A mapping method, device, storage medium and electronic device
Through matching and optimization algorithms, the misalignment problem in high-precision map construction under GPS signal interference is solved, and high-precision map splicing is achieved.
Patent Information
- Application Number
- CN202110009125.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-01-05
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2041-01-05
AI Technical Summary
The existing high-precision map mapping method relies on GPS signals, and the GPS signals are easily affected under strong electromagnetic interference, resulting in point cloud data misalignment.
By obtaining the point cloud data of each frame collected by the target device, matching adjacent frame data to determine the positioning pose transformation, and redetermining the positioning pose transformation according to the GPS signal state, avoiding misalignment caused by GPS signal abnormality.
It effectively avoids the misalignment of point cloud data under abnormal GPS signal state, and ensures the accuracy of splicing of high-precision maps.
Smart Images

Figure CN112712561B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a mapping method, device, storage medium and electronic device. Background Art
[0002] Nowadays, high-precision maps are widely used in various scenarios, and there are various methods for building high-precision maps according to different application scenarios.
[0003] In the prior art, high-precision maps use sensors such as the Global Positioning System (GPS), laser radar, and cameras on map collection vehicles to obtain the data required to build high-precision maps. When the map collection vehicle is driving in the area to be mapped, the GPS on the map collection vehicle obtains the position data of the map collection vehicle in real time, and the laser radar obtains the scanned point cloud data. Then, according to the different position data, the scanned point cloud data are spliced together to obtain a point cloud map. Finally, the relevant information in the point cloud map, such as lane lines and buildings, is annotated to obtain a high-precision map.
[0004] It can be seen that in the prior art, when building high-precision maps, it is necessary to rely on the position data of the map collection vehicle determined by the GPS signal. When the GPS signal is severely interfered by the outside world, for example, when there is strong electromagnetic interference, the position data obtained by GPS is not accurate, resulting in misalignment of the spliced point cloud data. Summary of the invention
[0005] The embodiments of this specification provide a mapping method, device, storage medium and electronic device to partially solve the problems existing in the above-mentioned prior art.
[0006] The embodiments of this specification adopt the following technical solutions:
[0007] This specification provides a mapping method, including:
[0008] Obtain each frame of point cloud data collected by the target device;
[0009] Matching each two adjacent frames of point cloud data, and determining the position transformation of the target device when collecting each two adjacent frames of point cloud data according to the matching results; and, for any two frames of point cloud data in each frame of point cloud data, determining the state of the GPS signal of the target device when collecting the two frames of point cloud data according to the two frames of point cloud data, wherein the state includes: normal state and abnormal state;
[0010] According to the posture data corresponding to the point cloud data in the normal state of the GPS signal, the point cloud data in the normal state of the GPS signal are spliced to obtain a local point cloud map;
[0011] Matching the point cloud data of the GPS signal abnormal state with the local point cloud map to determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map;
[0012] Taking the posture transformation and the matching relationship as constraints, a specified optimization algorithm is used to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data;
[0013] According to the re-determined posture transformation of the target device when collecting every two adjacent frames of point cloud data, each frame of point cloud data is re-joined to obtain a high-precision map.
[0014] Optionally, determining, according to the two frames of point cloud data, a state of a GPS signal of the target device when collecting the two frames of point cloud data specifically includes:
[0015] The two frames of point cloud data are matched, and a position change when the target device collects the two frames of point cloud data is obtained according to the matching result as the first position change;
[0016] According to the GPS signal when the target device collects the two frames of point cloud data, a posture change when the target device collects the two frames of point cloud data is obtained as a second posture change;
[0017] According to the difference between the first posture change and the second posture change, a state of a GPS signal of the target device when collecting the two frames of point cloud data is determined.
[0018] Optionally, determining, according to the two frames of point cloud data, a state of a GPS signal of the target device when collecting the two frames of point cloud data specifically includes:
[0019] Determine the position and posture data of the target device when collecting the two frames of point cloud data according to the GPS signal of the target device when collecting the two frames of point cloud data;
[0020] splicing the two frames of point cloud data according to the pose data when the target device collects the two frames of point cloud data;
[0021] According to the two frames of point cloud data that have been stitched together, points in one of the two frames of point cloud data are matched with points in the other frame of point cloud data;
[0022] According to the matched point pairs, the state of the GPS signal of the target device when collecting the two frames of point cloud data is determined.
[0023] Optionally, before determining the state of the GPS signal of the target device when collecting the two frames of point cloud data, the method further includes:
[0024] For each frame of point cloud data collected by the target device, detecting the GPS signal when the target device collects the frame of point cloud data;
[0025] If it is detected that the GPS signal when the target device collects the frame of point cloud data is normal, determining that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated normal state;
[0026] If it is detected that the GPS signal when the target device collects the frame of point cloud data is abnormal, it is determined that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated abnormal state.
[0027] Optionally, determining the state of the GPS signal of the target device when collecting the two frames of point cloud data according to the difference between the first posture change and the second posture change specifically includes:
[0028] When there is one frame of point cloud data in which the GPS signal is estimated to be in a normal state in the two frames of point cloud data, calculating a difference between the first position change and the second position change;
[0029] If the difference is greater than a preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of point cloud data of the two frames of point cloud data is abnormal;
[0030] If the difference is smaller than a preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of point cloud data in the two frames of point cloud data is normal.
[0031] Optionally, determining the state of the GPS signal of the target device when collecting the two frames of point cloud data according to the matched point pairs specifically includes:
[0032] When one frame of point cloud data in which the GPS signal is estimated to be in a normal state exists in the two frames of point cloud data, the distance between each point pair is calculated based on each point pair obtained by matching;
[0033] If the distance is greater than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of point cloud data in the two frames of point cloud data is abnormal;
[0034] If the distance is less than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of point cloud data in the two frames of point cloud data is normal.
[0035] Optionally, a specified optimization algorithm is used to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data, specifically including:
[0036] A graph optimization algorithm is used to re-determine the position and posture transformation of the target device when collecting every two adjacent frames of point cloud data.
[0037] This specification provides a mapping device, including:
[0038] An acquisition module is used to acquire each frame of point cloud data collected by the target device;
[0039] A posture transformation module is used to match every two adjacent frames of point cloud data, and determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data according to the matching result;
[0040] A first determination module is used to determine, for any two frames of point cloud data in each frame of point cloud data, the state of the GPS signal of the target device when the two frames of point cloud data are collected according to the two frames of point cloud data, wherein the state includes: a normal state and an abnormal state;
[0041] A splicing module, for splicing the point cloud data in a normal state of the GPS signal according to the posture data corresponding to the point cloud data in a normal state of the GPS signal, to obtain a local point cloud map;
[0042] A matching relationship determination module is used to match the point cloud data of the GPS signal abnormal state with the local point cloud map, and determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map;
[0043] A second determination module is used to use the posture transformation and the matching relationship as constraints and adopt a specified optimization algorithm to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data;
[0044] The mapping module is used to re-join the point cloud data of each frame according to the re-determined posture transformation of the target device when collecting every two adjacent frames of point cloud data to obtain a high-precision map.
[0045] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned mapping method is implemented.
[0046] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned mapping method when executing the program.
[0047] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:
[0048] The embodiments of this specification determine the posture transformation between each two adjacent frames of point cloud data and the state of the GPS signal when the target device collects each frame of point cloud data based on each frame of point cloud data collected by the target device, wherein the state includes: normal state and abnormal state. The local point cloud map obtained by splicing the point cloud data of the normal state of the GPS signal is matched with the point cloud data of the abnormal state of the GPS signal to obtain the matching relationship between the local point cloud map and the point cloud data of the abnormal state of the GPS signal. With the posture transformation and the matching relationship as constraints, the posture transformation between each two adjacent frames of point cloud data is re-determined, which can avoid the adverse effects of the point cloud data of the abnormal state of the GPS signal on the posture transformation between each two adjacent frames of point cloud data. By re-determining the posture transformation, the misalignment phenomenon can be avoided by re-splicing each frame of point cloud data. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:
[0050] Figure 1 A schematic diagram of the map construction process provided in the embodiments of this specification;
[0051] Figure 2 A schematic diagram of the pose transformation between two adjacent frames of point cloud data provided in the embodiments of this specification;
[0052] Figure 3a-3b A schematic diagram of splicing two frames of point cloud data provided in an embodiment of this specification;
[0053] Figure 4 A schematic diagram of a posture graph provided in an embodiment of this specification;
[0054] Figure 5 A schematic diagram of the structure of a mapping device provided in an embodiment of this specification;
[0055] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION
[0056] The mapping method provided in this specification aims to optimize the pose transformation between every two adjacent frames of point cloud data based on the pose transformation between each two adjacent frames of point cloud data and the matching relationship between the point cloud data in the abnormal GPS signal state and the local point cloud map constructed only by the point cloud data in the normal GPS signal state, and re-splice the point cloud data of each frame according to the optimized pose transformation to obtain a high-precision map.
[0057] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.
[0058] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.
[0059] Figure 1 The diagram of the map construction process provided in the embodiments of this specification includes:
[0060] S100: Acquire each frame of point cloud data collected by the target device.
[0061] In the embodiments of this specification, the target device may be a map collection vehicle. Sensors such as laser radar and GPS may be installed on the target device, wherein the laser radar may collect point cloud data of each frame, and the GPS may calculate the position and posture data of the target device based on the received satellite signal (i.e., GPS signal). When there is strong electromagnetic interference in the environment where the target device is located, the GPS signal may be interfered with, and the position and posture data calculated by the GPS based on the interfered GPS signal is not accurate.
[0062] S102: Matching every two adjacent frames of point cloud data, and determining, according to the matching result, a posture transformation of the target device when collecting every two adjacent frames of point cloud data.
[0063] In the embodiment of the present specification, after obtaining each frame of point cloud data through the above step S100, a generalized iterative closest point algorithm (GICP) can be used to match each two adjacent frames of point cloud data, and the position transformation of the target device when collecting each two adjacent frames of point cloud data is determined according to the matching results. Figure 2 As shown. Figure 2 In , i represents the i-th frame point cloud data, and T(i, i+1) represents the pose transformation between the i-th frame point cloud data and the i+1-th frame point cloud data.
[0064] S104: for any two frames of point cloud data in each frame of point cloud data, determine the state of the GPS signal of the target device when the two frames of point cloud data are collected according to the two frames of point cloud data, wherein the state includes: a normal state and an abnormal state.
[0065] In the embodiments of the present specification, for any two frames of point cloud data in each frame of point cloud data, there are two methods for determining the state of the GPS signal of the target device when collecting the two frames of point cloud data based on the two frames of point cloud data. In one method, for any two frames of point cloud data in each frame of point cloud data, the two frames of point cloud data can be matched, and the posture change when the target device collects the two frames of point cloud data is obtained according to the matching result as the first posture change, that is, the method for determining the first posture change is basically the same as the method of using the GICP matching algorithm in the above step S102 to obtain the posture change when the target device collects the two frames of point cloud data. According to the GPS signal when the target device collects the two frames of point cloud data, the posture change when the target device collects the two frames of point cloud data is obtained as the second posture change. According to the difference between the first posture change and the second posture change, the state of the GPS signal of the target device when collecting the two frames of point cloud data is determined. In this method, for any two frames of point cloud data, the first pose change when the target device collects the two frames of point cloud data is obtained by matching the two frames of point cloud data, which is relatively accurate. However, when the second pose change when the target device collects the two frames of point cloud data is obtained according to the GPS signal when the target device collects the two frames of point cloud data, the accuracy of the second pose change cannot be ensured because it is not possible to determine whether the GPS signal is interfered with. When the GPS signal is not interfered with, the first pose change should not be much different from the second pose change; on the contrary, when the GPS signal is interfered with, the first pose change is much different from the second pose change.
[0066] Specifically, if the difference between the first pose change and the second pose change is less than a preset threshold, it can be determined that the state of the GPS signal when the target device collected the two frames of point cloud data was normal. If the difference between the first pose change and the second pose change is greater than a preset threshold, it can be determined that the state of the GPS signal when the target device collected the two frames of point cloud data was abnormal.
[0067] Another method is that for any two frames of point cloud data in each frame of point cloud data, the position data of the target device when collecting the two frames of point cloud data can also be determined according to the GPS signal when the target device collects the two frames of point cloud data, and the two frames of point cloud data are spliced according to the position data when the target device collects the two frames of point cloud data. According to the two spliced frames of point cloud data, the points in one of the two frames of point cloud data are matched with the points in the other frame of point cloud data, and the state of the GPS signal of the target device when collecting the two frames of point cloud data is determined according to the matched point pairs. In this method, because it is impossible to determine whether the GPS signal of the target device when collecting the two frames of point cloud data is interfered, the two frames of point cloud data are spliced according to the position data determined by the GPS signal, and the splicing effect of the two frames of point cloud data cannot be guaranteed. If the GPS signal is not interfered, the point pairs obtained after the two frames of point cloud data are spliced completely overlap or there is a small distance between the point pairs; if the GPS signal is interfered, there is a large distance between the point pairs obtained after the two frames of point cloud data are spliced.
[0068] Specifically, based on the two spliced point cloud data frames, for any point in one of the two point cloud data frames, find the point closest to the point in the other of the two point cloud data frames as a point pair. The average distance between all point pairs in the two point cloud data frames can be calculated. If the average distance is less than a preset threshold, it can be determined that the GPS signal status of the target device when collecting the two frames of point cloud data is normal. If the average distance is greater than the preset threshold, it can be determined that the GPS signal status of the target device when collecting the two frames of point cloud data is abnormal. Figure 3a to Figure 3b shown.
[0069] exist Figure 3a In the figure, there are two frames of point cloud data, namely frame A point cloud data and frame B point cloud data. Frame A point cloud data contains points 1 to 5, and frame B point cloud data contains points 6 to 10. Figure 3b In the figure, after the A-frame point cloud data and the B-frame point cloud data are spliced, point 1 and point 6, point 2 and point 7, point 3 and point 8, point 4 and point 9, point 5 and point 10 form a point pair respectively, and the distances between the five point pairs are expressed as d1, d2, d3, d4, and d5 respectively. Then, the average distance between all point pairs is calculated: (d1+d2, d3+d4+d5) / 5. Finally, it is determined whether the calculated average distance is greater than the preset threshold. If the average distance is greater than the preset threshold, it can be determined that the state of the GPS signal when the target device collects the A-frame point cloud data and the B-frame point cloud data is abnormal.
[0070] It should be noted that there is no sequence distinction between step S102 and step S104.
[0071] S106: splicing the point cloud data in the normal state of the GPS signal according to the posture data corresponding to the point cloud data in the normal state of the GPS signal to obtain a local point cloud map.
[0072] In the embodiment of the present specification, after the state of the GPS signal when the target device collects each frame of point cloud data is determined through the above step S104, only the point cloud data with normal GPS signal state is spliced according to the posture data corresponding to the point cloud data with normal GPS signal state to obtain a local point cloud map.
[0073] For example, the laser radar collects 10 frames of point cloud data, among which the point cloud data with normal GPS signal includes: the 1st frame of point cloud data, the 3rd to 5th frames of point cloud data, and the 8th to 9th frames of point cloud data; the point cloud data with abnormal GPS signal includes: the 2nd frame of point cloud data, the 6th to 7th frames of point cloud data, and the 10th frame of point cloud data. The 1st frame of point cloud data, the 3rd to 5th frames of point cloud data, and the 8th to 9th frames of point cloud data are sequentially spliced into a local point cloud map.
[0074] S108: Matching the point cloud data of the GPS signal abnormal state with the local point cloud map to determine a matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map.
[0075] In the embodiment of this specification, the point cloud data of the GPS signal abnormal state can be matched with the local point cloud map obtained in step S106 using the Normal Distributions Transform (NDT) algorithm to determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map. The matching relationship refers to the transformation that the point cloud data of the GPS signal abnormal state must undergo in order to accurately splice the point cloud data of the GPS signal abnormal state into the local point cloud map.
[0076] Continuing with the above example, the 2nd frame point cloud data, the 6th to 7th frame point cloud data, and the 10th frame point cloud data are rotated or translated so that the 2nd frame point cloud data, the 6th to 7th frame point cloud data, and the 10th frame point cloud data are spliced into the local point cloud map.
[0077] S110: Taking the posture transformation and the matching relationship as constraints, a specified optimization algorithm is used to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data.
[0078] S112: Based on the re-determined position transformation of the target device when collecting every two adjacent frames of point cloud data, each frame of point cloud data is rejoined to obtain a high-precision map.
[0079] In the embodiment of this specification, the pose graph is constructed based on the pose transformation between each two adjacent frames of point cloud data and the matching relationship between the point cloud data of the abnormal state of the GPS signal and the local point cloud map, such as Figure 4 As shown. Figure 4 In it, i represents the i-th frame point cloud data, T(i, i+1) represents the pose transformation between the i-th frame point cloud data and the i+1-th frame point cloud data, and T(i, map) represents the matching relationship between the i-th frame point cloud data and the local point cloud map.
[0080] Then, a graph optimization algorithm is used to re-determine the position transformation of the target device when collecting every two adjacent frames of point cloud data. According to the re-determined position transformation of the target device when collecting every two adjacent frames of point cloud data, each frame of point cloud data is re-joined to obtain a high-precision map.
[0081] Through the above Figure 1 It can be seen from the method shown that this manual determines the posture transformation between each two adjacent frames of point cloud data and the state of the GPS signal when the target device collects each frame of point cloud data based on each frame of point cloud data collected by the target device, wherein the state includes: normal state and abnormal state. The local point cloud map obtained by splicing the point cloud data of the normal state of the GPS signal is matched with the point cloud data of the abnormal state of the GPS signal to obtain the matching relationship between the local point cloud map and the point cloud data of the abnormal state of the GPS signal. With the posture transformation and the matching relationship as constraints, the posture transformation between each two adjacent frames of point cloud data is re-determined, which can avoid the adverse effects of the point cloud data of the abnormal state of the GPS signal on the posture transformation between each two adjacent frames of point cloud data. By re-determining the posture transformation, the misalignment phenomenon can be avoided by re-splicing each frame of point cloud data.
[0082] Furthermore, in Figure 1 In step S104, the state of the GPS signal when the target device collects each frame of point cloud data is determined, and the state of the GPS signal when the target device collects the frame of point cloud data can be detected by the GPS installed on the target device for any frame of point cloud data. The state of the GPS signal includes: normal state and abnormal state.
[0083] Specifically, for each frame of point cloud data collected by the target device, the GPS signal when the target device collects the frame of point cloud data is detected. If it is detected that the GPS signal when the target device collects the frame of point cloud data is normal, then it is determined that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated normal state; if it is detected that the GPS signal when the target device collects the frame of point cloud data is abnormal, then it is determined that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated abnormal state. Among them, when the GPS signal is in an estimated normal state, it can be determined that the GPS signal is in a normal state; and when the GPS signal is in an estimated abnormal state, it cannot be determined whether the GPS signal at this time is in an abnormal state, and it may be a normal state or an abnormal state.
[0084] In order to more accurately determine the state of the GPS signal when the target device collects each frame of point cloud data, the method of detecting the state of the GPS signal can be combined with the two methods in step S104 to obtain two new methods for determining the state of the GPS signal when the target device collects each frame of point cloud data.
[0085] Method 1: First, use GPS to detect the state of the GPS signal when the target device collects each frame of point cloud data, and only determine the point cloud data with normal GPS signal status. Then, arbitrarily select a frame of point cloud data with normal GPS signal status as the benchmark, match the point cloud data with normal GPS signal status with any frame of point cloud data with estimated abnormal GPS signal status, and obtain the first position change when the target device collects the two frames of point cloud data. Based on the GPS signal when the target device collects the two frames of point cloud data, obtain the second position change when the target device collects the two frames of point cloud data. Based on the difference between the first position change and the second position change, determine the state of the GPS signal when the target device collects the point cloud data with estimated abnormal GPS signal status.
[0086] exist Figure 4 In the above, if the GPS detects that the GPS signal of the target device when collecting the i-th frame point cloud data and the i+2-th frame point cloud data is in a normal state, and the GPS signal when collecting the i+1-th frame point cloud data and the i+3-th frame point cloud data is in an estimated abnormal state, the i-th frame point cloud data and the i+2-th frame point cloud data can be used as a reference, and then the i-th frame point cloud data can be matched with the i+1-th frame point cloud data, and the i+2-th frame point cloud data can be matched with the i+3-th frame point cloud data.
[0087] Specifically, when there is one frame of point cloud data in which the GPS signal is estimated to be in a normal state in the two frames of point cloud data, that is, when there is one frame of point cloud data in which the GPS signal is in a normal state, the difference between the first pose change and the second pose change is calculated. If the difference is greater than a preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of the two frames of point cloud data is abnormal; if the difference is less than the preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of the two frames of point cloud data is normal.
[0088] Method 2: First, use GPS to detect the state of the GPS signal when the target device collects each frame of point cloud data, and only determine the point cloud data of the normal state of the GPS signal. Then, arbitrarily select a frame of point cloud data with a normal GPS signal as a reference, and splice the point cloud data of the normal GPS signal frame with any frame of point cloud data with an estimated abnormal GPS signal. Based on the two spliced point cloud data frames, match the points in one of the two point cloud data frames with the points in the other point cloud data frame, and determine the state of the GPS signal of the target device when collecting the point cloud data of the estimated abnormal state of the GPS signal frame based on the matched point pairs.
[0089] Specifically, when there is one frame of point cloud data in which the GPS signal is estimated to be in a normal state among the two frames of point cloud data, that is, when there is one frame of point cloud data in which the GPS signal is in a normal state, the distance between each point pair is calculated based on each point pair obtained by matching. If the distance is greater than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of the two frames of point cloud data is abnormal; if the distance is less than the preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of the two frames of point cloud data is normal.
[0090] The above is a mapping method provided in the embodiments of this specification. Based on the same idea, this specification also provides corresponding devices, storage media and electronic devices.
[0091] Figure 5 A schematic diagram of a mapping device provided in an embodiment of this specification, the device comprising:
[0092] The acquisition module 501 is used to acquire each frame of point cloud data collected by the target device;
[0093] A posture transformation determination module 502 is used to match every two adjacent frames of point cloud data, and determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data according to the matching result;
[0094] The first determination module 503 is used to determine, for any two frames of point cloud data in each frame of point cloud data, the state of the GPS signal of the target device when the two frames of point cloud data are collected according to the two frames of point cloud data, wherein the state includes: a normal state and an abnormal state;
[0095] A splicing module 504 is used to splice the point cloud data of the normal GPS signal according to the position and posture data corresponding to the point cloud data of the normal GPS signal to obtain a local point cloud map;
[0096] A matching relationship determination module 505 is used to match the point cloud data of the GPS signal abnormal state with the local point cloud map, and determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map;
[0097] A second determination module 506 is used to use the posture transformation and the matching relationship as constraints and adopt a specified optimization algorithm to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data;
[0098] The mapping module 507 is used to re-join the point cloud data of each frame according to the re-determined posture transformation of the target device when collecting every two adjacent frames of point cloud data to obtain a high-precision map.
[0099] Optionally, the first determination module 503 is specifically used to match the two frames of point cloud data, and obtain the posture change of the target device when collecting the two frames of point cloud data according to the matching result, as the first posture change; according to the GPS signal when the target device collects the two frames of point cloud data, obtain the posture change of the target device when collecting the two frames of point cloud data as the second posture change; according to the difference between the first posture change and the second posture change, determine the state of the GPS signal of the target device when collecting the two frames of point cloud data;
[0100] Determine the position data of the target device when collecting the two frames of point cloud data based on the GPS signal when the target device collects the two frames of point cloud data; splice the two frames of point cloud data based on the position data when the target device collects the two frames of point cloud data; match the points in one of the two frames of point cloud data with the points in the other frame of point cloud data based on the two spliced together frames of point cloud data; determine the state of the GPS signal of the target device when collecting the two frames of point cloud data based on the matched point pairs.
[0101] Optionally, before determining the state of the GPS signal of the target device when collecting the two frames of point cloud data, the first determination module 503 is also used to detect, for each frame of point cloud data collected by the target device, the GPS signal of the target device when collecting the frame of point cloud data; if it is detected that the GPS signal of the target device when collecting the frame of point cloud data is normal, then it is determined that the state of the GPS signal of the target device when collecting the frame of point cloud data is an estimated normal state; if it is detected that the GPS signal of the target device when collecting the frame of point cloud data is abnormal, then it is determined that the state of the GPS signal of the target device when collecting the frame of point cloud data is an estimated abnormal state.
[0102] Optionally, the first determination module 503 is specifically used to, when there is a frame of point cloud data in which the GPS signal is estimated to be in a normal state in the two frames of point cloud data, calculate the difference between the first posture change and the second posture change; if the difference is greater than a preset threshold, determine that the state of the GPS signal of the target device when collecting the other frame of point cloud data in the two frames of point cloud data is an abnormal state; if the difference is less than the preset threshold, determine that the state of the GPS signal of the target device when collecting the other frame of point cloud data in the two frames of point cloud data is a normal state;
[0103] When one frame of point cloud data in which the GPS signal is estimated to be in a normal state exists in the two frames of point cloud data, the distance between each point pair is calculated based on each point pair obtained by matching. If the distance is greater than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of the two frames of point cloud data is abnormal; if the distance is less than the preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of the two frames of point cloud data is normal.
[0104] This specification also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, it can be used to perform the above Figure 1 Provided mapping method.
[0105] based on Figure 1 The motion trajectory prediction method shown in the present specification also provides Figure 5 The structural diagram of the unmanned equipment is shown in FIG. Figure 6 At the hardware level, the unmanned equipment includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The mapping method described.
[0106] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0107] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0108] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0109] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0110] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0111] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0112] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0113] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0115] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0116] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0117] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0119] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0120] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0121] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0122] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.
Claims
1. A mapping method, characterized in that: include: Obtain each frame of point cloud data collected by the target device; Matching every two adjacent frames of point cloud data, and determining the position and posture transformation of the target device when collecting every two adjacent frames of point cloud data according to the matching result; And for any two frames of point cloud data in each frame of point cloud data, determine the state of the global positioning system GPS signal of the target device when the two frames of point cloud data are collected according to the two frames of point cloud data, wherein the state includes: a normal state and an abnormal state; According to the posture data corresponding to the point cloud data in the normal state of the GPS signal, the point cloud data in the normal state of the GPS signal are spliced to obtain a local point cloud map; Matching the point cloud data of the GPS signal abnormal state with the local point cloud map to determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map; Taking the posture transformation and the matching relationship as constraints, a specified optimization algorithm is used to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data; According to the re-determined posture transformation of the target device when collecting every two adjacent frames of point cloud data, each frame of point cloud data is re-joined to obtain a high-precision map.
2. The method according to claim 1, characterized in that Determining the state of the GPS signal of the target device when collecting the two frames of point cloud data according to the two frames of point cloud data, specifically includes: The two frames of point cloud data are matched, and a position change when the target device collects the two frames of point cloud data is obtained according to the matching result as the first position change; According to the GPS signal when the target device collects the two frames of point cloud data, a posture change when the target device collects the two frames of point cloud data is obtained as a second posture change; According to the difference between the first posture change and the second posture change, a state of a GPS signal of the target device when collecting the two frames of point cloud data is determined.
3. The method according to claim 1, characterized in that Determining the state of the GPS signal of the target device when collecting the two frames of point cloud data according to the two frames of point cloud data, specifically includes: Determine the position and posture data of the target device when collecting the two frames of point cloud data according to the GPS signal of the target device when collecting the two frames of point cloud data; splicing the two frames of point cloud data according to the pose data when the target device collects the two frames of point cloud data; According to the two frames of point cloud data that have been stitched together, points in one of the two frames of point cloud data are matched with points in the other frame of point cloud data; According to the matched point pairs, the state of the GPS signal of the target device when collecting the two frames of point cloud data is determined.
4. The method according to claim 2, characterized in that Before determining the state of the GPS signal of the target device when collecting the two frames of point cloud data, the method further includes: For each frame of point cloud data collected by the target device, detecting the GPS signal when the target device collects the frame of point cloud data; If it is detected that the GPS signal when the target device collects the frame of point cloud data is normal, determining that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated normal state; If it is detected that the GPS signal when the target device collects the frame of point cloud data is abnormal, it is determined that the state of the GPS signal when the target device collects the frame of point cloud data is an estimated abnormal state.
5. The method according to claim 4, characterized in that Determining, according to a difference between the first posture change and the second posture change, a state of a GPS signal of the target device when collecting the two frames of point cloud data, specifically includes: When there is one frame of point cloud data in which the GPS signal is estimated to be in a normal state in the two frames of point cloud data, calculating a difference between the first position change and the second position change; If the difference is greater than a preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of point cloud data of the two frames of point cloud data is abnormal; If the difference is smaller than a preset threshold, it is determined that the state of the GPS signal of the target device when collecting the other frame of point cloud data in the two frames of point cloud data is normal.
6. The method according to claim 4, characterized in that Determining the state of the GPS signal of the target device when collecting the two frames of point cloud data based on the matched point pairs, specifically includes: When one frame of point cloud data in which the GPS signal is estimated to be in a normal state exists in the two frames of point cloud data, the distance between each point pair is calculated based on each point pair obtained by matching; If the distance is greater than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of point cloud data in the two frames of point cloud data is abnormal; If the distance is less than a preset threshold, it is determined that the state of the GPS signal when the target device collects the other frame of point cloud data in the two frames of point cloud data is normal.
7. The method according to claim 1, characterized in that The specified optimization algorithm is used to re-determine the position and posture transformation of the target device when collecting every two adjacent frames of point cloud data, specifically including: A graph optimization algorithm is used to re-determine the position and posture transformation of the target device when collecting every two adjacent frames of point cloud data.
8. A mapping device, characterized in that: include: An acquisition module is used to acquire each frame of point cloud data collected by the target device; A posture transformation module is used to match every two adjacent frames of point cloud data, and determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data according to the matching result; A first determination module is used to determine, for any two frames of point cloud data in each frame of point cloud data, the state of the GPS signal of the target device when the two frames of point cloud data are collected according to the two frames of point cloud data, wherein the state includes: a normal state and an abnormal state; A splicing module, for splicing the point cloud data in a normal state of the GPS signal according to the posture data corresponding to the point cloud data in a normal state of the GPS signal, to obtain a local point cloud map; A matching relationship determination module is used to match the point cloud data of the GPS signal abnormal state with the local point cloud map, and determine the matching relationship between the point cloud data of the GPS signal abnormal state and the local point cloud map; A second determination module is used to use the posture transformation and the matching relationship as constraints and adopt a specified optimization algorithm to re-determine the posture transformation of the target device when collecting every two adjacent frames of point cloud data; The mapping module is used to re-join the point cloud data of each frame according to the re-determined posture transformation of the target device when collecting every two adjacent frames of point cloud data to obtain a high-precision map.
9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Laser point cloud map construction method, device, equipment and system
CN111553937A
Map construction method and device and computer readable storage medium
CN111735439A
Method, apparatus and terminal device for constructing map
US20190026920A1
Systems and methods for constructing high-definition map
WO2020113425A1
Positioning method and apparatus, electronic device, and readable storage medium
WO2020259481A1
