Map construction method and device, computer equipment and readable storage medium

Abstract

The invention relates to a map construction method and device, computer equipment and a readable storage medium. The method comprises the steps that in the moving process of a robot in a pipeline, laser radar point cloud, pipeline environment data, pipeline visual data and motion data collected by different sensors are obtained; under the condition that the current map building moment is reached, the initial pose of the robot is predicted according to the motion data, and a refractive index compensation factor of the pipeline is determined according to the pipeline environment data; determining an initial map point cloud of the target time period according to the initial pose, the refractive index compensation factor, and the laser radar point cloud and pipeline visual data in the target time period; according to a preset curvature threshold and a refractive index compensation factor, correcting the initial map point cloud to obtain a target local map; and updating the initial global map at the previous map construction moment according to the target local map to obtain a target global map. By adopting the method, the accuracy of the constructed map can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, in particular to a map construction method and device, computer equipment and a readable storage medium. BACKGROUND

[0002] As an important infrastructure for urban energy transmission and industrial fluid transportation, the detection and maintenance of underground pipelines are of great significance to ensure the safe operation. The traditional detection method mainly relies on manual or simple camera equipment, which is not only low in efficiency and high in labor intensity, but also poor in accessibility in long-distance, narrow or complex curved pipelines, and there are serious safety hazards.

[0003] With the development of robot technology, pipeline detection methods based on robots have been more and more widely used. However, due to the problems of weak light, few textures, dust and water vapor interference in the pipeline, the existing SLAM (Simultaneous Localization and Mapping) technology has accumulated errors and positioning drift, resulting in low accuracy of the constructed map. SUMMARY

[0004] Therefore, it is necessary to provide a map construction method, device, computer equipment and readable storage medium to improve the accuracy of the constructed map.

[0005] In a first aspect, the present application provides a map construction method, comprising:

[0006] During the movement of the robot in the pipeline, laser radar point clouds collected by different sensors carried by the robot, pipeline environment data, pipeline visual data and motion data of the robot are acquired;

[0007] In the case of reaching the current map construction moment, the initial pose of the robot is predicted according to the motion data of the current map construction moment, and the refractive index compensation factor of the pipeline is determined according to the pipeline environment data of the current map construction moment;

[0008] According to the initial pose, the refractive index compensation factor, and the laser radar point clouds and the pipeline visual data in the target period, the initial map point cloud of the target period is determined; wherein the target period is the time period between the current map construction moment and the last map construction moment;

[0009] According to the preset curvature threshold and the refractive index compensation factor, the initial map point cloud is corrected to obtain the target local map of the target period;

[0010] According to the target local map, the initial global map of the last map construction moment is updated to obtain the target global map of the current map construction moment.

[0011] In one of the embodiments, the motion data comprises inertial navigation measurement data and wheel rotation data; the initial pose of the robot is predicted according to the motion data at the current map construction time, comprising: determining initial motion parameters of the robot according to the wheel rotation data at the current map construction time, and correcting the initial motion parameters by using a preset slip coefficient to obtain target motion parameters after correction; predicting the pose of the robot by taking the inertial navigation measurement data as a prediction value and the target motion parameters as an observation value to obtain the initial pose of the robot.

[0012] In one of the embodiments, the pipeline environment data comprises temperature, humidity and pressure; the refractive index compensation factor of the pipeline is determined according to the pipeline environment data at the current map construction time, comprising: determining the refractive index compensation factor of the pipeline according to the temperature, humidity and pressure at the current map construction time.

[0013] In one of the embodiments, the motion data comprises inertial navigation measurement data; the initial map point cloud of the target period is determined according to the initial pose, the refractive index compensation factor, and the laser radar point cloud and the pipeline visual data in the target period, comprising: generating a current trajectory sequence of the robot in the target period according to the initial pose and the pipeline visual data in the target period; determining a pose set of the robot in the target period according to the current trajectory sequence and a pre-integration result of the inertial navigation measurement data in the target period; performing distortion compensation on the laser radar point cloud in the target period by using the pose set to obtain a compensated point cloud, and performing intensity correction on the compensated point cloud according to the refractive index compensation factor to obtain a corrected point cloud; performing filtering processing on the corrected point cloud according to radar echo data of each point in the corrected point cloud to obtain the initial map point cloud of the target period.

[0014] In one of the embodiments, the initial map point cloud is corrected according to a preset curvature threshold and the refractive index compensation factor to obtain a target local map of the target period, comprising: dividing the initial map point cloud into a first point cloud region and a second point cloud region according to the preset curvature threshold; wherein the curvature of the first point cloud region is less than the preset curvature threshold, and the curvature of the second point cloud region is not less than the preset curvature threshold; performing interpolation fusion on an interface region between the first point cloud region and the second point cloud region to obtain an initial local map; performing intensity correction on the initial local map according to the refractive index compensation factor to obtain the target local map of the target period.

[0015] In one of the embodiments, the updating of the initial global map at the previous map construction moment according to the target local map to obtain the target global map at the current map construction moment comprises: constructing an optimized local map at the current map construction moment according to the current trajectory sequence, the target local map, and the motion data corresponding to each trajectory point in the current trajectory sequence; screening a specified local map in which the pipeline structure features match the pipeline structure features of the optimized local map in the initial global map at the previous map construction moment; determining an overlap rate of a historical trajectory sequence corresponding to the specified local map and the current trajectory sequence; in a case where the overlap rate is greater than a preset overlap rate threshold, correcting the specified local map according to the target local map, and correcting the initial global map according to the specified local map after the correction to obtain the target global map at the current map construction moment.

[0016] In a second aspect, the present application further provides a map construction device, comprising:

[0017] a data acquisition module configured to acquire laser radar point clouds, pipeline environment data, pipeline visual data and motion data of the robot collected by different sensors carried by the robot during movement of the robot in the pipeline;

[0018] a pose prediction module configured to predict an initial pose of the robot according to the motion data at the current map construction moment in a case where the current map construction moment is reached;

[0019] a compensation factor determination module configured to determine a refractive index compensation factor of the pipeline according to the pipeline environment data at the current map construction moment;

[0020] a point cloud determination module configured to determine an initial map point cloud of a target period according to the initial pose, the refractive index compensation factor, and the laser radar point clouds and the pipeline visual data in the target period, wherein the target period is a time period between the current map construction moment and a previous map construction moment;

[0021] a map construction module configured to correct the initial map point cloud according to a preset curvature threshold and the refractive index compensation factor to obtain a target local map of the target period;

[0022] a map updating module configured to update the initial global map at the previous map construction moment according to the target local map to obtain the target global map at the current map construction moment.

[0023] In a third aspect, the present application further provides a computer device comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of each method embodiment provided in the first aspect when executing the computer program.

[0024] In a fourth aspect, the present application also provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the method embodiments provided in the first aspect.

[0025] In a fifth aspect, the present application also provides a computer program product, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments provided in the first aspect.

[0026] The above map construction method and device, computer device and readable storage medium, by loading multiple different sensors on the robot, to obtain various data collected by the different sensors, such as laser radar data, pipeline environment data, pipeline visual data and motion data of the robot, when the robot moves in the pipeline; thus, at each time when the current map construction moment is reached, the initial pose of the robot is predicted according to the motion data at the current map construction moment, and the refractive index compensation factor of the pipeline is determined according to the pipeline environment data at the current map construction moment; then, taking the time period between the current map construction moment and the last map construction moment as a target period, the initial map point cloud of the target period is determined according to the initial pose and the refractive index compensation factor, and the laser radar point cloud and the pipeline visual data in the target period, and the initial map point cloud is corrected according to the preset curvature threshold and the refractive index compensation factor, to obtain the target local map of the target period. Then, the initial global map at the last map construction moment is updated according to the target local map, to obtain the target global map at the current map construction moment, and thus the map construction at the current map construction moment is completed. In this way, on the one hand, the fusion of the multi-source data collected by the different sensors carried by the robot can realize high-precision map construction in a complex pipeline environment, and improve the accuracy of the constructed local map; on the other hand, the update of the historical global map by the local map at each map construction moment can reduce the positioning drift of the global map, improve the accuracy of the pipeline global map, and thus improve the detection accuracy of the pipeline detection based on the constructed map. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0028] Figure 1 The application environment diagram of the map construction method provided by some embodiments of the present application;

[0029] Figure 2A flowchart of a map construction method provided for some embodiments of the present application is shown in FIG. 1.

[0030] Figure 3 A flowchart of predicting an initial pose provided for some embodiments of the present application is shown in FIG. 2.

[0031] Figure 4 A flowchart of determining an initial point cloud of a map provided for some embodiments of the present application is shown in FIG. 3.

[0032] Figure 5 A flowchart of determining a target local map provided for some embodiments of the present application is shown in FIG. 4.

[0033] Figure 6 A flowchart of updating an initial global map provided for some embodiments of the present application is shown in FIG. 5.

[0034] Figure 7 A flowchart of a map construction method provided for some other embodiments of the present application is shown in FIG. 6.

[0035] Figure 8 A block diagram of a map construction apparatus provided for some embodiments of the present application is shown in FIG. 7.

[0036] Figure 9 An internal structure diagram of a computer device provided for some embodiments of the present application is shown in FIG. 8.

[0037] Figure 10 An internal structure diagram of a computer device provided for some other embodiments of the present application is shown in FIG. 9. DETAILED DESCRIPTION

[0038] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0039] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "multiple" used in the present application refers to two and more than two. The term "and / or" used in the present application refers to one of the options or any combination of multiple options.

[0040] With the development of robot technology, the pipeline detection method based on robot is more and more widely used. However, due to the problems such as weak light, few textures, dust and water vapor interference existing in the pipeline, the existing SLAM (Simultaneous Localization and Mapping) technology has cumulative error and positioning drift, resulting in low accuracy of the constructed map.

[0041] In order to solve the above technical problems, in one example embodiment, a map construction method is provided, which can be applied to the controller (processor) of the robot itself, and can also be applied to the back-end server of the robot. The back-end server can be a physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services, hereinafter referred to as server.

[0042] On the basis of the above embodiment, in one example embodiment, the map construction method provided by the embodiment of the present application can be applied to the application environment as shown in Figure 1 The robot 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The data storage system can record various data collected by different sensors carried by the robot, local maps constructed at each map construction moment, global maps, etc. Then the server 104 obtains the above data from the data storage system to execute the map construction method provided by the embodiment of the present application.

[0043] On the basis of the above embodiment, in one example embodiment, as shown in Figure 2 A map construction method is provided, which is applied to the controller (processor) of the robot itself as an example, which can include the following steps:

[0044] S201, during the movement of the robot in the pipeline, laser radar point cloud, pipeline environment data, pipeline vision data and motion data of the robot collected by different sensors carried by the robot are obtained.

[0045] Generally, various sensors such as laser radar, IMU (Inertial Measurement Unit), wheel speed meter, image acquisition device, environmental sensor (such as thermometer, hygrometer, pressure sensor) can be carried on the robot to collect data during the movement of the robot in the pipeline to obtain laser radar point cloud, pipeline vision data, pipeline vision data and motion data of the robot.

[0046] Optionally, the motion data of the robot includes inertial navigation measurement data collected by the IMU and wheel rotation data collected by the wheel speed meter. In addition to the IMU and the wheel speed meter, other sensors can also be mounted on the robot to collect motion data of the robot, such as an odometer for collecting displacement as motion data, which is not limited in particular.

[0047] Optionally, the image acquisition device includes a global shutter camera and / or an event camera for acquiring the pipeline visual data. The pipeline visual data collected by the global shutter camera is pipeline image data, and the pipeline visual data collected by the event camera is a pipeline event stream, which is a time series data set based on asynchronous visual sensing principles, triggered by pixel-level brightness changes to generate discrete event units. In addition to the global shutter camera and the event camera, other sensors such as a depth camera can also be mounted on the robot to collect pipeline visual data, which is not limited in particular.

[0048] Optionally, the robot is mounted with a laser radar, so that the laser radar can generate a laser radar point cloud according to the radar signal emitted and the echo signal received.

[0049] Optionally, the robot is mounted with a near-infrared illumination (NIR illumination) device to provide a light source for the image acquisition device to accurately collect the pipeline visual data.

[0050] S202, in the case of reaching the current map construction time, predicting the initial pose of the robot according to the motion data at the current map construction time.

[0051] Optionally, the robot is periodically mapped during movement in the pipeline, so the map construction period can be set in advance, and then every time interval corresponding to the above-mentioned map construction period is passed, i.e. a map construction time is reached, for example, the map construction period of the robot is 0.01 seconds, and a map construction time is reached every 0.01 seconds. The map construction period is the current map construction time.

[0052] Optionally, during movement of the robot in the pipeline, the map construction time is determined according to the running state of the robot, for example, in the case where the detected change in speed of the robot is greater than the speed change threshold, the current time is determined as the current map construction time, which can determine that the motion state of the robot changes dramatically at this time, such as turning of the robot in the pipeline; for example, in the case where the detected texture feature change rate of the pipeline image data is greater than the feature change rate threshold, the current time is determined as the current map construction time, which can determine that the robot moves to a new environment at this time.

[0053] Based on this, in the case of detecting that the current map construction moment is reached, the initial pose of the robot at the current map construction moment can be predicted according to the motion data of the current map construction moment in the data collected by the different sensors, to obtain the initial pose of the robot.

[0054] Optionally, a Kalman filter is used to determine the initial pose of the robot according to the motion data. For example, the initial pose of the robot at the previous map construction moment is predicted, and the control parameters at the previous map construction moment are determined; then, the motion data observation value of the robot at the current map construction moment is determined according to the actual pose of the robot at the previous map construction moment, and the prior pose is optimized according to the motion data of the robot at the current map construction moment and the motion data observation value, to obtain the initial pose of the robot at the current map construction moment.

[0055] Optionally, since the collection period of different sensors carried by the robot is different from the determination period (or determination method under non-periodic) of the map construction moment, at the current map construction moment, the data collected by the different sensors carried by the robot at the last time can be obtained as the collection data at the current map construction moment, and the plurality of collection data is time-synchronized to time-align the different sensors. Optionally, the time synchronization can be performed by the following formula:

[0056]

[0057] wherein, PCB (Printed Circuit Board) trace length, dielectric constant, digital-to-analog conversion delay (to ensure microsecond-level time synchronization accuracy), speed of light, time stamp of the original collection moment, time stamp of the collection moment after time synchronization.

[0058] In addition, considering that the coordinate systems used by sensors such as IMU, lidar, and image collection devices are different when collecting data, the coordinate systems of different sensors can be unified when predicting the initial pose, to realize the external parameter calibration of the robot. Optionally, by performing a spiral trajectory (i.e., completing specific parameter calibration through controllable spiral motion) in the calibration field, the external parameter set after the coordinate system is unified can be obtained, as shown in the following formula:

[0059]

[0060] wherein, denotes a set of extrinsic parameters, denotes a transformation from the image acquisition device coordinate system to the IMU coordinate system, is a transformation from the lidar sensor coordinate system to the IMU coordinate system, is a transformation from the wheel encoder coordinate system to the robot base coordinate system.

[0061] Optionally, the radius of the spiral trajectory gradually increases and covers a certain range in both horizontal and vertical directions to ensure full coverage of the sensor in space posture and position.

[0062] S203, determining the refractive index compensation factor of the pipeline according to the pipeline environment data at the current map construction time.

[0063] The so-called refractive index compensation factor (Refractive Index Compensation Factor, RICF) is a dimensionless correction coefficient introduced in the measurement scene based on the principles of optics / electromagnetics, to correct the measurement error caused by the deviation of the refractive index of the medium (such as gas, liquid, solid material) on the measurement path from the standard value.

[0064] Correspondingly, the refractive index compensation factor of the pipeline is a dimensionless dynamic correction coefficient introduced in the pipeline-related measurement scene based on the principles of optics / electromagnetics, to correct the deviation of the measurement result caused by the deviation of the refractive index of the pipeline material, the transmission / housing medium in the pipeline, and the environmental conditions from the standard value.

[0065] In an optional embodiment, the above-mentioned pipeline environment data includes temperature, humidity and pressure, and the above-mentioned S103 can include determining the refractive index compensation factor of the pipeline according to the temperature, humidity and pressure at the current map construction time. Optionally, the refractive index compensation factor of the pipeline can be determined by the following formula:

[0066]

[0067] wherein, is the refractive index compensation factor of the pipeline (abbreviated as ), is the temperature at the current map construction time, is the humidity at the current map construction time, is the pressure (such as atmospheric pressure) at the current map construction time, and is a preset coefficient.

[0068] S204, determining the initial map point cloud of the target period according to the initial pose, the refractive index compensation factor, and the lidar point cloud and pipeline visual data in the target period.

[0069] wherein the target period is a time period between the current map construction time and the previous map construction time.

[0070] The local map constructed at each map construction time is a map of the path passed by the robot in the time period between the previous map construction time and the current map construction time. During the movement of the robot, the laser radar performs laser scanning at preset laser scanning times to construct laser radar point clouds, and the image acquisition device also performs pipeline visual data acquisition at an acquisition frequency, so that at the current map construction time, the laser radar point clouds and the pipeline visual data in the target period between the current map construction time and the previous map construction time can be determined, and the initial map point cloud of the target period can be determined according to the initial pose, the refractive index compensation factor, and the laser radar point clouds and the pipeline visual data in the target period.

[0071] S205, correcting the initial map point cloud according to the preset curvature threshold and the refractive index compensation factor to obtain a target local map of the target period.

[0072] Considering that the laser radar point cloud is prone to distortion in the generation process due to the continuous movement of the robot, the initial map point cloud can be first corrected according to the preset curvature threshold and the refractive index compensation factor to obtain a corrected point cloud, and the corrected point cloud can be output in the form of a structured map to obtain the target local map of the target period.

[0073] S206, updating the initial global map at the previous map construction time according to the target local map to obtain a target global map at the current map construction time.

[0074] Since the local map constructed at each map construction time is a map of the path passed by the robot in the time period between the previous map construction time and the current map construction time, after obtaining the target local map of the target period, the initial global map (also referred to as the historical global map) at the previous map construction time is updated according to the target local map to obtain the target global map at the current map construction time.

[0075] Optionally, the pipeline structure features (such as bending radius, flange, valve structure, and support rhythm) of the target local map are extracted, and from the initial global map at the previous map construction time, a specified local map having a pipeline structure feature matching the pipeline structure feature of the target local map is screened out, and the specified local map is replaced by the target local map to obtain the target global map at the current map construction time.

[0076] Optionally, the target local map and the initial global map at the previous map construction time are time-series spliced to obtain the target global map at the current map construction time.

[0077] In the above map construction method, a plurality of different sensors are mounted on the robot to obtain various types of data collected by the different sensors, such as lidar data, pipeline environment data, pipeline visual data, and robot motion data, during movement of the robot in the pipeline; thus, at each current map construction time, the initial pose of the robot is predicted according to the motion data at the current map construction time, and the refractive index compensation factor of the pipeline is determined according to the pipeline environment data at the current map construction time; then, taking the time period between the current map construction time and the last map construction time as a target time period, the initial map point cloud of the target time period is determined according to the initial pose, the refractive index compensation factor, and the lidar point cloud and the pipeline visual data in the target time period, and the initial map point cloud is corrected according to the preset curvature threshold and the refractive index compensation factor to obtain the target local map of the target time period. Then, the initial global map at the last map construction time is updated according to the target local map to obtain the target global map at the current map construction time, and thus the current map construction at the current map construction time is completed. In this way, on the one hand, the fusion of the multi-source data collected by the different sensors mounted on the robot can realize high-precision map construction in a complex pipeline environment and improve the accuracy of the constructed local map; on the other hand, the updating of the historical global map by the local map at each map construction time can reduce the positioning drift of the global map and improve the accuracy of the pipeline global map, thereby improving the detection accuracy of pipeline detection based on the constructed map.

[0078] On the basis of each of the above embodiments, in an exemplary embodiment, the prediction of the initial pose in S202 is further refined. Optionally, the motion data includes inertial navigation measurement data and wheel rotation data, and as shown in Figure 3 may include the following steps:

[0079] S301, determining the initial motion parameters of the robot according to the wheel rotation data at the current map construction time, and correcting the initial motion parameters by a preset slip coefficient to obtain calibrated target motion parameters.

[0080] In the embodiment, the robot is equipped with an IMU and a wheel speed meter, and the inertial navigation measurement data collected by the IMU and the wheel rotation data collected by the wheel speed meter are motion data of the robot. The wheel rotation data includes wheel speed and wheel steering angle, so that the initial motion parameters of the robot at the current map construction time can be determined according to the wheel rotation data. Optionally, the initial motion parameters include an initial linear speed. Furthermore, considering the drift of the wheel rotation data caused by wheel slip due to wet and slippery pipeline, in order to ensure the accuracy of the finally created map, a preset slip coefficient can be used to correct the initial motion parameters to obtain calibrated target motion parameters. Optionally, the preset slip coefficient is determined based on a preset slip ratio, wherein the preset slip ratio is, for example, as shown in the following formula:

[0081]

[0082] wherein, is the preset slip ratio, is the linear speed determined based on the wheel rotation data, is the actual linear speed. Optionally, the actual linear speed can be determined in various ways, such as collecting linear speed by using a high-precision speed sensor such as a laser Doppler velocimeter, collecting linear speed by using an IMU and a GPS (Global Positioning System), and the like, without specific limitation.

[0083] Optionally, the calibrated target motion parameters are as shown in the following formula:

[0084] ,

[0085] wherein, is the linear speed in the calibrated target motion parameters, is the angular speed in the calibrated target motion parameters, is the angular speed of the left wheel of the robot in the initial motion parameters, is the angular speed of the right wheel of the robot in the initial motion parameters, is the wheelbase of the left and right wheels of the robot, is a preset slip coefficient (such as 1 / (1+ )) determined based on the preset slip ratio.

[0086] S302, with the inertial navigation measurement data as the prediction value and the target motion parameters as the observation value, the pose of the robot is predicted to obtain the initial pose of the robot.

[0087] Since the inertial navigation measurement data includes three-axis angular velocity and three-axis linear acceleration of the robot, the robot can be pose and motion data predicted according to the inertial navigation measurement data to obtain predicted pose and predicted motion data; and then the predicted motion data is compared with the target motion parameters determined above, so as to correct the predicted pose by the residual data obtained by comparison, so as to obtain the initial pose of the robot.

[0088] Optionally, the initial pose is determined by a Kalman filter. Wherein, in the case of predicting the predicted pose and the predicted motion data, the noise covariance matrix (process noise covariance matrix and measurement noise covariance matrix) of the Kalman filter is updated; and then the predicted pose is corrected according to the residual data and the updated noise covariance matrix, so as to obtain the initial pose of the robot. Wherein, the initial pose is as follows:

[0089]

[0090] Wherein, is the initial pose, is the inertial navigation measurement data, is the target motion parameter, is the function of EKF (Extended Kalman Filter, Extended Kalman Filter) state transition and observation update.

[0091] Optionally, the process noise covariance matrix is determined by experiment statistics, and the measurement noise covariance matrix is set by the calibration data and the measured error distribution provided by the sensor manufacturer when the sensor is manufactured.

[0092] On the basis of the above embodiments, in an exemplary embodiment, the determination of the initial map point cloud in S204 is further refined. Optionally, the motion data includes inertial navigation measurement data, which can include the following steps as shown in Figure 4 .

[0093] S401, generating the current trajectory sequence of the robot in the target period according to the initial pose and the pipeline visual data in the target period.

[0094] Optionally, the pipeline visual data includes pipeline image data and pipeline event stream, and appropriate pipeline visual data can be selected according to the illumination condition in the pipeline to generate the current trajectory sequence. In the case that the illumination in the pipeline is sufficient (for example, the ambient brightness collected by the brightness sensor carried by the robot is greater than a brightness threshold), sparse feature points (for example, ORB (Oriented FAST and Rotated BRIEF, Oriented FAST and Rotated BRIEF) features) of the pipeline image data are used to generate the current trajectory sequence of the robot in the target period; correspondingly, in the case that the illumination in the pipeline is insufficient (for example, the ambient brightness collected by the brightness sensor carried by the robot is not greater than the brightness threshold), the event camera carried by the robot is triggered to increase the timing resolution feature through the pipeline event stream to generate the current trajectory sequence of the robot in the target period, so as to improve the robustness.

[0095] S402, determining the pose set of the robot in the target period according to the current trajectory sequence and the pre-integration result of the inertial navigation measurement data in the target period.

[0096] The pre-integration result represents the relative motion increment of the inertial navigation measurement data from the last map construction time to the current map construction time, and the relative motion increment includes a rotation pre-integration component (i.e., rotation increment, representing the relative attitude change), a velocity pre-integration component (i.e., velocity increment, representing the relative velocity change), and a displacement pre-integration component (i.e., position change increment, representing the relative displacement), wherein, is the last map construction time, is the current map construction time. Then, the pose set of the robot in the target period can be obtained by solving the optimization target with the above pre-integration result as the constraint condition.

[0097] Optionally, the optimization target is as follows:

[0098]

[0099] wherein, is the visual residual of the pipeline visual data in the target period, is the IMU residual of the inertial navigation measurement data in the target period, is the geometric residual based on the diameter constraint of the pipeline.

[0100] Thus, the above optimization objective integrates visual residuals, IMU residuals, and geometric residuals based on pipe diameter constraints. Furthermore, the weight coefficients of the above three types of residuals are calibrated experimentally and adaptively adjusted in combination with online residual statistics to maintain balance in different scenarios.

[0101] S403 uses pose set to perform distortion compensation on the lidar point cloud within the target time period to obtain the compensated point cloud, and then performs intensity correction on the compensated point cloud according to the refractive index compensation factor to obtain the corrected point cloud.

[0102] By using edge interpolation compensation technology, the LiDAR pose at each laser scanning moment of the LiDAR within the target time period is calculated based on each pose in the above pose set. Then, the distortion compensation of the LiDAR point cloud within the target time period is performed based on the above LiDAR pose to correct the LiDAR point cloud and obtain the compensated point cloud.

[0103] Optionally, distortion compensation can be performed on the lidar point cloud within the target time period using the following formula to obtain a spatiotemporally consistent compensated point cloud:

[0104]

[0105] in, To compensate for the laser scanning time in the point cloud The corresponding point cloud coordinates, Laser scanning time The pose of the lidar. The laser scanning time in the lidar point cloud within the target time period. The corresponding point cloud coordinates.

[0106] Furthermore, based on the aforementioned refractive index compensation factor and considering the aerosol scattering effect, the intensity values ​​of the compensated point cloud can be adaptively corrected to obtain the corrected point cloud. Optionally, the intensity values ​​of the compensated point cloud can be adaptively corrected using the following formula:

[0107]

[0108] in, To correct the intensity values ​​of the point cloud, To compensate for the intensity value of the point cloud, This is the straight-line distance from the laser radar's emission point to the target surface reached by the radar. This is the empirical scattering coefficient. The corrected intensity value better reflects actual physical properties and helps distinguish between pipe wall material and surface defects.

[0109] S404: Based on the radar echo data of each point in the corrected point cloud, the corrected point cloud is filtered to obtain the initial map point cloud for the target time period.

[0110] According to the characteristics of the laser radar, each point in the above-mentioned corrected point cloud can have multiple radar echo data, and then the radar echo data of each point in the corrected point cloud can be filtered to obtain a filtered initial map point cloud.

[0111] Optionally, the corrected point cloud can be filtered by the following confidence weighting selection formula:

[0112]

[0113] wherein, the filtering result of the i-th point in the corrected point cloud, the i-th point, the intensity weight of the j-th echo data of the i-th point, the j-th echo data of the i-th point, the j-th echo data of the i-th point, the j-th echo data of the i-th point, the j-th echo data of the i-th point, the j-th echo data of the i-th point, the decay coefficient.

[0114] In the embodiment, not only the original point cloud of the laser radar point cloud of the target period is adaptively corrected according to the environment, but also the multi-echo return characteristics of each point in the laser radar point cloud are utilized to weight and select different echo signals of the same point to ensure the balanced preservation of high reflection and weak reflection points. In the filtering link, a selection mechanism based on a weight threshold is introduced to effectively eliminate pseudo points caused by metal walls or foreign object reflection, while key points contributing to the geometric structure are preserved.

[0115] On the basis of the above-mentioned embodiments, in an exemplary embodiment, the determination of the target local map in S205 is further refined. Optionally, as shown in Figure 5 the method can include the following steps:

[0116] S501, according to a preset curvature threshold, dividing the initial map point cloud into a first point cloud region and a second point cloud region.

[0117] Wherein, the curvature of the first point cloud region is less than the preset curvature threshold, and the curvature of the second point cloud region is not less than the preset curvature threshold.

[0118] The curvature of each region in the initial map point cloud is determined, so that the region with a curvature less than the preset curvature threshold is divided into the first point cloud region, and the region with a curvature not less than the preset curvature threshold is divided into the second point cloud region.

[0119] Optionally, the preset curvature threshold is 0.005 Optionally, a two-grid map is constructed for the first point cloud region, and a three-dimensional sparse voxel hash SDF (Signed Distance Function) is used for modeling the second point cloud region. The curvature threshold is determined based on experimental statistics, and a suitable curvature threshold can effectively distinguish between smooth wall regions and complex structure regions in the pipeline. The two-dimensional map is constructed for the first point cloud region, which has lower computational overhead and is suitable for long-distance inspection real-time operation. The three-dimensional map is constructed for the second point cloud region, which can significantly enhance the expression ability of small structures and defects, thereby achieving a balance between efficiency and accuracy of map construction.

[0120] S502, interpolating and fusing the intersection region between the first point cloud region and the second point cloud region to obtain an initial local map.

[0121] The boundaries of the first point cloud region and the second point cloud region are determined to determine the intersection region between the first point cloud region and the second point cloud region, so that the initial local map with smooth transition is obtained by interpolating and fusing the intersection region. Optionally, different map construction methods are used to construct maps for the first point cloud region and the second point cloud region, and the intersection region of the obtained different maps is interpolated and fused to obtain the initial local map, and the smooth transition between the different maps corresponding to the first point cloud region and the second point cloud region in the initial local map is ensured to avoid geometric jumps in the obtained initial local map.

[0122] Optionally, the intersection region is within a region with a predetermined width (such as 2 meters) of the intersection center of the first point cloud region and the second point cloud region. Further, the intersection region between the first point cloud region and the second point cloud region is interpolated and fused by the following formula:

[0123]

[0124] wherein, is the map of the interpolated and fused intersection region, is the map of the intersection region obtained by constructing a map for the first point cloud region, is the map of the intersection region obtained by constructing a map for the second point cloud region, is a predetermined weight coefficient.

[0125] S503, intensity correction of the initial local map according to the refractive index compensation factor to obtain a target local map of a target period.

[0126] Optionally, the initial map point cloud is intensity corrected according to the refractive index compensation factor to obtain a correction result, and then the initial local map is intensity corrected using the correction result to obtain a local map point cloud of a target period.

[0127] Optionally, the above target local map is divided into multiple sub-tiles, and saved through compression and breakpoint resume mechanism to support offline running and indirect return of map construction, so as to ensure that the robot can still solidify and safely store the mapping results in a long-distance underground pipeline environment without a continuous communication link.

[0128] On the basis of the above embodiments, in an exemplary embodiment, the updating of the initial global map in S106 is further refined. Optionally, as shown in Figure 6 may include the following steps:

[0129] S601, according to the current trajectory sequence and the target local map, and the motion data corresponding to each trajectory point in the current trajectory sequence, an optimized local map at the current map construction time is constructed.

[0130] For each trajectory point in the current trajectory sequence, the map position corresponding to the trajectory point in the above target local map is determined, and the motion data and pipeline visual data corresponding to the trajectory point are determined from the above acquired motion data and pipeline visual data; then for any two adjacent trajectory points in the current trajectory sequence, the difference between the map positions of the two trajectory points is determined, as well as the difference between the motion data and pipeline visual data corresponding to the two adjacent trajectory points, and the residual between the above two differences is determined, so as to select the trajectory point with the smallest residual from the above current trajectory sequence, and to construct the optimized local map at the current map construction time through the selected trajectory points.

[0131] Optionally, according to the above current trajectory sequence and target local map, and the motion data and pipeline visual data within the target period, a factor graph optimization model is constructed, and the optimized local map at the current map construction time is obtained by solving the following optimization objective:

[0132]

[0133] wherein, is the motion residual of the wheel rotation data within the target period, is the visual residual of the pipeline visual data within the target period, is the IMU residual of the inertial measurement unit (IMU) measurement data within the target period, is the geometric residual based on the diameter constraint of the pipeline.

[0134] S602, in the initial global map at the last map construction time, a specified local map whose pipeline structure features match the pipeline structure features of the optimized local map is screened.

[0135] The pipeline structure features (such as bend radius, flange, valve structure, support rhythm, etc.) of the above-mentioned optimized local map are extracted, and the specified local map whose pipeline structure features match the pipeline structure features of the optimized local map is screened from the initial global map at the last map construction moment. Optionally, the specified local map whose pipeline structure features have a similarity greater than a similarity threshold value with the pipeline structure features of the optimized local map is screened.

[0136] S603, determining an overlap rate of the historical trajectory sequence corresponding to the specified local map and the current trajectory sequence.

[0137] Generally, when the robot passes through the same section of the pipeline multiple times, the multiple movement trajectory sequences formed should have a high overlap rate. Therefore, when the specified local map is obtained, the historical trajectory sequence corresponding to the specified local map can be determined from the historical trajectory sequence of the robot, and the overlap rate of the historical trajectory sequence and the current trajectory sequence can be determined.

[0138] Optionally, the above steps S602-S603 can be realized by loop detection, that is, the structure features of the pipeline are extracted, and loop detection is performed in combination with a 3D (Three-Dimensional) scene-based BoW (Bag of Words) global appearance description. The similarity function is as follows:

[0139]

[0140] wherein, is the similarity, when S exceeds a threshold value and the priori residual / posteriori residual ratio , it is confirmed that a loop is detected, and a loop factor (i.e., the specified local map is the loop factor, used to correct the initial global map), and is the fusion weight, is a residual discrimination threshold value, used to avoid false loops; is the priori residual, is the posteriori residual. The priori residual refers to the residual between the target local point cloud and the specified local point cloud, and the posteriori residual refers to the residual between the optimized local map and the specified local point cloud.

[0141] S604, in the case where the overlap rate is greater than a preset overlap rate threshold value, the specified local map is corrected according to the target local map, and the initial global map is corrected according to the corrected specified local map, to obtain a target global map at the current map construction moment.

[0142] As described above, in the case that the determined overlap rate is greater than the preset overlap rate threshold, it can be considered that the drift of the constructed target local map is small, so that the specified local map can be directly corrected according to the target local map, and the initial global map can be corrected according to the corrected specified local map to obtain a target global map at the current map construction moment, so as to realize low-drift SLAM in a long-distance pipeline environment. Optionally, the specified local map and the initial global map are corrected in a sliding window manner, wherein the correction frequency of the specified local map is higher than that of the initial global map.

[0143] On the basis of the above embodiments, in an exemplary embodiment, as shown in Figure 7 The map construction method can include the following steps:

[0144] S701, during movement of the robot in the pipeline, laser radar point clouds collected by different sensors carried by the robot, pipeline environment data, pipeline visual data and motion data of the robot are acquired.

[0145] S702, according to wheel rotation data at the current map construction moment, initial motion parameters of the robot are determined, and the initial motion parameters are corrected by using a preset slip coefficient to obtain target motion parameters after correction; wherein the motion data includes inertial navigation measurement data and wheel rotation data.

[0146] S703, the robot is pose predicted by taking the inertial navigation measurement data as a prediction value and the target motion parameters as an observation value to obtain an initial pose of the robot, and a refractive index compensation factor of the pipeline is determined according to temperature, humidity and pressure at the current map construction moment; wherein the pipeline environment data includes temperature, humidity and pressure.

[0147] S704, a current trajectory sequence of the robot in a target period is generated according to the initial pose and the pipeline visual data in the target period, and a pose set of the robot in the target period is determined according to the current trajectory sequence and a pre-integration result of the inertial navigation measurement data in the target period.

[0148] S705, the pose set is used to perform distortion compensation on the laser radar point clouds in the target period to obtain compensated point clouds, and the compensated point clouds are intensity corrected according to the refractive index compensation factor to obtain corrected point clouds.

[0149] S706, the corrected point clouds are filtered according to radar echo data of each point in the corrected point clouds to obtain initial map point clouds of the target period, and the initial map point clouds are divided into a first point cloud region and a second point cloud region according to a preset curvature threshold; wherein the curvature of the first point cloud region is less than the preset curvature threshold, and the curvature of the second point cloud region is not less than the preset curvature threshold.

[0150] S707, interpolation and fusion are performed on the boundary area between the first point cloud region and the second point cloud region to obtain an initial local map, and intensity correction is performed on the initial local map according to the refractive index compensation factor to obtain the target local map for the target time period.

[0151] S708: Based on the current trajectory sequence, the target local map, and the motion data corresponding to each trajectory point in the current trajectory sequence, construct an optimized local map at the current map construction time.

[0152] S709, In ​​the initial global map at the previous map construction time, select a specified local map whose pipeline structure features match the pipeline structure features of the optimized local map, and determine the overlap rate between the historical trajectory sequence and the current trajectory sequence corresponding to the specified local map.

[0153] S710: If the overlap rate is greater than the preset overlap rate threshold, the specified local map is corrected according to the target local map, and the initial global map is corrected according to the corrected specified local map to obtain the target global map at the current map construction time.

[0154] The specific implementation methods of S701-S710 are the same as those in the above method embodiments, and will not be repeated here.

[0155] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0156] Based on the same inventive concept, this application also provides a map building apparatus for implementing the map building method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more map building apparatus embodiments provided below can be found in the limitations of the map building method described above, and will not be repeated here.

[0157] In one exemplary embodiment, such as Figure 8 As shown, a map building apparatus is provided, including: a data acquisition module 810, a pose prediction module 820, a compensation factor determination module 830, a point cloud determination module 840, a map building module 850, and a map update module 860, wherein:

[0158] The data acquisition module 810 is used to acquire lidar point cloud, pipeline environment data, pipeline visual data and robot motion data collected by different sensors on the robot during the robot's movement in the pipeline.

[0159] The pose prediction module 820 is used to predict the robot's initial pose based on the motion data at the current map building time.

[0160] The compensation factor determination module 830 is used to determine the refractive index compensation factor of the pipeline based on the pipeline environment data at the current map construction time.

[0161] The point cloud determination module 840 is used to determine the initial map point cloud for the target time period based on the initial pose, refractive index compensation factor, and LiDAR point cloud and pipeline visual data within the target time period; wherein, the target time period is the time period between the current map building time and the previous map building time.

[0162] The map building module 850 is used to correct the initial map point cloud according to the preset curvature threshold and refractive index compensation factor to obtain the target local map for the target time period.

[0163] The map update module 860 is used to update the initial global map at the time of the previous map construction based on the target local map, so as to obtain the target global map at the time of the current map construction.

[0164] In an exemplary embodiment, the motion data includes inertial navigation measurement data and wheel rotation data; the pose prediction module 820 is specifically used to: determine the robot's initial motion parameters based on the wheel rotation data at the current map construction time, and correct the initial motion parameters using a preset slip coefficient to obtain the calibrated target motion parameters; and predict the robot's pose using the inertial navigation measurement data as the predicted value and the target motion parameters as the observed value to obtain the robot's initial pose.

[0165] In an exemplary embodiment, the pipeline environmental data includes temperature, humidity, and pressure; the compensation factor determination module 830 is specifically used to determine the refractive index compensation factor of the pipeline based on the temperature, humidity, and pressure at the current map construction time.

[0166] In an example embodiment, the point cloud determination module 840 is specifically configured to: generate a current trajectory sequence of the robot in the target period according to the initial pose and the pipeline visual data in the target period; determine a pose set of the robot in the target period according to the current trajectory sequence and a pre-integration result of the inertial navigation measurement data in the target period; perform distortion compensation on the laser radar point cloud in the target period by using the pose set to obtain a compensated point cloud, and perform intensity correction on the compensated point cloud according to the refraction index compensation factor to obtain a corrected point cloud; and perform filtering processing on the corrected point cloud according to the radar echo data of each point in the corrected point cloud to obtain the initial map point cloud of the target period.

[0167] In an example embodiment, the map construction module 850 is specifically configured to: divide the initial map point cloud into a first point cloud region and a second point cloud region according to a preset curvature threshold; wherein the curvature of the first point cloud region is less than the preset curvature threshold, and the curvature of the second point cloud region is not less than the preset curvature threshold; perform interpolation fusion on an interface region between the first point cloud region and the second point cloud region to obtain an initial local map; and perform intensity correction on the initial local map according to the refraction index compensation factor to obtain the target local map of the target period.

[0168] In an example embodiment, the map updating module 860 is specifically configured to: construct an optimized local map at a current map construction time according to the current trajectory sequence and the target local map, and motion data corresponding to each trajectory point in the current trajectory sequence; filter a specified local map in which the pipeline structure features match the pipeline structure features of the optimized local map from an initial global map at a previous map construction time; determine an overlap rate of a historical trajectory sequence corresponding to the specified local map and the current trajectory sequence; and in a case where the overlap rate is greater than a preset overlap rate threshold, correct the specified local map according to the target local map, and correct the initial global map according to the corrected specified local map to obtain a target global map at the current map construction time.

[0169] The above modules in the map construction device can be all or partially implemented by software, hardware and combinations thereof. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above modules.

[0170] In an example embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store various data collected by different sensors carried by the robot, local maps constructed at each map construction moment, global maps and the like. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a map construction method.

[0171] In an exemplary embodiment, a computer device is provided, which can be a robot, and the internal structure diagram thereof can be as shown in the figure. Figure 10 As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be realized through WIFI, mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. The computer program is executed by the processor to implement a map construction method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0172] Those skilled in the art can understand that, Figure 9 and Figure 10The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in each method embodiment of the above map construction method when executing the computer program.

[0174] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in each method embodiment of the above map construction method when executed by a processor.

[0175] In an embodiment, a computer program product is provided, comprising a computer program, and the computer program implementing the steps in each method embodiment of the above map construction method when executed by a processor.

[0176] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0177] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0178] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A map construction method characterized by comprising: The method comprises: During movement of the robot in the pipeline, laser radar point clouds collected by different sensors carried by the robot, pipeline environment data, pipeline visual data and motion data of the robot are acquired; In the case of reaching a current map construction time, an initial pose of the robot is predicted according to motion data of the current map construction time, and a refractive index compensation factor of the pipeline is determined according to pipeline environment data of the current map construction time; According to the initial pose, the refractive index compensation factor and laser radar point clouds and pipeline visual data in a target period, an initial map point cloud of the target period is determined; wherein the target period is a time period between the current map construction time and a previous map construction time; According to a preset curvature threshold and the refractive index compensation factor, the initial map point cloud is corrected to obtain a target local map of the target period; According to the target local map, an initial global map of the previous map construction time is updated to obtain a target global map of the current map construction time.

2. The method of claim 1, wherein, The motion data comprises inertial navigation measurement data and wheel rotation data; and the initial pose of the robot is predicted according to the motion data of the current map construction time, which comprises: According to wheel rotation data of the current map construction time, initial motion parameters of the robot are determined, and the initial motion parameters are corrected by using a preset slip coefficient to obtain calibrated target motion parameters; The robot is pose-predicted by taking the inertial navigation measurement data as a prediction value and the target motion parameters as an observation value to obtain the initial pose of the robot.

3. The method of claim 1, wherein, The pipeline environment data comprises temperature, humidity and pressure; and the refractive index compensation factor of the pipeline is determined according to the pipeline environment data of the current map construction time, which comprises: The refractive index compensation factor of the pipeline is determined according to temperature, humidity and pressure of the current map construction time.

4. The method of claim 1, wherein, The motion data comprises inertial navigation measurement data; and the initial map point cloud of the target period is determined according to the initial pose, the refractive index compensation factor and laser radar point clouds and pipeline visual data in the target period, which comprises: According to the initial pose and pipeline visual data in the target period, a current trajectory sequence of the robot in the target period is generated; According to the current trajectory sequence and a pre-integration result of the inertial navigation measurement data in the target period, a pose set of the robot in the target period is determined; The laser radar point clouds in the target period are subjected to distortion compensation by using the pose set to obtain compensated point clouds, and the compensated point clouds are subjected to intensity correction according to the refractive index compensation factor to obtain corrected point clouds; The corrected point clouds are subjected to filtering processing according to radar echo data of each point in the corrected point clouds to obtain the initial map point cloud of the target period.

5. The method of claim 4, wherein, The initial map point cloud is corrected according to the preset curvature threshold and the refractive index compensation factor to obtain the target local map of the target period, which comprises: The initial map point cloud is divided into a first point cloud region and a second point cloud region according to a preset curvature threshold; wherein the curvature of the first point cloud region is less than the preset curvature threshold, and the curvature of the second point cloud region is not less than greater than the preset curvature threshold; The initial local map is obtained by interpolating and fusing a boundary region between the first point cloud region and the second point cloud region; The initial local map is intensity corrected according to the refractive index compensation factor to obtain the target local map of the target time period.

6. The method of claim 5, wherein, The initial global map at the previous map construction moment is updated according to the target local map to obtain the target global map at the current map construction moment. The optimization local map at the current map construction moment is constructed according to the current trajectory sequence, the target local map, and the motion data corresponding to each trajectory point in the current trajectory sequence; In the initial global map at the previous map construction moment, a specified local map is screened out, which has a pipe structure feature matching the pipe structure feature of the optimization local map; The overlap rate of the historical trajectory sequence corresponding to the specified local map and the current trajectory sequence is determined; In the case where the overlap rate is greater than a preset overlap rate threshold, the specified local map is corrected according to the target local map, and the initial global map is corrected according to the corrected specified local map to obtain the target global map at the current map construction moment.

7. A map construction apparatus characterized by comprising: The device comprises: A data acquisition module is configured to acquire laser radar point cloud, pipe environment data, pipe visual data and motion data of the robot carried by different sensors of the robot during movement of the robot in the pipe; A pose prediction module is configured to predict an initial pose of the robot according to the motion data at the current map construction moment when the current map construction moment is reached; A compensation factor determination module is configured to determine a refractive index compensation factor of the pipe according to the pipe environment data at the current map construction moment; A point cloud determination module is configured to determine an initial map point cloud of a target time period according to the initial pose, the refractive index compensation factor, and the laser radar point cloud and pipe visual data in the target time period; wherein the target time period is a time period between the current map construction moment and the previous map construction moment; A map construction module is configured to correct the initial map point cloud according to a preset curvature threshold and the refractive index compensation factor to obtain a target local map of the target time period; A map update module is configured to update the initial global map at the previous map construction moment according to the target local map to obtain a target global map at the current map construction moment. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images