Lane matching posture determination method, device, equipment and medium

Abstract

A method, device, equipment and medium for determining lane line matching posture, belonging to the field of automobile technology. The method includes: determining the recursive change amount of the track within the cycle time based on the vehicle track at the i-th perception moment and the i-th perception moment; determining the first initial matching posture of the lane line at the i-th perception moment based on the recursive change amount of the track and the target matching posture of the lane line at the i-th perception moment, the lane line is the lane line in the shooting result obtained by the shooting device on the vehicle shooting the road in front of the vehicle; constructing a graph optimizer based on the first initial matching posture; determining the target lane line in the map based on the first initial matching posture; determining the minimum residual from the target point to the target lane line for the target point; adding the target input data to the graph optimizer; running the graph optimizer according to the preset number of iterations, and outputting the target matching posture of the lane line at the i-th perception moment, which can improve the lane line matching position accuracy.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a method, device, equipment and computer-readable storage medium for determining lane matching posture. Background Art

[0002] During vehicle driving, especially in scenes such as turning and U-turns, lane line matching and positioning is the key to vehicle safety. How to accurately perform lane line matching and positioning has become an urgent problem to be solved. In related technologies, due to cost and technical limitations, there will be large deviations between existing high-precision maps and the real world in some areas. If the vehicle is driving in these areas, when performing lane line matching and positioning, the high-precision map is fused with the real-time dynamic carrier differential technology / global navigation satellite system (Real-time Kinematic / Global Navigation Satellite System, RTK / GNSS). Due to the deviation between the high-precision map and the real world, the lane line matching posture in the fused positioning result is inaccurate, and there is a risk of the vehicle running over the lane line, hitting the wall, or even causing a safety accident. Summary of the invention

[0003] The present application provides a lane line matching posture determination method, device, equipment and computer-readable storage medium, which can solve the technical problems existing in the prior art of low lane line matching positioning accuracy, the risk of vehicles running over lane lines, hitting walls, and even causing safety accidents.

[0004] In a first aspect, an embodiment of the present application provides a lane line matching posture determination method, the lane line matching posture determination method comprising:

[0005] Based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time, determining the recursive change amount of the track within the cycle time;

[0006] Determine a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change of the track and the target matching pose of the lane line at the i-1th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting the road ahead of the vehicle by a shooting device on the vehicle;

[0007] Based on the first initial matching pose, construct a graph optimizer;

[0008] Determine a target lane line in the map based on the first initial matching pose;

[0009] For the target point, determine the minimum residual from the target point to the target lane line, the distance threshold is the distance between the longitudinal position of the lane line and the vehicle, and the target point is a point in the lane line point set obtained after analyzing the lane lines within the distance threshold range;

[0010] Adding target input data to the graph optimizer, the target input data including a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual;

[0011] Run the graph optimizer according to the preset number of iterations and output the target matching pose of the lane line at the i-th perception moment.

[0012] In combination with the first aspect, in one implementation, the recursive change amount of the track within the cycle time is determined based on the vehicle track at the i-1th perception time and the vehicle track at the i-th perception time, and the corresponding formula is:

[0013]

[0014] in, is the recursive change of the track within the cycle time, is the vehicle track at the i-th perception time, is the vehicle track at the i-1th sensing moment.

[0015] In combination with the first aspect, in one implementation, the first initial matching pose of the lane line at the i-th sensing moment is determined based on the recursive change amount of the track and the target matching pose of the lane line at the i-1th sensing moment, and the corresponding formula is:

[0016]

[0017] in, is the first initial matching pose of the lane line at the i-th perception moment, is the recursive change of the track, The target matching pose of the lane line at the i-1th perception moment.

[0018] In combination with the first aspect, in one implementation, for the target point, determining the minimum residual from the target point to the target lane line, the corresponding formula is:

[0019]

[0020]

[0021] in, is the minimum residual from the jth target point to the target lane line, The first initial matching pose of the lane line at the i-th perception moment, is the map segment vector, p start is the homogeneous matrix of the starting points in the lane line point set, p endis the homogeneous matrix of the lane line point set endpoints, is the homogeneous matrix of the j-th target point, for The antisymmetric matrix of .

[0022] In combination with the first aspect, in one implementation, the target input data further includes a second initial matching posture of the lane line and a second information matrix corresponding to the second initial matching posture of the lane line, wherein the process of determining the second initial matching posture of the lane line includes:

[0023] Determine the RTK / GNSS change within the cycle time based on the vehicle RTK / GNSS data at the i-1th sensing moment and the vehicle RTK / GNSS data at the i-th sensing moment;

[0024] Based on the rtk / gnss change and the target matching pose of the lane line at the i-1th sensing moment, a second initial matching pose of the lane line at the i-th sensing moment is determined.

[0025] In combination with the first aspect, in one implementation, the RTK / GNSS data of the vehicle at the i-1th sensing moment and the RTK / GNSS data of the vehicle at the i-th sensing moment are used to determine the RTK / GNSS change in the cycle time, and the corresponding formula is:

[0026]

[0027] in, is the change of rtk / gnss within the cycle time, is the vehicle RTK / GNSS data at the i-th sensing moment, is the vehicle RTK / GNSS data at the i-1th sensing moment.

[0028] In combination with the first aspect, in one implementation, the second initial matching pose of the lane line at the i-th sensing moment is determined based on the rtk / gnss change and the target matching pose of the lane line at the i-1th sensing moment, and the corresponding formula is:

[0029]

[0030]

[0031]

[0032] in, is the rtk / gnss change, is the transposed matrix of rtk / gnss variation, The target matching pose of the lane line at the i-1th sensing moment, The second initial matching position of the lane line at the i-th sensing moment, t is the position of the vehicle, R 3*3 is the rotation matrix.

[0033] In a second aspect, an embodiment of the present application provides a lane line matching posture determination device, the lane line matching posture determination device comprising:

[0034] A first determination module is used to determine a recursive change amount of the track within the cycle time based on the vehicle track at the i-1th perception time and the vehicle track at the i-th perception time;

[0035] A second determination module is used to determine a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change amount of the track and the target matching pose of the lane line at the i-1-th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting a road ahead of the vehicle by a shooting device on the vehicle;

[0036] A construction module, configured to construct a graph optimizer based on the first initial matching pose;

[0037] A third determination module, configured to determine a target lane line in the map based on the first initial matching posture;

[0038] A fourth determination module is used to determine, for a target point, a minimum residual from the target point to a target lane line, wherein the distance threshold is a distance between a longitudinal position of the lane line and a vehicle, and the target point is a point in a lane line point set obtained by analyzing lane lines within a range of the distance threshold;

[0039] An adding module, configured to add target input data to the graph optimizer, wherein the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual;

[0040] The output module is used to run the graph optimizer according to a preset number of iterations and output the target matching pose of the lane line at the i-th perception moment.

[0041] In the third aspect, an embodiment of the present application provides a lane line matching posture determination device, which includes a processor, a memory, and a lane line matching posture determination program stored in the memory and executable by the processor, wherein when the lane line matching posture determination program is executed by the processor, the steps of the lane line matching posture determination method as described in any one of the first aspects are implemented.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a lane line matching posture determination program is stored. When the lane line matching posture determination program is executed by a processor, the steps of the lane line matching posture determination method as described in any one of the first aspects are implemented.

[0043] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0044] Based on the vehicle track at the i-1th perception moment and the vehicle track at the i-th perception moment, the recursive change amount of the track in the cycle time is determined; based on the recursive change amount of the track and the target matching posture of the lane line at the i-1th perception moment, the first initial matching posture of the lane line at the i-th perception moment is determined, and the lane line is a lane line in the shooting result obtained by the shooting device on the vehicle shooting the road in front of the vehicle; based on the first initial matching posture, a map optimizer is constructed; based on the first initial matching posture, the target lane line in the map is determined; for the target point, the minimum residual from the target point to the target lane line is determined, and the distance threshold is the distance between the longitudinal position of the lane line and the vehicle. distance, the target point is a point in the lane line point set obtained after parsing the lane lines within the distance threshold range; the target input data is added to the graph optimizer, the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual and a residual information matrix corresponding to each minimum residual; according to a preset number of iterations, the graph optimizer is run to output the target matching pose of the lane line at the i-th perception moment, and the inter-frame pose matching of the lane line is realized by constraining the lane line through the vehicle track. The graph optimizer is used to determine the optimal matching pose, which can improve the lane line matching position accuracy and reduce the risk of vehicles running over lane lines, hitting walls, and causing safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of the first embodiment of the lane matching posture determination method of the present application;

[0046] Figure 2 This is a schematic diagram of the functional modules of an embodiment of a lane matching posture determination device of the present application;

[0047] Figure 3 Schematic diagram of the hardware structure of the lane matching posture determination device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0050] In a first aspect, an embodiment of the present application provides a method for determining lane matching posture.

[0051] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the lane matching posture determination method of the present application. Figure 1 As shown, the lane line matching posture determination method includes:

[0052] Step 110: determining a recursive change amount of the track within the cycle time based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time;

[0053] The perception moment refers to the moment when a camera mounted on the vehicle captures the road ahead of the vehicle.

[0054] During the driving process of the vehicle, data is continuously collected, such as: obtaining the vehicle speed through the wheel speed sensor, obtaining the vehicle's posture data (i.e., IMU data) through the Inertial Measurement Unit (IMU), obtaining the vehicle's RTK / GNSS data through RTK / GNSS, and obtaining the lane line data in front of the vehicle through the surround view camera or front camera.

[0055] Furthermore, the collected data is preprocessed. Since the data is affected by the vehicle system time, the collected data needs to be tested for validity. The specific testing methods include: whether the timestamp of the collected data has backflow or jump, etc.; and whether the collected data exceeds the upper and lower limits of the vehicle's theoretical output value. If the timestamp of the collected data has backflow or jump, and the collected data exceeds the upper and lower limits of the vehicle's theoretical output value, it is considered invalid; otherwise, it is considered valid.

[0056] If the data collected N times in a row are invalid, a fault is reported, prompting manual takeover, and specific fault information is displayed; if the collected data are valid, the format of the collected data is converted to the format required by the algorithm in this application to improve the versatility of the lane line matching posture determination method in this application. In addition, the lane line point set is obtained by parsing the perceived lane lines within the distance threshold range, and the distance threshold is the distance between the longitudinal position of the lane line and the vehicle. Preferably, the distance threshold can be 20m.

[0057] The vehicle track is obtained by recursively integrating the vehicle speed and IMU data. The vehicle track and rtk / gnss data closest to the i-th perception moment are obtained by using the lane line frame header time perceived at the i-th perception moment, and the vehicle track and rtk / gnss data are interpolated to the perception frame header time using linear interpolation, that is, time synchronization is performed, and the vehicle track and vehicle rtk / gnss data at each perception moment can be obtained.

[0058] Based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time, the recursive change of the track within the cycle time is determined. The corresponding formula is:

[0059]

[0060] in, is the recursive change of the track within the cycle time, is the vehicle track at the i-th perception time, is the vehicle track at the i-1th sensing moment.

[0061] The recursive change amount of the track within the cycle time is determined to prepare for determining the first initial matching pose of the lane line at the i-th perception moment.

[0062] Step 120: determining a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change in the track and the target matching pose of the lane line at the i-1th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting the road ahead of the vehicle by a shooting device on the vehicle;

[0063] The lane lines are obtained by photographing the road ahead of the vehicle using a photographing device on the vehicle. Since the photographing result is real-time, the lane lines in the photographing result are dynamic.

[0064] The first initial matching pose of the lane line at the i-th sensing moment is determined based on the recursive change of the track and the target matching pose of the lane line at the i-1-th sensing moment. The corresponding formula is:

[0065]

[0066] in, is the first initial matching pose of the lane line at the i-th perception moment, is the recursive change of the track, The target matching pose of the lane line at the i-1th perception moment.

[0067] Determine the first initial matching pose of the lane line at the i-th perception moment in preparation for building a map optimizer and determining the target lane line in the high-precision map.

[0068] Step 130: construct a graph optimizer based on the first initial matching pose;

[0069] In a specific implementation, a graph optimizer is constructed by taking the first initial matching pose as a vertex.

[0070] Step 140: Determine a target lane line in the map based on the first initial matching pose;

[0071] In specific implementation, the first initial matching pose prediction position is used to find the corresponding target lane line in the high-precision map.

[0072] Step 150: for a target point, determine a minimum residual from the target point to a target lane line, wherein the distance threshold is the distance between the longitudinal position of the lane line and the vehicle, and the target point is a point in a lane line point set obtained by analyzing the lane lines within the distance threshold range;

[0073] For the target point, determine the minimum residual from the target point to the target lane line to reduce the impact of lane line recognition anomalies, low accuracy at a distance, etc. on the lane line matching posture.

[0074] For the target point, the minimum residual from the target point to the target lane line is determined, and the corresponding formula is:

[0075]

[0076]

[0077] in, is the minimum residual from the jth target point to the target lane line, The first initial matching pose of the lane line at the i-th perception moment, is the map segment vector, p start is the homogeneous matrix of the starting points in the lane line point set, p end is the homogeneous matrix of the lane line point set endpoints, is the homogeneous matrix of the j-th target point, for The antisymmetric matrix of .

[0078] Step 160: Add target input data to the graph optimizer, wherein the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual;

[0079] Among them, the first information matrix corresponding to the first initial matching posture is set based on the perception confidence. The higher the perception confidence, the higher the value of the set first information matrix. The residual information matrix corresponding to the minimum residual is set according to the distance between the point in the lane line point set and the vehicle and the perception confidence. The farther the distance, the smaller the value of the set residual information matrix; the higher the perception information, the higher the value of the set residual information matrix.

[0080] During specific implementation, the target input data is added to the graph optimizer, and the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual and a residual information matrix corresponding to each minimum residual; it should be noted that the first information matrix and the residual information matrix are added to the graph optimizer in the form of unary edges.

[0081] Step 170: Run the graph optimizer according to a preset number of iterations to output the target matching pose of the lane line at the i-th perception moment.

[0082] This application uses a graph optimizer to perform iterative optimization according to a preset number of iterations to obtain the target matching posture of the lane line at the i-th perception moment, which can improve the system's anti-interference ability.

[0083] In this embodiment, the recursive change amount of the track during the cycle time is determined based on the vehicle track at the i-1th perception moment and the vehicle track at the i-th perception moment; the first initial matching pose of the lane line at the i-th perception moment is determined based on the recursive change amount of the track and the target matching pose of the lane line at the i-1th perception moment, and the lane line is a lane line in a shooting result obtained by shooting the road in front of the vehicle by a shooting device on the vehicle; based on the first initial matching pose, a map optimizer is constructed; based on the first initial matching pose, a target lane line in the map is determined; for the target point, the minimum residual from the target point to the target lane line is determined, and the distance threshold is the distance between the longitudinal position of the lane line and the vehicle The target point is a point in the lane line point set obtained after parsing the lane lines within the distance threshold range; adding the target input data to the graph optimizer, the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual and a residual information matrix corresponding to each minimum residual; running the graph optimizer according to a preset number of iterations, outputting the target matching pose of the lane line at the i-th perception moment, realizing the inter-frame pose matching of the lane line through the vehicle track constraint, and using the graph optimizer to determine the optimal matching pose, which can improve the lane line matching position accuracy and reduce the risk of vehicles running over lane lines, hitting walls, and causing safety accidents.

[0084] Furthermore, in one embodiment, the target input data also includes a second initial matching posture of the lane line and a second information matrix corresponding to the second initial matching posture of the lane line, wherein the second information matrix corresponding to the second initial matching posture of the lane line is set according to the status information of RTK / GNSS.

[0085] The process of determining the second initial matching position of the lane line includes:

[0086] Step 210: Determine the RTK / GNSS variation within the cycle time based on the vehicle RTK / GNSS data at the i-1th sensing moment and the vehicle RTK / GNSS data at the i-th sensing moment;

[0087] Based on the vehicle RTK / GNSS data at the i-1th perception moment and the vehicle RTK / GNSS data at the i-th perception moment, the RTK / GNSS change within the cycle time is determined to prepare for determining the second initial matching posture of the lane line at the i-th perception moment.

[0088] The RTK / GNSS data of the vehicle at the i-1th sensing moment and the RTK / GNSS data of the vehicle at the i-th sensing moment are used to determine the RTK / GNSS change within the cycle time. The corresponding formula is:

[0089]

[0090] in, is the change of rtk / gnss within the cycle time, is the vehicle RTK / GNSS data at the i-th sensing moment, is the vehicle RTK / GNSS data at the i-1th sensing moment.

[0091] Step 220: Determine a second initial matching pose of the lane line at the i-th sensing moment based on the rtk / gnss change and the target matching pose of the lane line at the i-1-th sensing moment.

[0092] Based on the rtk / gnss change and the target matching pose of the lane line at the i-1th sensing moment, a second initial matching pose of the lane line at the i-th sensing moment is determined to constrain the longitudinal accuracy of the lane line matching through the longitudinal information of RTK / GNSS.

[0093] The second initial matching pose of the lane line at the i-th sensing moment is determined based on the rtk / gnss change and the target matching pose of the lane line at the i-1-th sensing moment. The corresponding formula is:

[0094]

[0095]

[0096]

[0097] in, is the rtk / gnss change, is the transposed matrix of rtk / gnss variation, The target matching pose of the lane line at the i-1th sensing moment, The second initial matching position of the lane line at the i-th sensing moment, t is the position of the vehicle, R 3*3 is the rotation matrix.

[0098] Since there is a certain deviation between high-precision maps and the real world, and RTK / GNSS data is bound to the real world, in order to better examine the impact of this error on lane matching and positioning, only the longitudinal information of RTK / GNSS is used during recursion, which is x in the above formula.

[0099] It should be noted that the second information matrix corresponding to the second initial matching posture of the lane line is also added to the graph optimizer in the form of a unary edge.

[0100] In this embodiment, the RTK / GNSS change within the cycle time is determined based on the vehicle RTK / GNSS data at the i-1th perception moment and the vehicle RTK / GNSS data at the i-th perception moment; the second initial matching pose of the lane line at the i-1th perception moment is determined based on the RTK / GNSS change and the target matching pose of the lane line at the i-1th perception moment, so that the longitudinal accuracy of the lane line matching can be constrained by the longitudinal information of RTK / GNSS.

[0101] In a second aspect, an embodiment of the present application also provides a lane line matching posture determination device.

[0102] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of an embodiment of the lane line matching posture determination device of the present application. Figure 2 As shown, the lane matching posture determination device 200 includes:

[0103] A first determination module 210 is used to determine a recursive change amount of the track within a periodic time based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time;

[0104] A second determination module 220 is used to determine a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change amount of the track and the target matching pose of the lane line at the i-1-th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting the road ahead of the vehicle by a shooting device on the vehicle;

[0105] A construction module 230, configured to construct a graph optimizer based on the first initial matching pose;

[0106] A third determination module 240, configured to determine a target lane line in the map based on the first initial matching pose;

[0107] A fourth determination module 250 is used to determine, for a target point, a minimum residual from the target point to a target lane line, wherein the distance threshold is a distance between a longitudinal position of the lane line and a vehicle, and the target point is a point in a lane line point set obtained by analyzing lane lines within a range of the distance threshold;

[0108] An adding module 260, configured to add target input data to the graph optimizer, wherein the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual;

[0109] The output module 270 is used to run the graph optimizer according to a preset number of iterations and output the target matching pose of the lane line at the i-th perception moment.

[0110] Further, in one embodiment, the first determination module determines the recursive change amount of the track within the period time, and the corresponding formula is:

[0111]

[0112] in, is the recursive change of the track within the cycle time, is the vehicle track at the i-th perception time, is the vehicle track at the i-1th sensing moment.

[0113] Further, in one embodiment, the second determination module determines the first initial matching pose of the lane line at the i-th sensing moment, and the corresponding formula is:

[0114]

[0115] in, is the first initial matching pose of the lane line at the i-th perception moment, is the recursive change of the track, The target matching pose of the lane line at the i-1th perception moment.

[0116] Further, in one embodiment, the second determination module determines the minimum residual from the target point to the target lane line, and the corresponding formula is:

[0117]

[0118]

[0119] in, is the minimum residual from the jth target point to the target lane line, The first initial matching pose of the lane line at the i-th perception moment, is the map segment vector, p start is the homogeneous matrix of the starting points in the lane line point set, p end is the homogeneous matrix of the lane line point set endpoints, is the homogeneous matrix of the j-th target point, for The antisymmetric matrix of .

[0120] Furthermore, in one embodiment, the target input data further includes a second initial matching posture of the lane line and a second information matrix corresponding to the second initial matching posture of the lane line, and the lane line matching posture determination device further includes a fifth determination module, and the fifth determination module is specifically used to:

[0121] Determine the RTK / GNSS change within the cycle time based on the vehicle RTK / GNSS data at the i-1th sensing moment and the vehicle RTK / GNSS data at the i-th sensing moment;

[0122] Based on the rtk / gnss change and the target matching pose of the lane line at the i-1th sensing moment, a second initial matching pose of the lane line at the i-th sensing moment is determined.

[0123] Further, in one embodiment, the fifth determination module determines the rtk / gnss change within the cycle time, and the corresponding formula is:

[0124]

[0125] in, is the change of rtk / gnss within the cycle time, is the vehicle RTK / GNSS data at the i-th sensing moment, is the vehicle RTK / GNSS data at the i-1th sensing moment.

[0126] Further, in one embodiment, the fifth determination module determines the second initial matching posture of the lane line at the i-th sensing moment, and the corresponding formula is:

[0127]

[0128]

[0129]

[0130] in, is the rtk / gnss change, is the transposed matrix of rtk / gnss variation, The target matching pose of the lane line at the i-1th sensing moment, The second initial matching position of the lane line at the i-th sensing moment, t is the position of the vehicle, R 3*3 is the rotation matrix.

[0131] Among them, the functional implementation of each module in the above-mentioned lane line matching posture determination device corresponds to the various steps in the above-mentioned lane line matching posture determination method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0132] In a third aspect, an embodiment of the present application provides a lane line matching posture determination device, which can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0133] Reference Figure 3 , Figure 3 Schematic diagram of the hardware structure of the lane line matching posture determination device involved in the embodiment of the present application. In the embodiment of the present application, the lane line matching posture determination device may include a processor, a memory, a communication interface and a communication bus.

[0134] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0135] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the lane matching posture determination device, and the interface used to realize the interconnection between the lane matching posture determination device and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0136] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0137] The processor may be a general-purpose processor, which may call the lane line matching posture determination program stored in the memory and execute the lane line matching posture determination method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the lane line matching posture determination program is called may refer to the various embodiments of the lane line matching posture determination method of the present application, which will not be repeated here.

[0138] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0139] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0140] A lane line matching posture determination program is stored on the computer-readable storage medium of the present application, and when the lane line matching posture determination program is executed by a processor, the steps of the lane line matching posture determination method as described above are implemented.

[0141] Among them, the method implemented when the lane line matching posture determination program is executed can refer to the various embodiments of the lane line matching posture determination method of the present application, and will not be repeated here.

[0142] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0143] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0144] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0145] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0146] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0147] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0148] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A lane matching posture determination method, characterized in that: The lane line matching posture determination method comprises: Based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time, determining the recursive change amount of the track within the cycle time; Determine a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change amount of the track and the target matching pose of the lane line at the i-1th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting the road ahead of the vehicle by a shooting device on the vehicle; Based on the first initial matching pose, construct a graph optimizer; Determine a target lane line in the map based on the first initial matching pose; For the target point, determine the minimum residual from the target point to the target lane line, the distance threshold is the distance between the longitudinal position of the lane line and the vehicle, and the target point is a point in the lane line point set obtained after analyzing the lane lines within the distance threshold range; Adding target input data to the graph optimizer, the target input data including a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual; Run the graph optimizer according to the preset number of iterations and output the target matching pose of the lane line at the i-th perception moment.

2. The lane matching posture determination method according to claim 1, characterized in that: The recursive change amount of the track within the cycle time is determined based on the vehicle track at the i-1th sensing time and the vehicle track at the i-th sensing time. The corresponding formula is: in, is the recursive change of the track within the cycle time, is the vehicle track at the i-th perception time, is the vehicle track at the i-1th sensing moment.

3. The lane matching posture determination method according to claim 1, characterized in that: The first initial matching pose of the lane line at the i-th sensing moment is determined based on the recursive change of the track and the target matching pose of the lane line at the i-1-th sensing moment. The corresponding formula is: in, is the first initial matching pose of the lane line at the i-th perception moment, is the recursive change of the track, The target matching pose of the lane line at the i-1th perception moment.

4. The lane matching posture determination method according to claim 1, characterized in that: For the target point, the minimum residual from the target point to the target lane line is determined, and the corresponding formula is: in, is the minimum residual from the jth target point to the target lane line, The first initial matching pose of the lane line at the i-th perception moment, is the map segment vector, p start is the homogeneous matrix of the starting points in the lane line point set, p end is the homogeneous matrix of the lane line point set endpoints, is the homogeneous matrix of the j-th target point, for The antisymmetric matrix of .

5. The lane matching posture determination method according to claim 1, characterized in that: The target input data also includes a second initial matching posture of the lane line and a second information matrix corresponding to the second initial matching posture of the lane line, wherein the process of determining the second initial matching posture of the lane line includes: Determine the RTK / GNSS change within the cycle time based on the vehicle RTK / GNSS data at the i-1th sensing moment and the vehicle RTK / GNSS data at the i-th sensing moment; Based on the rtk / gnss change and the target matching pose of the lane line at the i-1th sensing moment, a second initial matching pose of the lane line at the i-th sensing moment is determined.

6. The lane matching posture determination method according to claim 5, characterized in that: The RTK / GNSS data of the vehicle at the i-1th sensing moment and the RTK / GNSS data of the vehicle at the i-th sensing moment are used to determine the RTK / GNSS change within the cycle time. The corresponding formula is: in, is the change of rtk / gnss within the cycle time, is the vehicle RTK / GNSS data at the i-th sensing moment, is the vehicle RTK / GNSS data at the i-1th sensing moment.

7. The lane matching posture determination method according to claim 5, characterized in that: The second initial matching pose of the lane line at the i-th sensing moment is determined based on the rtk / gnss change and the target matching pose of the lane line at the i-1-th sensing moment. The corresponding formula is: in, is the rtk / gnss change, is the transposed matrix of rtk / gnss variation, The target matching pose of the lane line at the i-1th sensing moment, The second initial matching position of the lane line at the i-th sensing moment, t is the position of the vehicle, R 3*3 is the rotation matrix.

8. A lane matching posture determination device, characterized in that: The lane line matching position determination device comprises: A first determination module is used to determine a recursive change amount of the track within the cycle time based on the vehicle track at the i-1th perception time and the vehicle track at the i-th perception time; A second determination module is used to determine a first initial matching pose of the lane line at the i-th sensing moment based on the recursive change amount of the track and the target matching pose of the lane line at the i-1-th sensing moment, wherein the lane line is a lane line in a shooting result obtained by shooting a road ahead of the vehicle by a shooting device on the vehicle; A construction module, configured to construct a graph optimizer based on the first initial matching pose; A third determination module, configured to determine a target lane line in the map based on the first initial matching posture; A fourth determination module is used to determine, for a target point, a minimum residual from the target point to a target lane line, wherein the distance threshold is a distance between a longitudinal position of the lane line and a vehicle, and the target point is a point in a lane line point set obtained by analyzing lane lines within a range of the distance threshold; An adding module, configured to add target input data to the graph optimizer, wherein the target input data includes a first initial matching pose, a first information matrix corresponding to the first initial matching pose, each minimum residual, and a residual information matrix corresponding to each minimum residual; The output module is used to run the graph optimizer according to a preset number of iterations and output the target matching pose of the lane line at the i-th perception moment.

9. A lane matching posture determination device, characterized in that: The lane line matching posture determination device includes a processor, a memory, and a lane line matching posture determination program stored in the memory and executable by the processor, wherein when the lane line matching posture determination program is executed by the processor, the steps of the lane line matching posture determination method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a lane line matching posture determination program, wherein when the lane line matching posture determination program is executed by a processor, the steps of the lane line matching posture determination method as described in any one of claims 1 to 7 are implemented.

Images