In-tunnel vehicle positioning method, device and system based on laser radar

Abstract

The invention discloses an in-tunnel vehicle positioning method, device and system based on a laser radar. The method comprises the following steps: receiving point cloud data sent by the laser radar arranged on a first vehicle after scanning an environment in a tunnel; extracting contour information of the second vehicle according to curvature information of each surface corresponding to surface point data in the point cloud data; the first vehicle and the second vehicle are located in the tunnel; determining position information of the second vehicle relative to the first vehicle based on the contour information; determining pose information of the second vehicle according to the position information of the second vehicle and the pose information of the first vehicle; wherein the pose information of the first vehicle is determined based on the point cloud data and image information collected by camera equipment arranged on the first vehicle. According to the technical scheme provided by the invention, the positioning of the vehicle in the tunnel can be realized without arranging a fixed marker.

Description

Technical Field

[0001] The present application relates to the field of vehicle positioning technology, and in particular to a laser radar-based vehicle positioning method, device and system in a tunnel. Background Art

[0002] With the development of science and technology, the use of GPS (Global Positioning System) positioning navigation, satellite navigation and other technical means for vehicle navigation has greatly facilitated vehicle driving control.

[0003] Usually, vehicle navigation needs to determine the current position of the vehicle. However, in some scenarios, these technological means may not be applicable. For example, when a vehicle is driving in a tunnel or working in a tunnel, GPS navigation or satellite navigation often has no signal and cannot complete positioning, thus failing to navigate the vehicle. In response to this situation, the prior art may use radar and artificially arranged markers to achieve vehicle positioning in tunnels, but more markers need to be arranged, which increases the complexity of construction. In addition, if the marker is damaged or moved, it may affect the accuracy of vehicle positioning.

[0004] Therefore, how to provide a solution that can realize the positioning of vehicles in tunnels without the need to arrange a large number of markers is a technical problem that urgently needs to be solved in this field. Summary of the invention

[0005] The present application provides a method, device, system, equipment, storage medium, and computer program product for positioning a vehicle in a tunnel based on laser radar, which can accurately position the vehicle in the tunnel without setting up additional fixed markers.

[0006] On the one hand, an embodiment of this specification provides a method for positioning a vehicle in a tunnel based on a laser radar, the method comprising:

[0007] receiving point cloud data sent by a laser radar disposed on the first vehicle after scanning the environment in the tunnel;

[0008] Extracting contour information of a second vehicle according to curvature information of each surface corresponding to the surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in the tunnel;

[0009] Determine the position information of the second vehicle in the coordinate system of the laser radar based on the contour information;

[0010] The posture information of the second vehicle is determined based on the position information of the second vehicle and the posture information of the first vehicle, and the posture information includes: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and image information collected by a camera device installed on the first vehicle.

[0011] On the other hand, an embodiment of this specification provides a laser radar-based vehicle positioning device in a tunnel, the device comprising:

[0012] A data receiving module, used to receive point cloud data sent by a laser radar installed on the first vehicle after scanning the environment in the tunnel;

[0013] A contour extraction module, configured to extract contour information of a second vehicle according to curvature information of each surface corresponding to surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in the tunnel;

[0014] A relative position determination module, used to determine the position information of the second vehicle in the coordinate system of the laser radar based on the contour information;

[0015] A positioning module is used to determine the posture information of the second vehicle based on the position information of the second vehicle and the posture information of the first vehicle, wherein the posture information includes: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and the image information collected by the camera device installed on the first vehicle.

[0016] On the other hand, an embodiment of the present specification provides a laser radar-based vehicle positioning system in a tunnel, the system comprising: a first vehicle, a second vehicle and a navigation controller, the first vehicle and the second vehicle are located in a tunnel, and the first vehicle is provided with a laser radar and a camera device;

[0017] The laser radar is used to scan the environment in the tunnel to obtain point cloud data, and the camera device is used to collect image information when the first vehicle travels in the tunnel;

[0018] The navigation controller is used to determine the position and posture information of the first vehicle in a preset coordinate system based on the point cloud data and the image information, and based on the position and posture information of the first vehicle in the preset coordinate system, the above-mentioned laser radar-based in-tunnel vehicle positioning method is used to determine the position and posture information of the second vehicle in the preset coordinate system.

[0019] On the other hand, an embodiment of this specification provides an electronic device, including: a processor;

[0020] a memory for storing instructions executable by the processor;

[0021] The processor is configured to execute the instructions to implement any of the above-mentioned methods for positioning a vehicle in a tunnel based on laser radar.

[0022] On the other hand, an embodiment of the present specification provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is able to execute any of the above-mentioned laser radar-based vehicle positioning methods in a tunnel.

[0023] On the other hand, the embodiments of this specification provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the laser radar-based in-tunnel vehicle positioning method provided in the above various optional implementations.

[0024] The laser radar-based vehicle positioning method, device, system, equipment, storage medium, and computer program product provided in this application have the following technical effects:

[0025] The laser radar-based vehicle positioning method in the tunnel provided by the present application uses the laser radar set on the first vehicle to collect the point cloud data in the tunnel, and the image information collected by the camera device set on the first vehicle, and first determines the posture information of the first vehicle. Then, based on the point cloud data scanned by the laser radar, the contour information of the second vehicle in the tunnel is determined, and the position information of the second vehicle in the laser radar coordinate system is determined based on the contour information. The position information can characterize the position of the second vehicle relative to the first vehicle. Based on the posture information of the first vehicle and the position information of the second vehicle in the laser radar coordinate system, the position information of the second vehicle relative to the first vehicle can be converted into the posture information of the second vehicle in the preset coordinate system, so as to realize the positioning of the second vehicle in the tunnel. The whole process does not require the artificial setting of fixed markers, realizes the accurate and rapid positioning of the second vehicle in the tunnel, and has stronger applicability and simple operation for the positioning of multiple vehicles that need to be used in the tunnel. Based on the positioning information of the vehicle, the driving of the vehicle in the tunnel can be navigated or automatically controlled, which improves the safety of the vehicle driving in the tunnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 It is a flow chart of a method for positioning a vehicle in a tunnel based on a laser radar provided in an embodiment of the present application;

[0028] Figure 2 is a schematic diagram of a preset coordinate system in a construction scene in a tunnel in one embodiment of this specification;

[0029] Figure 3 is a schematic diagram of the principle of positioning a road roller in one embodiment of the present specification;

[0030] Figure 4 is a schematic diagram of two adjacent frames of images captured by a camera device in one embodiment of the present specification;

[0031] Figure 5 is a schematic diagram of a paver and a roller traveling in a tunnel in a scene example of this specification;

[0032] Figure 6 It is a structural schematic diagram of a laser radar-based vehicle positioning device in a tunnel provided in an embodiment of the present application;

[0033] Figure 7 is a block diagram of an electronic device for positioning a vehicle in a tunnel based on a laser radar, provided in an embodiment of the present application;

[0034] Figure 8 This is a block diagram of another electronic device for positioning a vehicle in a tunnel based on a laser radar, provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] The laser radar-based vehicle positioning method in the tunnel in the embodiment of this specification can be applied to vehicles under construction in the tunnel, or it can also be applied to vehicles traveling in the tunnel. The embodiment of this specification does not specifically limit the specific application scenario. The laser radar-based vehicle positioning method in the tunnel in the embodiment of this specification generally requires two or more vehicles in the tunnel, one of which can be used as a reference vehicle. The reference vehicle can be equipped with a laser radar and a camera device, and the laser radar is used to scan the environment in the tunnel to obtain point cloud data. At the same time, the camera device can be used to capture images of the vehicle during driving, and the reference vehicle is positioned based on the scanned point cloud data and images. The point cloud data scanned by the laser radar set on the reference vehicle is then used to identify the outline of the vehicle that needs to be positioned and navigated, and the position information of the vehicle relative to the reference vehicle is identified based on the scanned outline information. Combined with the posture information of the located reference vehicle, the posture information of the vehicle that needs to be positioned and navigated in the tunnel can be determined, thereby realizing the positioning of the vehicle in the tunnel and the navigation of the vehicle in the tunnel.

[0038] In one scenario example of this specification, the laser radar-based tunnel vehicle positioning method can be applied to the paver and roller working in the tunnel, for example, paving the road in the tunnel. A paver is a construction equipment mainly used for paving various materials on the base and surface layers of the road. A roller, also known as a soil roller, is a road repair equipment. Among engineering machinery, a roller belongs to the category of road equipment and can roll sandy, semi-viscous and cohesive soils, roadbed stabilized soil and asphalt concrete pavement layers. The roller uses the gravity of the machine itself and is suitable for various compaction operations to make the rolled layer permanently deformed and dense. Generally, when constructing in a tunnel, the paver can generally be controlled manually. In order to improve operating efficiency and reduce labor costs, the roller can be controlled automatically, which requires positioning and navigation of the roller. During construction, the paver will move forward in one direction in the direction of the road at a slow and uniform speed. After the paver unloads the material, the roller behind it compacts the road surface by rolling back and forth. In the tunnel construction environment, the high-precision navigation system cannot complete positioning due to the lack of signal. Therefore, how to locate the roller working in the tunnel to achieve navigation control of the roller in the tunnel and improve work efficiency is an important technology.

[0039] The following is an introduction to a method for positioning a vehicle in a tunnel based on a laser radar. Figure 1 It is a flow chart of a method for positioning a vehicle in a tunnel based on a laser radar provided in an embodiment of the present application. This specification provides method operation steps such as the embodiment or the flow chart, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many steps, and does not represent the only execution order. When the system or server product is executed in practice, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment). The method for positioning a vehicle in a tunnel based on a laser radar provided in the embodiment of this specification can be used in devices capable of data processing, such as controllers, computers, smart phones, tablet computers, smart wearable devices, vehicle-mounted devices or servers, and the embodiments of this specification do not make specific limitations. The data processing device can be set on the first vehicle or the second vehicle, or it can be set separately at other locations, wherein the first vehicle, the second vehicle, the laser radar, the camera device and the device for data processing can communicate data, transfer data or commands, etc. through a wireless or wired network, and the embodiments of this specification do not make specific limitations on this. Specifically, Figure 1 As shown, the vehicle positioning method in a tunnel based on laser radar may include:

[0040] S102: Receive point cloud data sent by a laser radar installed on the first vehicle after scanning the environment in the tunnel.

[0041] In the specific implementation process, the laser radar-based vehicle positioning method in the tunnel in the embodiment of this specification can be applied to the scene where there are two or more vehicles in the tunnel, wherein the first vehicle can be understood as a reference vehicle, and other vehicles can be positioned based on the posture information of the first vehicle. A laser radar can be provided on the first vehicle, and the laser radar can be used to scan the environment in the tunnel and obtain point cloud data. When applied to the road paving scene in the tunnel, the first vehicle can be a paver, and a laser radar is provided on the paver. Among them, the laser radar can be connected to a device capable of data processing, such as a controller, a computer, a server, etc., and the collected point cloud data is sent to the data processing device to facilitate the processing of the collected point cloud data. Point cloud data can be understood as a data set, each point in the data set represents a set of X, Y, Z geometric coordinates and an intensity value, and this intensity value records the intensity of the return signal according to the reflectivity of the surface of the object. When these points are combined together, a point cloud is formed, that is, a set of data points representing a three-dimensional shape or object in space. When the laser radar scans the environment in the tunnel, the reflectivity of the tunnel wall and the equipment in the tunnel is different, and point cloud data can be obtained. The point cloud data in the embodiments of this specification may include surface feature information of the tunnel wall and the equipment in the tunnel.

[0042] S104: Extracting contour information of the second vehicle according to curvature information of each surface corresponding to the surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in a tunnel.

[0043] In the specific implementation process, as described in the above embodiment, the vehicle located in the tunnel in the embodiment of this specification includes a second vehicle in addition to the first vehicle. When applied to the road paving scene in the tunnel, the second vehicle can be a roller. Generally, the roller is located behind the paver. After the paver unloads the material, the roller follows the paver to compact the material. When the laser radar set on the first vehicle scans the environment in the tunnel, it can scan the surface contour of the second vehicle located in the tunnel, and then the point cloud data obtained by the laser radar scanning contains the contour information of the second vehicle. The embodiment of this specification can process the obtained point cloud data, extract the surface point data therein, and then extract the contour information of the second vehicle based on the surface point data and the shape, size and other features of the second vehicle. The surface point data can be understood as a data set of points corresponding to each surface (plane or curved surface) in the point cloud data. The point cloud data can reflect the surface features of the scanned object, and the point cloud data belonging to a surface can be regarded as a group of surface point data. The surface corresponding to each set of surface point data has a different curvature. In this way, based on the curvature of the surface corresponding to the surface point data in the point cloud data, the surface point data matching the curvature of the contour of the second vehicle can be extracted to obtain the contour information of the second vehicle.

[0044] The contour information of the second vehicle may be understood as information that can characterize the position characteristics of the second vehicle, and may include point cloud data that can characterize the position characteristics of the second vehicle.

[0045] In some embodiments of the present specification, extracting the contour information of the second vehicle according to the curvature information of each surface corresponding to the surface point data in the point cloud data includes:

[0046] Extract surface point data from point cloud data;

[0047] Calculate the curvature of each surface in the surface point data according to the surface point data belonging to the same surface;

[0048] According to the curvature of each surface, extract the surface point data corresponding to the surface whose curvature is greater than the preset curvature, and obtain the wheel point cloud data of the second vehicle;

[0049] The contour information of the second vehicle is determined based on the wheel point cloud data of the second vehicle.

[0050] In the specific implementation process, after obtaining the point cloud data scanned by the laser radar, the surface point data therein can be extracted first, and then the curvature of the corresponding surface can be calculated based on the surface point data belonging to the same surface (plane or curved surface). Then, based on the obtained curvatures of each surface, the surface point data corresponding to the surface whose curvature is greater than the preset curvature is screened out to obtain the wheel point cloud data of the second vehicle. Among them, the value of the preset curvature can be set according to actual needs, such as: it can be set to the curvature corresponding to the wheel of the second vehicle, or slightly smaller than the curvature of the wheel of the second vehicle, or directly set to a non-zero value, so that the plane can be eliminated. The embodiment of this specification does not specifically limit the value of the preset curvature. Alternatively, the curvatures corresponding to each surface can be compared, and the surface point data of the surface whose curvature is different from that of other surfaces by more than a certain value can be screened out as the wheel point cloud data of the second vehicle. The embodiment of this specification does not specifically limit this.

[0051] Normally, the curvature of the vehicle's wheels is much greater than the curvature of the plane, while other surfaces in the tunnel are generally planes, and only the top of the tunnel may be a curved surface. However, the top is generally avoided during laser radar scanning, and the height position of the tunnel top and the vehicle wheel is also different, so it is easy to distinguish the tunnel top and the vehicle wheel. Therefore, the vehicle wheel is relatively easy to distinguish from other planes or curved surfaces in the tunnel. If the second vehicle is a press, the wheel of the roller can generally be understood as a wheel used to roll materials. Usually, the curvature characteristics of the wheel of the roller rolling materials are more obvious, and the wheel will be easier to identify. In the embodiment of this specification, the curvature of the surface point data of the point cloud data scanned by the laser radar is analyzed, so that the wheel point cloud data of the second vehicle can be accurately and quickly screened out. Then, according to the wheel point cloud data, the contour information of the second vehicle can be quickly obtained, such as: the contour represented by the vehicle point cloud data can be directly used as the contour information of the second vehicle, or the contour composed of the point cloud data within a preset range around the vehicle point cloud data can be used as the contour information of the second vehicle, or other methods are used to determine the contour information of the second vehicle, which is not specifically limited in the embodiment of this specification. The contour information of the second vehicle in this manual is mainly used to locate the position of the second vehicle in the lidar coordinate system of the first vehicle, which can also be understood as the position of the second vehicle relative to the first vehicle. The contour information does not need to be precisely matched with the actual contour of the second vehicle.

[0052] Among them, the laser radar coordinate system, that is, the coordinate system of the laser radar, can be understood as a coordinate system constructed based on the current position of the laser radar on the first vehicle. The specific construction method can be set according to actual needs, and the embodiments of this specification do not make specific limitations.

[0053] Of course, the positional relationship between the first vehicle and the second vehicle can be set to more accurately identify the contour information of the second vehicle. The specific positional relationship between the first vehicle and the second vehicle can be set according to actual needs, and this specification does not specifically limit it. For example, if the first vehicle is a paver and the second vehicle is a roller, the paver is generally in front of the roller in the direction of travel, so that the laser radar on the paver can more clearly scan the wheels of the roller, which is convenient for identifying the contour of the roller.

[0054] In some embodiments of the present specification, after extracting the surface point data corresponding to the surface whose curvature is greater than the preset curvature, the method further includes:

[0055] The extracted surface point data are screened according to the wheel size information of the second vehicle, and the point cloud data in the surface point data that meets the wheel size information of the second vehicle is used as the wheel point cloud data.

[0056] In the specific implementation process, after selecting the surface point data corresponding to the surface with a curvature greater than the preset curvature based on the curvature of the surface corresponding to each surface point data in the point cloud data, the selected surface point data can also be filtered according to the size information of the wheel of the second vehicle, such as length, width, curvature, etc., and the point cloud data in the surface point data with a high degree of matching with the wheel size information of the second vehicle is used as the wheel point cloud data. For example, when selecting the surface point data based on the preset curvature, some surface point data with a large difference in curvature from the wheel of the second vehicle may be extracted, and such data can be filtered out. If there are multiple surfaces with the same curvature as the wheel of the second vehicle, the extracted surfaces can be further screened and filtered according to the length, width, etc. of the wheel of the second vehicle, and the data with a relatively low degree of matching with the length and width of the wheel of the second vehicle can be deleted. In this way, point cloud data with a relatively high degree of matching with the wheel size of the second vehicle can be obtained, thereby improving the accuracy of the wheel point cloud data extraction of the second vehicle.

[0057] The embodiment of this specification filters the extracted point cloud data based on the wheel size of the second vehicle, which can prevent other obstacles in the tunnel with similar curvature to the vehicle wheels from being mistaken for the wheel information of the second vehicle, thereby improving the accuracy of the second vehicle's wheel information recognition, and further improving the accuracy of the second vehicle's contour recognition, laying a data foundation for the precise positioning of the second vehicle.

[0058] In some embodiments of the present specification, determining the contour information of the second vehicle according to the wheel point cloud data of the second vehicle includes:

[0059] According to the vehicle size information of the second vehicle and the wheel point cloud data of the second vehicle, contour information of the second vehicle is determined from the point cloud data.

[0060] In a specific implementation process, after extracting the wheel point cloud data of the second vehicle, the wheel contour of the second vehicle can be determined, and then based on the vehicle size information of the second vehicle, such as the positional relationship between the vehicle contour and the wheel contour, the point cloud data of a specified position near the wheel point cloud data of the second vehicle is extracted from the point cloud data scanned by the laser radar, thereby determining the contour information of the second vehicle. Wherein, when determining the contour information of the second vehicle from the point cloud data, a specified position or area can be specified on the second vehicle, and the point cloud data corresponding to the specified position or area can be screened out as the contour information of the second vehicle, and it is not necessary to extract the contour of the entire second vehicle. Wherein, the specified position or area can generally be close to the wheel of the second vehicle, such as: a road roller can set the cover surface above the road roller wheel as the specified position or area, that is, the cover surface above the road roller wheel is used as the vehicle contour of the road roller, which can improve the accuracy of determining the contour information of the second vehicle, and thus improve the accuracy of positioning the second vehicle.

[0061] The embodiment of this specification can quickly and accurately identify the contour information of the second vehicle based on the wheel point cloud data of the second vehicle and the vehicle size information of the second vehicle, thereby improving the efficiency and accuracy of data processing.

[0062] S106: Determine the position information of the second vehicle in the coordinate system of the laser radar based on the contour information.

[0063] In the specific implementation process, the determined contour information of the second vehicle is determined based on the point cloud data scanned by the laser radar set on the first vehicle. Based on the contour information, the position information of the second vehicle in the coordinate system of the laser radar (i.e., the laser radar coordinate system) can be determined. This position information can be understood as the position information of the second vehicle relative to the first vehicle. In the embodiment of this specification, the position information of the second vehicle in the laser radar coordinate system may include the position coordinates of the second vehicle in the current coordinate system of the laser radar and the angle of the contour information of the second vehicle relative to the current coordinate system of the laser radar, etc. Of course, other methods can also be used to characterize the position information of the second vehicle according to actual needs, and this specification embodiment does not make specific limitations. Among them, the center point of the contour in the contour information can be used as the position point of the second vehicle, and the position coordinates of the second vehicle in the laser radar coordinate system are calculated based on this position point.

[0064] Figure 2 is a schematic diagram of a preset coordinate system in a construction scene in a tunnel in an embodiment of this specification, such as Figure 2 As shown, Figure 2 The vehicle in the middle tunnel is a paver, which is equipped with a laser radar and a camera device (i.e., camera equipment). Figure 2 The upper and lower dotted lines in the middle are the inner walls of the tunnel. The direction of travel of the paver is set as the longitudinal direction, and the direction perpendicular to the travel direction is set as the transverse direction. Based on the characteristics of the paver construction, the screed extends to the edge of the road width in the transverse direction, and the direction of travel of the paver is parallel to the direction of road extension. Therefore, during the initial construction, the initial angle of the paver (i.e., the initial heading angle) is set to 0. At this time, the point cloud on both sides of the tunnel wall scanned by the laser radar is parallel to the Y-axis of the laser radar coordinate system. Set the coordinate in the longitudinal direction to 0; set the zero point of the transverse coordinate to the parallel line in the middle of the tunnel wall point cloud, that is, the 0 point of the transverse coordinate is at the same transverse distance from the tunnel walls on both sides. The laser radar coordinate system at the initial position of the paver (i.e., the first vehicle) can be set to the preset coordinate system.

[0065] S108. Determine the posture information of the second vehicle based on the position information of the second vehicle and the posture information of the first vehicle, the posture information including: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and the image information collected by the camera device installed on the first vehicle.

[0066] In the specific implementation process, in the embodiment of this specification, the position information of the first vehicle in the preset coordinate system can be determined based on the point cloud data collected by the laser radar on the first vehicle and the image information collected by the camera device installed on the first vehicle, and then based on the position information of the first vehicle and the position information of the second vehicle in the laser radar coordinate system, the position information of the second vehicle relative to the first vehicle can be converted into the position information of the second vehicle in the preset coordinate system, that is, the position information of the first vehicle in the tunnel is determined. In the embodiment of this specification, the position information can be understood as the position coordinates and heading angle of the first vehicle or the second vehicle in the preset coordinate system. The preset coordinate system can be set at the beginning of positioning, such as: the initial position of the first vehicle in the tunnel can be used as the coordinate origin, and the length direction of the tunnel and the width direction of the tunnel can be used as the two coordinate axes, or the laser radar coordinate system of the first vehicle at the initial position in the tunnel can be used as the preset coordinate system.

[0067] When the first vehicle and the second vehicle are traveling in a tunnel, the method described in the above embodiment can be used to calculate the position and posture information of the first vehicle and the second vehicle in the first coordinate system. Combined with the preset coordinate system, the position and travel direction of the first vehicle and the second vehicle in the tunnel can be determined, that is, the positioning of the second vehicle in the tunnel is realized. Based on the position and posture information of the second vehicle in the tunnel, the second vehicle can be controlled to travel in the tunnel, thereby providing a data basis for the subsequent navigation control of the second vehicle in the tunnel. In addition, the entire process does not require the manual setting of markers, the operation is simple, and the positioning is accurate. Of course, the movement of the first vehicle in the tunnel can also be navigated and controlled based on the position and posture information of the first vehicle.

[0068] Among them, the number of second vehicles can be determined according to actual conditions. If there are multiple second vehicles, the contour information of each second vehicle can be determined separately, and each second vehicle can be distinguished by continuous posture information, that is, the posture information of multiple vehicles currently obtained can be matched with the historical posture information, and the new posture information of each vehicle can be determined based on the continuity with the historical posture information. It can be adjusted and set according to actual conditions, and the embodiments of this specification do not make specific limitations.

[0069] The embodiment of this specification provides a method for positioning a vehicle in a tunnel based on a laser radar, which uses a laser radar set on a first vehicle to collect point cloud data in the tunnel and image information collected by a camera set on the first vehicle, and first determines the position information of the first vehicle. Then, based on the point cloud data scanned by the laser radar, the contour information of the second vehicle in the tunnel is determined, and the position information of the second vehicle in the laser radar coordinate system is determined based on the contour information, and the position information can characterize the position of the second vehicle relative to the first vehicle. Based on the position information of the first vehicle and the position information of the second vehicle in the laser radar coordinate system, the position information of the second vehicle relative to the first vehicle can be converted into the position information of the second vehicle in the preset coordinate system, thereby realizing the positioning of the second vehicle in the tunnel. The whole process does not require the manual setting of fixed markers, realizes accurate and rapid positioning of the second vehicle in the tunnel, and has stronger applicability and simple operation for positioning multiple vehicles that need to be used in the tunnel. Based on the positioning information of the vehicle, the driving of the vehicle in the tunnel can be navigated or automatically controlled, thereby improving the safety of the vehicle driving in the tunnel.

[0070] In some embodiments of this specification, determining the position and posture information of the second vehicle according to the position information of the second vehicle and the position and posture information of the first vehicle includes:

[0071] Calculate the rotation and translation matrix of the second vehicle relative to a preset coordinate system according to the posture information of the first vehicle and the position information of the second vehicle;

[0072] Based on the rotation and translation matrix, the posture information of the first vehicle and the position information of the second vehicle, the posture information of the second vehicle is determined.

[0073] In the specific implementation process, Figure 3 Schematic diagram of the principle of positioning of a road roller in one embodiment of this specification. Figure 3 As shown in the scene of road paving in the tunnel, the paver can be used as the first vehicle and the roller can be used as the second vehicle. Figure 3 As an example, how to obtain the position information of the second vehicle based on the position information of the second vehicle and the position information of the first vehicle is described. Figure 3 The midpoint O is used as the origin of the preset coordinate system. The Y axis of the coordinate system is parallel to the paver and the tunnel wall point cloud, and the X axis is perpendicular to the Y axis. At a certain moment, the paver runs to point O_paver. At this time, the position information of the paver is ((X, Y)_paver, θ). The position information of the paver can be determined based on the point cloud data scanned by the laser radar and the image data collected by the camera. Among them, (X, Y)_paver can be understood as the position coordinates of the paver in the preset coordinate system, and θ can be understood as the heading angle of the paver in the preset coordinate system. Figure 3The coordinate system corresponding to O_paver is the coordinate system of the current lidar.

[0074] Generally, during the construction process, the angle between the roller and the paver will not exceed 90°, so the laser radar on the paver can scan the complete contour point cloud of the roller. The roller point cloud can be selected from the laser radar single circle point cloud by presetting the size and other methods, so as to identify the roller. For specific methods, please refer to the method for identifying the contour information of the second vehicle in the above embodiment. In the laser radar coordinate system, that is, Figure 3 The coordinate system with O_spreader as the origin can obtain the angle α between the surface where the point cloud is located and the Y axis of the laser radar coordinate system based on the contour point cloud of the roller. According to the processing of the contour point cloud, the coordinates of the center point of the contour (that is, the coordinates of the center point of the contour in the laser radar coordinate system) can be obtained through geometric relationships, that is, (X, Y)_Road Roller IN Paver. In this way, the position coordinates (X, Y)_Road Roller IN Paver and the angle α can be used as the posture of the roller in the laser radar coordinate system (that is, the position information of the second vehicle relative to the first vehicle), hereinafter referred to as posture_Road Roller IN Paver. Among them, the position coordinates (X, Y)_Road Roller and the angle θ are hereinafter referred to as the paver posture, that is, the posture information of the paver in the preset coordinate system.

[0075] According to the heading angle θ of the paver and the angle α between the surface corresponding to the contour information of the roller and the Y-axis of the laser radar coordinate system, the heading angle β of the roller in the preset coordinate system can be calculated using geometric relationships, β = 90°-α-θ. Then, according to the posture_roller IN paver and the posture of the paver, the rotation and translation matrix R0 can be calculated. The rotation and translation matrix can characterize the transformation relationship of the position information of the second vehicle in the laser radar coordinate system to the preset coordinate system. The specific calculation method of the rotation and translation matrix can be selected according to actual needs, and the embodiments of this specification do not make specific limitations. Based on this conversion relationship, according to the rotation and translation matrix R0 and the posture_roller IN paver, the posture information of the roller in the preset coordinate system with O as the origin can be calculated, that is, O_roller. The specific calculation method depends on the actual situation and is not specifically limited in the embodiments of this specification.

[0076] The embodiment of this specification is based on the position information of the first vehicle and the position relationship between the second vehicle and the first vehicle. The rotation and translation matrix of the second vehicle in the laser radar coordinate system of the first vehicle is first calculated to convert the position of the second vehicle to the preset coordinate system, and then the position information of the second vehicle in the laser radar coordinate system of the first vehicle is converted to the preset coordinate system based on the rotation and translation matrix to obtain the position information of the second vehicle in the preset coordinate system. The purpose of using the position of the first vehicle to locate the second vehicle is achieved, and then the second vehicle can be controlled or navigated in the tunnel based on the obtained position information, without the need to set up too many additional fixed markers, the method is simple, and the data processing speed is fast.

[0077] In some embodiments of this specification, a method for determining the position and posture information of the first vehicle includes:

[0078] Determine the lateral displacement and heading angle of the first vehicle in a preset coordinate system according to the point cloud data;

[0079] Determining the longitudinal displacement of the first vehicle based on two adjacent frames of image information collected by a camera on the first vehicle;

[0080] Based on the lateral displacement, the longitudinal displacement and the heading angle, the position information of the first vehicle is determined.

[0081] In a specific implementation process, the first vehicle may be laterally positioned based on the point cloud data obtained by laser radar scanning, such as Figure 2 As shown in the figure, at the initial position, the laser radar coordinate system of the first vehicle can be used as the initial coordinate system. In addition, at the initial position, the 0 point of the lateral coordinate of the first vehicle is at an equal lateral distance from the tunnel walls on both sides. The vertical distance of the laser radar relative to the left and right boundaries of the tunnel at any time can be obtained based on the point cloud data scanned by the laser radar. According to the zero point in the lateral direction of the preset coordinate system, combined with the vertical distance relative to the left and right boundaries of the tunnel, it can be converted into Figure 2 The lateral displacement △X shown. For example: Taking the first vehicle in the above scenario as a paver as an example, at any time, according to the pre-set initial angle of the paver is 0, and in the laser radar coordinate system, the point clouds of the left and right tunnel walls are parallel to the Y axis. When the angle of the paver changes during driving, the angle between the parallel line in the middle of the tunnel wall point cloud and the Y axis of the laser radar coordinate system can be used as the lateral direction angle of the current laser radar. The angle from the axis of the paver to the middle line of the tunnel wall point cloud can be set, clockwise is positive, counterclockwise is negative, that is, corresponding to Figure 2 In summary, through the point cloud data of the laser radar on the paver, the lateral displacement of the paver at any time and the angle change relative to the center line of the tunnel wall point cloud, that is, the heading angle of the paver, can be calculated.

[0082] After the paving machine, i.e., the first vehicle, is positioned laterally, the paving machine (i.e., the first vehicle) can be positioned longitudinally using the images captured by the camera device installed on the paving machine to determine the longitudinal displacement of the paving machine. Figure 2 As shown, the number of camera devices, i.e., camera means, can be set according to actual needs, and can be set to 1, 2, 3 or more, and this specification does not specifically limit this. The horizontal direction in the specification embodiment can be understood as perpendicular to the length direction of the tunnel, and the longitudinal direction can be understood as the length direction of the tunnel, which is usually also the direction of travel of the vehicle. When performing longitudinal positioning, the longitudinal displacement of the first vehicle can be determined based on the displacement of two adjacent frames of image information in the image information captured by the camera device during the movement of the first vehicle.

[0083] In some embodiments of the present specification, determining the longitudinal displacement of the first vehicle according to two adjacent frames of image information collected by a camera on the first vehicle includes:

[0084] Calculate the displacement of any two adjacent frames of image information;

[0085] The longitudinal displacement of the first vehicle is determined based on the displacement of each of two adjacent frames of image information in the image information.

[0086] In the specific implementation process, Figure 4 is a schematic diagram of two adjacent frames of images captured by a camera device in one embodiment of this specification, such as Figure 4 As shown in the figure, based on the tunnel construction environment, the tunnel walls are mostly rough cement walls. Based on the subtle wall texture features and combined with the front and back frame matching of the camera equipment, an image incremental odometer can be realized. Figure 4 As shown, taking a paver as the first vehicle as an example, when the paver moves in the longitudinal direction, the camera device located on the screed plate will also move accordingly. Assuming that the image captured by the camera device at time T1 is frame 1, and the image captured by the camera device at time T2 is frame 2, relative to frame 1, frame 2 contains the common part with frame 1 and the newly added part. Figure 4 The middle rectangular box can be understood as the common part of frame 1 and frame 2, and the rightmost rectangular box can be understood as the newly added part of frame 2 relative to frame 1. By matching the same part of the latter frame with the previous frame, the same part of the tunnel wall texture can be represented as the same position. Combined with the distance information reflected by the camera pixel point, the movement increment of the paver, that is, the longitudinal displacement, can be calculated. The solution is simple and does not require additional fixed markers to achieve the longitudinal positioning of the vehicle. For example: If pixel A in frame 1 and pixel B in frame 2 correspond to the same position in the tunnel, based on the position of pixel A in frame 1 and the position of pixel B in frame 2, the displacement of frame 2 relative to frame 1 can be calculated, and then the displacement of the image can be converted into the movement increment of the vehicle.

[0087] In the embodiments of this specification, based on the changes in the previous and next frames, the displacement and rotation between the two frames can be calculated by the phase correlation method, and then the displacement of the paver can be obtained by integrating the displacement of multiple frames. Among them, the phase correlation method can be understood as a method that can calculate the offset and rotation angle of two images. In addition, in the embodiments of this specification, the camera equipment is generally set at both ends of the screed of the paver. Since the camera is always perpendicular to the road surface, it will not rotate. In addition, due to the height changes of the road surface, the increment along the driving direction of the paver can be extracted as the integral unit for the displacement obtained, thereby obtaining the longitudinal increment of the paver, that is, Figure 2 The longitudinal increment △Y shown is the longitudinal displacement of the paver.

[0088] Based on the lateral displacement and heading angle determined by the lateral positioning, and the longitudinal displacement determined by the longitudinal positioning, the complete position information of the first vehicle in the tunnel can be obtained. Then, based on the position information of the first vehicle, the position information of the second vehicle in the tunnel can be determined. Based on the position information, the positioning and navigation control of the second vehicle and the first vehicle in the tunnel can be realized.

[0089] The embodiment of this specification uses the laser radar installed on the first vehicle to scan the environment in the tunnel to obtain point cloud data to achieve the lateral positioning of the first vehicle. Combined with the image information collected by the camera installed on the first vehicle, the longitudinal displacement of the first vehicle is determined based on the displacement of two adjacent frames of images through the texture features of the tunnel wall to achieve the longitudinal positioning of the first vehicle. The first vehicle can be positioned in the tunnel by using multi-sensor fusion. There is no need to set up multiple fixed markers to achieve the positioning of the vehicle in the tunnel. In addition, based on the posture information of the first vehicle, the second vehicle in the tunnel can be positioned. The solution is simple and the positioning is accurate.

[0090] Figure 5 This is a schematic diagram of a paver and a roller moving in a tunnel in a scene example of this specification. Figure 5 The following describes a method for positioning a vehicle in a tunnel based on a laser radar in an embodiment of the present specification:

[0091] During the construction process, rollers 1, 2, and 3 are responsible for rolling two lanes respectively, and there are three basic actions: lane change action; forward action; backward action. A single task can be a combination of single or multiple basic actions. The paver travels in one direction and can calculate its own posture in real time. For details, please refer to the lateral positioning and longitudinal positioning process of the first vehicle in the above embodiment, which will not be repeated here. In the initial state, the corresponding posture point is set to the roller as the initial value through the initialization process. Afterwards, the roller can obtain its own posture in real time through the network transmission equipment according to the laser radar installed on the paver, so as to navigate.

[0092] When determining the roller's posture based on the paver's posture, it is necessary to identify the roller's contour information based on the laser radar on the paver. The specific process can be referred to as follows:

[0093] In general, due to the characteristics of paver and roller construction, during the construction process, the front of the roller is facing the direction of the paver. Even when the roller is changing lanes, the angle between its front and the direction of the paver will not exceed 90 degrees. Based on this feature, the laser radar mounted on the paver can completely scan the front profile of the roller. Based on the relatively stable working conditions of tunnel construction, the objects scanned by the laser radar in a single circle include rollers, tunnel walls, construction personnel, small construction tools and other objects. The roller profile determination process includes:

[0094] 1) For the single-circle point cloud data obtained by laser radar scanning, the corner points and surface points are first extracted;

[0095] 2) Based on the above features of the front face of the roller, the wheel information of the roller can be extracted according to the curvature of the face;

[0096] 3) According to the size of the roller, the extracted surfaces that meet the curvature requirements can be filtered once;

[0097] 4) Combined with the surface point information that meets the requirements, the rectangular contour information on the roller can be found according to the surrounding surface points, which can be the cover surface above the wheels of the roller;

[0098] 5) Based on the screened cover surface, the contour feature of the regular rectangle of the roller can be obtained, that is, the matrix rectangular contour of the cover surface;

[0099] 6) Based on the rectangular contour feature of the rule, its center point can be calculated as the roller position point through geometric relationship;

[0100] 7) Based on the regular rectangular contour feature, the angle relationship between the surface where the part of the point cloud is located and the coordinate axis of the laser radar coordinate system can be obtained. Combined with the position point, the position information of the roller relative to the paver can be obtained.

[0101] After determining the position information of the roller relative to the paver, the posture information of the roller in the preset coordinate system can be obtained by referring to the records of the above embodiment, thereby realizing the positioning of the roller, and the movement of the roller in the tunnel can be controlled or navigated based on the posture information.

[0102] In addition, the laser radar carried on the paver can distinguish point cloud features such as tunnel walls and rollers from the tunnel environment. At the same time, it can know the coordinates of the corresponding feature objects based on its own positioning and the laser radar scanning point cloud. Through the network transmission equipment, it can remind the roller whether it is too close to the tunnel wall or other rollers, thereby playing the role of obstacle avoidance.

[0103] like Figure 5 As shown, there can be multiple rollers. When there are multiple rollers, the rollers can be distinguished by continuous posture information. Since the rollers are responsible for rolling different areas during the construction process, the corresponding number of postures can be obtained according to the paver positioning and lidar scanning data in the continuous process. Therefore, they can be matched according to the historical postures, and different rollers can obtain the correct updated postures.

[0104] In the embodiments of this specification, the characteristics of tunnel paver and roller construction are combined to provide high-precision lateral positioning of the paver through the characteristics of the tunnel wall; through the texture characteristics of the tunnel wall, combined with the camera device, the paver is provided with high-precision longitudinal positioning in the form of an image odometer, and the high-precision positioning of the paver is obtained through multi-sensor fusion. For the roller, the external contour of the roller is identified through the laser radar installed on the paver, and the position of the roller in the local coordinate system of the laser radar carried by the paver is obtained. Combined with the paver position obtained by the above multi-sensor fusion, the current position of the roller in the global coordinate system is calculated, thereby realizing the navigation of the roller.

[0105] The vehicle navigation in the tunnel provided in the embodiment of this specification, through lateral positioning combined with texture image navigation, can ensure positioning accuracy without using artificial markers such as targets, and locate the roller through the laser radar on the paver, thereby reducing the number of equipment, simplifying the vehicle navigation solution in the tunnel, and realizing accurate and rapid positioning of vehicles in the tunnel.

[0106] Based on the above-mentioned method for positioning a vehicle in a tunnel based on a laser radar, one or more embodiments of this specification also provide a client and a server for positioning a vehicle in a tunnel based on a laser radar. The client and the server may include a device (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0107] It can be seen from the technical solutions provided in the above embodiments of this specification that the embodiments of this specification also provide a vehicle positioning device in a tunnel based on laser radar. Figure 6 is a schematic diagram of the structure of a vehicle positioning device in a tunnel based on a laser radar provided in an embodiment of the present application, such as Figure 6 As shown, the above device comprises:

[0108] The data receiving module 610 is used to receive the point cloud data sent by the laser radar installed on the first vehicle after scanning the environment in the tunnel;

[0109] A contour extraction module 620, configured to extract contour information of a second vehicle according to curvature information of each surface corresponding to the surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in the tunnel;

[0110] A relative position determination module 630, configured to determine the position information of the second vehicle in the coordinate system of the laser radar based on the profile information;

[0111] The positioning module 640 is used to determine the posture information of the second vehicle based on the position information of the second vehicle and the posture information of the first vehicle, wherein the posture information includes: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and the image information collected by the camera device installed on the first vehicle.

[0112] In some embodiments of the present specification, a laser radar-based vehicle positioning system in a tunnel is also provided, the system comprising: a first vehicle, a second vehicle and a navigation controller, the first vehicle and the second vehicle are located in a tunnel, and the first vehicle is provided with a laser radar and a camera device;

[0113] The laser radar is used to scan the environment in the tunnel to obtain point cloud data, and the camera device is used to collect image information when the first vehicle travels in the tunnel;

[0114] The navigation controller is used to determine the position and posture information of the first vehicle in the preset coordinate system based on the point cloud data and the image information, and based on the position and posture information of the first vehicle in the preset coordinate system, the position and posture information of the second vehicle in the preset coordinate system is determined using the method described in the above embodiment.

[0115] Among them, the specific process of determining the position and posture information of the first vehicle in the preset coordinate system and the position and posture information of the second vehicle in the preset coordinate system can be found in the records of the above embodiments and will not be repeated here.

[0116] As described in the above embodiments, in a scenario example of the present specification, the first vehicle may be a paver, and the second vehicle may be a road roller. The paver is provided with a laser radar and a camera device, and data communication can be performed between the various devices through a wireless network to realize the positioning and navigation of the paver and the road roller in the tunnel.

[0117] Regarding the device and system in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be described in detail here. The device in the above embodiment may also include other implementation methods according to the description of the method embodiment, and the specific implementation method can refer to the description of the relevant method embodiment, which will not be repeated here.

[0118] Figure 7 is a block diagram of an electronic device for positioning a vehicle in a tunnel based on a laser radar provided in an embodiment of the present application. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for positioning a vehicle in a tunnel based on a laser radar is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0119] Figure 8 is a block diagram of another electronic device for positioning a vehicle in a tunnel based on a laser radar provided in an embodiment of the present application. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for positioning a vehicle in a tunnel based on a laser radar is implemented.

[0120] Those skilled in the art will understand that Figure 7 or Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] In an exemplary embodiment, an electronic device is also provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a laser radar-based in-tunnel vehicle positioning method as in the embodiment of the present disclosure.

[0122] In an exemplary embodiment, a computer-readable storage medium is also provided. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the laser radar-based in-tunnel vehicle positioning method in the embodiment of the present disclosure.

[0123] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the laser radar-based in-tunnel vehicle positioning method provided in the above-mentioned various optional implementations.

[0124] It is understandable that in the specific implementation of this application, user-related data is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0125] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0126] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0127] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for positioning a vehicle in a tunnel based on laser radar, characterized in that: The method comprises: receiving point cloud data sent by a laser radar disposed on the first vehicle after scanning the environment in the tunnel; Extracting contour information of a second vehicle according to curvature information of each surface corresponding to the surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in the tunnel; Determine the position information of the second vehicle in the coordinate system of the laser radar based on the contour information; The posture information of the second vehicle is determined based on the position information of the second vehicle and the posture information of the first vehicle, and the posture information includes: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and image information collected by a camera device installed on the first vehicle.

2. The method according to claim 1, characterized in that The extracting the contour information of the second vehicle according to the curvature information of each surface corresponding to the surface point data in the point cloud data includes: Extracting surface point data from the point cloud data; Calculating the curvature of each surface in the surface point data according to the surface point data belonging to the same surface; According to the curvature of each surface, extracting surface point data corresponding to the surface whose curvature is greater than a preset curvature, to obtain wheel point cloud data of the second vehicle; The contour information of the second vehicle is determined based on the wheel point cloud data of the second vehicle.

3. The method according to claim 2, characterized in that After extracting the surface point data corresponding to the surface whose curvature is greater than the preset curvature, the method further includes: The extracted surface point data are screened according to the wheel size information of the second vehicle, and the point cloud data in the surface point data that conforms to the wheel size information of the second vehicle is used as the wheel point cloud data.

4. The method according to claim 2, characterized in that: Determining contour information of the second vehicle according to the wheel point cloud data of the second vehicle includes: According to the vehicle size information of the second vehicle and the wheel point cloud data of the second vehicle, the contour information of the second vehicle is determined from the point cloud data.

5. The method according to claim 1, characterized in that The determining the position information of the second vehicle according to the position information of the second vehicle and the position information of the first vehicle includes: Calculating a rotation and translation matrix of the second vehicle relative to the preset coordinate system according to the posture information of the first vehicle and the position information of the second vehicle; Based on the rotation and translation matrix and the position information of the second vehicle, the position information of the second vehicle is determined.

6. The method according to claim 1, characterized in that The method for determining the position information of the first vehicle includes: Determine the lateral displacement and heading angle of the first vehicle in the preset coordinate system according to the point cloud data; Determining the longitudinal displacement of the first vehicle based on two adjacent frames of image information collected by a camera on the first vehicle; Based on the lateral displacement, the longitudinal displacement and the heading angle, position information of the first vehicle is determined.

7. The method according to claim 6, characterized in that The determining the longitudinal displacement of the first vehicle according to two adjacent frames of image information collected by a camera device on the first vehicle includes: Calculating the displacement of any two adjacent frames of image information in the image information; The longitudinal displacement of the first vehicle is determined based on the displacement of each of two adjacent frames of image information in the image information.

8. A vehicle positioning device in a tunnel based on laser radar, characterized in that: The device comprises: A data receiving module, used to receive point cloud data sent by a laser radar installed on the first vehicle after scanning the environment in the tunnel; A contour extraction module, configured to extract contour information of a second vehicle according to curvature information of each surface corresponding to surface point data in the point cloud data; wherein the first vehicle and the second vehicle are located in the tunnel; A relative position determination module, used to determine the position information of the second vehicle in the coordinate system of the laser radar based on the contour information; A positioning module is used to determine the posture information of the second vehicle based on the position information of the second vehicle and the posture information of the first vehicle, wherein the posture information includes: the position coordinates and heading angle of the first vehicle or the second vehicle in a preset coordinate system; wherein the posture information of the first vehicle is determined based on the point cloud data and the image information collected by the camera device installed on the first vehicle.

9. A laser radar-based vehicle positioning system in a tunnel, characterized in that: The system comprises: a first vehicle, a second vehicle and a navigation controller, the first vehicle and the second vehicle are located in a tunnel, and the first vehicle is provided with a laser radar and a camera device; The laser radar is used to scan the environment in the tunnel to obtain point cloud data, and the camera device is used to collect image information when the first vehicle travels in the tunnel; The navigation controller is used to determine the position and posture information of the first vehicle in a preset coordinate system based on the point cloud data and the image information, and based on the position and posture information of the first vehicle in the preset coordinate system, the laser radar-based in-tunnel vehicle positioning method as described in any one of claims 1 to 7 is used to determine the position and posture information of the second vehicle in the preset coordinate system.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the laser radar-based in-tunnel vehicle positioning method as described in any one of claims 1 to 7.

Images