Method and device for detecting relative pose of trailer

The angle value and time stamp are obtained through various preset methods, abnormal detection is performed, and the size and distance information is combined, which solves the problem of low accuracy of relative posture detection of trailers in the prior art, and achieves higher accuracy posture detection.

CN119687860AActive Publication Date: 2025-03-25HANGZHOU FABU TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411815162.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-10
Publication Date
2025-03-25
Estimated Expiration
2044-12-10

AI Technical Summary

Technical Problem

The existing trailer relative posture detection methods have low detection accuracy and are difficult to achieve high-precision posture detection.

Method used

By obtaining the angle value and time stamp of the trailer relative to the tractor under the current frame determined by multiple preset methods, abnormal detection is performed on at least two preset methods to obtain the target angle value, and combining the size information of the trailer and the distance information of the traction coupling point, the relative position information of the trailer is determined.

Benefits of technology

The accuracy of the relative posture detection of the trailer is improved, and the position information of the trailer relative to the tractor can be determined more accurately.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119687860A_ABST
    Figure CN119687860A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a trailer relative pose detection method and device. The method comprises the following steps: acquiring first angle values of a trailer relative to a tractor under a current frame determined by a plurality of preset modes and first timestamps corresponding to the current frame under the plurality of first angle values; performing anomaly detection on at least two preset modes according to the plurality of first angle values and the plurality of first timestamps to obtain a target angle value; and according to the target angle value, the size information of the trailer and the distance information between the trailer and the traction coupling point and between the tractor and the traction coupling point, the relative pose information of the trailer is determined, and the effect of improving the trailer relative pose detection accuracy is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of loading and unloading technology, and in particular to a method and device for detecting the relative posture of a trailer. Background Art

[0002] With the rapid development of logistics and transportation, the need for high-precision detection of the relative position of trailers is increasing. For example, in automated cargo loading and unloading operations, it is necessary to accurately know the position and posture of the trailer relative to the tractor in order to achieve efficient and safe cargo transportation.

[0003] Traditional trailer relative posture detection methods mainly rely on position sensors to estimate vehicle position and posture in order to detect the posture of the trailer relative to the tractor.

[0004] However, existing methods for detecting the relative posture of trailers have the problem of low detection accuracy. Summary of the invention

[0005] The embodiments of the present application provide a method and device for detecting the relative posture of a trailer, so as to achieve the effect of improving the accuracy of detecting the relative posture of the trailer.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting a relative posture of a trailer, comprising:

[0007] Acquire a first angle value of the trailer relative to the tractor in the current frame and a first timestamp corresponding to the current frame under the multiple first angle values ​​determined by multiple preset methods, wherein the multiple preset methods include: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the crossbeam of the trailer, determining based on the second point cloud data of the fender of the trailer, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer;

[0008] According to the multiple first angle values ​​and the multiple first timestamps, performing anomaly detection on the at least two preset modes to obtain a target angle value;

[0009] The relative position information of the trailer is determined according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0010] In a possible implementation, performing abnormality detection on the at least two preset modes according to the multiple first angle values ​​and the multiple first timestamps to obtain a target angle value includes:

[0011] Obtaining a second angle value of the trailer relative to the tractor in a previous frame and a second timestamp corresponding to a previous frame under the second angle value;

[0012] For any first angle value, determining a first difference between the first angle value and the second angle value, and a second difference between the first timestamp and the second timestamp;

[0013] If the ratio of the first difference to the second difference is less than a first preset threshold, determining that the first angle value is a third non-abnormal angle value, wherein the first preset threshold is determined based on the operation information of the tractor;

[0014] The target angle value is determined according to at least one third angle value.

[0015] In a possible implementation, determining the target angle value according to at least one third angle value includes:

[0016] If the number of the at least one third angle value is an integer greater than 1, two fourth angle values ​​with the smallest angle difference are determined from the at least one third angle value;

[0017] If the angle difference between the two fourth angle values ​​is greater than a second preset threshold, the target angle value is determined from the fourth angle values ​​based on a first priority sequence, wherein the priority order in the first priority sequence is, from largest to smallest, a beam or baffle, a lane line, the motion information, and the first position information of the tractor;

[0018] If the angle difference between the two fourth angle values ​​is not greater than the second preset threshold, the target angle value is determined in the fourth angle values ​​based on a second priority sequence, and the priority order in the second priority sequence is from large to small: the first posture information of the tractor, the motion information, the beam or baffle, and the lane line.

[0019] In a possible implementation manner, determining the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively includes:

[0020] Determine the relative position and relative angle of the center of the trailer relative to the tractor according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the tractor coupling point respectively;

[0021] The relative position and the relative angle are determined as relative posture information of the trailer.

[0022] In a possible implementation manner, the preset manner is determined based on the position information of the tractor in the previous frame;

[0023] Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes:

[0024] Obtaining the first pose information of the tractor in the previous frame and the second pose information of the tractor in the current frame, the pose information including: timestamp, speed, and absolute orientation;

[0025] The first angle value is determined according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0026] In a possible implementation manner, the preset manner is determined based on first point cloud data of a crossbeam of the trailer;

[0027] Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes:

[0028] Determine the crossbeam region of interest of the trailer according to the distance information of the trailer and the tractor respectively from the traction coupling point and the angle information of the trailer in the previous frame;

[0029] According to the crossbeam region of interest, filtering the third point cloud data corresponding to the trailer to obtain the first point cloud data of the crossbeam;

[0030] Determining a first straight line equation of the beam on a horizontal plane according to the first point cloud data;

[0031] The first angle value is determined according to the first straight line equation.

[0032] In a possible implementation manner, the preset manner is determined based on second point cloud data of the fender of the trailer;

[0033] Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes:

[0034] Determine the baffle region of interest according to the distance information between the trailer and the tractor and the traction coupling point respectively and the angle information of the trailer in the previous frame;

[0035] According to the baffle region of interest, filtering the fourth point cloud data corresponding to the trailer to obtain the second point cloud data of the baffle;

[0036] Determining a second straight line equation of the baffle in a horizontal plane according to the second point cloud data;

[0037] The first angle value is determined according to the second straight line equation.

[0038] In a possible implementation manner, the preset manner is determined based on image data including lane lines behind the trailer;

[0039] Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes:

[0040] Inputting the image data including the lane line behind the trailer into the lane line detection model to obtain the position information of the lane line;

[0041] Determining a fifth angle value of the lane line relative to the trailer according to the position information of the lane line;

[0042] The first angle value is determined according to the fifth angle value and the absolute orientation of the lane line.

[0043] In a possible implementation manner, the preset manner is determined based on movement information of a meter wheel on the contact surface of the trailer;

[0044] Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes:

[0045] Acquiring the motion information of the meter wheel collected by the rotary encoder of the tractor on the coupling base;

[0046] Determining, based on the motion information, an angle change of the trailer relative to the tractor;

[0047] The first angle value is determined according to the second angle value of the trailer relative to the tractor in the previous frame and the angle change.

[0048] In a second aspect, an embodiment of the present application provides a device for detecting a relative posture of a trailer, comprising:

[0049] an acquisition module, used for acquiring a first angle value of the trailer relative to the tractor in the current frame and a first timestamp corresponding to the current frame under the multiple first angle values ​​determined by multiple preset methods, wherein the multiple preset methods include: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the crossbeam of the trailer, determining based on the second point cloud data of the fender of the trailer, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer;

[0050] A detection module, configured to perform anomaly detection on the at least two preset modes according to the multiple first angle values ​​and the multiple first time stamps to obtain a target angle value;

[0051] A determination module is used to determine the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0052] In a possible implementation manner, the detection module is specifically used to:

[0053] Obtaining a second angle value of the trailer relative to the tractor in a previous frame and a second timestamp corresponding to a previous frame under the second angle value;

[0054] For any first angle value, determining a first difference between the first angle value and the second angle value, and a second difference between the first timestamp and the second timestamp;

[0055] If the ratio of the first difference to the second difference is less than a first preset threshold, determining that the first angle value is a third non-abnormal angle value, wherein the first preset threshold is determined based on the operation information of the tractor;

[0056] The target angle value is determined according to at least one third angle value.

[0057] In a possible implementation, the detection module determines the target angle value according to at least one third angle value, specifically for:

[0058] If the number of the at least one third angle value is an integer greater than 1, two fourth angle values ​​with the smallest angle difference are determined from the at least one third angle value;

[0059] If the angle difference between the two fourth angle values ​​is greater than a second preset threshold, the target angle value is determined from the fourth angle values ​​based on a first priority sequence, wherein the priority order in the first priority sequence is, from largest to smallest, a beam or baffle, a lane line, the motion information, and the first position information of the tractor;

[0060] If the angle difference between the two fourth angle values ​​is not greater than the second preset threshold, the target angle value is determined in the fourth angle values ​​based on a second priority sequence, and the priority order in the second priority sequence is from large to small: the first posture information of the tractor, the motion information, the beam or baffle, and the lane line.

[0061] In a possible implementation manner, the determining module is specifically configured to:

[0062] Determine the relative position and relative angle of the center of the trailer relative to the tractor according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the tractor coupling point respectively;

[0063] The relative position and the relative angle are determined as relative posture information of the trailer.

[0064] In a possible implementation manner, the preset manner is determined based on the position information of the tractor in the previous frame;

[0065] Correspondingly, the acquisition module acquires the first angle value of the trailer relative to the tractor in the current frame determined by the preset method, specifically for:

[0066] Obtaining the first pose information of the tractor in the previous frame and the second pose information of the tractor in the current frame, the pose information including: timestamp, speed, and absolute orientation;

[0067] The first angle value is determined according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0068] In a possible implementation manner, the preset manner is determined based on first point cloud data of a crossbeam of the trailer;

[0069] Correspondingly, the acquisition module acquires the first angle value of the trailer relative to the tractor in the current frame determined by the preset method, specifically for:

[0070] Determine the crossbeam region of interest of the trailer according to the distance information of the trailer and the tractor respectively from the traction coupling point and the angle information of the trailer in the previous frame;

[0071] According to the crossbeam region of interest, filtering the third point cloud data corresponding to the trailer to obtain the first point cloud data of the crossbeam;

[0072] Determining a first straight line equation of the beam on a horizontal plane according to the first point cloud data;

[0073] The first angle value is determined according to the first straight line equation.

[0074] In a possible implementation manner, the preset manner is determined based on second point cloud data of the fender of the trailer;

[0075] Correspondingly, the acquisition module acquires the first angle value of the trailer relative to the tractor in the current frame determined by the preset method, specifically for:

[0076] Determine the crossbeam region of interest of the baffle according to the distance information of the trailer and the tractor from the traction coupling point respectively and the angle information of the trailer in the previous frame;

[0077] According to the crossbeam region of interest, filtering the fourth point cloud data corresponding to the trailer to obtain the second point cloud data of the baffle;

[0078] Determining a second straight line equation of the baffle in a horizontal plane according to the second point cloud data;

[0079] The first angle value is determined according to the second straight line equation.

[0080] In a possible implementation manner, the preset manner is determined based on image data including lane lines behind the trailer;

[0081] Correspondingly, the acquisition module acquires the first angle value of the trailer relative to the tractor in the current frame determined by the preset method, specifically for:

[0082] Inputting the image data including the lane line behind the trailer into the lane line detection model to obtain the position information of the lane line;

[0083] Determining a fifth angle value of the lane line relative to the trailer according to the position information of the lane line;

[0084] The first angle value is determined according to the fifth angle value and the absolute orientation of the lane line.

[0085] In a possible implementation manner, the preset manner is determined based on movement information of a meter wheel on the contact surface of the trailer;

[0086] Correspondingly, the acquisition module acquires the first angle value of the trailer relative to the tractor in the current frame determined by the preset method, specifically for:

[0087] Acquiring the motion information of the meter wheel collected by the rotary encoder of the tractor on the coupling base;

[0088] Determining, based on the motion information, an angle change of the trailer relative to the tractor;

[0089] The first angle value is determined according to the second angle value of the trailer relative to the tractor in the previous frame and the angle change.

[0090] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0091] The memory stores computer-executable instructions;

[0092] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0093] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0094] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0095] The embodiments of the present application provide a method and device for detecting the relative posture of a trailer, by obtaining a first angle value of the trailer relative to the tractor in the current frame determined by multiple preset methods and a first timestamp corresponding to the current frame under multiple first angle values, the multiple preset methods including: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the trailer's crossbeam, determining based on the second point cloud data of the trailer's fender, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer; performing abnormality detection on at least two preset methods according to the multiple first angle values ​​and the multiple first timestamps to obtain a target angle value; determining the relative posture information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively, so as to achieve the effect of improving the accuracy of the relative posture detection of the trailer. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0097] Figure 1 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 1 ;

[0098] Figure 2 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 2 ;

[0099] Figure 3 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 3 ;

[0100] Figure 4 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 4 ;

[0101] Figure 5 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 5 ;

[0102] Figure 6 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 6 ;

[0103] Figure 7 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 7 ;

[0104] Figure 8 A schematic diagram of the structure of a device for detecting relative position of a trailer provided in this application;

[0105] Fig. 9 A schematic diagram of the structure of the electronic device provided in this application.

[0106] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0107] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0108] First, the terms involved in this application are explained:

[0109] Lane markings: refers to the markings on the road surface that divide different lanes with lines;

[0110] Point cloud data: refers to a data structure used to represent the geometry of a three-dimensional object or environment. It consists of a set of points in three-dimensional space, each of which usually contains spatial coordinates and may contain other information such as color, reflection intensity, etc.

[0111] Secondly, the technical background technology involved in this application is described as follows:

[0112] With the rapid development of logistics and transportation, the need for high-precision detection of the relative position of trailers is increasing. For example, in automated cargo loading and unloading operations, it is necessary to accurately know the position and posture of the trailer relative to the tractor in order to achieve efficient and safe cargo transportation.

[0113] The traditional trailer relative posture detection method mainly relies on sensors, etc., to estimate the vehicle position and posture through position sensors, etc., and then estimate the angle of the trailer relative to the tractor based on the vehicle position and posture as the final angle.

[0114] However, the existing trailer relative posture detection method has low detection accuracy and is difficult to represent the trailer relative posture in actual conditions.

[0115] The detection method and device of the relative posture of the trailer provided in the present application are intended to solve the above technical problems of the prior art. The inventive concept of the present application is as follows: the factors affecting the relative posture information of the trailer include the angle value of the trailer relative to the tractor, the size information of the trailer, and the distance information of the trailer and the tractor from the traction coupling point respectively. At this time, multiple angle values ​​of the trailer relative to the tractor and the corresponding timestamps can be obtained according to different data sources, wherein the data source can be radar, camera, motion deduction, rotary encoder, etc., and then the angle values ​​obtained from different sources can be detected for abnormalities, unreliable angle values ​​can be removed, and a more accurate angle value of the trailer relative to the tractor can be obtained, thereby, based on the reliable angle value, a more accurate relative posture of the trailer can be determined.

[0116] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0117] Figure 1 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0118] The electronic device may be the vehicle itself or a control device installed on the vehicle.

[0119] Step 11, obtaining a first angle value of the trailer relative to the tractor in the current frame determined by multiple preset methods and a first timestamp corresponding to the current frame under multiple first angle values;

[0120] Among them, multiple preset methods include: determination based on the first position information of the tractor in the previous frame, determination based on the first point cloud data of the trailer's crossbeam, determination based on the second point cloud data of the trailer's fender, determination based on image data including lane lines behind the trailer, and determination based on at least two of the motion information of the meter wheel on the trailer's contact surface.

[0121] In this step, there are multiple preset methods to determine the first angle value of the trailer relative to the tractor in the current frame, and at least two preset methods are selected from the multiple preset methods. Then, the corresponding at least two first angle values ​​are obtained according to the specific contents of the at least two selected preset methods, and the first timestamps corresponding to the current frame under the at least two first angle values ​​are obtained.

[0122] In a possible implementation, the first point cloud data refers to three-dimensional spatial data describing a crossbeam of a trailer; and the second point cloud data refers to three-dimensional spatial data describing a fender of the trailer.

[0123] In one possible implementation, preset method 1 can be determined based on the first position information of the tractor in the previous frame, preset method 2 can be determined based on the first point cloud data of the crossbeam of the trailer, preset method 3 can be determined based on the second point cloud data of the fender of the trailer, preset method 4 can be determined based on the image data including the lane line behind the trailer, and preset method 5 can be determined based on the motion information of the meter wheel on the contact surface of the trailer.

[0124] Obtaining the first angle value of the trailer relative to the tractor in the current frame can be determined by two preset methods, such as preset method 1 and preset method 2, preset method 3 and preset method 4, etc.; it can be determined by three preset methods, such as preset method 1, preset method 2 and preset method 3, or preset method 2, preset method 3 and preset method 4, etc.; it can also be determined by four preset methods, such as preset method 1, preset method 2, preset method 3 and preset method 4.

[0125] In addition, the first timestamp corresponding to the current frame under the multiple first angle values ​​can be obtained by using log data or timestamp data included in the relevant information and data in multiple preset methods.

[0126] Step 12: Perform anomaly detection on at least two preset modes according to the multiple first angle values ​​and the multiple first timestamps to obtain a target angle value.

[0127] In this step, based on multiple first angle values ​​and multiple first timestamps, anomaly detection can be performed on at least two preset methods for determining multiple first angle values ​​and multiple first timestamps, the detected abnormal values ​​are processed, and at least one processed first angle value is used as the target angle value.

[0128] Exemplarily, anomaly detection refers to performing anomaly processing on multiple first angle values ​​and multiple first timestamps determined by at least two preset methods; the target angle value refers to the multiple first angle values ​​obtained by screening after anomaly detection.

[0129] In a possible implementation, anomaly detection can be performed on multiple first angle values ​​of the current frame based on multiple historical first angle values ​​and multiple first timestamps determined in at least two preset ways. Different thresholds for the trailer angle change speed are set according to different actual application scenarios. When the trailer angle change speed is greater than the threshold corresponding to the application scenario, it indicates that an abnormal trailer angle change value has occurred, and the abnormally detected trailer angle change value is deleted.

[0130] For example, the actual application scenario may be a reversing scenario, a turning scenario, a stable driving scenario, a hill start or a hill climbing scenario, etc. Different thresholds may be set for the operation information of the tractor in different scenarios.

[0131] Step 13: Determine the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0132] In this step, the distance information between the trailer and the traction coupling point can be obtained according to the position of the traction coupling point and the position of the trailer, and the distance information between the tractor and the traction coupling point can be obtained according to the position of the traction coupling point and the position of the tractor. Then, according to the target angle value, the angle of the trailer relative to the tractor is determined, and according to the length and width information in the size information of the trailer, the positions of the four sides of the trailer relative to the tractor are determined, and finally the relative posture information of the trailer is determined.

[0133] Exemplarily, the traction coupling point refers to the center point of connection between the trailer and the tractor, and the relative position information of the trailer refers to information indicating the position and posture of the trailer relative to the tractor.

[0134] In a possible implementation, the distance information between the trailer and the traction coupling point may be the straight-line distance between the center point of the rear axle of the trailer and the traction coupling point, and the distance information between the tractor and the traction coupling point may be the straight-line distance between the center point of the rear axle of the tractor and the traction coupling point.

[0135] Optionally, step 13 may include the following implementation: determining the relative position and relative angle of the center of the trailer relative to the tractor based on the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively; and determining the relative position and relative angle as the relative posture information of the trailer.

[0136] In this implementation, the center of the trailer can be determined based on the size information of the trailer (such as the length, width, height, etc. of the trailer), and then the distance information between the center of the trailer and the center of the tractor and the traction coupling point is determined.

[0137] Furthermore, taking the traction coupling point as the origin of the reference coordinate system, the distance between the trailer and the traction coupling point and the coordinates of the trailer, as well as the distance between the tractor and the traction coupling point and the coordinates of the tractor are obtained, and coordinate calculation is performed to obtain the relative position of the center of the trailer relative to the tractor. According to the coordinate relationship, trigonometric calculation is performed to obtain the relative angle of the center of the trailer relative to the tractor, and the relative position and relative angle are determined as the relative posture information of the trailer.

[0138] In a possible implementation, the center of the trailer may be the center of the front axle or the center of the rear axle of the trailer, and the center of the tractor may be the center of the front axle or the center of the rear axle of the tractor.

[0139] The method for detecting the relative posture of a trailer provided in an embodiment of the present application obtains a first angle value of the trailer relative to the tractor in the current frame determined by multiple preset methods and a first timestamp corresponding to the current frame under multiple first angle values, wherein the multiple preset methods include: determining based on the first posture information of the tractor in the previous frame, determining based on the first point cloud data of the trailer's crossbeam, determining based on the second point cloud data of the trailer's fender, determining based on the image data including the lane line behind the trailer, and determining based on the motion information of the meter wheel on the contact surface of the trailer. At least two of the preset methods are detected for abnormalities based on the multiple first angle values ​​and the multiple first timestamps to obtain a target angle value; the relative posture information of the trailer is determined based on the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively, so as to achieve the effect of improving the detection accuracy of the relative posture of the trailer.

[0140] Based on the above embodiments, Figure 2 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 2 ,like Figure 2 As shown, the above step 12 may include the following implementations:

[0141] Step 21, obtaining a second angle value of the trailer relative to the tractor in the previous frame and a second timestamp corresponding to the previous frame under the second angle value.

[0142] In this step, relevant information of the previous frame can be detected, from which the second angle value of the trailer relative to the tractor in the previous frame and the second timestamp corresponding to the previous frame under the second angle value can be obtained.

[0143] In actual implementation, for different preset modes, the second angle value and the second timestamp can be the angle value and the timestamp of the previous frame under the preset mode; or they can be the standard angle and the standard timestamp of the previous frame under actual circumstances.

[0144] For example, the second angle value of the trailer relative to the tractor in the previous frame and the second timestamp corresponding to the previous frame under the second angle value may be obtained according to the historical records or logs.

[0145] Step 22: For any first angle value, determine a first difference between the first angle value and the second angle value, and a second difference between the first timestamp and the second timestamp.

[0146] In this step, for each first angle value, the difference between the first angle value and the second angle value can be calculated and recorded as the first difference; the difference between the first timestamp and the second timestamp can be calculated and recorded as the second difference.

[0147] Optionally, before step 22, the following can also be performed: filtering any of the above-mentioned first angle values ​​and second angle values, and a Kalman filtering method can be used to predict the first angle value based on the second angle value, and the predicted first angle value is compared with the existing first angle value to smooth the noisy first angle value to eliminate noise fluctuations.

[0148] Step 23: if the ratio of the first difference to the second difference is less than a first preset threshold, determine that the first angle value is a third angle value that is not abnormal;

[0149] The first preset threshold is determined based on the operating information of the tractor.

[0150] In this step, the first difference is divided by the second difference to obtain a ratio, and the first preset threshold value under the current operating state is determined according to the operating information of the tractor. The ratio is compared with the first preset threshold value. If the ratio is less than the first preset threshold value, the first angle value is used as a non-abnormal third angle value.

[0151] In a possible implementation, different application scenarios may be: reversing, turning, climbing, and going straight, and the operation information of the tractor may be the speed information, gear information, steering wheel angle, etc. of the vehicle in the corresponding scenario.

[0152] A reasonable first preset threshold value can be determined based on the operation information of the tractor. Under different operation information, the angle value between the tractor and the trailer changes differently. When it is determined based on the operation information that the tractor is moving straight at a constant speed, the relative angle between the tractor and the trailer changes slightly, and the first preset threshold value is relatively small at this time; when it is determined that the tractor is turning, the steering angle of the tractor will affect the path and angle of the trailer, causing the relative angle between the tractor and the trailer to change, and the first preset threshold value is relatively large at this time.

[0153] Step 24: Determine a target angle value according to at least one third angle value.

[0154] In this step, at least one third angle value may be filtered based on a preset rule to obtain a filtered third angle value as a target angle value.

[0155] Optionally, the above step 24 may include the following implementation:

[0156] Step 1: If the number of at least one third angle value is an integer greater than 1, two fourth angle values ​​with the smallest angle difference are determined from the at least one third angle value.

[0157] For example, if the number of at least one third angle value is 2, the two third angle values ​​are determined as two fourth angle values; if the number of at least one third angle value is 3, the angle difference 1 between the third angle value 1 and the third angle value 2, the angle difference 2 between the third angle value 1 and the third angle value 3, and the angle difference 3 between the third angle value 2 and the third angle value 3 are calculated, and the sizes of the angle difference 1, the angle difference 2, and the angle difference 3 are compared, and the two third angle values ​​with the smallest angle difference are taken as the two fourth angle values.

[0158] In a possible implementation, if the number of the at least one third angle value is 1, the at least one third angle value is determined to be a target angle value.

[0159] Step 2: If the angle difference between the two fourth angle values ​​is greater than the second preset threshold, the target angle value is determined in the fourth angle value based on the first priority sequence, and the priority order in the first priority sequence is from large to small: beam or baffle, lane line, motion information, and the first position information of the tractor.

[0160] In this implementation, the angle difference between the two fourth angle values ​​is compared with the second preset threshold. If it is greater than the second preset threshold, the fourth angle value corresponding to the higher priority is used as the target angle value according to the priority order in the first priority sequence.

[0161] The first priority sequence refers to the priority of multiple preset methods, that is, the priority order is: radar (beam or baffle), camera (lane line), rotary encoder (motion information), motion deduction (the first position information of the tractor).

[0162] Step 3: If the angle difference between the two fourth angle values ​​is not greater than the second preset threshold, the target angle value is determined in the fourth angle value based on the second priority sequence, and the priority order in the second priority sequence is from large to small: the first position information of the tractor, motion information, beam or baffle, and lane line.

[0163] In this implementation, the angle difference between the two fourth angle values ​​is compared with the second preset threshold. If it is not greater than the second preset threshold, the fourth angle value corresponding to the higher priority is used as the target angle value according to the priority order in the second priority sequence.

[0164] Exemplarily, the second priority sequence refers to the priorities of multiple preset methods, that is, the priorities are: motion deduction (the first position information of the tractor), rotary encoder (motion information), radar (beam or baffle), camera (lane line).

[0165] It should be understood that the examples of the values ​​involved in this application are only for the purpose of illustrating the principles of the scheme and do not limit the actual values.

[0166] The detection method of the relative posture of the trailer provided in the embodiment of the present application obtains the second angle value of the trailer relative to the tractor in the previous frame and the second timestamp corresponding to the previous frame under the second angle value, and then determines the first difference between the first angle value and the second angle value, and the second difference between the first timestamp and the second timestamp for any first angle value. If the ratio of the first difference to the second difference is less than the first preset threshold, the first angle value is determined to be a non-abnormal third angle value, and the first preset threshold is determined based on the operation information of the tractor. Finally, the target angle value is determined based on at least one third angle value. The technical solution uses the first preset threshold to filter out angle values ​​that do not conform to the vehicle operation conditions, thereby obtaining an accurate target angle value corresponding to the trailer relative to the tractor, and ensuring the accuracy of the subsequent determination of the relative posture of the trailer.

[0167] Based on the above embodiment, the preset method is determined based on the posture information of the tractor in the previous frame; accordingly, Figure 3 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 3 In the above step 11, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by a preset method may include the following implementation:

[0168] Step 31, obtaining the first pose information of the tractor in the previous frame and the second pose information of the tractor in the current frame;

[0169] The first pose information and the second pose information may both include: timestamp, speed, and absolute orientation in the corresponding frame.

[0170] In this step, the current frame information is first determined, and the second posture information of the tractor in the current frame is obtained. According to the current frame information, the previous frame information is determined, and then the first posture information of the tractor in the previous frame is obtained.

[0171] In one possible implementation, the timestamp can be a standard time format for recording the trailer posture data collection; the speed can be the linear speed or angular velocity of the trailer, which helps to dynamically track the changes in the trailer movement; the absolute orientation can be the orientation determined based on the latitude, longitude and altitude information.

[0172] Step 32: Determine a first angle value according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0173] In this step, the distance information between the trailer and the tractor and the traction coupling point respectively (i.e., the distance information between the trailer and the traction coupling point and the distance information between the tractor and the traction coupling point) can be obtained based on the structural data (size data) of the trailer and the tractor, and then the first posture information, the second posture information, and the distance information are input into the kinematic deduction model to obtain the first angle value of the trailer relative to the tractor.

[0174] The method for detecting the relative posture of the trailer provided in the embodiment of the present application obtains the first posture information of the tractor in the previous frame and the second posture information of the tractor in the current frame, and the posture information includes: timestamp, speed, and absolute orientation; then, the first angle value is determined according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively. In this technical solution, the first angle value of the trailer relative to the tractor can be obtained according to the posture information of the previous frame and the current frame, as well as the structural data of the vehicle.

[0175] On the basis of the above embodiment, the preset method is determined based on the first point cloud data of the cross beam of the trailer; accordingly, Figure 4 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 4 In the above step 11, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by a preset method may include the following implementation:

[0176] Among them, a sensor laser radar is installed on the tractor, and the installation position and angle can cover the entire trailer. The point cloud data of the entire trailer is further obtained based on the sensor laser radar, and the sensor data is converted to a coordinate system fixed on the tractor (such as the center of the tractor) to obtain the third point cloud data.

[0177] Step 41: Determine the crossbeam region of interest of the trailer according to the distance information of the trailer and the tractor from the traction coupling point respectively and the angle information of the trailer in the previous frame.

[0178] In this step, the distance information between the trailer and the tractor and the traction coupling point, and the angle information of the trailer in the previous frame can be analyzed to obtain the position data and angle data related to the crossbeam area of ​​interest, and the boundary of the crossbeam area of ​​interest can be determined based on the length and width of the trailer crossbeam, thereby determining the crossbeam area of ​​interest of the trailer.

[0179] In a possible implementation, the specific position of the trailer relative to the tractor can be determined based on the distance information of the trailer and the tractor from the traction coupling point and the angle information of the trailer in the previous frame, and then the specific position of the trailer beam relative to the tractor can be determined. Through coordinate transformation, the coordinate position of the beam is transformed from the trailer local coordinate system to the above-mentioned coordinate system of the tractor and the trailer. At the same time, considering the width and length of the trailer beam, the interest area of ​​the trailer beam is determined.

[0180] Step 42: Filter the third point cloud data corresponding to the trailer according to the region of interest of the crossbeam to obtain the first point cloud data of the crossbeam.

[0181] In this step, the third point cloud data is obtained, and according to the relative area of ​​the area of ​​interest of the trailer beam to the overall area of ​​the trailer, the point cloud data corresponding to the relative area in the third point cloud data is extracted, and the extracted point cloud data is used as the first point cloud data of the beam.

[0182] Step 43: Determine a first straight line equation of the beam in the horizontal plane according to the first point cloud data.

[0183] In this step, a random sampling consistency method may be used to fit the first point cloud data to obtain a first straight line equation of the beam in the horizontal plane.

[0184] In a possible implementation, the normal vector (n x , n y , n z ), where n x *n x +n y *n y +n z *n z = 1. Project the normal vector of each point onto the xy plane (i.e., the horizontal plane) to obtain a two-dimensional vector (n x , n y ), according to the relationship n x *n x +n y *n y >T filtering obtains points in the point cloud whose normal vectors are approximately parallel to the xy plane, that is, points that fall on the vertical plane of the trailer beam, where T is a set threshold, such as 0.99.

[0185] The random sampling consistency method is used to perform plane fitting on the points falling on the vertical plane of the trailer beam, and the vertical plane equation of the trailer beam is obtained as ax+by+cz+d=0. At the same time, the internal points in the fitting process are obtained, that is, the points that are finally used to determine the vertical plane equation of the trailer beam in the fitting process.

[0186] According to the points in the vertical plane equation of the trailer beam, the z values ​​of the point cloud are all assigned to 0, that is, the point cloud is compressed to the xy plane to obtain a group of two-dimensional point clouds. The random sampling consistency method is used to perform straight line fitting on the obtained two-dimensional point cloud, and the first straight line equation of the trailer beam in the xy plane is obtained as ax+by+c=0.

[0187] Step 44: Determine a first angle value according to the first straight line equation.

[0188] In a possible implementation, an angle value obtained by calculating arctan(b / a) according to coefficients a and b in the first straight line equation is used as the first angle value.

[0189] The method for detecting the relative posture of the trailer provided in the embodiment of the present application first determines the crossbeam region of interest of the trailer based on the distance information of the trailer and the tractor respectively from the traction coupling point and the angle information of the trailer in the previous frame; then, based on the crossbeam region of interest, the third point cloud data corresponding to the trailer is filtered to obtain the first point cloud data of the crossbeam; then, based on the first point cloud data, the first straight line equation of the crossbeam in the horizontal plane is determined; finally, based on the first straight line equation, the first angle value is determined. Through the point cloud data of the crossbeam region of the trailer, the angle value of the trailer relative to the tractor can be accurately mapped.

[0190] On the basis of the above embodiment, the preset method is determined based on the second point cloud data of the baffle of the trailer; accordingly, Figure 5 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 5 In the above step 11, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by a preset method may include the following implementation:

[0191] Among them, a sensor laser radar is installed on the tractor, and the installation position and angle can cover the entire trailer, and the sensor data is converted to a coordinate system fixed to the tractor (such as the center of the tractor) to obtain the fourth point cloud data.

[0192] Step 51 : Determine the baffle region of interest based on the distance information between the trailer and the tractor and the traction coupling point, and the angle information of the trailer in the previous frame.

[0193] In this step, the boundaries of the regions of interest of the left and right side baffles of the trailer are determined respectively according to the distance information of the trailer and the tractor from the traction coupling point and the angle information of the trailer in the previous frame, and the regions of interest of the baffles include the regions of interest of the baffles corresponding to the left and right side baffles of the trailer.

[0194] Step 52: Filter the fourth point cloud data corresponding to the trailer according to the baffle area of ​​interest to obtain the second point cloud data of the baffle.

[0195] In this step, according to the region of interest of the baffle of the trailer, point cloud data corresponding to the region of interest of the baffle in the fourth point cloud data is extracted, and the extracted point cloud data is used as the second point cloud data of the baffle.

[0196] Step 53: Determine a second straight line equation of the baffle in the horizontal plane according to the second point cloud data.

[0197] In this step, a random sampling consistency method may be used to fit the second point cloud data to obtain a second straight line equation of the baffle in the horizontal plane.

[0198] In one possible implementation, the normal vector of each point in the area of ​​interest of the baffle is estimated respectively, and the normal vector is projected to the xy ground to obtain a two-dimensional vector, which is further filtered to obtain the points falling on the vertical plane of the trailer side baffle, and the point clouds on the vertical planes of the left and right trailer side baffles are merged into the vertical plane point cloud of the trailer side baffle. The point cloud is then fitted to obtain the vertical plane equation of the trailer side baffle mx+ny+pz+q=0, and the inner points in the fitting process are obtained, and the z values ​​of the inner point cloud are all assigned to 0, and the second straight line equation of the trailer side baffle in the xy plane is further fitted to obtain mx+ny+q=0.

[0199] Step 54: Determine the first angle value according to the second straight line equation.

[0200] In a possible implementation, an angle value obtained by calculating arctan(n / m) according to the coefficients m and n in the second straight line equation is used as the first angle value.

[0201] The method for detecting the relative posture of the trailer provided in the embodiment of the present application first determines the baffle region of interest based on the distance information of the trailer and the tractor from the traction coupling point respectively and the angle information of the trailer in the previous frame; then, based on the baffle region of interest, the fourth point cloud data corresponding to the trailer is filtered to obtain the second point cloud data of the baffle; then, based on the second point cloud data, the second straight line equation of the baffle in the horizontal plane is determined; finally, based on the second straight line equation, the first angle value is determined. In this technical solution, the angle value of the trailer relative to the tractor can be accurately mapped through the point cloud data of the baffle area of ​​the trailer.

[0202] Based on the above embodiment, the preset method is determined based on the image data including the lane line behind the trailer; accordingly, Figure 6 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 6 In the above step 11, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by a preset method may include the following implementation:

[0203] Among them, a sensor camera is installed on the trailer, and the installation position and angle need to cover the ground area directly behind the trailer.

[0204] Step 61: Input the image data including the lane line behind the trailer into the lane line detection model to obtain the position information of the lane line.

[0205] In this step, based on the camera, image data including the lane line behind the trailer is obtained, and the image data is analyzed and processed through the lane line detection model to detect and identify the lane line in the image data, extract the coordinate data of the lane, and obtain the position information of the lane line.

[0206] Exemplarily, a lane detection model refers to a model for detecting and recognizing lanes in an image.

[0207] In a possible implementation, the image data can be the data collected by the camera, which is converted into a coordinate system with the center point of the tractor as the coordinate origin through coordinate transformation, with the positive direction of the x-axis of the coordinate system directly in front of the tractor, the positive direction of the y-axis directly to the left of the tractor, and the positive direction of the z-axis directly above the tractor.

[0208] Step 62: Determine a fifth angle value of the lane line relative to the trailer based on the position information of the lane line.

[0209] In one possible implementation, the position information of the lane line may include the coordinates of the center points at both ends of the lane line. The fifth angle value of the lane line relative to the trailer can be obtained based on the coordinates of the trailer in the coordinate system of the tractor and the coordinates of the lane line in the coordinate system of the tractor.

[0210] Step 63: Determine the first angle value according to the fifth angle value and the absolute direction of the lane line.

[0211] In this step, all the relevant angle value data included may be calculated to obtain the first angle value according to the absolute position of the trailer, the absolute orientation of the lane line, and the fifth angle value of the lane line relative to the trailer.

[0212] In one possible implementation, the absolute position of the trailer can be calculated based on the absolute position of the tractor in the previous frame and the relative position of the trailer to the tractor. The absolute orientation of the lane line in the map of the area behind the trailer can be obtained based on the absolute position of the trailer and the standard map information. Then, the fifth angle value and the absolute orientation of the lane line are added to obtain the absolute orientation of the trailer. Then, the first angle value of the trailer relative to the tractor is determined based on the absolute orientation of the trailer and the absolute orientation of the tractor.

[0213] The method for detecting the relative posture of the trailer provided in the embodiment of the present application obtains the position information of the lane line by inputting the image data including the lane line behind the trailer into the lane line detection model; then, according to the position information of the lane line, the fifth angle value of the lane line relative to the trailer is determined; finally, according to the fifth angle value and the absolute orientation of the lane line, the first angle value is determined. In this technical solution, the angle value of the trailer relative to the tractor can be accurately mapped through the orientation of the lane line of the trailer at the center point of the tractor and the absolute orientation of the lane line.

[0214] Based on the above embodiment, the preset method is determined based on the motion information of the meter wheel on the contact surface of the trailer; accordingly, Figure 7 Schematic diagram of the process of detecting the relative posture of the trailer provided in this application Figure 7 In the above step 11, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by a preset method may include the following implementation:

[0215] Step 71: Obtain the motion information of the meter wheel collected by the rotary encoder on the coupling base of the tractor.

[0216] In this step, a rotary encoder is installed on the coupling base of the tractor, and a meter wheel is placed on the contact surface of the trailer.

[0217] Furthermore, the acquired encoder data is converted into a coordinate system with the center point of the tractor as the coordinate origin through coordinate conversion. The front of the tractor is the positive direction of the x-axis of the coordinate system, the left side of the tractor is the positive direction of the y-axis, and the top of the tractor is the positive direction of the z-axis, so as to obtain the motion information of the meter wheel.

[0218] Step 72: Determine the angle change of the trailer relative to the tractor based on the motion information.

[0219] In this step, the motion information of the meter wheel can be converted into the angle change of the trailer relative to the tractor according to the processing of the encoder.

[0220] Step 73: Determine the first angle value according to the second angle value and angle change of the lower trailer relative to the tractor in the previous frame.

[0221] In this step, the angle of the trailer relative to the tractor in the current frame, i.e., the first angle value, is calculated based on the angle value of the trailer relative to the tractor at the previous frame of the encoder (i.e., the second angle value) and the change in the angle value of the trailer relative to the tractor in step 72.

[0222] In a possible implementation, the first angle value is the sum of the second angle value and the angle change.

[0223] The method for detecting the relative posture of the trailer provided in the embodiment of the present application obtains the motion information of the meter wheel collected by the rotary encoder on the coupling base of the tractor; then determines the angle change of the trailer relative to the tractor based on the motion information; finally determines the first angle value based on the second angle value and angle change of the trailer relative to the tractor in the previous frame. In this technical solution, the angle of the trailer relative to the tractor can be accurately determined by the rotary encoder.

[0224] Figure 8 The schematic diagram of the structure of the trailer relative posture detection device provided in this application is as follows: Figure 8 As shown, the trailer relative posture detection device provided in this embodiment includes:

[0225] an acquisition module 81, for acquiring a first angle value of the trailer relative to the tractor in the current frame and a first timestamp corresponding to the current frame under multiple first angle values ​​determined by multiple preset methods, wherein the multiple preset methods include: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the crossbeam of the trailer, determining based on the second point cloud data of the fender of the trailer, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer;

[0226] A detection module 82, configured to perform anomaly detection on at least two preset modes according to the plurality of first angle values ​​and the plurality of first time stamps, to obtain a target angle value;

[0227] The determination module 83 is used to determine the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0228] In a possible implementation, the detection module 82 is specifically configured to:

[0229] Obtain a second angle value of the trailer relative to the tractor in the previous frame and a second timestamp corresponding to the previous frame under the second angle value;

[0230] For any first angle value, determining a first difference between the first angle value and the second angle value, and a second difference between the first timestamp and the second timestamp;

[0231] If the ratio of the first difference to the second difference is less than a first preset threshold, determining the first angle value to be a third angle value that is not abnormal, the first preset threshold being determined based on the operating information of the tractor;

[0232] A target angle value is determined based on at least one third angle value.

[0233] In a possible implementation, the detection module 82 determines the target angle value according to at least one third angle value, specifically for:

[0234] If the number of at least one third angle value is an integer greater than 1, two fourth angle values ​​with the smallest angle difference are determined at the at least one third angle value;

[0235] If the angle difference between the two fourth angle values ​​is greater than the second preset threshold, a target angle value is determined from the fourth angle values ​​based on the first priority sequence, wherein the priority order in the first priority sequence is, from largest to smallest, the beam or baffle, the lane line, the motion information, and the first position information of the tractor;

[0236] If the angle difference between the two fourth angle values ​​is not greater than the second preset threshold, the target angle value is determined in the fourth angle value based on the second priority sequence, and the priority order in the second priority sequence is from large to small: the first posture information of the tractor, motion information, beam or baffle, and lane line.

[0237] In a possible implementation, the determination module 83 is specifically configured to:

[0238] Determine the relative position and angle of the center of the trailer relative to the tractor according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the tractor coupling point respectively;

[0239] The relative position and relative angle are determined as the relative posture information of the trailer.

[0240] In a possible implementation, the preset mode is determined based on the position information of the tractor in the previous frame;

[0241] Correspondingly, the acquisition module 81 acquires the first angle value of the trailer relative to the tractor in the current frame determined in a preset manner, which is specifically used for:

[0242] Get the first pose information of the tractor in the previous frame and the second pose information of the tractor in the current frame. The pose information includes: timestamp, speed, and absolute orientation.

[0243] A first angle value is determined according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively.

[0244] In a possible implementation, the preset manner is determined based on first point cloud data of a crossbeam of the trailer;

[0245] Correspondingly, the acquisition module 81 acquires the first angle value of the trailer relative to the tractor in the current frame determined in a preset manner, which is specifically used for:

[0246] According to the distance information of the trailer and the tractor to the traction coupling point respectively and the angle information of the trailer in the previous frame, the crossbeam area of ​​interest of the trailer is determined;

[0247] According to the region of interest of the beam, the third point cloud data corresponding to the trailer is filtered to obtain the first point cloud data of the beam;

[0248] Determine a first straight line equation of the beam on a horizontal plane according to the first point cloud data;

[0249] According to the first straight line equation, a first angle value is determined.

[0250] In a possible implementation, the preset manner is determined based on second point cloud data of a fender of the trailer;

[0251] Correspondingly, the acquisition module 81 acquires the first angle value of the trailer relative to the tractor in the current frame determined in a preset manner, which is specifically used for:

[0252] According to the distance information of the trailer and the tractor respectively from the traction coupling point and the angle information of the trailer in the previous frame, the baffle area of ​​interest is determined;

[0253] According to the region of interest of the baffle, the fourth point cloud data corresponding to the trailer is filtered to obtain the second point cloud data of the baffle;

[0254] Determine a second straight line equation of the baffle on the horizontal plane according to the second point cloud data;

[0255] According to the second straight line equation, a first angle value is determined.

[0256] In a possible implementation, the preset manner is determined based on image data including lane lines behind the trailer;

[0257] Correspondingly, the acquisition module 81 acquires the first angle value of the trailer relative to the tractor in the current frame determined in a preset manner, which is specifically used for:

[0258] Input the image data including the lane line behind the trailer into the lane line detection model to obtain the position information of the lane line;

[0259] Determine a fifth angle value of the lane line relative to the trailer according to the position information of the lane line;

[0260] The first angle value is determined according to the fifth angle value and the absolute direction of the lane line.

[0261] In a possible implementation, the preset manner is determined based on the motion information of the meter wheel on the contact surface of the trailer;

[0262] Correspondingly, the acquisition module 81 acquires the first angle value of the trailer relative to the tractor in the current frame determined in a preset manner, which is specifically used for:

[0263] Obtaining the motion information of the meter wheel collected by the rotary encoder on the coupling base of the tractor;

[0264] According to the motion information, determine the angle change of the trailer relative to the tractor;

[0265] The first angle value is determined according to the second angle value and the angle change of the trailer relative to the tractor in the previous frame.

[0266] The trailer relative posture detection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0267] Fig. 9 This is a schematic diagram of the structure of the electronic device provided in this application. Fig. 9 As shown, the electronic device 9 provided in this embodiment includes: at least one processor 91 and a memory 92.

[0268] Optionally, the device 9 further includes a communication component 93 , wherein the processor 91 , the memory 92 and the communication component 93 are connected via a bus 94 .

[0269] In a specific implementation process, at least one processor 91 executes computer-executable instructions stored in the memory 92, so that at least one processor 91 executes the above method.

[0270] The specific implementation process of the processor 91 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0271] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0272] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0273] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0274] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0275] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0276] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0277] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0278] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0279] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0280] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0281] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0282] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0283] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for detecting relative posture of a trailer, characterized in that: include: Acquire a first angle value of the trailer relative to the tractor in the current frame and a first timestamp corresponding to the current frame under the multiple first angle values ​​determined by multiple preset methods, wherein the multiple preset methods include: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the crossbeam of the trailer, determining based on the second point cloud data of the fender of the trailer, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer; According to the multiple first angle values ​​and the multiple first timestamps, performing anomaly detection on the at least two preset modes to obtain a target angle value; The relative position information of the trailer is determined according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

2. The method according to claim 1, characterized in that The performing abnormality detection on the at least two preset modes according to the multiple first angle values ​​and the multiple first timestamps to obtain a target angle value includes: Obtaining a second angle value of the trailer relative to the tractor in a previous frame and a second timestamp corresponding to a previous frame under the second angle value; For any first angle value, determining a first difference between the first angle value and the second angle value, and a second difference between the first timestamp and the second timestamp; If the ratio of the first difference to the second difference is less than a first preset threshold, determining that the first angle value is a third non-abnormal angle value, wherein the first preset threshold is determined based on the operation information of the tractor; The target angle value is determined according to at least one third angle value.

3. The method according to claim 2, characterized in that The step of determining the target angle value according to at least one third angle value comprises: If the number of the at least one third angle value is an integer greater than 1, two fourth angle values ​​with the smallest angle difference are determined from the at least one third angle value; If the angle difference between the two fourth angle values ​​is greater than a second preset threshold, the target angle value is determined from the fourth angle values ​​based on a first priority sequence, wherein the priority order in the first priority sequence is, from largest to smallest, a beam or baffle, a lane line, the motion information, and the first position information of the tractor; If the angle difference between the two fourth angle values ​​is not greater than the second preset threshold, the target angle value is determined in the fourth angle values ​​based on a second priority sequence, and the priority order in the second priority sequence is from large to small: the first posture information of the tractor, the motion information, the beam or baffle, and the lane line.

4. The method according to claim 1, characterized in that: Determining the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively includes: Determine the relative position and relative angle of the center of the trailer relative to the tractor according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the tractor coupling point respectively; The relative position and the relative angle are determined as relative posture information of the trailer.

5. The method according to any one of claims 1 to 4, characterized in that: The preset method is determined based on the position information of the tractor in the previous frame; Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes: Obtaining the first pose information of the tractor in the previous frame and the second pose information of the tractor in the current frame, the pose information including: timestamp, speed, and absolute orientation; The first angle value is determined according to the first posture information, the second posture information, and the distance information between the trailer and the tractor and the traction coupling point respectively.

6. The method according to any one of claims 1 to 4, characterized in that: The preset method is determined based on first point cloud data of the crossbeam of the trailer; Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes: Determine the crossbeam region of interest of the trailer according to the distance information of the trailer and the tractor respectively from the traction coupling point and the angle information of the trailer in the previous frame; According to the crossbeam region of interest, filtering the third point cloud data corresponding to the trailer to obtain the first point cloud data of the crossbeam; Determining a first straight line equation of the beam on a horizontal plane according to the first point cloud data; The first angle value is determined according to the first straight line equation.

7. The method according to any one of claims 1 to 4, characterized in that: The preset manner is determined based on the second point cloud data of the fender of the trailer; Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes: Determine the baffle region of interest according to the distance information between the trailer and the tractor and the traction coupling point respectively and the angle information of the trailer in the previous frame; According to the baffle region of interest, filtering the fourth point cloud data corresponding to the trailer to obtain the second point cloud data of the baffle; Determining a second straight line equation of the baffle in a horizontal plane according to the second point cloud data; The first angle value is determined according to the second straight line equation.

8. The method according to any one of claims 1 to 4, characterized in that: The preset method is determined based on image data including lane lines behind the trailer; Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes: Inputting the image data including the lane line behind the trailer into the lane line detection model to obtain the position information of the lane line; Determining a fifth angle value of the lane line relative to the trailer according to the position information of the lane line; The first angle value is determined according to the fifth angle value and the absolute orientation of the lane line.

9. The method according to any one of claims 1 to 4, characterized in that: The preset method is determined based on the movement information of the meter wheel on the contact surface of the trailer; Correspondingly, obtaining the first angle value of the trailer relative to the tractor in the current frame determined by the preset method includes: Acquiring the motion information of the meter wheel collected by the rotary encoder of the tractor on the coupling base; Determining, based on the motion information, an angle change of the trailer relative to the tractor; The first angle value is determined according to the second angle value of the trailer relative to the tractor in the previous frame and the angle change.

10. A device for detecting relative position of a trailer, characterized in that: include: an acquisition module, used for acquiring a first angle value of the trailer relative to the tractor in the current frame and a first timestamp corresponding to the current frame under the multiple first angle values ​​determined by multiple preset methods, wherein the multiple preset methods include: determining based on the first position information of the tractor in the previous frame, determining based on the first point cloud data of the crossbeam of the trailer, determining based on the second point cloud data of the fender of the trailer, determining based on the image data including the lane line behind the trailer, and determining based on at least two of the motion information of the meter wheel on the contact surface of the trailer; A detection module, configured to perform anomaly detection on the at least two preset modes according to the multiple first angle values ​​and the multiple first time stamps to obtain a target angle value; A determination module is used to determine the relative position information of the trailer according to the target angle value, the size information of the trailer, and the distance information between the trailer and the tractor and the traction coupling point respectively.

Citation Information

Patent Citations

  • Trailer pose detection method and device, target trailer and storage medium

    CN116543045A

  • Hitch-angle estimation for tractor-trailer combination

    US20230176222A1