Two-dimensional grid mapping method, apparatus, device, and storage medium

Abstract

A two-dimensional grid mapping method, an apparatus, a device, and a storage medium, which belong to the field of mapping. The two-dimensional grid mapping method comprises: obtaining, in real time, first pose data and second pose data of a robot at the current moment, the first pose data being pose data determined by a two-dimensional lidar, and the second pose data being pose data determined by a combination navigation device, where the pose data determined by the combination navigation device is pose data obtained by merging position data measured by a satellite navigation device and orientation data measured by an inertial measurement unit device (S110); merging the first pose data and the second pose data, and obtaining merged pose data (S120); and constructing a two-dimensional grid map according to the merged pose data (S130).

Description

Two-dimensional grid map construction method, device, equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application 202311808109.3, filed on December 26, 2023, entitled “Two-dimensional grid map construction method, device, equipment and storage medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of map construction, and in particular to a two-dimensional grid map construction method, device, equipment and storage medium. Background Art

[0004] There are two main approaches to building outdoor 2D grid maps based on LiDAR. One uses multi-line LiDAR point cloud data to construct a 3D outdoor point cloud map, then compresses the point cloud in the height direction to generate a 2D grid map. The other directly uses single-line LiDAR, or compresses multi-line LiDAR point clouds into single-line data. The resulting 2D grid map is then generated through scan matching, loop closure detection, and back-end optimization.

[0005] Building a 3D point cloud map is computationally intensive, and resource consumption increases dramatically with the size of the point cloud map. This makes real-time execution difficult on low-cost industrial computers. Most approaches rely on first collecting data and then processing it offline. Only after the 3D map is fully constructed can it be compressed into a 2D map, making real-time 2D map construction impossible.

[0006] When the existing two-dimensional lidar scanning matching method is applied in outdoor scenes, the scanning matching accuracy is low due to the empty scene and the small number of feature points, which easily leads to the failure of the entire environment map construction. Summary of the Invention

[0007] The embodiments of the present application provide a two-dimensional grid map construction method, apparatus, device, and storage medium, which can construct a two-dimensional grid map in real time and improve the accuracy of map construction.

[0008] In a first aspect, an embodiment of the present application provides a method for constructing a two-dimensional grid map, the method comprising:

[0009] Acquire the robot's first and second pose data at the current moment in real time. The first pose data is the pose data determined by the two-dimensional laser radar, and the second pose data is the pose data determined by the integrated navigation device. The pose data determined by the integrated navigation device is the pose data obtained by fusing the position data measured by the satellite navigation device and the pose data measured by the inertial measurement unit device.

[0010] Fusing the first pose data and the second pose data to obtain fused pose data;

[0011] Construct a two-dimensional grid map based on the fused pose data.

[0012] In some embodiments of the present application, fusing the first pose data and the second pose data to obtain fused pose data includes:

[0013] Performing a posture transformation on the first posture data according to the first posture data and a preset posture transformation relationship to obtain transformed first posture data, wherein the preset posture transformation relationship is determined based on historical posture data of the robot determined by a two-dimensional laser radar and historical posture data of the robot determined by an integrated navigation device;

[0014] The transformed first pose data and the second pose data are fused to obtain fused pose data.

[0015] In some embodiments of the present application, fusing the transformed first pose data and the second pose data to obtain fused pose data includes:

[0016] Obtaining a first weight corresponding to the transformed first pose data and a second weight corresponding to the transformed second pose data;

[0017] The posture data is fused according to the transformed first posture data, the first weight, the second posture data and the second weight to obtain fused posture data.

[0018] In some embodiments of the present application, before obtaining the first weight corresponding to the transformed first pose data and the second weight corresponding to the second pose data, the method further includes:

[0019] The first weight and the second weight are determined according to the point cloud matching result of the two-dimensional laser radar and the positioning result of the robot measured by the satellite navigation device.

[0020] In some embodiments of the present application, after fusing the first pose data and the second pose data to obtain fused pose data, the method further includes:

[0021] A graph structure model is constructed based on the fused pose data and the historical fused pose data of the historical moments before the current moment. The vertices of the graph structure model are the fused pose data, and the edges between the vertices are the pose transformation relationships between the fused pose data.

[0022] In some embodiments of the present application, the method further comprises:

[0023] performing loop closure detection on the positioning data based on the positioning data in the second posture data and the positioning data in the posture data of the robot at historical moments before the current moment determined by the combined navigation device;

[0024] When it is determined that the positioning data passes the loop closure detection, the constraint relationship between the edges of the vertices in the graph structure model is updated according to the fused pose data corresponding to the positioning data detected by the loop closure and the fused pose data at the current moment.

[0025] In some embodiments of the present application, the method further comprises:

[0026] Optimize the graph structure model to obtain an optimized graph structure model;

[0027] Construct a two-dimensional grid map based on the fused pose data, including:

[0028] A two-dimensional grid map is constructed based on the fused pose data in the optimized graph structure model.

[0029] In a second aspect, an embodiment of the present application provides a two-dimensional grid map construction device, the device comprising:

[0030] An acquisition module is used to obtain the first and second pose data of the robot at the current moment in real time. The first pose data is the pose data determined by the two-dimensional laser radar, and the second pose data is the pose data determined by the integrated navigation device. The pose data determined by the integrated navigation device is the pose data obtained by fusing the position data measured by the satellite navigation device and the pose data measured by the inertial measurement unit device;

[0031] A fusion module, used to fuse the first pose data and the second pose data to obtain fused pose data;

[0032] The first construction module is used to construct a two-dimensional grid map based on the fused posture data.

[0033] In a third aspect, an embodiment of the present application provides a two-dimensional grid map construction device, the two-dimensional grid map construction device comprising: a processor and a memory storing computer program instructions;

[0034] When the processor executes the computer program instructions, the two-dimensional grid map construction method of any of the above embodiments is implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the two-dimensional grid map construction method of any of the above embodiments is implemented.

[0036] According to the two-dimensional grid map construction method, device, equipment and storage medium of the embodiments of the present application, since the posture data determined by the two-dimensional laser radar and the combined navigation device are respectively fused, and the two-dimensional grid map is constructed using the fused posture data, compared with the related art of first constructing an outdoor three-dimensional point cloud map and then compressing the point cloud map in the height direction to generate a two-dimensional grid map, the effect of real-time construction of a two-dimensional grid map can be achieved. Compared with the related art of generating a two-dimensional grid map using only a two-dimensional laser radar scanning matching method, more accurate posture data can be obtained, thereby improving the accuracy of map construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] FIG1 is a flow chart of a method for constructing a two-dimensional grid map according to an embodiment of the present application;

[0039] FIG2 is another flow chart of a method for constructing a two-dimensional grid map according to an embodiment of the present application;

[0040] FIG3 is a schematic diagram of another flow chart of the method for constructing a two-dimensional grid map according to an embodiment of the present application;

[0041] FIG4 is a schematic diagram of the structure of a two-dimensional grid map construction device provided in an embodiment of the present application;

[0042] FIG5 is a schematic diagram of the structure of a two-dimensional grid map construction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0044] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0045] There are two main approaches to building outdoor 2D grid maps based on LiDAR. One uses multi-line LiDAR point cloud data to construct a 3D outdoor point cloud map, then compresses the point cloud in the height direction to generate a 2D grid map. The other directly uses single-line LiDAR, or compresses multi-line LiDAR point clouds into single-line data. The resulting 2D grid map is then generated through scan matching, loop closure detection, and back-end optimization.

[0046] Building a 3D point cloud map is computationally intensive, and resource consumption increases dramatically with the size of the point cloud map. This makes real-time execution difficult on low-cost industrial computers. Most approaches rely on first collecting data and then processing it offline. Only after the 3D map is fully constructed can it be compressed into a 2D map, making real-time 2D map construction impossible.

[0047] When the existing two-dimensional lidar scanning matching method is applied in outdoor scenes, the scanning matching accuracy is low due to the open space and few feature points in the scene, which easily leads to the failure of building the entire environment map.

[0048] In order to solve the above technical problems, the embodiments of the present application provide a two-dimensional grid map construction method, device, equipment and storage medium. Since the posture data determined by the two-dimensional laser radar and the combined navigation device are fused, and the two-dimensional grid map is constructed using the fused posture data, compared with the related art of first constructing an outdoor three-dimensional point cloud map and then compressing the point cloud map in the height direction to generate a two-dimensional grid map, the effect of real-time construction of a two-dimensional grid map can be achieved. Compared with the related art of only using a two-dimensional laser radar scanning matching method to generate a two-dimensional grid map, more accurate posture data can be obtained, thereby improving the accuracy of map construction.

[0049] FIG1 is a flow chart of a method for constructing a two-dimensional grid map according to an embodiment of the present application;

[0050] Below, in conjunction with FIG1 , a two-dimensional grid map construction method provided by an embodiment of the present application is described. The method includes:

[0051] S110, obtaining first and second pose data of the robot at the current moment in real time, where the first pose data is pose data determined by a two-dimensional laser radar, and the second pose data is pose data determined by an integrated navigation device, where the pose data determined by the integrated navigation device is pose data obtained by fusing position data measured by a satellite navigation device and pose data measured by an inertial measurement unit device;

[0052] S120, fusing the first pose data and the second pose data to obtain fused pose data;

[0053] S130: Construct a two-dimensional grid map based on the fused posture data.

[0054] According to the two-dimensional grid map construction method of the embodiment of the present application, since the posture data determined by the two-dimensional laser radar and the combined navigation device are fused, and the fused posture data is used to construct the two-dimensional grid map, compared with the related art of first constructing an outdoor three-dimensional point cloud map and then compressing the point cloud map in the height direction to generate a two-dimensional grid map, the effect of real-time construction of a two-dimensional grid map can be achieved. Compared with the related art of only using a two-dimensional laser radar scanning matching method to generate a two-dimensional grid map, more accurate posture data can be obtained, thereby improving the accuracy of map construction.

[0055] Regarding S110 above, the robot is equipped with a two-dimensional laser radar. During the robot's walking process, the two-dimensional laser radar can determine the robot's first pose data in real time. The pose data includes position data and posture data. Specifically, the pose data can be obtained using a scan matching method, such as the ICP algorithm and the NDT normal distribution transformation algorithm.

[0056] The robot is also equipped with a combined navigation device. During the robot's walking process, the combined navigation device can obtain the robot's second posture data in real time. The combined navigation device includes a satellite navigation device and an inertial measurement unit device. The satellite navigation device is used to measure the robot's position information, and the inertial measurement unit device is used to measure the robot's posture data. The second posture data of the robot can be obtained by fusing the two data. Specifically, the extended Kalman filter algorithm can be used for fusion.

[0057] With respect to the above S120, after obtaining the first pose data and the second pose data, the two are fused to obtain fused pose data. Specifically, a weighted least squares algorithm can be used for fusion.

[0058] Regarding the above S130, after obtaining the fused posture data, the fused posture data can be used to construct a two-dimensional grid map. Specifically, the Karto algorithm can be used to achieve the construction of the two-dimensional grid map.

[0059] FIG2 is another flow chart of a two-dimensional grid map construction method provided in an embodiment of the present application. As shown in FIG2 , in some embodiments of the present application, fusing the first pose data and the second pose data to obtain fused pose data includes S210 and S220.

[0060] S210, according to the first pose data and the preset pose transformation relationship, the first pose data is subjected to pose transformation to obtain the transformed first pose data, and the preset pose transformation relationship is determined based on the historical pose data of the robot determined by the two-dimensional laser radar and the historical pose data of the robot determined by the combined navigation device.

[0061] Specifically, the preset pose transformation relationship is used to convert the pose data determined by the radar into pose data in Earth coordinates, facilitating fusion with the second pose data. Specifically, a transformation matrix can be determined based on the robot's historical pose data measured by a two-dimensional lidar and the robot's historical pose data determined by an integrated navigation device, and the transformation matrix can be used as the preset pose transformation relationship.

[0062] S220 , fusing the transformed first pose data and the second pose data to obtain fused pose data.

[0063] Specifically, after obtaining the transformed first pose data and second pose data, the two are fused to obtain fused pose data. Specifically, a weighted least squares algorithm can be used for fusion.

[0064] FIG3 is another flow chart of a two-dimensional grid map construction method provided in an embodiment of the present application. As shown in FIG3 , in some embodiments of the present application, fusing the transformed first pose data and the second pose data to obtain fused pose data includes S310 and S320.

[0065] S310, obtaining a first weight corresponding to the transformed first pose data and a second weight corresponding to the transformed second pose data.

[0066] In some embodiments of the present application, before obtaining the first weight corresponding to the transformed first pose data and the second weight corresponding to the second pose data, the method further includes:

[0067] The first weight and the second weight are determined according to the point cloud matching result of the two-dimensional laser radar and the positioning result of the robot measured by the satellite navigation device.

[0068] Specifically, if the current location is determined to belong to an open area based on the point cloud matching results and the positioning results, since open areas generally have less or no obstructions, and radar requires more reference objects to locate more accurately, the satellite navigation positioning accuracy is higher than the radar positioning accuracy. The second weight can be made greater than the first weight. For example, the first weight is 20% and the second weight is 80%. Of course, it can also be other values, as long as the second weight is greater than the first weight.

[0069] If it is determined based on the point cloud matching results and the positioning results that the current location belongs to a densely populated area, such as an area with many high-rise buildings in the city, the satellite positioning accuracy is low due to more obstructions, while the radar positioning is more accurate due to the presence of more reference objects. Therefore, the first weight can be made greater than the second weight. For example, the first weight is 80% and the second weight is 20%. Of course, other data can also be used, as long as the first weight is greater than the second weight.

[0070] S320, performing posture data fusion according to the transformed first posture data, the first weight, the second posture data, and the second weight to obtain fused posture data.

[0071] Specifically, the first pose data, the first weight, the second pose data and the second weight are weightedly fused in a weighted fusion manner to obtain fused pose data.

[0072] In some embodiments of the present application, after fusing the first pose data and the second pose data to obtain fused pose data, the method further includes:

[0073] A graph structure model is constructed based on the fused pose data and the historical fused pose data of the historical moments before the current moment. The vertices of the graph structure model are the fused pose data, and the edges between the vertices are the pose transformation relationships between the fused pose data.

[0074] Specifically, the graph structure model shows the dependency relationship between data, making it easier to optimize data.

[0075] In some embodiments of the present application, the method further comprises:

[0076] performing loop closure detection on the positioning data based on the positioning data in the second posture data and the positioning data in the posture data of the robot at historical moments before the current moment determined by the combined navigation device;

[0077] When it is determined that the positioning data passes the loop closure detection, the constraint relationship between the edges of the vertices in the graph structure model is updated according to the fused pose data corresponding to the positioning data detected by the loop closure and the fused pose data at the current moment.

[0078] Specifically, in the prior art, loop detection is often performed based on positioning data determined by radar. However, the positioning data determined by radar is obtained based on scan matching. Once the position data is wrong, there will be a problem of cumulative drift, and loop detection will be difficult to make correct judgments. The map will have errors such as overlapping and deflection. In this application, loop detection is performed using positioning data determined by a combined navigation device. Satellite data does not have the disadvantage of cumulative drift. Therefore, loop detection using satellite data is more likely to succeed, greatly improving the accuracy of constructing two-dimensional raster maps.

[0079] The positioning data in the currently obtained second pose data can be continuously matched with the positioning data in the historical second pose data. If the distance between the two positioning data is less than a preset value, the loop is considered successful, and a constraint relationship is added between the corresponding two vertices in the graph structure model.

[0080] In some embodiments of the present application, the method further comprises:

[0081] Optimize the graph structure model to obtain an optimized graph structure model;

[0082] Construct a two-dimensional grid map based on the fused pose data, including:

[0083] A two-dimensional grid map is constructed based on the fused pose data in the optimized graph structure model.

[0084] Specifically, the method for optimizing the graph structure model can be the LM algorithm or the Gauss-Newton algorithm, the purpose of which is to complete the optimization adjustment of the posture data.

[0085] After optimizing the pose data, a two-dimensional grid map is constructed based on the optimized pose data, which can improve the construction accuracy of the two-dimensional grid map.

[0086] The following describes the entire two-dimensional grid map construction process of the present application through a specific embodiment, which includes the following steps:

[0087] Step (1): Receive the lidar data, match the current radar data with the previous radar data, and estimate the radar pose (using the ICP algorithm or the NDT normal distribution transformation algorithm), denoted as p l , and establish the environment map, recorded as m, the first frame pose data is recorded as p l1 , the time is recorded as t1;

[0088] Step (2): Receive the data measured by the inertial measurement unit and the satellite data, fuse them using the extended Kalman filter algorithm, and output the combined navigation pose data p g , and cache it in the queue, record the posture data at time t1, recorded as p g1 ;

[0089] Step (3): According to the posture transformation relationship, p l1 =E*p g1 , calculate the transformation matrix E, and then transform the coordinate system direction of the environment map m to the earth coordinate system;

[0090] Step (4): According to the transformation matrix E, the pose data p of the subsequent laser radar scan matching is converted to l , transformed to the earth coordinate system, denoted as p t , that is, P t =inv(E)*P l ;

[0091] Step (5): Inertial measurement unit / satellite combined navigation pose data p g , LiDAR scan matching pose data p t , use the weighted least squares algorithm to fuse and generate new pose data p f , that is, p f =p g *w1+p t *w2, w1+w2=1

[0092] Among them, w1 and w2 are the weights of the combined navigation pose and the lidar scanning matching pose, respectively. These two weight values ​​can be determined according to the satellite positioning status and the matching degree of the lidar point cloud;

[0093] Step (6): Construct a graph structure model using the fused pose data p f As the vertices of the graph structure, the constraints between vertices (i.e., the posture transformation relationship) are the edges of the graph structure;

[0094] Step (7): Considering the characteristic of satellite data without cumulative drift, the inertial measurement unit / satellite combined navigation pose data is used to perform loop detection and judgment, and the current combined navigation pose data p is continuously updated. g Store it in a queue and search the queue for a data frame whose distance from the current integrated navigation position is less than a threshold Δth. If a data frame is found, it is considered that a loop has occurred.

[0095] Step (8): Combine the loop data frame moment and the current moment pose data p f Data is added to the graph structure as a loop constraint;

[0096] Step (9): Use the LM algorithm or Gauss-Newton algorithm to optimize the graph structure, complete the posture adjustment and map update;

[0097] Repeat steps (3) to (9) until the map is constructed.

[0098] The method for constructing a two-dimensional grid map using inertial measurement unit / satellite combined navigation assistance, proposed in the embodiments of this application, has the advantage of lower computational complexity compared to constructing maps based on three-dimensional lidar measurement data, is more robust than constructing maps based on pure two-dimensional radar data, and can be deployed on low-cost industrial computers. To address the challenges of outdoor environments with few features and large errors in lidar scan matching and loop detection, the scan matching / loop detection phase of lidar grid map construction is optimized by leveraging the high outdoor accuracy and lack of accumulated drift of inertial measurement unit / satellite combined navigation data, significantly improving the accuracy of outdoor two-dimensional grid map construction.

[0099] FIG4 is a schematic diagram of the structure of the two-dimensional grid map construction device provided in an embodiment of the present application. Below, the two-dimensional grid map construction device provided in an embodiment of the present application is described in conjunction with FIG4. The device includes:

[0100] Acquisition module 401 is used to acquire the first pose data and second pose data of the robot at the current moment in real time, where the first pose data is pose data determined by a two-dimensional laser radar, and the second pose data is pose data determined by an integrated navigation device, which is pose data obtained by fusing position data measured by a satellite navigation device and pose data measured by an inertial measurement unit device;

[0101] A fusion module 402 is configured to fuse the first pose data and the second pose data to obtain fused pose data;

[0102] The first construction module 403 is used to construct a two-dimensional grid map according to the fused posture data.

[0103] In some embodiments of the present application, the fusion module 402 includes:

[0104] a transformation unit, configured to perform a posture transformation on the first posture data according to the first posture data and a preset posture transformation relationship to obtain transformed first posture data, wherein the preset posture transformation relationship is determined based on historical posture data of the robot determined by a two-dimensional laser radar and historical posture data of the robot determined by an integrated navigation device;

[0105] The fusion unit is used to fuse the transformed first pose data and the second pose data to obtain fused pose data.

[0106] In some embodiments of the present application, the fusion unit is specifically configured to:

[0107] Obtaining a first weight corresponding to the transformed first pose data and a second weight corresponding to the transformed second pose data;

[0108] The posture data is fused according to the transformed first posture data, the first weight, the second posture data and the second weight to obtain fused posture data.

[0109] In some embodiments of the present application, the fusion module 402 further includes:

[0110] A determination unit is used to determine a first weight and a second weight according to a point cloud matching result of a two-dimensional laser radar and a positioning result of the robot measured by a satellite navigation device.

[0111] In some embodiments of the present application, the apparatus comprises:

[0112] The second construction module is used to construct a graph structure model based on the fused pose data and the historical fused pose data of the historical moments before the current moment. The vertices of the graph structure model are the fused pose data, and the edges between the vertices are the pose transformation relationships between the fused pose data.

[0113] In some embodiments of the present application, the apparatus further comprises:

[0114] The detection module is used to perform loop closure detection on the positioning data based on the positioning data in the second posture data and the positioning data in the posture data of the robot at historical moments before the current moment determined by the combined navigation device; when it is determined that the positioning data passes the loop closure detection, the constraint relationship of the edges between the vertices in the graph structure model is updated based on the fused posture data corresponding to the positioning data detected by the loop closure and the fused posture data at the current moment.

[0115] In some embodiments of the present application, the apparatus further comprises:

[0116] The optimization module is used to optimize the graph structure model to obtain the optimized graph structure model;

[0117] The first building block 403 is specifically configured to:

[0118] A two-dimensional grid map is constructed based on the fused pose data in the optimized graph structure model.

[0119] According to the two-dimensional grid map construction device of the embodiment of the present application, since the posture data determined by the two-dimensional laser radar and the combined navigation device are respectively fused, and the two-dimensional grid map is constructed using the fused posture data, compared with the related art of first constructing an outdoor three-dimensional point cloud map and then compressing the point cloud map in the height direction to generate a two-dimensional grid map, the effect of real-time construction of a two-dimensional grid map can be achieved. Compared with the related art of generating a two-dimensional grid map using only a two-dimensional laser radar scanning matching method, more accurate posture data can be obtained, thereby improving the accuracy of map construction.

[0120] FIG5 is a schematic diagram of the structure of a two-dimensional grid map construction device provided in an embodiment of the present application.

[0121] The two-dimensional grid map construction device may include a processor 501 and a memory 502 storing computer program instructions.

[0122] Specifically, the processor 501 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0123] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 502 may include removable or non-removable (or fixed) media. Where appropriate, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0124] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0125] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement the two-dimensional grid map construction method in the above embodiment.

[0126] In one example, the two-dimensional grid map construction device may further include a communication interface 503 and a bus 510. As shown in FIG5, the processor 501, the memory 502, and the communication interface 503 are connected via the bus 510 and communicate with each other.

[0127] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0128] The bus 510 includes hardware, software, or both, coupling the components of the two-dimensional grid map construction device to each other. By way of example and not limitation, the bus may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front-side bus (FSB), a hypertransport (HT) interconnect, an industry standard architecture (ISA) bus, an infinite bandwidth interconnect, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 510 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0129] The two-dimensional grid map construction device executes the two-dimensional grid map construction method in the embodiment of the present application, thereby realizing the two-dimensional grid map construction method shown in Figures 1, 2 and 3.

[0130] In addition, in conjunction with the two-dimensional grid map construction method in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the two-dimensional grid map construction methods in the above embodiments is implemented.

[0131] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0132] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0133] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0134] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box 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 or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0135] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for constructing a two-dimensional grid map, the method comprising: Obtaining in real time the first pose data and the second pose data of the robot at the current moment, where the first pose data is the pose data determined by a two-dimensional lidar, and the second pose data is the pose data determined by a combined navigation device, and the pose data determined by the combined navigation device is the pose data obtained by fusing the position data measured by a satellite navigation device and the attitude data measured by an inertial measurement unit device; Fusing the first pose data and the second pose data to obtain the fused pose data; Constructing a two-dimensional grid map according to the fused pose data.

2. The method according to claim 1, wherein, The fusing the first pose data and the second pose data to obtain the fused pose data includes: Performing a pose transformation on the first pose data according to the first pose data and a preset pose transformation relationship to obtain the transformed first pose data, where the preset pose transformation relationship is determined based on the historical pose data of the robot determined by the two-dimensional lidar and the historical pose data of the robot determined by the combined navigation device; Fusing the transformed first pose data and the second pose data to obtain the fused pose data.

3. The method according to claim 2, wherein, The fusing the transformed first pose data and the second pose data to obtain the fused pose data includes: Obtaining a first weight corresponding to the transformed first pose data and a second weight corresponding to the second pose data; Performing pose data fusion according to the transformed first pose data, the first weight, the second pose data, and the second weight to obtain the fused pose data.

4. According to the method described in claim 3, before obtaining the first weight corresponding to the transformed first pose data and the second weight corresponding to the second pose data, the method further includes: Determining the first weight and the second weight according to the point cloud matching result of the two-dimensional lidar and the positioning result of the robot measured by the satellite navigation device.

5. The method according to claim 1, wherein After fusing the first pose data and the second pose data to obtain the fused pose data, the method further includes: Constructing a graph structure model according to the fused pose data and the historical fused pose data at historical moments before the current moment, where the vertices of the graph structure model are the fused pose data, and the edges between vertices are the pose transformation relationships between the fused pose data.

6. According to the method described in claim 5, the method further includes: Performing loop detection on the positioning data according to the positioning data in the second pose data and the positioning data in the pose data of the robot at historical moments before the current moment determined by the combined navigation device; In the case where it is determined that the positioning data passes the loop detection, updating the constraint relationship of the edges between vertices in the graph structure model according to the fused pose data corresponding to the positioning data detected by the loop detection and the fused pose data at the current moment.

7. According to the method described in claim 6, the method further includes: Optimize the graph structure model to obtain an optimized graph structure model; The constructing a two-dimensional grid map according to the fused pose data includes: Construct a two-dimensional grid map according to the fused pose data in the optimized graph structure model.

8. A two-dimensional grid map construction device, the device includes: An acquisition module, configured to acquire in real time the first pose data and the second pose data of the robot at the current moment, where the first pose data is the pose data determined by a two-dimensional lidar, and the second pose data is the pose data determined by a combined navigation device, and the pose data determined by the combined navigation device is the pose data obtained by fusing the position data measured by a satellite navigation device and the attitude data measured by an inertial measurement unit device; A fusion module, configured to fuse the first pose data and the second pose data to obtain fused pose data; A first construction module, configured to construct a two-dimensional grid map according to the fused pose data.

9. A two-dimensional grid map construction device, the device comprising: A processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the two-dimensional grid map construction method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the two-dimensional grid map construction method according to any one of claims 1 to 7 is implemented.

Images