A method and device for measuring the angle of a trailer, and a vehicle

Abstract

The application provides a trailer included angle measurement method and device and a vehicle, and relates to the technical field of automatic driving vehicles. According to the initial trailer included angle obtained, the application can determine whether to apply a single-line laser radar to measure the trailer included angle or to apply a multi-line laser radar to measure the trailer included angle. When it is determined to apply the multi-line laser radar to measure the trailer included angle, the deflection direction of the semitrailer is obtained, and the laser emitted by the multi-line laser radar on the side of the deflection direction reflected by the surface of the trailer is collected. The laser point cloud is subjected to coordinate transformation and screening processing to form candidate point cloud. The candidate point cloud is subjected to optimization solving according to a target optimization function constructed in advance to determine a trailer boundary straight line. The trailer included angle is determined according to the trailer boundary straight line. The embodiment of the application can realize a scheme for simply, quickly and accurately measuring the trailer included angle.

Description

Technical Field

[0001] This application relates to the field of autonomous vehicle technology, and in particular to a method, device and vehicle for measuring trailer angle. Background Technology

[0002] Currently, with the development of the logistics and transportation industry, the application of semi-trailers (including container trucks and trailers) is becoming increasingly widespread. As a heavy-duty transportation tool, semi-trailers, compared to monocoque trucks, can improve the overall economic efficiency of road transportation. Furthermore, with the development of autonomous driving technology, the trailer angle (e.g., ...) is becoming increasingly important. Figure 1 The top view of the semi-trailer shown shows that the trailer angle (α) refers to the angle between the centerline of the tractor 11 and the centerline of the trailer 12. As the basis for autonomous driving planning and control points, it has become the focus of research.

[0003] Currently, how to develop a simple, fast, and accurate method for measuring trailer angles has become an urgent problem to be solved. Summary of the Invention

[0004] The embodiments of this application provide a method, device, and vehicle for measuring trailer angle, which can realize a simple, fast, and accurate solution for measuring trailer angle.

[0005] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0006] A first aspect of this application provides a method for measuring the trailer angle, applied to a semi-trailer, the semi-trailer including a tractor and a trailer; a single-line lidar is provided at the rear of the tractor, at least one multi-line lidar is provided on each side of the tractor, and a laser reflector corresponding to the position of the single-line lidar is provided at the head of the trailer.

[0007] The method for measuring the trailer angle includes:

[0008] Obtain the initial trailer angle;

[0009] Based on the initial trailer angle, determine whether to use a single-line lidar or a multi-line lidar to measure the trailer angle.

[0010] When determining the application of multi-line lidar for trailer angle measurement, the deflection direction of the semi-trailer is obtained, and the laser emitted by the multi-line lidar on the side of the deflection direction reflected by the trailer surface is collected.

[0011] The laser point cloud is subjected to coordinate transformation and filtering to form a candidate point cloud;

[0012] The candidate point cloud is optimized and solved according to the pre-constructed target optimization function to determine the trailer boundary line;

[0013] The trailer angle is determined based on the straight line of the trailer boundary.

[0014] A second aspect of this application provides a measuring device for trailer angle, applied to a semi-trailer, the semi-trailer including a tractor and a trailer; a single-line lidar is provided at the rear of the tractor, at least one multi-line lidar is provided on each side of the tractor, and a laser reflector corresponding to the position of the single-line lidar is provided at the head of the trailer.

[0015] The device for measuring the trailer angle includes:

[0016] Initial trailer angle acquisition unit, used to obtain the initial trailer angle;

[0017] The measurement selection unit is used to determine whether to use a single-line lidar or a multi-line lidar to measure the trailer angle based on the initial trailer angle.

[0018] The laser point cloud acquisition and control unit is used to obtain the deflection direction of the semi-trailer when determining the trailer angle measurement using multi-line lidar, and to acquire the laser emitted by the multi-line lidar on the side of the deflection direction reflected by the trailer surface.

[0019] A point cloud processing unit is used to perform coordinate transformation and filtering on the laser point cloud to form a candidate point cloud;

[0020] The trailer boundary line determination unit is used to optimize the candidate point cloud according to a pre-constructed target optimization function to determine the trailer boundary line;

[0021] The trailer angle determination unit is used to determine the trailer angle based on the straight line of the trailer boundary.

[0022] A third aspect of this application provides a vehicle, including a trailer angle measuring device, a tractor and a trailer; a single-line lidar is provided at the rear of the tractor, at least one multi-line lidar is provided on each side of the tractor, and a laser reflector corresponding to the position of the single-line lidar is provided at the head of the trailer.

[0023] The trailer angle measuring device is communicatively connected to a single-line lidar and various multi-line lidars to obtain the initial trailer angle. Based on the initial trailer angle, it is determined whether to use a single-line lidar or a multi-line lidar for trailer angle measurement. When using a multi-line lidar, the deflection direction of the semi-trailer is obtained, and the laser emitted by the multi-line lidar on one side of the deflection direction reflected from the trailer surface is collected. The laser point cloud is subjected to coordinate transformation and filtering to form a candidate point cloud. The candidate point cloud is optimized and solved according to a pre-constructed target optimization function to determine the trailer boundary line. The trailer angle is determined based on the trailer boundary line.

[0024] A fourth aspect of this application provides a computer-readable storage medium including a program or instructions that, when executed on a computer, implement the trailer angle measurement method described in the first aspect above.

[0025] A fifth aspect of this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the trailer angle measurement method as described in the first aspect above.

[0026] A sixth aspect of this application provides a chip system including a processor coupled to a memory, the memory storing program instructions, which, when executed by the processor, implement the trailer angle measurement method described in the first aspect.

[0027] A seventh aspect of the embodiments of this application provides a computer server, including a memory and one or more processors communicatively connected to the memory;

[0028] The memory stores instructions that can be executed by the one or more processors to enable the one or more processors to implement the trailer angle measurement method as described in the first aspect above.

[0029] This application provides a method, device, and vehicle for measuring trailer angle, applicable to a semi-trailer with a tractor and a trailer. A single-line lidar is installed at the rear of the tractor, and at least one multi-line lidar is installed on each side of the tractor. A laser reflector corresponding to the position of the single-line lidar is installed at the front of the trailer. Thus, this application allows for determining whether to use a single-line lidar or a multi-line lidar to measure the trailer angle based on the initial trailer angle. When multi-line lidar is used, the deflection direction of the semi-trailer is obtained, and the laser emitted by the multi-line lidar on the deflection direction side reflected from the trailer surface is collected. The laser point cloud is then subjected to coordinate transformation and filtering to form a candidate point cloud. The candidate point cloud is optimized using a pre-constructed objective optimization function to determine the trailer boundary line. Finally, the trailer angle is determined based on the trailer boundary line. Therefore, this application provides a simple, fast, and accurate solution for measuring trailer angle. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of the trailer angle involved in the embodiments of this application;

[0032] Figure 2 A flowchart of a method for measuring trailer angle provided in this application embodiment Figure 1 ;

[0033] Figure 3 This is a schematic diagram of the semi-trailer in the embodiments of this application;

[0034] Figure 4 This is a schematic diagram of a lidar acquisition scenario in an embodiment of this application. Figure 1 ;

[0035] Figure 5 This is a schematic diagram of a lidar acquisition scenario in an embodiment of this application. Figure 2 ;

[0036] Figure 6 This is a schematic diagram of the distribution of the multi-line lidar in the embodiments of this application. Figure 1 ;

[0037] Figure 7 This is a schematic diagram of the distribution of the multi-line lidar in the embodiments of this application. Figure 2 ;

[0038] Figure 8 A flowchart of a method for measuring trailer angle provided in this application embodiment Figure 2 ;

[0039] Figure 9 This is a schematic diagram of the coordinate system in the semi-trailer environment in the embodiments of this application;

[0040] Figure 10 This is a schematic diagram of the preset three-dimensional coordinate range in the embodiments of this application;

[0041] Figure 11 This is a schematic diagram of the structure of the trailer angle measuring device in the embodiments of this application;

[0042] Figure 12 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] To enable those skilled in the art to better understand this application, some technical terms appearing in the embodiments of this application are explained below:

[0046] Point cloud: In reverse engineering, the collection of point data on the surface of an object obtained by measuring instruments is called a point cloud.

[0047] IMU: Inertial Measurement Unit, is a device that measures the three-axis attitude angles (or angular rates) and acceleration of an object.

[0048] Frame: The measurement data received by a sensor after completing one observation. For example, a frame of data from a camera is an image, and a frame of data from a lidar is a set of laser point clouds.

[0049] The term "vehicle" as used in this application typically includes: a powertrain system, a sensor system, a control system, peripheral devices, and a computer system. In other embodiments, a vehicle may include more, fewer, or different systems.

[0050] The powertrain is the system that provides power for the vehicle's movement, including: engine / motor, transmission, wheels / tires, and energy unit.

[0051] The control system may include a combination of devices for controlling the vehicle and its components, such as a steering unit, a throttle, and a braking unit.

[0052] Peripheral devices can be devices that allow a vehicle to interact with external sensors, other vehicles, external computing devices and / or users, such as wireless communication systems, touch screens, microphones and / or speakers.

[0053] Based on the vehicles described above, autonomous vehicles are also equipped with sensor systems and autonomous driving control devices.

[0054] The sensor system may include multiple sensors for sensing information about the vehicle's environment, 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 GPS sensors, inertial measurement units, radio detection and ranging (RADAR) units, cameras, laser rangefinders, light detection and ranging (LIDAR) units, and / or acoustic sensors; the sensor system may also include sensors that monitor systems inside the vehicle (e.g., O2 monitors, fuel gauges, engine temperature gauges, etc.).

[0055] An autonomous driving control device may include a processor and a memory. The memory stores at least one machine-executable instruction, and the processor executes this 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 positioning module provide map and location information. The perception module perceives objects in the vehicle's environment based on information acquired by the sensor system and map information provided by the map engine. The navigation or path module plans a driving path for the vehicle based on the processing results from the map engine, positioning module, and perception module. The automatic control module parses and converts the decision information input from modules such as the navigation or path module into control commands for the vehicle control system. These commands are then sent to the corresponding components in the vehicle control system via an in-vehicle network (e.g., an internal electronic network system implemented via CAN bus, local area network, multimedia orientation system, etc.) to achieve automatic vehicle control. The automatic control module can also obtain information from various components within the vehicle via the in-vehicle network.

[0056] Currently, existing technologies for measuring trailer angles can be divided into contact and non-contact solutions. Contact solutions, such as those using contact sensors based on magnetic induction, have stringent installation requirements and are unsuitable for scenarios with irregular relative movements between the tractor and trailer, posing safety hazards. Non-contact solutions typically use a single radar for measurement, but suffer from three main drawbacks: first, the detection range is insufficient for the application scenario, failing to achieve full-angle coverage; second, the solution lacks generalization ability, requiring complex preparation and hindering rapid adaptation to various truck models; and third, the detection accuracy, output frequency, and robustness are unsuitable for high-precision scenarios, such as autonomous reversing in port areas. This application provides subsequent embodiments to overcome these problems.

[0057] like Figure 2 As shown in the embodiments of this application, a method for measuring the trailer angle is provided, which is applied to, for example... Figure 3 ( Figure 3 The image shows a semi-trailer 20 (bottom view). The semi-trailer 20 includes a tractor unit 201 and a trailer 202, connected by a pivot 205, allowing the trailer 202 to rotate relative to the tractor unit 201. At least one multi-line lidar 203 is provided on each side of the tractor unit 201 (e.g., the left and right sides of the front of the tractor unit 201, i.e., the left and right sides of the vehicle's front). (For example, there could be one, two, or more multi-line lidars on each side.) Figure 3 Due to limitations, only the case where one multi-line lidar is set on each of the left and right sides is shown (also as...). Figure 3 As shown, a single-line lidar 206 is installed at the rear of the tractor 201, and a laser reflector 204 corresponding to the position of the single-line lidar is installed at the front of the trailer 202.

[0058] like Figure 2 As shown, the method for measuring the included angle of the trailer includes:

[0059] Step 301: Obtain the initial trailer angle.

[0060] Step 302: Based on the initial trailer angle, determine whether to use a single-line lidar or a multi-line lidar to measure the trailer angle.

[0061] Step 303: When determining the application of multi-line lidar for trailer angle measurement, obtain the deflection direction of the semi-trailer and collect the laser emitted by the multi-line lidar on the side of the deflection direction reflected by the trailer surface.

[0062] Step 304: Perform coordinate transformation and filtering on the laser point cloud to form a candidate point cloud.

[0063] Step 305: Optimize the candidate point cloud according to the pre-constructed target optimization function to determine the trailer boundary line.

[0064] Step 306: Determine the trailer angle based on the straight line of the trailer boundary.

[0065] Considering that a single-line lidar 206 can be installed at the rear of the tractor 201 to emit laser light onto the reflective surface of the laser reflector 204, this single-line lidar 206 is generally sufficient to measure the trailer angle. However, for scenarios with larger trailer angles, such as... Figure 4 As shown, the laser reflector 204 may have moved to the side of the tractor 201, entering the blind zone of the single-line lidar 206. The laser emitted by the single-line lidar 206 can no longer reach the reflective surface of the laser reflector 204, causing the trailer angle measurement to fail. Therefore, in this embodiment, the current trailer angle environment (an environment with a large trailer angle or an environment with a small trailer angle) can be determined based on the initial trailer angle, thereby determining whether to use the single-line lidar 206 or the multi-line lidar 203 for trailer angle measurement.

[0066] like Figure 5 As shown, this application employs at least one multi-line lidar 203 on each side of the tractor 201 (e.g., the left and right sides of the front of the tractor 201, i.e., the left and right sides of the front face). (For example, one, two, or more multi-line lidars can be installed on each side.) Figure 5(Due to limitations, only the case where one multi-line lidar is set on each of the left and right sides is shown.) In this way, when the laser reflector 204 moves to the side of the tractor 201, the laser emitted by the multi-line lidar on at least one side can hit the surface of the trailer, and thus can be used to measure the trailer angle.

[0067] Here, to indicate that at least one multi-line lidar 203 is installed on each side of the tractor 201, such as Figure 6 and Figure 7 As shown, the multi-line lidar 203 can be distributed at the front end of the tractor 201 in such a way that there is one multi-line lidar 203 on each of the left and right sides. Figure 6 ), or each has two multi-line lidars 203 ( Figure 7 However, it is not limited to this. Without considering the cost, more multi-line lidars can be set up on the left and right sides, and the measurement results can be fused together to make the measurement results more accurate.

[0068] It is worth noting that the multi-line lidar used in the embodiments of this application can be, for example, a 16-line, 32-line, or 64-line lidar, but is not limited to these.

[0069] To enable those skilled in the art to better understand this application, a more detailed embodiment is described below, such as... Figure 8 As shown in the figure, this application provides a method for measuring the trailer angle, which is applied to the above-mentioned... Figure 3 The semi-trailer 20 shown has had its structure described above and will not be repeated here. The method includes:

[0070] Step 401: Obtain the initial trailer angle.

[0071] It is worth noting that the trailer angle measurement can be performed according to a preset cycle, such as once every 1 second. Therefore, the initial trailer angle can be the trailer angle obtained in the previous cycle according to the method of the embodiments of this application. In addition, when initially measuring the trailer angle, the initial trailer angle can also be an initial value obtained from the external environment (such as human input, external visual sensor recognition, etc.). For example, for consideration of actual working conditions and robustness, it can be initialized from a small angle, such as by obtaining the initial trailer angle using a single-line lidar, but it is not limited to this. There are many specific ways to obtain the initial trailer angle, which will not be listed here.

[0072] Step 402: Determine whether the initial trailer angle is greater than the preset angle threshold.

[0073] Here, the included angle threshold can be preset according to the installation position of the single-line lidar or multi-line lidar, as well as the structure of the tractor and trailer, to ensure that the included angle of the trailer can be measured when using both single-line and multi-line lidar. For example, the included angle threshold can be 30°, 40°, 45°, etc., but it is not limited to these.

[0074] If the initial trailer angle is less than or equal to the preset angle threshold, proceed to step 403.

[0075] If the initial trailer angle is greater than the preset angle threshold, proceed to step 405.

[0076] Step 403: Determine the application of a single-line lidar for trailer angle measurement, control the single-line lidar to emit laser light, and receive the laser point cloud reflected by the laser reflector.

[0077] Step 404: Compute the trailer angle based on the laser points received from the single-line lidar.

[0078] Here, the method of cloud computing the trailer angle based on the laser point received from the single-line lidar can be found in the patent application with publication number CN108761481A, which will not be repeated here.

[0079] Step 405: Determine the application of multi-line lidar to measure the trailer angle, obtain the deflection direction of the semi-trailer, and collect the laser emitted by the multi-line lidar on the side of the deflection direction reflected by the trailer surface.

[0080] Here, the deflection direction of the semi-trailer can be obtained in several ways:

[0081] Method 1: Determine whether the semi-trailer is turning left or right based on the trailer angle of the previous cycle.

[0082] Method 2: Determine whether the semi-trailer is turning left or right based on its turning signals.

[0083] There are several ways to obtain the deflection direction of a semi-trailer, which will not be listed here.

[0084] When the semi-trailer turns left, a multi-line lidar on the left side of the semi-trailer can be used; when the semi-trailer turns right, a multi-line lidar on the right side of the semi-trailer can be used, so that the multi-line lidar can collect point cloud data on the surface of the trailer.

[0085] The trailer here may or may not carry a trailer box; there is no restriction.

[0086] Generally, the sampling frequency of each multi-line lidar can be 10Hz, but it is not limited to this. Furthermore, each multi-line lidar carries its own corresponding identifier when emitting laser light, ensuring that when receiving the laser point cloud reflected from the trailer's surface, it only receives the laser point cloud corresponding to its own location, and not the laser point clouds corresponding to other multi-line lidars. Additionally, due to the structural characteristics of the semi-trailer 20, when there is a certain trailer angle, generally only one side of the multi-line lidar can receive the laser point cloud reflected from the trailer's surface.

[0087] Step 406: Transform the laser point cloud from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer to form rotation center coordinate system point cloud data.

[0088] It is worth noting that, generally in autonomous driving technology, in order to study semi-trailers with tractor units and trailers, such as... Figure 9 As shown, the coordinate system of the entire semi-trailer can be a multi-line lidar coordinate system l (including the left-side multi-line lidar (Lidar_L) coordinate system l). l And the coordinate system of the multi-line lidar (Lidar_R) on the right r When applying a multi-line lidar coordinate system, the corresponding multi-line lidar coordinate system is determined according to whether the vehicle turns left or right, the rotation center coordinate system j of the tractor and trailer, and the vehicle body inertial measurement unit (IMU) coordinate system b.

[0089] In step 406 above, transforming the laser point cloud from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer to form rotation center coordinate system point cloud data can be achieved in the following way:

[0090] Laser point cloud in multi-line lidar coordinate system:

[0091]

[0092] According to the formula:

[0093]

[0094] Transform the coordinates to the rotation center coordinate system of the tractor and trailer to form point cloud data in the rotation center coordinate system: P′={p0′,...,p i ′,...,p′ n};in, The dimension of the laser point cloud is represented by x, y, z, which represent the three-dimensional coordinates of the laser point cloud, and i represents the reflection intensity. The transformation relationship between the vehicle body's inertial measurement unit (IMU) coordinate system b and the rotation center coordinate system j of the tractor and trailer; T l bThe transformation relationship from the multi-line lidar coordinate system l to the vehicle body IMU coordinate system b; The rotation matrix represents the rotation from the multi-line lidar coordinate system l to the rotation center coordinate system j of the tractor and trailer; This represents the translation matrix from the multi-line lidar coordinate system l to the rotation center coordinate system j of the tractor and trailer.

[0095] Step 407: Perform Region of Interest (ROI) filtering on the point cloud data of the rotation center coordinate system using preset conditions.

[0096] In step 407 here, the point cloud data of the rotation center coordinate system is filtered for the region of interest (ROI) using preset conditions. This can be achieved in the following way:

[0097] From the point cloud data in the rotation center coordinate system: P′={p0′,...,p i ′,...,p′ n Select point cloud data that meets the preset conditions from the list.

[0098] The preset conditions include the following:

[0099] ① In the xy plane of the rotation center coordinate system, the distance between the point cloud and the origin of the rotation center coordinate system is less than a preset distance threshold d. t .

[0100] Condition ① allows you to remove distant interference points.

[0101] ② The three-dimensional coordinates of the point cloud data in the rotation center coordinate system are within the preset three-dimensional coordinate range.

[0102] The preset three-dimensional coordinate range here can be determined based on the coordinates of the three-dimensional model points on the vehicle surface in the rotation center coordinate system, as well as the trailer angle of the previous cycle. For example, based on the trailer angle of the previous cycle and the pre-known coordinates of the three-dimensional model points on the vehicle surface in the rotation center coordinate system (used to represent the size of the vehicle body, which can be determined in advance by external LiDAR scanning), a preset distance area outside the trailer in the previous cycle will be determined as the preset three-dimensional coordinate range.

[0103] For example, such as Figure 10As shown, given the trailer's included angle from the previous cycle and the coordinates of the 3D model points on the vehicle's surface in the rotation center coordinate system, the trailer's current attitude can be determined. This allows us to define a preset distance range outside the trailer from the previous cycle (the shaded area in the figure only describes the area within a planar range; similar areas also exist above and below the trailer). This three-dimensional area can then be used as the preset 3D coordinate range. This is because the time between adjacent cycles is short (typically 0.1s), resulting in minimal changes to the trailer's included angle. Therefore, the trailer's change between the current and previous cycles is small and should remain within the preset 3D coordinate range.

[0104] According to condition ②, interference points that extend beyond a certain range around the vehicle can be removed.

[0105] ③ The reflection intensity of the point cloud in the rotation center coordinate system point cloud data is greater than the preset reflection intensity threshold.

[0106] Based on condition ③, points with low reflection intensity, which may be noise, can be removed.

[0107] Step 408: Downsample the point cloud data of the rotation center coordinate system after ROI filtering to form candidate point clouds.

[0108] Step 409: Optimize the candidate point cloud according to the pre-constructed target optimization function to determine the trailer boundary line.

[0109] In step 409 here, the candidate point cloud is optimized and solved according to the pre-constructed objective optimization function to determine the trailer boundary line. This can be achieved in the following way:

[0110] Based on the pre-constructed objective function:

[0111]

[0112] The candidate point cloud is optimized (e.g., using the Levenberg-Marquardt (LM) method) to determine the trailer boundary line; where X is the independent variable, X = {a, b}, where X = {a, b} represents the parameters a and b in the trailer boundary line y = ax + b to be determined, and f(X) is the residual function. denoted as the robust kernel function; x and y represent the coordinate information of the candidate point cloud in the xy plane of the rotation center coordinate system; α is a pre-set regularization penalty factor.

[0113] In this way, the trailer boundary line obtained by the objective optimization function can surround the candidate point cloud on the side with the vehicle, and make the point cloud as close as possible to the trailer boundary line.

[0114] Step 410: Determine the trailer angle based on the slope of the trailer boundary line in the xy plane of the rotation center coordinate system.

[0115] In addition, such as Figure 11 As shown in the illustration, this application also provides a device for measuring the trailer angle, applied to a semi-trailer, which includes a tractor and a trailer. A single-line lidar is provided at the rear of the tractor, and at least one multi-line lidar is provided on each side of the tractor. A laser reflector corresponding to the position of the single-line lidar is provided at the front of the trailer. The specific structure of the semi-trailer has been described in the above embodiments and will not be repeated here.

[0116] exist Figure 11 The measuring device for the trailer's included angle includes:

[0117] The initial trailer angle acquisition unit 51 is used to obtain the initial trailer angle.

[0118] The measurement selection unit 52 is used to determine whether to use a single-line lidar or a multi-line lidar to measure the trailer angle based on the initial trailer angle.

[0119] The laser point cloud acquisition and control unit 53 is used to obtain the deflection direction of the semi-trailer when determining the trailer angle measurement using a multi-line lidar, and to collect the laser emitted by the multi-line lidar on the side of the deflection direction reflected by the surface of the trailer.

[0120] The point cloud processing unit 54 is used to perform coordinate transformation and filtering on the laser point cloud to form a candidate point cloud.

[0121] The trailer boundary line determination unit 55 is used to optimize the candidate point cloud according to the pre-constructed target optimization function to determine the trailer boundary line.

[0122] Trailer angle determination unit 56 is used to determine the trailer angle based on the straight line of the trailer boundary.

[0123] In addition, such as Figure 12 As shown, this application embodiment provides a vehicle 50, including a trailer angle measuring device 601, a tractor 201, and a trailer 202; a single-line lidar 206 is provided at the rear of the tractor 201, and at least one multi-line lidar 203 is provided on each side of the tractor 201 (for example, one, two, or more multi-line lidars can be provided on each side, depending on the specific configuration). Figure 12 Due to limitations, only the case where a multi-line lidar is set on each of the left and right sides is shown. A laser reflector 204 corresponding to the position of the single-line lidar 206 is set at the head of the trailer 202.

[0124] The trailer angle measuring device 601 is communicatively connected to the single-line lidar 206 and each multi-line lidar 203 to obtain the initial trailer angle. Based on the initial trailer angle, it is determined whether to use a single-line lidar or a multi-line lidar for trailer angle measurement. When using a multi-line lidar, the deflection direction of the semi-trailer is obtained, and the laser emitted by the multi-line lidar on one side of the deflection direction reflected from the trailer surface is collected. The laser point cloud is subjected to coordinate transformation and screening to form a candidate point cloud. The candidate point cloud is optimized and solved according to a pre-constructed target optimization function to determine the trailer boundary line. The trailer angle is determined based on the trailer boundary line.

[0125] In addition, this application also provides a computer-readable storage medium, including a program or instructions, which, when run on a computer, implements the method for measuring the trailer angle in the above embodiments, and will not be described again here.

[0126] In addition, this application also provides a computer program product containing instructions. When the computer program product is run on a computer, it causes the computer to perform the trailer angle measurement method as described in the above embodiments, which will not be repeated here.

[0127] In addition, this application embodiment also provides a chip system including a processor, the processor being coupled to a memory, the memory storing program instructions, and when the program instructions stored in the memory are executed by the processor, the method for measuring the trailer angle in the above embodiment is implemented, which will not be described in detail here.

[0128] In addition, embodiments of this application also provide a computer server, including a memory and one or more processors communicatively connected to the memory;

[0129] The memory stores instructions that can be executed by the one or more processors. These instructions are executed by the one or more processors to enable the one or more processors to implement the trailer angle measurement method as described in the above embodiment, which will not be repeated here.

[0130] This application provides a method, device, and vehicle for measuring trailer angle, applicable to a semi-trailer with a tractor and a trailer. A single-line lidar is installed at the rear of the tractor, and at least one multi-line lidar is installed on each side of the tractor. A laser reflector corresponding to the position of the single-line lidar is installed at the front of the trailer. Thus, this application allows for determining whether to use a single-line lidar or a multi-line lidar to measure the trailer angle based on the initial trailer angle. When multi-line lidar is used, the deflection direction of the semi-trailer is obtained, and the laser emitted by the multi-line lidar on the deflection direction side reflected from the trailer surface is collected. The laser point cloud is then subjected to coordinate transformation and filtering to form a candidate point cloud. The candidate point cloud is optimized using a pre-constructed objective optimization function to determine the trailer boundary line. Finally, the trailer angle is determined based on the trailer boundary line. Therefore, this application provides a simple, fast, and accurate solution for measuring trailer angle.

[0131] Furthermore, the embodiments of this application can be deployed quickly on any type of semi-trailer truck without relying on prior models. Regarding performance parameters, the embodiments of this application can achieve full-angle detection, with the error between the detection result and the true value within 0.3°, and the consistency fluctuation of the detection results in static and dynamic scenes within ±0.25°. The detection frequency can reach 20Hz, thus ensuring the real-time performance of the results.

[0132] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] This application uses specific embodiments to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for measuring the included angle of a trailer, characterized in that, The invention is applied to a semi-trailer, which includes a tractor and a trailer; a single-line lidar is provided at the rear of the tractor, at least one multi-line lidar is provided on each side of the tractor, and a laser reflector corresponding to the position of the single-line lidar is provided at the front of the trailer. The method for measuring the trailer angle includes: Obtain the initial trailer angle for this cycle; When the initial trailer angle is greater than a preset angle threshold, it is determined that a multi-line lidar will be used to measure the trailer angle. When the initial trailer angle is less than a preset angle threshold, a single-line lidar is used to measure the trailer angle. When determining the application of multi-line lidar for trailer angle measurement, the deflection direction of the semi-trailer is obtained, and the laser point cloud emitted by the multi-line lidar on the side of the deflection direction reflected from the trailer surface is acquired. The laser point cloud is subjected to coordinate transformation and filtering to form a candidate point cloud; The trailer angle for this cycle is determined based on the candidate point cloud. The process of transforming and filtering the laser point cloud to form a candidate point cloud includes: The point cloud data is filtered for Region of Interest (ROI) using preset conditions, which include: the three-dimensional coordinates of the point cloud data are within a preset three-dimensional coordinate range; the preset three-dimensional coordinate range is determined based on the coordinates of the three-dimensional model points on the vehicle body surface and the trailer angle of the previous cycle.

2. The method according to claim 1, characterized in that, The process of performing coordinate transformation and filtering on the laser point cloud to form a candidate point cloud also includes: The point cloud data after ROI filtering is downsampled to form candidate point clouds.

3. The method according to claim 1, characterized in that, The process of performing coordinate transformation and filtering on the laser point cloud to form a candidate point cloud also includes: The laser point cloud is transformed from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer to form rotation center coordinate system point cloud data.

4. The method according to claim 3, characterized in that, The laser point cloud is transformed from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer, forming rotation center coordinate system point cloud data, including: Laser point cloud in multi-line lidar coordinate system: ， According to the formula: ， Transform the coordinates to the rotation center coordinate system of the tractor and trailer to form point cloud data in the rotation center coordinate system: ;in, Indicates the dimension of the laser point cloud. x, y, z Represents the three-dimensional coordinates of the laser point cloud. i Indicates the intensity of reflection; For the vehicle body inertial measurement unit (IMU) coordinate system b coordinate system of the rotation center of the tractor and trailer j The transformation relationship; Multi-line lidar coordinate system l To the vehicle body IMU coordinate system b The transformation relationship; Represents the coordinate system of a multi-line lidar. l coordinate system of the rotation center of the tractor and trailer j rotation matrix; Represents the coordinate system of a multi-line lidar. l coordinate system of the rotation center of the tractor and trailer j The translation matrix.

5. The method according to claim 3, characterized in that, The point cloud data is filtered for the Region of Interest (ROI) using preset conditions, including: Select point cloud data that meets preset conditions from the point cloud data of the rotation center coordinate system; The preset conditions also include the following conditions: In the coordinate system of the center of rotation xy In the plane, the distance between the point cloud and the origin of the rotation center coordinate system is less than a preset distance threshold; The reflection intensity of the point cloud in the rotation center coordinate system point cloud data is greater than the preset reflection intensity threshold.

6. The method according to claim 1, characterized in that, The step of determining the trailer angle for this period based on the candidate point cloud includes: The candidate point cloud is optimized and solved according to the pre-constructed target optimization function to determine the trailer boundary line; The trailer angle for this cycle is determined based on the straight line of the trailer boundary.

7. The method according to claim 6, characterized in that, The step of optimizing the candidate point cloud according to a pre-constructed objective optimization function to determine the trailer boundary line includes: Based on the pre-constructed objective function: The candidate point cloud is optimized to determine the trailer boundary line; where X is the independent variable, X={ a , b }, X={ a , b } represents the straight line representing the trailer boundary to be determined. y=ax+b Parameters in a and b , For the residual function, ; Represents a robust kernel function; x , y Represents the coordinate information of the candidate point cloud; This is a pre-set regularization penalty factor.

8. The method according to claim 6, characterized in that, Determining the trailer angle based on the straight line of the trailer boundary includes: Based on the coordinate system of the rotation center of the tractor and trailer, the boundary line of the trailer is... xy The slope of the plane determines the trailer angle.

9. The method according to claim 1, characterized in that, Also includes: When determining the application of single-line lidar for trailer angle measurement, the single-line lidar is controlled to emit laser and receive the laser point cloud reflected by the laser reflector. The trailer angle is calculated based on the laser points received from the single-line lidar.

10. A device for measuring the included angle of a trailer, characterized in that, The invention is applied to a semi-trailer, which includes a tractor and a trailer; a single-line lidar is provided at the rear of the tractor, at least one multi-line lidar is provided on each side of the tractor, and a laser reflector corresponding to the position of the single-line lidar is provided at the front of the trailer. The device for measuring the trailer angle includes: The initial trailer angle acquisition unit is used to obtain the initial trailer angle for this cycle. The measurement selection unit is used to determine whether to use a multi-line lidar to measure the trailer angle when the initial trailer angle is greater than a preset angle threshold; and to determine whether to use a single-line lidar to measure the trailer angle when the initial trailer angle is less than the preset angle threshold. The laser point cloud acquisition control unit is used to obtain the deflection direction of the semi-trailer when determining the application of multi-line lidar for trailer angle measurement, and to acquire the laser point cloud emitted by the multi-line lidar on the side of the deflection direction reflected by the trailer surface. The point cloud processing unit is used to perform coordinate transformation and filtering on the laser point cloud to form candidate point clouds; Trailer angle determination unit, used to determine the trailer angle for the current period based on the candidate point cloud; The point cloud processing unit is further adapted to: The point cloud data is filtered for Region of Interest (ROI) using preset conditions, which include: the three-dimensional coordinates of the point cloud data are within a preset three-dimensional coordinate range; the preset three-dimensional coordinate range is determined based on the coordinates of the three-dimensional model points on the vehicle body surface and the trailer angle of the previous cycle.

11. A vehicle, characterized in that, The system includes a device for measuring the trailer angle, a tractor and a trailer; a single-line lidar is installed at the rear of the tractor, at least one multi-line lidar is installed on each side of the tractor, and a laser reflector is installed at the front of the trailer corresponding to the position of the single-line lidar. The trailer angle measuring device is communicatively connected to a single-line lidar and various multi-line lidars to obtain the initial trailer angle for the current cycle. This initial trailer angle is the same as the trailer angle calculated in the previous cycle. Based on the initial trailer angle, it is determined whether to use a single-line lidar or a multi-line lidar for trailer angle measurement. When using a multi-line lidar, the deflection direction of the semi-trailer is obtained, and the laser point cloud emitted by the multi-line lidar on one side of the deflection direction reflected from the trailer surface is acquired. The laser point cloud undergoes coordinate transformation and filtering to form a candidate point cloud. The trailer angle for the current cycle is determined based on the candidate point cloud. The trailer angle measuring device is further used for: When the initial trailer angle is greater than a preset angle threshold, a multi-line lidar is used to measure the trailer angle; when the initial trailer angle is less than the preset angle threshold, a single-line lidar is used to measure the trailer angle. The point cloud data is filtered for Region of Interest (ROI) using preset conditions, which include: the three-dimensional coordinates of the point cloud data are within a preset three-dimensional coordinate range; the preset three-dimensional coordinate range is determined based on the coordinates of the three-dimensional model points on the vehicle body surface and the trailer angle of the previous cycle.

12. The vehicle according to claim 11, characterized in that, Based on the initial trailer angle, determine whether to use a single-line lidar or a multi-line lidar for trailer angle measurement, including: Determine whether the initial trailer angle is greater than a preset angle threshold; When the initial trailer angle is greater than a preset angle threshold, it is determined that a multi-line lidar will be used to measure the trailer angle. When the initial trailer angle is less than or equal to a preset angle threshold, it is determined that a single-line lidar will be used to measure the trailer angle.

13. The vehicle according to claim 11, characterized in that, The process of performing coordinate transformation and filtering on the laser point cloud to form a candidate point cloud also includes: The laser point cloud is transformed from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer to form rotation center coordinate system point cloud data.

14. The vehicle according to claim 13, characterized in that, The laser point cloud is transformed from the multi-line lidar coordinate system to the rotation center coordinate system of the tractor and trailer, forming rotation center coordinate system point cloud data, including: Laser point cloud in multi-line lidar coordinate system: ， According to the formula: ， Transform the coordinates to the rotation center coordinate system of the tractor and trailer to form point cloud data in the rotation center coordinate system: ;in, Indicates the dimension of the laser point cloud. x, y, z Represents the three-dimensional coordinates of the laser point cloud. i Indicates the intensity of reflection; For the vehicle body inertial measurement unit (IMU) coordinate system b coordinate system of the rotation center of the tractor and trailer j The transformation relationship; Multi-line lidar coordinate system l To the vehicle body IMU coordinate system b The transformation relationship; Represents the coordinate system of a multi-line lidar. l coordinate system of the rotation center of the tractor and trailer j rotation matrix; Represents the coordinate system of a multi-line lidar. l coordinate system of the rotation center of the tractor and trailer j The translation matrix.

15. The vehicle according to claim 13, characterized in that, The point cloud data is filtered for the Region of Interest (ROI) using preset conditions, including: Select point cloud data that meets preset conditions from the point cloud data of the rotation center coordinate system; The preset conditions also include the following conditions: In the coordinate system of the center of rotation xy In the plane, the distance between the point cloud and the origin of the rotation center coordinate system is less than a preset distance threshold; The reflection intensity of the point cloud in the rotation center coordinate system point cloud data is greater than the preset reflection intensity threshold.

16. A computer-readable storage medium, characterized in that, Includes a program or instructions that, when run on a computer, implement the method for measuring the trailer angle as described in any one of claims 1 to 9.

17. A chip system, characterized in that, The device includes a processor coupled to a memory that stores program instructions. When the program instructions stored in the memory are executed by the processor, the device implements the method for measuring the trailer angle as described in any one of claims 1 to 9.

18. A computer server, characterized in that, Includes a memory, and one or more processors communicatively connected to the memory; The memory stores instructions that can be executed by the one or more processors to cause the one or more processors to implement the method for measuring trailer angle as described in any one of claims 1 to 9.

Images