in reflection, and normal in matching, then the abnormal detection results are determined to be normal. If any of the geometric anomalies, reflection anomalies, and matching anomalies appear in the anomaly detection results of the reflector, the anomaly detection result of the reflector shall be determined based on the distance difference, ratio result, and point cloud matching score. If any two or more of the following are found in the abnormality detection results of the reflector: geometric abnormality, reflection abnormality, and matching abnormality, then the abnormality detection results are determined to be abnormal.

[0054] In this embodiment, if the anomaly detection results of the reflector are geometrically normal, reflectively normal, and matching normally, then the anomaly detection result is determined to be normal. That is, if all anomaly detection results in different dimensions are normal, the anomaly detection result is determined to be normal. If any two or more of the geometrical anomaly, reflectively abnormal, and matching anomaly occur in the anomaly detection results of the reflector, then the anomaly detection result is determined to be abnormal. That is, if more dimensions are detected as abnormal than the dimensions are detected as normal in different dimensions, the anomaly detection result is determined to be abnormal.

[0055] When the number of detected anomalies is small but present—that is, if any one of the geometric anomalies, reflection anomalies, and matching anomalies appears in the anomaly detection results of the reflector—the anomaly detection result of the reflector is determined based on the distance difference, ratio result, and point cloud matching score. In other words, it is determined based on the anomaly value of each dimension, including the distance difference, ratio result, and point cloud matching score.

[0056] In this embodiment, by refining the detection results of anomaly detection in different dimensions, when determining the anomaly detection result of the reflector, a small error can be allowed for normal reflectors, thereby avoiding the error of identifying normal reflectors as abnormal reflectors and improving the detection accuracy of abnormal reflectors.

[0057] Optionally, the anomaly detection result of the reflector is determined based on the distance difference, ratio result, and point cloud matching score, including: The first difference between the distance difference and the preset distance threshold is calculated, and the first weight value is calculated based on the ratio of the first difference to the preset distance threshold. The second difference between the ratio result and the preset ratio threshold is calculated, and the second weight value is calculated based on the ratio of the second difference to the preset ratio threshold. The third difference between the point cloud matching score and the preset matching threshold is calculated, and the third weight value is calculated based on the ratio of the third difference to the preset matching threshold. Based on the first weight value, the second weight value, and the third weight value, the reciprocal of the distance difference, the ratio result, and the point cloud matching score are weighted and summed to obtain the target value; If the target value is less than the preset threshold, the abnormal detection result will be identified as abnormal.

[0058] In this embodiment, the difference between the corresponding error and the normal value in each dimension is calculated separately. The weight value of each dimension is determined based on the magnitude of the difference, and a weighted sum is then performed. Specifically, the reciprocal of the distance difference, the ratio result, and the point cloud matching score are weighted according to the first, second, and third weight values ​​to obtain the target value. For example, the target value is obtained by multiplying the reciprocal of the distance difference by the first weight value, adding the ratio result by the second weight value, and adding the point cloud matching score by the third weight value. A larger target value (i.e., a larger reciprocal of the distance difference, the ratio result, and the point cloud matching score) indicates a more normal reflector. A smaller target value (i.e., a smaller reciprocal of the distance difference, the ratio result, and the point cloud matching score) indicates a more abnormal reflector. Therefore, if the target value is less than a preset threshold, the abnormal detection result is determined as abnormal; otherwise, it is considered normal. The preset threshold is a pre-set threshold determined based on actual conditions.

[0059] In this embodiment, when the abnormal detection result of the corresponding reflector is uncertain, the difference between the corresponding error and the normal value in each dimension is calculated respectively. The weight value of each dimension is determined according to the size of the corresponding difference, and then a weighted sum is performed to obtain the corresponding target value. The target value is determined based on the corresponding target value. The abnormal situation of the reflector is comprehensively considered to avoid the situation where the corresponding reflector is detected as abnormal when there is a small error in each dimension.

[0060] S103: Traverse all reflectors observed by the positioning device at the current position, obtain the abnormal detection result of each reflector, determine the number of abnormal reflectors and the number of normal reflectors based on the abnormal detection result of each reflector, and determine the weight value of the reflectors based on the ratio of the number of abnormal reflectors to the number of normal reflectors.

[0061] In step S103, the weight value of the reflector is determined based on the ratio of the number of abnormal reflectors to the number of normal reflectors. That is, the weight value of the reflector is determined based on the number of abnormal reflectors. The weight value of the reflector is dynamically adjusted, that is, the influence of the reflector on the positioning is dynamically adjusted to avoid treating abnormal reflectors as normal reflectors in the calculation, which would affect the positioning accuracy.

[0062] In this embodiment, all reflectors observed by the positioning device at the current position are traversed to obtain the anomaly detection result for each reflector. Based on the anomaly detection result for each reflector, the number of abnormal reflectors and the number of normal reflectors are determined. This allows for the discarding of corresponding abnormal reflectors or a reduction in the weight value of corresponding reflectors during positioning optimization.

[0063] Based on the ratio of the number of abnormal reflectors to the number of normal reflectors, a corresponding weight value is assigned to each reflector, resulting in a reflector weight value. When the ratio of abnormal reflectors to normal reflectors is large, it is considered that there are more abnormal reflectors, and a smaller weight value is assigned to each reflector. Conversely, when the ratio of abnormal reflectors to normal reflectors is small, it is considered that there are more normal reflectors, and a larger weight value is assigned to each reflector.

[0064] For example, when the ratio increases, meaning the number of abnormal reflectors increases, a smaller weight value is assigned to each reflector; for instance, the weight value can be decreased based on the rate of increase in the ratio. Conversely, when the ratio decreases, meaning the number of abnormal reflectors decreases, a larger weight value is assigned to each reflector; for instance, the weight value can be increased based on the rate of decrease in the ratio.

[0065] It should be noted that if the same reflector is detected as an abnormal reflector for a continuous period of time, the corresponding reflector will be removed. That is, when traversing all the reflectors observed by the positioning device at the current position, the removed reflectors will not be observed.

[0066] In this embodiment, the weight value of the reflector is determined based on the number of abnormal light-emitting plates, and the weight value of the reflector is dynamically adjusted, that is, the influence of the reflector on the positioning is dynamically adjusted, so as to avoid treating abnormal reflectors as normal reflectors in the calculation, thereby improving the positioning accuracy.

[0067] S104: Obtain the fixed coordinates of each reflector, calculate the reflector error of each reflector based on the observed coordinates and fixed coordinates of each reflector, and calculate the target error of the positioning device pose at the current moment based on the weight value of the reflector, the reflector error and the preset optimization function.

[0068] In step S104, the fixed coordinates of each reflector are the coordinate values ​​in the X, Y, and Z axes of the global coordinate system, i.e., the coordinates in the world coordinate system, which are pre-obtained coordinates. The observed coordinates are the reflector coordinate information observed by the positioning device. Based on the observed coordinates and the fixed coordinates, the error of each reflector is calculated, i.e., the error between the global coordinates obtained by transforming the observed coordinates and the fixed coordinates.

[0069] In this embodiment, fixed coordinates (Xg, Yg, Zg) are obtained, where Xg, Yg, and Zg represent the coordinate values ​​of the reflector in the X, Y, and Z axes of the global coordinate system, respectively. A certain spatial relationship exists between the positioning device coordinate system and the global coordinate system, which can be represented by a coordinate transformation matrix. The positioning device coordinate system is based on the positioning device as the origin. The transformation relationship between the two coordinate systems includes translation and rotation. First, the positioning device's own positioning module (such as an IMU inertial measurement unit combined with a GPS positioning module) obtains the translation parameters (Tx, Ty, Tz) of the positioning device in the global coordinate system, where Tx, Ty, and Tz represent the translation amounts of the origin of the positioning device's coordinate system in the X, Y, and Z axes of the global coordinate system, respectively. Simultaneously, the positioning device's pose parameters, including roll, pitch, and yaw, are obtained. These pose parameters are used to determine the rotation relationship between the positioning device's coordinate system and the global coordinate system. Based on the translation and pose parameters obtained above, a transformation matrix is ​​constructed from the positioning device coordinate system to the global coordinate system. Using the transformation matrix and the observed coordinates, the global coordinates of the reflector in the global coordinate system are calculated. The difference between the fixed coordinates and the transformed global coordinates is calculated to obtain the error for each reflector.

[0070] The target error of the positioning device's pose at the current moment is calculated based on the reflector's weight value, reflector error, and a preset optimization function. The preset optimization function is a Pose-Graph optimization function, which includes reflector error, odometer error, and inertial navigation (INS) error terms. Each error term has a preset weight value. The reflector error, odometer error, and INS error terms are weighted and summed according to their respective weight values ​​to obtain the corresponding target error. The reflector error term is the sum of the errors of each reflector. The odometer error term represents the relative pose deviation between adjacent frames, i.e., the difference between the "estimated relative motion state" and the "actual relative motion state" between two consecutive keyframes of the positioning device. The INS error term represents the inertial relative pose deviation between adjacent frames, i.e., the difference between the "estimated inertial relative pose" obtained through INS pre-integration between two adjacent frames of the positioning device and the actual relative pose of the two frames.

[0071] Based on the weight values ​​of the reflectors, the weight values ​​of the odometer error term and the inertial navigation error term are adjusted, where the sum of the weight values ​​of the reflectors, odometer error term, and inertial navigation error term is 1. When adjusting the weight values ​​of the odometer and inertial navigation error terms, the same weight value can be increased or decreased simultaneously. For example, if the weight value of the reflectors is determined based on the ratio of the number of abnormal reflectors to the number of normal reflectors, increasing the reflector's weight value is accompanied by decreasing the same weight value, and decreasing the reflector's weight value is accompanied by increasing the same weight value. That is, when the number of abnormal reflectors increases, the reflector's weight value is automatically decreased while the same weight value is increased to activate and introduce the inertial navigation factor and odometer factor, thereby ensuring that the system's positioning accuracy does not drop sharply when the main landmark fails. When the number of abnormal reflectors decreases, the reflector's weight value is automatically increased while the same weight value is decreased. Other methods can also be used for adjustment; this embodiment is not limited to any particular method. When automatically increasing or decreasing the weight value of the reflector, the adjustment can be made according to preset rules, and this embodiment does not limit the adjustment.

[0072] S105: Optimize the pose of the positioning device based on the target error to obtain the optimized pose, and construct the target map based on the optimized pose.

[0073] In step S105, a target map is constructed based on the optimized pose. That is, based on the optimized pose, the global coordinates of the point cloud are determined according to the corresponding LiDAR point cloud data to obtain the corresponding target map.

[0074] In this embodiment, the pose of the positioning device is optimized based on the target error to eliminate the corresponding error. After pose optimization, the optimized pose data is used in conjunction with environmental feature information and, according to preset map construction rules, the collected environmental data is integrated into the map framework to ultimately form a target map that accurately reflects the actual environment.

[0075] Optionally, after constructing the target map based on the optimized pose, the following steps are also included: Obtain the original map and the sub-maps segmented based on the original map. Based on the differences between the target map and the corresponding sub-maps of the target map, obtain the map change information detected by the corresponding positioning device. Iterate through the map change information corresponding to all positioning devices to obtain the target map change information. Update the original map based on the target map change information to obtain the updated map.

[0076] Change information: The original map is updated based on the change information of the target map to obtain the updated map.

[0077] In this embodiment, an original map and various sub-maps segmented from the original map are obtained. Each sub-map corresponds to a positioning device for simultaneous positioning and mapping. Based on the differences between the target map and its corresponding sub-maps, map change information detected by the corresponding positioning device is obtained. The map change information corresponding to all positioning devices is traversed, and all map change information is uploaded to a cloud server. The cloud server uses a merging algorithm based on CRDT (Conflict-Free Copy Data Type) to handle concurrent map update requests from multiple positioning devices. Based on the target map change information, the original map is updated to obtain the updated map.

[0078] In this embodiment, the merging algorithm based on CRDT handles concurrent map update requests from multiple positioning devices. Each device can respond to environmental changes in real time and update the map synchronously, effectively improving the real-time performance of map maintenance and the overall robustness of the system.

[0079] This application performs anomaly detection on reflectors based on observed coordinates, reflection intensity, and local point cloud information to determine the anomaly detection results. Based on the anomaly detection results, it determines the weight values ​​of the reflectors, obtains the fixed coordinates of each reflector, calculates the reflector error for each reflector based on the observed coordinates and fixed coordinates, and calculates the target error of the positioning device's pose at the current moment based on the reflector's weight value, reflector error, and a preset optimization function. The positioning device's pose is then optimized based on the target error to obtain the optimized pose, and a target map is constructed based on the optimized pose. Cross-validation is performed using multi-dimensional anomaly detection results to confirm the anomaly detection results of the reflectors, avoiding misjudgments and missed detections. Therefore, in the reflector-based positioning optimization process, the corresponding positioning accuracy is improved.

[0080] Please see Figure 2 , Figure 2 This is a schematic diagram of a simultaneous positioning and mapping device according to an embodiment of this application. This simultaneous positioning and mapping device corresponds one-to-one with the simultaneous positioning and mapping method described in the above embodiments. Please refer to [link / reference] for details. Figure 1 as well as Figure 1 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 1 The positioning and mapping device 20 includes: an extraction module 21, a first determination module 22, a second determination module 23, a calculation module 24, and an optimization module 25.

[0081] Extraction module 21 is used to acquire lidar point cloud data and extract reflector observation information from the lidar point cloud data. The reflector observation information includes at least the reflector's observation coordinates, reflection intensity, and local point cloud information. The lidar point cloud data is the data collected by the lidar carried by the positioning device.

[0082] The first determining module 22 is used to perform anomaly detection on the reflector based on the observed coordinates, reflection intensity and local point cloud information, and determine the anomaly detection result of the reflector.

[0083] The second determining module 23 is used to traverse all reflectors observed by the positioning device at the current position, obtain the abnormal detection result of each reflector, determine the number of abnormal reflectors and the number of normal reflectors based on the abnormal detection result of each reflector, and determine the weight value of the reflector based on the ratio of the number of abnormal reflectors to the number of normal reflectors.

[0084] The calculation module 24 is used to obtain the fixed coordinates of each reflector, calculate the reflector error of each reflector based on the observed coordinates and fixed coordinates of each reflector, and calculate the target error of the positioning device pose at the current moment based on the weight value of the reflector, the reflector error and the preset optimization function.

[0085] The optimization module 25 is used to optimize the pose of the positioning device according to the target error, obtain the optimized pose, and construct the target map based on the optimized pose.

[0086] Optionally, the first determining module 22 includes: The first detection unit is used to obtain the fixed coordinates of the reflector, and to detect the geometric anomalies of the reflector based on the observed coordinates and the fixed coordinates, and to determine the geometric anomaly detection results of the reflector.

[0087] The second detection unit is used to obtain the preset reflection intensity of the reflector, and to detect the reflection anomaly of the reflector based on the reflection intensity and the preset reflection intensity, and to determine the reflection anomaly detection result of the reflector.

[0088] The third detection unit is used to calculate the point cloud matching score of local point cloud information in point cloud matching, and to detect the matching anomaly of the reflector based on the point cloud matching score, and to determine the detection result of the matching anomaly of the reflector.

[0089] The determination unit is used to determine the anomaly detection results of the reflector based on the geometric anomaly detection results, reflection anomaly detection results, matching anomaly detection results, and the preset detection mechanism.

[0090] Optionally, the first detection unit includes: The first calculation subunit is used to obtain the pose of the positioning device and calculate the global coordinates of the reflector based on the pose of the positioning device and the observed coordinates.

[0091] The second calculation subunit is used to calculate the distance between the global coordinates and the fixed coordinates, and obtain the distance difference.

[0092] The second judgment subunit is used to determine the geometric anomaly detection result of the reflector as geometric anomaly if the distance difference is greater than a preset distance threshold.

[0093] The second judgment subunit is used to determine the geometric anomaly detection result of the reflector as geometrically normal if the distance difference is not greater than a preset distance threshold.

[0094] Optionally, the second detection unit includes: The third calculation subunit is used to calculate the ratio of the reflection intensity to the preset reflection intensity and obtain the ratio result.

[0095] The third judgment subunit is used to determine the reflection abnormality detection result of the reflector as a reflection abnormality if the ratio result is less than the preset ratio threshold.

[0096] The fourth judgment subunit is used to determine the reflection abnormality detection result of the reflector as normal if the ratio result is not less than the preset ratio threshold.

[0097] Optionally, the third detection unit includes: The fifth judgment subunit is used to determine the matching anomaly detection result of the reflector as a matching anomaly if the point cloud matching score is less than the preset matching threshold.

[0098] The sixth judgment subunit is used to determine the matching anomaly detection result of the reflector as normal if the point cloud matching score is not less than the preset matching threshold.

[0099] Optionally, the determined unit includes: The seventh judgment subunit is used to determine the abnormal detection result as normal if the abnormal detection result of the reflector is geometrically normal, reflectively normal, and matching normal.

[0100] If any of the geometric anomalies, reflection anomalies, or matching anomalies appear in the anomaly detection results of the reflector, the anomaly detection result of the reflector is determined based on the distance difference, ratio result, and point cloud matching score.

[0101] The eighth judgment subunit is used to determine the abnormality detection result as abnormal if any two or more of the geometric abnormality, reflection abnormality and matching abnormality appear in the abnormality detection result of the reflector.

[0102] Optionally, the simultaneous positioning and mapping device 20 also includes: The acquisition module is used to acquire the original map and the various sub-maps segmented based on the original map. Based on the differences between the target map and the corresponding sub-maps of the target map, the module obtains the map change information detected by the corresponding positioning device.

[0103] The update module is used to traverse the map change information corresponding to all positioning devices, obtain the target map change information, update the original map based on the target map change information, and obtain the updated map.

[0104] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0105] Figure 3 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. For example... Figure 3 As shown, the computer device of this embodiment includes: at least one processor ( Figure 3 Only one is shown in the diagram), a memory, and a computer program stored in the memory and executable on at least one processor, wherein the processor executes the computer program to implement the steps in any of the above-described mapping method embodiments.

[0106] This computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 3 The examples of computer devices are merely examples and do not constitute a limitation on computer devices. Computer devices may include more or fewer components than shown in the illustration, or combinations of certain components, or different components, such as network interfaces, displays, and input devices.

[0107] The processor referred to can be a CPU, but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0108] Memory includes readable storage media, internal memory, etc., wherein internal memory can be the RAM of a computer device, providing an environment for the operation of the operating system and computer-readable instructions stored in the readable storage media. The readable storage media can be the hard drive of a computer device, or in other embodiments, it can be an external storage device of the computer device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, memory can include both internal storage units and external storage devices of the computer device. Memory is used to store the operating system, applications, bootloader, data, and other programs, such as program code for computer programs. Memory can also be used to temporarily store data that has been output or will be output.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code, a recording medium, a computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0110] The implementation of all or part of the processes in the methods of the above embodiments can also be accomplished by a computer program product. When the computer program product is run on a computer device, it enables the computer device to execute the steps in the above method embodiments.

[0111] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implementation should not be considered beyond the scope of this application.

[0113] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or 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.

[0114] 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.

[0115] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for simultaneous localization and mapping, characterized in that, The simultaneous localization and mapping method includes: Acquire lidar point cloud data, extract reflector observation information from the lidar point cloud data, the reflector observation information includes at least the reflector's observation coordinates, reflection intensity and local point cloud information, the lidar point cloud data is data collected by the lidar carried by the positioning device; Based on the observed coordinates, reflection intensity, and local point cloud information, anomaly detection is performed on the reflector to determine the anomaly detection result of the reflector; Iterate through all reflectors observed by the positioning device at the current position, obtain the anomaly detection result of each reflector, determine the number of abnormal reflectors and the number of normal reflectors based on the anomaly detection result of each reflector, and determine the weight value of the reflectors based on the ratio of the number of abnormal reflectors to the number of normal reflectors. Obtain the fixed coordinates of each reflector, calculate the reflector error of each reflector based on the observed coordinates and the fixed coordinates of each reflector, and calculate the target error of the positioning device pose at the current moment based on the weight value of the reflector, the reflector error and the preset optimization function. The pose of the positioning device is optimized based on the target error to obtain the optimized pose, and a target map is constructed based on the optimized pose.

2. The simultaneous positioning and mapping method as described in claim 1, characterized in that, The step of performing anomaly detection on the reflector based on the observed coordinates, reflection intensity, and local point cloud information, and determining the anomaly detection result of the reflector, includes: Obtain the fixed coordinates of the reflector, and based on the observed coordinates and the fixed coordinates of the reflector, detect the geometric anomalies of the reflector and determine the geometric anomaly detection result of the reflector. Obtain the preset reflection intensity of the reflector, and detect the reflection anomaly of the reflector based on the reflection intensity and the preset reflection intensity to determine the reflection anomaly detection result of the reflector; Based on the local point cloud information, the point cloud matching score of the local point cloud information in point cloud matching is calculated. Based on the point cloud matching score, the matching anomaly of the reflector is detected, and the matching anomaly detection result of the reflector is determined. Based on the geometric anomaly detection results, the reflection anomaly detection results, the matching anomaly detection results, and the preset detection mechanism, the anomaly detection results of the reflector are determined.

3. The simultaneous positioning and mapping method as described in claim 2, characterized in that, The geometric anomaly detection results include geometrically normal and geometrically abnormal; The step of detecting geometric anomalies of the reflector based on the observed coordinates and the fixed coordinates, and determining the geometric anomaly detection result of the reflector, includes: The pose of the positioning device is obtained, and the global coordinates of the reflector are calculated based on the pose of the positioning device and the observed coordinates. Calculate the distance between the global coordinates and the fixed coordinates to obtain the distance difference; If the distance difference is greater than a preset distance threshold, then the geometric anomaly detection result of the reflector is the geometric anomaly. If the distance difference is not greater than a preset distance threshold, then the geometric anomaly detection result of the reflector is that it is geometrically normal.

4. The simultaneous positioning and mapping method as described in claim 2, characterized in that, The results of the abnormal reflection detection include normal reflection and abnormal reflection. The step of detecting reflection anomalies in the reflector based on the reflection intensity and a preset reflection intensity, and determining the reflection anomaly detection result of the reflector, includes: Calculate the ratio of the reflected intensity to the preset reflected intensity to obtain the ratio result; If the ratio result is less than the preset ratio threshold, then the reflection anomaly detection result of the reflector is determined to be a reflection anomaly; If the ratio result is not less than the preset ratio threshold, then the reflection anomaly detection result of the reflector is determined to be normal.

5. The simultaneous positioning and mapping method as described in claim 2, characterized in that, The matching anomaly detection results include normal matching and abnormal matching. The step of detecting matching anomalies in the reflector based on the point cloud matching score and determining the detection result of the matching anomaly in the reflector includes: If the point cloud matching score is less than the preset matching threshold, then the matching anomaly detection result of the reflector is determined to be a matching anomaly. If the point cloud matching score is not less than the preset matching threshold, then the matching anomaly detection result of the reflector is determined to be a normal match.

6. The simultaneous positioning and mapping method as described in any one of claims 2 to 5, characterized in that, The step of determining the anomaly detection result of the reflector based on the geometric anomaly detection result, the reflection anomaly detection result, the matching anomaly detection result, and a preset detection mechanism includes: If the abnormality detection result of the reflector is that the geometry is normal, the reflection is normal, and the matching is normal, then the abnormality detection result is determined to be normal. If any one of the geometric anomalies, reflection anomalies, and matching anomalies appears in the anomaly detection results of the reflector, the anomaly detection result of the reflector is determined based on the distance difference, ratio result, and point cloud matching score. If any two or more of the geometric anomalies, reflection anomalies, and matching anomalies appear in the anomaly detection results of the reflector, then the anomaly detection results are determined to be anomalies.

7. The simultaneous positioning and mapping method as described in claim 1, characterized in that, After constructing the target map based on the optimized pose, the process further includes: Obtain the original map and each sub-map segmented based on the original map; and obtain the map change information detected by the corresponding positioning device based on the differences between the target map and the corresponding sub-maps of the target map. The map change information corresponding to all positioning devices is traversed to obtain the target map change information. The original map is then updated based on the target map change information to obtain the updated map.

8. A device for simultaneous positioning and mapping, characterized in that, The simultaneous positioning and mapping device includes: An extraction module is used to acquire lidar point cloud data and extract reflector observation information from the lidar point cloud data. The reflector observation information includes at least the observation coordinates, reflection intensity, and local point cloud information of the reflector. The lidar point cloud data is data collected by the lidar carried by the positioning device. The first determining module is used to perform anomaly detection on the reflector based on the observed coordinates, reflection intensity and local point cloud information, and determine the anomaly detection result of the reflector; The second determining module is used to traverse all reflectors observed by the positioning device at the current position, obtain the abnormal detection result of each reflector, determine the number of abnormal reflectors and the number of normal reflectors based on the abnormal detection result of each reflector, and determine the weight value of the reflector based on the ratio of the number of abnormal reflectors to the number of normal reflectors. The calculation module is used to obtain the fixed coordinates of each reflector, calculate the reflector error of each reflector based on the observed coordinates and the fixed coordinates of each reflector, and calculate the target error of the positioning device pose at the current moment based on the weight value of the reflector, the reflector error and the preset optimization function. An optimization module is used to optimize the pose of the positioning device based on the target error to obtain an optimized pose, and to construct a target map based on the optimized pose.

9. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the simultaneous localization and mapping method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the simultaneous localization and mapping method as described in any one of claims 1 to 7.

Images