A method and device for positioning a movable device and a movable device

Abstract

The present application provides a positioning method, device and movable device for a movable device, and relates to the field of autonomous driving technology. The method includes: obtaining laser point cloud data of a preset area above the movable device; extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to preset rules; matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining the position information of the movable device according to the transformation matrix. By performing the above processing, the present invention can solve the problem in the related art that the movable device cannot be accurately positioned when the GNSS signal is affected and the laser point cloud data in front cannot be accurately obtained; at the same time, since the point cloud data above the movable device is collected, it will not be affected by temporary obstacles during use.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a positioning method and device for a movable device and the movable device. Background Art

[0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] Mobile devices refer to devices such as vehicles, drones, and intelligent robots that can travel on a preset path. In the field of autonomous driving technology, in order to ensure the accurate operation of autonomous driving vehicles, drones, and intelligent robots, it is generally necessary to accurately locate these mobile devices. Currently, there are many ways to locate, such as using GNSS sensors (Global Navigation Satellite System) and machine vision sensors (cameras, lidar, millimeter wave radar, ultrasonic radar) on mobile devices, or communicating with external base stations for positioning.

[0004] Generally, GNSS sensors are used for positioning in areas with good satellite signals. However, if during autonomous driving, a mobile device moves from an area with good satellite signal quality to an area with poor satellite signal quality, the accuracy of GNSS positioning will be greatly reduced, and the accuracy of positioning of the mobile device will be greatly reduced, making it impossible to guarantee the accuracy of positioning of the mobile device. Summary of the invention

[0005] The embodiments of the present application provide a positioning method and apparatus for a movable device and a movable device to solve the problem of accurately positioning the movable device in an area with poor satellite signal quality.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] On the one hand, an embodiment of the present application provides a positioning method for a movable device, wherein the movable device travels in a tunnel with a bilaterally symmetrical cross-section, comprising:

[0008] Acquire laser point cloud data of a preset area above the movable device;

[0009] Extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule;

[0010] The first type of point cloud and the second type of point cloud are matched to obtain a transformation matrix, and the position and posture information of the movable device is determined according to the transformation matrix.

[0011] On the other hand, an embodiment of the present invention provides a positioning device for a movable device, wherein the movable device travels in a tunnel with a bilaterally symmetrical cross section, comprising:

[0012] A laser point cloud acquisition module, used to acquire laser point cloud data of a preset area above the movable device;

[0013] A point cloud extraction module, used for extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule;

[0014] The point cloud matching module is used to match the first type of point cloud with the second type of point cloud to obtain a transformation matrix, and determine the posture information of the movable device according to the transformation matrix.

[0015] On the other hand, an embodiment of the present invention provides a movable device, wherein the movable device includes the positioning device of the movable device as described above, and the positioning device of the movable device is used to implement the positioning method of the movable device as described above.

[0016] On the other hand, an embodiment of the present invention provides a server, which includes the positioning device of the movable device mentioned above, and the positioning device of the movable device is used to implement the positioning method of the movable device as mentioned above.

[0017] On the other hand, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the positioning method of a movable device as described above is implemented.

[0018] On the other hand, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the positioning method for a movable device as described above is implemented.

[0019] According to the technical solution provided by the embodiment of the present invention, by acquiring the laser point cloud data of the preset area above the movable device, the laser point cloud data is extracted into the first type of point cloud and the second type of point cloud located on the left and right sides of the movable device respectively according to the preset rules, and the first type of point cloud and the second type of point cloud are matched to obtain the transformation matrix, and then the posture information of the movable device is determined according to the transformation matrix. By performing the above processing, the solution of the present invention can solve the problem in the related technology that the movable device cannot be accurately positioned when the GNSS signal is affected and the laser point cloud data in front cannot be accurately obtained; at the same time, because the point cloud data above the movable device is collected, it will not be affected by temporary obstacles when in use. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings 8 in the following description are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 A schematic diagram of the structure of a positioning device for a movable device provided in an embodiment of the present application;

[0022] Figure 2a to 2c They are respectively schematic diagrams of tunnel cross-sections provided in the embodiments of the present application;

[0023] Figure 3 A schematic diagram of the structure of a mobile device provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of a flow chart of a method for positioning a movable device provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of a laser radar scanning surface and a movable device provided in an embodiment of the present application;

[0026] Figure 6a-6c A schematic diagram of point cloud sampling above a movable device provided in an embodiment of the present application;

[0027] Figure 7 A schematic flow chart of a method for dividing a point cloud above a movable device provided in an embodiment of the present application;

[0028] Figure 8 A schematic diagram of a process flow of a point cloud matching method provided in an embodiment of the present application;

[0029] Fig. 9 A schematic diagram of a flow chart of a yaw angle calculation method provided in an embodiment of the present application;

[0030] Fig.10a A schematic diagram of a plane projection for preprocessing a point cloud provided in an embodiment of the present application;

[0031] Fig.10b A schematic diagram of a plane projection for matching point clouds provided in an embodiment of the present application;

[0032] Fig.11 A schematic diagram of extracting a point cloud for straight line fitting provided in an embodiment of the present application;

[0033] Fig.12 A schematic diagram of the geometric relationship during yaw angle calculation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] 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 creative work are within the scope of protection of this application.

[0035] It is worth noting that the term "mobile device" is widely interpreted in this application as including any mobile object, including, for example, aircraft, ships, spacecraft, cars, trucks, vans, semi-trailers, motorcycles, golf carts, off-road vehicles, warehouse transport vehicles or agricultural vehicles and mobile devices running on tracks, such as trams or trains and other rail vehicles. The "mobile device" in this application can generally include: a power system, a sensor system, a control system, peripheral equipment and a computer system. In other embodiments, the mobile device may include more, fewer or different systems.

[0036] Based on the above-described movable device, for example, an unmanned vehicle is also equipped with a sensor system and an unmanned driving control device.

[0037] The sensor system may include a plurality of sensors for sensing information about the environment in which the movable device is located, and one or more actuators for changing the position and / or orientation of the sensors. The sensor system may include any combination of sensors such as a global positioning system sensor, an inertial measurement unit, a radio detection and ranging (RADAR) unit, a camera, a laser rangefinder, a light detection and ranging (LIDAR) unit, and / or an acoustic sensor; the sensor system may also include sensors for monitoring the internal systems of the movable device (e.g., an O2 monitor, a fuel gauge, an engine temperature gauge, etc.).

[0038] The unmanned driving control device may include a processor and a memory, wherein at least one machine executable instruction is stored in the memory, and the processor executes at least one machine executable instruction to implement functions including a map engine, a positioning module, a perception module, a navigation or path module, and an automatic control module. The map engine and the positioning module are used to provide map information and positioning information. The perception module is used to perceive things in the environment where the mobile device is located according to the information obtained by the sensor system and the map information provided by the map engine. The navigation or path module is used to plan a driving path for the mobile device according to the processing results of the map engine, the positioning module and the perception module. The automatic control module converts the decision information input of the navigation or path module and other modules into a control command output for the control system of the mobile device, and sends the control command to the corresponding component in the control system of the mobile device through the vehicle network (for example, the internal electronic network system of the mobile device realized by the CAN bus, the local area interconnection network, the multimedia directional system transmission, etc.), so as to realize automatic control of the mobile device; the automatic control module can also obtain information of each component in the mobile device through the vehicle network.

[0039] In order to enable those skilled in the art to better understand the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0040] GPS: Global Positioning System.

[0041] GNSS: Global Navigation Satellite System.

[0042] IMU: Inertial Measurement Unit.

[0043] ICP: Iterative Closest Point, iterative closest point algorithm, a point cloud matching algorithm.

[0044] NDT: Normal Distributions Transform, a point cloud matching algorithm.

[0045] UWB: Ultra-wideband, an unlimited carrier communication technology.

[0046] Pose is a general term for position and posture, which includes 6 degrees of freedom, including 3 position degrees of freedom and 3 orientation degrees of freedom. The 3 orientation degrees of freedom are usually represented by pitch, roll, and yaw. In this application, since mobile equipment generally travels on a horizontal road, only the yaw angle can be considered.

[0047] In order to enable those skilled in the art to better understand the present application, the application environment involved in the present application is described below. For example, the present application can be applied to the positioning of autonomous driving vehicles in semi-enclosed environments such as tunnels and underground garages. The above are only individual application examples in the present application. It should be noted that under the guidance of the embodiments of the present application, those skilled in the art can also provide more application examples as needed, and the present application is not limited to these application examples.

[0048] In the process of implementing the embodiments of the present application, the inventors found that in scenarios such as tunnels where GNSS signals are affected, positioning is usually achieved by integrating inertial combined navigation data, lidar data and high-precision map data, and fusion of multiple data. However, the high-precision map does not contain information on temporary obstacles such as other social vehicles, pedestrians, non-motor vehicles, etc., and the laser point cloud collected in real time by the mobile device contains these temporary obstacle point clouds, which are difficult to filter. In addition, if the traffic volume is large and the autonomous driving vehicle is close to the vehicle in front, the image of the effective sign of the road ahead and the lidar point cloud cannot be obtained (such as the image and point cloud of the road lane line cannot be obtained) because of the problem of obstruction of sensors, etc., making it impossible for the sensor-based positioning algorithm to work, which will cause the positioning of the autonomous driving vehicle to fail.

[0049] In view of the above problems, the embodiments of the present application provide a positioning solution for a movable device. In this solution, the positioning device of the movable device can obtain laser point cloud data of a certain area above the movable device, extract the laser point cloud data according to preset rules, obtain point clouds on the left and right sides of the movable device respectively, further match the two types of point clouds, obtain a transformation matrix, and determine the position information of the movable device according to the transformation matrix. Therefore, the technical solution provided by the embodiments of the present application can solve the problem in the related technology that the movable device cannot be accurately positioned when the GNSS signal is affected and the laser point cloud data in front cannot be accurately obtained; at the same time, because the point cloud data above the movable device is collected, it will not be affected by temporary obstacles during use, and there is no need to build a high-precision map in advance.

[0050] Some embodiments of the present application provide a positioning solution for a mobile device. In order to achieve a reliable positioning method for a mobile device, in one embodiment, Figure 1As shown, a positioning device for a movable device is provided, wherein the movable device travels in a tunnel with a left-right symmetrical cross section, and the positioning device for the movable device comprises:

[0051] The laser point cloud acquisition module 11 is used to acquire laser point cloud data of a preset area above the movable device;

[0052] A point cloud extraction module 12, used for extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule;

[0053] The point cloud matching module 13 is used to match the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determine the posture information of the movable device according to the transformation matrix.

[0054] In specific implementation, the solution provided in this application does not restrict the shape of the tunnel, as long as the cross section is bilaterally symmetrical. Figure 2a to 2c Several tunnel cross-section diagrams are shown, but it should be noted that the diagrams do not constitute any limitation to the solutions of the present invention.

[0055] In one embodiment, if Figure 3 As shown, the embodiment of the present application also provides a movable device 102. The movable device is an autonomous driving vehicle or an intelligent robot that moves in a tunnel. The movable device 102 includes a positioning device 101 of the movable device. In addition, a variety of sensors can be set on the movable device 102. For example, the multiple sensors include any combination of GNSS sensors 104, UWB tags 105, IMU sensors 106, laser radar sensors 107, millimeter wave radar sensors 108, ultrasonic radar sensors 109 and cameras 110. For the convenience of description, the movable device 102 can be provided with each of the above multiple sensors. The positioning device 101 of the movable device can be a vehicle-mounted server, a vehicle-mounted computer and other devices on the movable device 102, which is not limited here.

[0056] In one embodiment, if Figure 4 As shown, the positioning device of the present application can provide a positioning method for the above-mentioned movable device, wherein the movable device travels in a tunnel with a left-right symmetrical cross section, and specifically comprises the following steps:

[0057] Step 201, obtaining laser point cloud data of a preset area above the movable device;

[0058] Step 203: extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule;

[0059] Step 205: Match the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determine the position and posture information of the movable device according to the transformation matrix.

[0060] In one embodiment, if Figure 5 As shown, a schematic diagram showing the scanning plane formed by the laser radar installed on the movable device when working and the intersection of the movable device is shown. In a specific implementation, the laser radar is set on the movable device 102, and its scanning plane will form a certain angle θ with the driving plane of the movable device, so that the laser radar can detect the top of the tunnel when working, thereby obtaining the laser point cloud data above the tunnel. θ is preferably an angle of 90 degrees, and the specific installation method is not limited here.

[0061] In one embodiment, in step 201, laser point cloud data of a preset area above the movable device is obtained. Specifically, laser point cloud data of a preset area on the top of the tunnel above the movable device can be obtained by a laser radar. By selecting a reference point of the movable device, a preset distance area (such as a preset distance area in front of the reference point tunnel) is further selected in a specific scenario. Figure 6a As shown), the preset distance area behind the reference point tunnel (as shown Figure 6b as shown) or the preset distance area before and after the reference point tunnel (as shown Figure 6c ) as the laser point cloud sampling area, thereby obtaining the laser point cloud data of the sampling area.

[0062] In one embodiment, if Figure 7 As shown, in the above step 203, the laser point cloud data is extracted according to a preset rule into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively, which can be implemented in the following manner:

[0063] Step 203a, obtaining the reference point coordinates of the reference point of the movable device in the preset coordinate system and the coordinates of each point cloud in the laser point cloud data;

[0064] Step 203b: according to the reference point coordinates and the coordinates of each point cloud, classify the point cloud corresponding to each point cloud coordinate into a first type of point cloud or a second type of point cloud.

[0065] For example, in one embodiment of the present application, the IMU coordinate system of the movable device can be used as a preset coordinate system, wherein the preset coordinate system includes an X-axis, a Y-axis, and a Z-axis, wherein the X-axis is the lateral direction of the movable device (for example, taking a vehicle as an example, the X-axis points to the right direction of the vehicle), the Y-axis is the longitudinal direction of the movable device (for example, taking a vehicle as an example, the Y-axis points to the front direction of the vehicle), and the Z-axis is perpendicular to the plane where the X-axis and the Y-axis are located (for example, taking a vehicle as an example, the Z-axis points to the top direction of the vehicle), thereby obtaining the reference point coordinates (0, 0, 0) of the reference point of the movable device in the preset coordinate system and the coordinates of each point cloud in the laser point cloud data, and dividing the point cloud corresponding to each point cloud coordinate into the first type of point cloud or the second type of point cloud according to the reference point coordinates and the coordinates of each point cloud. Further, for example, the point cloud whose coordinates satisfy x≥0 can be regarded as the first type of point cloud, and the point cloud whose coordinates satisfy x<0 can be regarded as the second type of point cloud. It should be noted that using the IMU coordinate system as the preset coordinate system here and in the following text is only one implementation method of the present application. It is only for the convenience of description here and does not constitute any limitation to the scheme of the present invention.

[0066] In one embodiment, if Figure 8 As shown, in the above step 205, the first type of point cloud and the second type of point cloud are matched to obtain a transformation matrix, and the posture information of the movable device is determined according to the transformation matrix, which can be done in the following way:

[0067] Step 205a, obtaining the number of points of the first type of point cloud and the second type of point cloud, and determining a type of point cloud with a larger number of points and another type of point cloud with a smaller number of points;

[0068] Step 205b, pre-processing another type of point cloud with a small number of point clouds to form a point cloud to be matched;

[0069] Step 205c: Match the point cloud to be matched with a type of point cloud with a large number of point clouds by using a preset registration algorithm to obtain a transformation matrix;

[0070] Step 205d: Determine the lateral position and yaw angle of the movable device according to the transformation matrix.

[0071] For example, after the point cloud is divided according to the reference point coordinates and the point cloud coordinates, the number of point clouds of the first type and the second type is further determined. When it is assumed that the number of point clouds of the first type is small, the first type of point cloud with fewer point clouds is preprocessed and matched to the second type of point cloud with more point clouds to obtain a transformation matrix. The position information of the movable device can be determined based on the transformation matrix. The position information includes the lateral position (or lateral displacement) of the movable device relative to the central axis of the tunnel ground and the yaw angle of the movable device.

[0072] In one embodiment, the number of point clouds of the first type of point cloud and the second type of point cloud is obtained in step 205a. Specifically, the point clouds can be counted through various open source or non-open source commercial software, or by developing a point cloud quantity statistics module independently. No limitation is imposed on the specific implementation method herein.

[0073] In one embodiment, step 205b preprocesses the other type of point cloud with a small number of point clouds to form a point cloud to be matched, which can be implemented as follows: the other type of point cloud with a small number of point clouds is rotated 180 degrees around the Z axis of the preset coordinate system to form a point cloud to be matched; wherein the preset coordinate system includes an X-axis, a Y-axis and a Z-axis, the X-axis is the lateral direction of the movable device (for example, taking a vehicle as an example, the X-axis points to the right direction of the vehicle), the Y-axis is the longitudinal direction of the movable device (for example, taking a vehicle as an example, the Y-axis points to the front direction of the vehicle), and the Z-axis is perpendicular to the plane where the X-axis and the Y-axis are located (for example, taking a vehicle as an example, the Z-axis points to the upper direction of the vehicle).

[0074] In one embodiment, step 205c matches the point cloud to be matched with a class of point clouds with a large number of point clouds through a preset alignment algorithm to obtain a transformation matrix, which can be implemented as follows: the point cloud to be matched obtained after the preprocessing is matched with a class of point clouds with a large number of point clouds through an iterative closest point ICP algorithm or a normal distribution transform NDT algorithm to obtain a transformation matrix; the transformation matrix includes a translation vector t(C, m, n); wherein C is the displacement in the X-axis direction of the preset coordinate system when the point clouds are matched, m is the displacement in the Y-axis direction of the preset coordinate system when the point clouds are matched, and n is the displacement in the Z-axis direction of the preset coordinate system when the point clouds are matched.

[0075] In one embodiment, the lateral position of the movable device is determined according to the transformation matrix in step 205d, which can be implemented in the following manner: according to the translation distance |C| of the X axis in the preset coordinate system during point cloud matching, the lateral distance of the movable device from the center line of the tunnel is determined as

[0076] In one embodiment, if Fig. 9 As shown, determining the yaw angle of the movable device according to the transformation matrix in step 205d specifically includes the following steps:

[0077] Step 301, determining a first vertex of the tunnel in laser point cloud data of a preset area on the top of the tunnel above the movable device according to the translation vector in the transformation matrix;

[0078] Step 302: According to the coordinates of the first vertex of the tunnel in the preset coordinate system, a target point cloud having a Z-axis coordinate within a preset range of the Z-axis coordinate value of the first vertex is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device;

[0079] Step 303: Determine a straight line equation according to the target point cloud; the straight line equation includes parameters to be solved;

[0080] Step 304: determine the cost function of all points in the target point cloud relative to the straight line;

[0081] Step 305, solving the cost function to determine the result of the parameter to be solved corresponding to the minimum cost value of the cost function;

[0082] Step 306: Determine the yaw angle of the movable device according to the result of the parameter to be solved.

[0083] In one embodiment, in the above step 301, the first vertex of the tunnel is determined in the laser point cloud data of the preset area on the top of the tunnel above the movable device according to the translation vector in the transformation matrix, which can be implemented in the following manner: according to the translation distance |C| of the X-axis in the preset coordinate system when the point cloud in the translation vector t(C, m, n) is matched, the first vertex of the tunnel is determined in the laser point cloud data of the preset area on the top of the tunnel above the movable device; wherein the X-axis coordinate of the first vertex in the preset coordinate system is When the Y-axis coordinate is 0, or the first vertex is the same as the X-axis coordinate in the laser point cloud data The point p0 (x0, y0, z0) whose distance to the point with Y-axis coordinate 0 is the smallest.

[0084] In one embodiment, in the above step 302, according to the coordinates of the first vertex of the above-mentioned tunnel in the preset coordinate system, a target point cloud with a Z-axis coordinate within a preset range of the Z-axis coordinate value of the first vertex is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device. This can be achieved in the following way: according to the coordinates of the first vertex of the tunnel in the preset coordinate system, a target point cloud with a Z-axis coordinate within a preset range (z0-d, z0+d) is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device; wherein d is a preset distance threshold; z0 is the Z-axis coordinate of the first vertex.

[0085] In one embodiment, in the above step 303, the straight line equation of a straight line is determined according to the target point cloud; the straight line equation contains parameters to be solved, which can be implemented in the following way: according to the target point cloud, the straight line equation of a straight line is determined: a(x-x0)+b(y-y0)=0; wherein a and b are parameters to be solved.

[0086] In one embodiment, in the above step 304, determining the cost function of all points in the target point cloud relative to the straight line can be implemented in the following manner: determining the cost function of all points (xi, yi, zi) in the target point cloud relative to the straight line:

[0087] In one embodiment, in the above step 305, solving the cost function to determine the result of the parameter to be solved corresponding to the minimum cost value of the cost function can be implemented in the following manner: performing minimum optimization on the cost function to determine the result a0 and b0 of the parameter to be solved corresponding to the minimum cost value of the cost function;

[0088] In one embodiment, in the above step 306, the yaw angle of the movable device is determined according to the result of the parameter to be solved, which can be implemented in the following manner: the yaw angle of the movable device relative to the tunnel is determined as

[0089] Through the above processing, this solution can obtain laser point cloud data of a certain area above the movable device in scenes such as tunnels where the GNSS signal is affected, extract the laser point cloud data according to preset rules, obtain point clouds on the left and right sides of the movable device respectively, further match the two types of point clouds, obtain a transformation matrix, and determine the position information of the movable device according to the transformation matrix. Therefore, the technical solution provided by the embodiment of the present application can solve the problem in the related technology that the movable device cannot be accurately positioned when the GNSS signal is affected and the laser point cloud data in front cannot be accurately obtained; at the same time, because the point cloud data above the movable device is collected, it will not be affected by temporary obstacles when in use, and there is no need to build a high-precision map in advance.

[0090] The following is a detailed description of how to implement a positioning method for a movable device provided by the present invention using an embodiment.

[0091] In one embodiment, a movable device (such as an autonomous vehicle) travels in a tunnel, with the origin of the IMU coordinate system as the movable reference point, and 5M in front of and behind the reference point as the sampling area. Fig.10a The top view of the sampling area is shown in Figure 1. The point cloud with fewer points is recorded as point cloud A (see the shaded part on the right), and the point cloud with more points is recorded as point cloud B (see the blank part on the left). Before matching point clouds A and B, point cloud A needs to be rotated 180 degrees around the Z axis of the IMU coordinate system to form point cloud A' to be matched (see the shaded part on the bottom).

[0092] Furthermore, if Fig.10bAs shown, point cloud A' is matched with point cloud B through a preset registration algorithm to obtain a transformation matrix, and the translation vector of point cloud A' relative to B is extracted from the transformation matrix, so as to determine the lateral position of the movable device. Specifically, when matching point clouds A' and B, an iterative closest point ICP algorithm or a normal distribution transform NDT algorithm can be used to obtain a transformation matrix, which includes a translation vector t(C, m, n), wherein C is the displacement in the X-axis direction of the IMU coordinate system when the point cloud is matched, m is the displacement in the Y-axis direction of the IMU coordinate system when the point cloud is matched, and n is the displacement in the Z-axis direction of the IMU coordinate system when the point cloud is matched. At this point, the lateral distance of the movable device from the center line of the tunnel can be determined by geometric relationships.

[0093] Furthermore, according to the translation distance |C| on the X-axis in the preset coordinate system during point cloud matching, the first vertex of the tunnel is determined in the laser point cloud data of the preset area on the top of the tunnel above the movable device. Assume that at this time There is a point P0 at y = 0, so let is the first vertex of the tunnel. Fig.11 As shown, according to the coordinates of the first vertex of the tunnel in the IMU coordinate system, a target point cloud E with a Z-axis coordinate within a preset range (z0-0.2, z0+0.2) is selected from the laser point cloud data of a preset area on the top of the tunnel above the movable device.

[0094] Furthermore, if Fig.12 As shown, according to the target point cloud E, a straight line equation L is set: a(x-x0)+b(y-y0)=0, where a and b are parameters to be solved, and the cost function of all points (xi, yi, zi) in the target point cloud E relative to the straight line is solved: The cost function is optimized to find the minimum value, and the corresponding results a0 and b0 of the parameters to be solved when the cost value of the cost function is the minimum are determined. At this time, the straight line L should pass through the point And its projection is the straight line that best fits the central axis of the tunnel ground. At the same time, the straight line L is perpendicular to the plane vector (a0, b0). According to the geometric relationship, the yaw angle of the movable device relative to the tunnel can be deduced. Furthermore, when the tunnel's own yaw angle is α0, the yaw angle of the mobile device in the global map is

[0095] Through the above processing, the method provided in the embodiment of the present application can effectively assist the movable device to be accurately positioned in scenes such as tunnels, so as to obtain the lateral distance and yaw angle between the movable device and the central axis of the tunnel ground, avoid interference from obstacles ahead, and accurately obtain the relative position of the movable device without relying on high-precision maps.

[0096] In one embodiment, the embodiment of the present application further provides a cloud server, which includes a positioning device for a movable device. The positioning device for the movable device is used to implement the above-mentioned positioning method for the movable device, which will not be repeated here.

[0097] In one embodiment, the embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned positioning method of a movable device is implemented, which will not be described in detail here.

[0098] In one embodiment, the embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned positioning method of the movable device is implemented, which will not be repeated here.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0103] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core idea of ​​this application. At the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A method for positioning a movable device, wherein the movable device is traveling in a tunnel with a bilaterally symmetrical cross section, characterized in that: include Acquire laser point cloud data of a preset area above the movable device; Extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule; Matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining the position and posture information of the movable device according to the transformation matrix; The laser point cloud data is extracted according to a preset rule into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device, respectively, including: Obtaining the reference point coordinates of the movable device reference point in a preset coordinate system and the coordinates of each point cloud in the laser point cloud data; According to the reference point coordinates and the coordinates of each point cloud, the point cloud corresponding to each point cloud coordinate is divided into a first type of point cloud or a second type of point cloud; Matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining the position and posture information of the movable device according to the transformation matrix, including: Obtaining the number of points of the first type of point cloud and the second type of point cloud, respectively, and determining a type of point cloud with a larger number of points and another type of point cloud with a smaller number of points; Preprocessing another type of point cloud with a small number of point clouds to form a point cloud to be matched; The point cloud to be matched is matched with a type of point cloud with a large number of point clouds through a preset registration algorithm to obtain a transformation matrix.

2. The method for positioning a movable device according to claim 1, characterized in that: The movable device is provided with a laser radar, and a scanning plane of the laser radar is perpendicular to a driving plane of the movable device, or an angle exists between the scanning plane of the laser radar and the driving plane of the movable device; The step of obtaining laser point cloud data of a preset area above the movable device includes: The laser radar is used to obtain laser point cloud data of a preset area on the top of the tunnel above the movable device.

3. The method for positioning a movable device according to claim 1, characterized in that: The preset area is a preset distance area in front of a reference point of the movable device, a preset distance area behind a reference point of the movable device, or a preset distance area before and after a reference point of the movable device.

4. The method for positioning a movable device according to claim 1, characterized in that: Matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining the position and posture information of the movable device according to the transformation matrix, including: Matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining a lateral position and a yaw angle of the movable device according to the transformation matrix; Wherein, the transformation matrix includes a translation vector; The determining the lateral position of the movable device according to the transformation matrix comprises: A lateral position of the movable device is determined based on the translation vector.

5. The method for positioning a movable device according to claim 1, characterized in that: Preprocessing the other type of point cloud with a small number of point clouds to form a point cloud to be matched includes: The point cloud of the other type with a smaller number of point clouds is rotated 180 degrees around the Z axis of the preset coordinate system to form a point cloud to be matched; wherein the preset coordinate system includes an X axis, a Y axis and a Z axis, the X axis is the lateral direction of the movable device, the Y axis is the longitudinal direction of the movable device, and the Z axis is perpendicular to the plane where the X axis and the Y axis are located; Through a preset registration algorithm, the point cloud to be matched is matched with a type of point cloud with a large number of point clouds to obtain a transformation matrix, including: By iterating the closest point ICP algorithm or the normal distribution transformation NDT algorithm, the point cloud to be matched is matched with a class of point clouds with a large number of point clouds to obtain a transformation matrix; the transformation matrix includes a translation vector t(C, m, n); wherein C is the displacement in the X-axis direction of the preset coordinate system when the point cloud is matched, m is the displacement in the Y-axis direction of the preset coordinate system when the point cloud is matched, and n is the displacement in the Z-axis direction of the preset coordinate system when the point cloud is matched; Determining the lateral position of the movable device according to the translation vector includes: According to the X-axis translation distance |C| in the preset coordinate system during point cloud matching, the lateral distance between the movable device and the tunnel centerline is determined as 6. The method for positioning a movable device according to claim 5, characterized in that: Determining the yaw angle of the movable device according to the transformation matrix includes: Determine a first vertex of the tunnel in the laser point cloud data of a preset area on the top of the tunnel above the movable device according to the translation vector in the transformation matrix; According to the coordinates of the first vertex of the tunnel in the preset coordinate system, a target point cloud with a Z-axis coordinate within a preset range of the Z-axis coordinate value of the first vertex is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device; Determine a straight line equation according to the target point cloud; the straight line equation includes parameters to be solved; Determine a cost function of all points in the target point cloud relative to the straight line; Solving the cost function to determine the result of the parameter to be solved corresponding to the minimum cost value of the cost function; The yaw angle of the movable device is determined according to the result of the parameter to be solved.

7. The method for positioning a movable device according to claim 6, characterized in that: Determining a first vertex of the tunnel in laser point cloud data of a preset area on the top of the tunnel above the movable device according to the translation vector in the transformation matrix includes: According to the translation distance |C| of the X axis in the preset coordinate system when the point cloud in the translation vector t(C, m, n) is matched, the first vertex of the tunnel is determined in the laser point cloud data of the preset area on the top of the tunnel above the movable device; wherein the X axis coordinate of the first vertex in the preset coordinate system is When the Y-axis coordinate is 0, or the first vertex is the same as the X-axis coordinate in the laser point cloud data The point p0 (x0, y0, z0) with the shortest distance from the point with Y-axis coordinate 0; According to the coordinates of the first vertex of the tunnel in the preset coordinate system, a target point cloud whose Z-axis coordinates are within a preset range of the Z-axis coordinate values ​​of the first vertex is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device, including: According to the coordinates of the first vertex of the tunnel in the preset coordinate system, a target point cloud with a Z-axis coordinate within a preset range (z0-d, z0+d) is selected from the laser point cloud data of the preset area on the top of the tunnel above the movable device; wherein d is a preset distance threshold; and z0 is the Z-axis coordinate of the first vertex; According to the target point cloud, a straight line equation is determined; the straight line equation contains parameters to be solved, including: According to the target point cloud, determine the straight line equation: a(x-x0)+b(y-y0)=0; wherein a and b are parameters to be solved; Determining a cost function of all points in the target point cloud relative to the straight line includes: Determine the cost function of all points (xi, yi, zi) in the target point cloud relative to the straight line: Solving the cost function to determine the result of the corresponding parameter to be solved when the cost value of the cost function is minimized includes: Performing minimum optimization on the cost function to determine the corresponding results a0 and b0 of the parameters to be solved when the cost value of the cost function is minimum; Determining the yaw angle of the movable device according to the result of the parameter to be solved includes: Determine the yaw angle of the movable device relative to the tunnel as 8. A positioning device for a movable device, wherein the movable device travels in a tunnel with a bilaterally symmetrical cross section, characterized in that: include: A laser point cloud acquisition module, used to acquire laser point cloud data of a preset area above the movable device; A point cloud extraction module, used for extracting the laser point cloud data into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device respectively according to a preset rule; A point cloud matching module, used for matching the first type of point cloud with the second type of point cloud to obtain a transformation matrix, and determining the position and posture information of the movable device according to the transformation matrix; The laser point cloud data is extracted according to a preset rule into a first type of point cloud and a second type of point cloud located on the left and right sides of the movable device, respectively, including: Obtaining the reference point coordinates of the movable device reference point in a preset coordinate system and the coordinates of each point cloud in the laser point cloud data; According to the reference point coordinates and the coordinates of each point cloud, the point cloud corresponding to each point cloud coordinate is divided into a first type of point cloud or a second type of point cloud; Matching the first type of point cloud and the second type of point cloud to obtain a transformation matrix, and determining the position and posture information of the movable device according to the transformation matrix, including: Obtaining the number of points of the first type of point cloud and the second type of point cloud, respectively, and determining a type of point cloud with a larger number of points and another type of point cloud with a smaller number of points; Preprocessing another type of point cloud with a small number of point clouds to form a point cloud to be matched; The point cloud to be matched is matched with a type of point cloud with a large number of point clouds through a preset registration algorithm to obtain a transformation matrix.

9. A movable device, characterized in that: The movable device comprises a positioning device of the movable device, and the positioning device of the movable device is used to implement the positioning method of the movable device according to any one of claims 1 to 7.

10. A server, characterized in that: The server comprises a positioning device for a movable device, and the positioning device for a movable device is used to implement the positioning method for a movable device as described in any one of claims 1 to 7.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the positioning method of a movable device as described in any one of claims 1 to 7 is implemented.

12. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the positioning method for a movable device as described in any one of claims 1 to 7 is implemented.

Images