A reference line determination method, device, equipment and medium

Abstract

The embodiments of the present application disclose a reference line determination method, device, equipment and medium, which belong to the technical field of autonomous driving and can be applied to closed parks such as ports and logistics, or urban transportation, or highways, etc. Since the path point information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so that the accuracy of the reference line information determined based on the measured path point information on the target route and the perception information of the target vehicle is higher, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic equipment that determines the reference line, and reduces the cost of the electronic equipment.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a reference line determination method, device, equipment and medium. Background Art

[0002] For high-level autonomous driving systems, such as L3 or L4, the control algorithm is the "core brain" of the autonomous driving system, responsible for integrating the reference line information and the vehicle's perception information, making appropriate decision-making and planning control instructions to control the autonomous driving vehicle to make reasonable movements. In order to achieve precise control of the autonomous driving vehicle, the control algorithm of the high-level autonomous driving system used by the autonomous vehicle needs to be verified and tested in a large number of scenarios so that the control algorithm can cope with various complex road environments.

[0003] In the related technology, the simulation of reference lines is an important new module of high-level autonomous driving simulation systems compared to low-level autonomous driving simulation systems. In order to realize the simulation of reference lines, it is generally necessary to first obtain the map and vehicle positioning information. Then, according to the map algorithm, the reference line information is determined based on the acquired map and positioning information. For this method, if there is a problem with the map algorithm, it will affect the accuracy of the acquired reference line information, which will not be conducive to a large number of scenario tests on the regulatory control algorithm in the early and mid-term development of the high-level autonomous driving system, nor will it be conducive to the iterative update of the regulatory control algorithm of the high-level autonomous driving system. At the same time, the map algorithm needs to perform complex indexing and path planning operations, which requires high hardware computing power for the electronic equipment using the high-level autonomous driving simulation system, and increases the cost of the electronic equipment using the high-level autonomous driving simulation system. Summary of the invention

[0004] The embodiments of the present application provide a reference line determination method, apparatus, device and medium to solve the problem that reference line information cannot be accurately obtained in the prior art.

[0005] In a first aspect, the present application provides a reference line determination method, the method comprising:

[0006] Obtaining the waypoint information on the target route and the perception information of the target vehicle;

[0007] Based on the waypoint information and the perception information, reference line information is determined.

[0008] Since the waypoint information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so that the reference line information subsequently determined based on the measured waypoint information on the target route and the perception information of the target vehicle is more accurate, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic equipment for determining the reference line, and reduces the cost of the electronic equipment.

[0009] In some possible implementations, the waypoint information includes one or more of the following:

[0010] The first coordinate information of the path point, the first heading information of the vehicle passing the path point, the first road slope information at the path point, the first time information of the vehicle passing the path point, and the first road curvature information at the path point. In this way, the reference point information can be accurately determined.

[0011] In some possible implementations, the perception information includes one or more of the following:

[0012] The second coordinate information of the target vehicle, the lane line information corresponding to the lanes associated with the target vehicle, and the second heading information of the target vehicle. In this way, the reference point information can be accurately determined.

[0013] In some possible implementations, the reference line information includes navigation information and / or reference point information.

[0014] In some possible implementations, when the waypoint information includes first coordinate information of the waypoint and first time information of the vehicle passing through the waypoint, and the perception information includes second coordinate information of the target vehicle and lane line information corresponding to lanes associated with the target vehicle, determining the reference line information based on the waypoint information and the perception information includes:

[0015] In the case where the navigation information includes a lane number, a target path point is determined from each of the path points according to the second coordinate information and the first coordinate information respectively corresponding to each of the path points; a reference path point after the target path point is determined from each of the path points according to the first time information respectively corresponding to each of the path points; a target straight line passing through the target path point and the reference path point is determined; a distance between the target vehicle and the target straight line is obtained; and a lane number corresponding to the distance interval in which the distance is located is determined according to the correspondence between the distance interval and the lane number;

[0016] In the case where the navigation information includes a lane change type, obtaining current time information; determining the lane change type corresponding to the time interval in which the current time information is located according to a pre-configured correspondence between the time interval and the lane change type; wherein the time interval is determined according to the first time information corresponding to each of the path points;

[0017] In the case where the navigation information includes a lane change distance, current time information is acquired; a target lane change point corresponding to the time interval in which the current time information is located is determined according to a pre-configured correspondence between the time interval and the lane change point; and the lane change distance is determined based on the coordinate information of the target lane change point; wherein the lane change distance indicates the distance between the target vehicle and the next lane change point;

[0018] In a case where the navigation information includes a lane line coefficient, the lane line coefficient is determined according to lane line information respectively corresponding to lanes associated with the target vehicle.

[0019] Through the above-mentioned method, it is possible to use a small amount of simple calculations to quickly determine navigation information based on path point information and perception information, thereby reducing the amount of calculations required to determine the navigation information, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined navigation information, and eliminating the need for complex indexing and path planning operations, thereby greatly reducing the amount of calculations required to determine the navigation information, reducing the hardware computing power requirements for electronic devices that determine reference lines, and reducing the cost of the electronic equipment.

[0020] In some possible implementations, when the waypoint information includes first coordinate information of the waypoint, first heading information of the vehicle passing through the waypoint, first road slope information at the waypoint, and first road curvature information at the waypoint, and the perception information includes second coordinate information of the target vehicle and second heading information of the target vehicle, determining the reference line information based on the waypoint information and the perception information includes:

[0021] In the case where the reference point information includes heading information of the reference point, determining a reference path point from each of the path points; for each of the reference path points, determining the reference heading information of the reference point according to the second heading information and the first heading information corresponding to the reference path point;

[0022] In the case where the reference point information includes coordinate information of the reference point, determining a reference path point from each of the path points; for each of the reference path points, determining the coordinate information of the reference point according to the second coordinate information, the first coordinate information corresponding to the reference path point, and the first heading information corresponding to the reference path point;

[0023] In the case where the reference point information includes the slope information of the reference point, determining a reference path point from the path points; for each reference path point, determining the slope information of the reference point according to the first road slope information corresponding to the reference path point;

[0024] In the case where the reference point information includes curvature information of the reference point, a reference path point is determined from the path points; and for each reference path point, the curvature information of the reference point is determined according to the first road curvature information corresponding to the reference path point.

[0025] Through the above-mentioned method, it is possible to use a small amount of simple calculations to quickly determine the reference point information based on the path point information and the perception information, thereby reducing the amount of calculations required to determine the reference point information, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference point information, and eliminating the need for complex indexing and path planning operations, thereby greatly reducing the amount of calculations required to determine the reference point information, reducing the hardware computing power requirements for the electronic device that determines the reference line, and reducing the cost of the electronic device.

[0026] In a second aspect, a reference line determination device is provided, the device comprising:

[0027] An acquisition unit, used to acquire waypoint information on a target route and perception information of a target vehicle;

[0028] A processing unit is used to determine reference line information based on the waypoint information and the perception information.

[0029] An embodiment of the present application provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of the reference line determination method as described above when executing a computer program stored in the memory.

[0030] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the steps of the reference line determination method as described above when the computer program is executed by a processor.

[0031] An embodiment of the present application provides a computer program product, which includes: computer program code, when the computer program code is executed on a computer, enables the computer to execute the steps of the reference line determination method as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a reference line determination process provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of a specific reference line determination process provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of another specific reference line determination process provided in an embodiment of the present application;

[0035] Figure 4 A schematic diagram of the structure of a reference line determination device provided in an embodiment of the present application;

[0036] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than 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 the present application.

[0038] Those skilled in the art know that the embodiments of the present application can be implemented as a system, device, equipment, method or computer program product. Therefore, the present application can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0039] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0040] In order to accurately determine reference line information, embodiments of the present application provide a reference line determination method, apparatus, device, and medium.

[0041] Embodiment 1:

[0042] Figure 1 A schematic diagram of a reference line determination process provided in an embodiment of the present application, the process includes:

[0043] S101: Acquire the waypoint information on the target route and the perception information of the target vehicle.

[0044] The reference line determination method provided in the present application is applied to an electronic device, which may be an intelligent device, such as a physical simulation machine, a PC, etc., or a server, such as an application server, a cloud server, etc.

[0045] In a possible application scenario, when it is necessary to simulate the reference line, the staff can input a simulation request through a smart device. Among them, the staff can input the simulation request by clicking an icon on the display of the smart device to start the test, or by inputting a voice message to start the test. After the smart device receives the simulation request, the smart device can directly simulate the reference line information based on the reference line determination method provided in the present application, or send the simulation request to an electronic device for reference line determination, so that after the electronic device receives the simulation request, it simulates the reference line information based on the reference line determination method provided in the present application.

[0046] In order to accurately determine the reference line, in this application, it is necessary to obtain the path point information on the target route and the perception information of the target vehicle. Among them, the information (including path point information and / or perception information) can be collected by itself or sent by other devices. For example, the path point information is pre-configured in the electronic device by the staff, that is, the electronic device itself collects it, and the perception information is sent to the electronic device by the PC, or both the path point information and the perception information are sent to the electronic device by the PC.

[0047] Taking the case where the perception information is sent by other devices as an example, the electronic device creates one or more communication ports (sockets) according to a pre-configured communication protocol, such as a pre-configured communication protocol corresponding to the current simulation environment. And receives data packets sent by other devices through the one or more communication sockets. The perception information carried in the data packets is obtained by unpacking and decoding the received data packets. Based on the acquired perception information, corresponding processing is performed to determine the reference line.

[0048] It should be noted that the electronic device may obtain the perception information at a certain period, or after receiving an acquisition command, or at a preset time point. In the specific implementation process, it can be flexibly set according to needs, and no specific limitation is made here.

[0049] In one example, the waypoint information on the target route includes one or more of the following:

[0050] The first coordinate information of the waypoint, the first heading information of the vehicle passing the waypoint, the first road slope information at the waypoint, the first time information of the vehicle passing the waypoint, and the first road curvature information at the waypoint can accurately determine the reference line information.

[0051] The target route is determined by multiple path points, and any path point is used to represent the location that the target vehicle will pass through when traveling from the starting point to the destination.

[0052] For example, according to the starting point and destination of the target vehicle, a pre-configured target route for the simulated vehicle to travel from the starting point to the destination at a constant speed is determined, and information about the path points that the simulated vehicle passes through on the target route during driving (recorded as path point information) is collected. For example, the first coordinate information of the path point (x n ,y n ), the first heading information h of the vehicle passing through the path point n , the first road slope information at the path point (slope_x n , slope_y n ), the first time information t of the vehicle passing through the path point n , the first road curvature information at the path pointcure n . Where n represents the nth path point.

[0053] The first road slope information includes first transverse slope information slope_x n , and / or, first road longitudinal slope information slope_y n .

[0054] In a possible implementation, since the path point information obtained by the electronic device generally does not change during the process of determining the reference line, the electronic device can store the obtained path point information locally after obtaining the path point information, so as to facilitate the subsequent process of determining the reference line, directly obtain the path point information from the local, and reduce the resources consumed in obtaining the path point information. For example, the electronic device can write the obtained path point information into a one-dimensional or multi-dimensional matrix in chronological order.

[0055] In one example, the perception information includes one or more of the following:

[0056] The second coordinate information of the target vehicle, the lane line information corresponding to the lanes associated with the target vehicle, and the second heading information of the target vehicle can accurately determine the reference line information.

[0057] For example, the perception information acquired by the electronic device includes the second coordinate information (ego_x, ego_y) of the target vehicle, the lane line information corresponding to the lanes associated with the target vehicle, and the second heading information ego_h of the target vehicle.

[0058] In a possible implementation, the lanes associated with the target vehicle include the first lane where the target vehicle is currently located, two lanes adjacent to the first lane, such as the second lane on the left of the first lane and the third lane on the right of the first lane. Therefore, when acquiring the lane line information corresponding to the lanes associated with the target vehicle, the lane line information of the left and right lane lines of the first lane can be acquired, such as the lane line information of the left lane line includes LA0, LA1, LA2, LA3, the lane line information of the right lane line includes RAO, RA1, RA2, RA3, the lane line information of the left and right lane lines of the second lane, such as the lane line information of the left lane line of the second lane includes LLA0, LLA1, LLA2, LLA3, and the lane line information of the left and right lane lines of the third lane, such as the lane line information of the right lane line of the third lane includes RRAO, RRA1, RRA2, RRA3.

[0059] It should be noted that, considering that the right lane line of the second lane is the left lane line of the first lane, and the left lane line of the third lane is the right lane line of the first lane, when obtaining the lane line information corresponding to the lanes associated with the target vehicle, if the lane line information of the left and right lane lines of the first lane is obtained, then the lane line information of the right lane line of the second lane and the lane line information of the left lane line of the third lane may no longer be obtained, thereby reducing the resources consumed in obtaining the lane line information corresponding to the lanes associated with the target vehicle.

[0060] S102: Determine reference line information based on the path point information and the perception information.

[0061] After the path point information and the perception information are obtained based on the above-mentioned embodiments, the reference line information can be determined by performing corresponding processing using the reference line determination method provided in the present application based on the obtained path point information and the perception information.

[0062] The reference line information is used to instruct the target vehicle to travel from the current location to the destination within a certain range of the current location of the target vehicle.

[0063] In the present application, the reference line information includes navigation information and / or reference point information, that is, the reference line information may include only navigation information, only reference point information, or both navigation information and reference point information.

[0064] In one example, the reference line information may be determined by a preset reference line determination algorithm based on the path point information and the perception information.

[0065] In a possible implementation, by using a preset reference line determination algorithm, based on the path point information and the perception information, the reference line information is determined in the following two cases:

[0066] Case 1: The reference line information includes navigation information.

[0067] In this application, the navigation information includes one or more of the following:

[0068] Lane number, lane change type, distance between the target vehicle and the next lane change point (recorded as change distance), and lane line coefficient.

[0069] Exemplarily, if the reference line information includes navigation information, the method of determining the navigation information includes the following:

[0070] Method 1: If the navigation information includes a lane number, the lane number can be determined based on the first coordinate information included in the waypoint information and the second coordinate information included in the perception information. Exemplarily, the target waypoint is determined from each waypoint based on the second coordinate information and the first coordinate information corresponding to each of the waypoints. The target waypoint may be a waypoint that is close to or closest to the target vehicle. Based on the first time information corresponding to each of the waypoints, a reference waypoint after the target waypoint is determined from each of the waypoints. For example, the first time information corresponding to the target waypoint is t n , the first time information is t n+1 The path point is determined as the reference path point. A target straight line passing through the target path point and the reference path point is determined. For example, the target straight line can be determined by the first coordinate information corresponding to the target path point and the reference path point respectively. The distance between the target vehicle and the target straight line is obtained. According to the correspondence between the distance interval and the lane number, the lane number corresponding to the distance interval in which the distance is located is determined. For example, the lane number corresponding to the distance interval 1 is 1, the lane number corresponding to the distance interval 2 is 2, and the lane number corresponding to the distance interval 3 is 3. If it is determined that the distance is located in the distance interval 2, the lane number is the lane number 2 corresponding to the distance interval 2.

[0071] In one example, the distance interval can be determined based on the lane line information of the lane where the target vehicle is located. For example, the lane line information of the lane where the target vehicle is located includes RA0 and LA0, and the lane width is determined based on the absolute value of the difference between RA0 and LA0, and the distance interval is determined based on the lane width. For example, if the lane width is N, it will be no greater than The distance interval determines the distance interval 1, which will be greater than and not greater than The distance interval determines the distance interval 2, which will be greater than and not greater than The distance interval determines the distance interval 3, which will be greater than and not greater than The distance interval determines the distance interval 4.

[0072] For example, the second coordinate information of the target vehicle is p(ego_x, ego_y), and the lane width is N, which is not greater than The lane number corresponding to the distance interval is 1, and the lane number greater than and not greater than The lane number corresponding to the distance interval is 2, which is greater than and not greater than The lane number corresponding to the distance interval is 3, which is greater than and not greater than The lane number corresponding to the distance interval is 4. According to the first coordinate information included in the path point information, the first coordinate information (x z ,y z ), the first coordinate information (x z ,y z ) is determined as the target path point Q1. According to the first time information t corresponding to the target path point z , determine the first time information as t z+1 The path point Q2 is the reference path point Q2. The first coordinate information (x z+1 ,y z+1 ). According to the first coordinate information (x z ,y z ), and the first coordinate information (x z+1 ,y z+1 ), determine the target straight line passing through the target coordinate point Q1 and the reference path point Q2. Obtain the distance S3 between the target vehicle and the target straight line. For example, the distance S3 between the target vehicle and the target straight line can be obtained by the formula S3 = abs(det([Q2-Q1, p-Q1]) / norm(Q2-Q1)). If The lane number is 1; if The lane number is 2; if The lane number is 3; if The lane number is 4.

[0073] Method 2: If the navigation information includes a lane change type, the lane change type can be determined based on the current time information and the first time information corresponding to each of the path points. The current time information is the time information when the perception information is collected. Exemplarily, the current time information is obtained. Then, based on the correspondence between the pre-configured time interval and the lane change type, the lane change type corresponding to the time interval where the current time information is located is determined.

[0074] In one example, a path point (first path point) that requires lane change is pre-configured, and the lane change type corresponding to the first path point is identified. For each first path point with a lane change type identified, a time interval is determined based on the first time information included in the path point information of the first path point and the first time information included in the path point information of the second path point. Among them, the second path point is a path point that requires lane change after the first path point. Determine the lane change type corresponding to the second path point in the time interval. For example, the first time information corresponding to the first path point is t(1), the lane change type corresponding to the first path point is 1, the first time information corresponding to the second path point is t(2), and the lane change type corresponding to the second path point is 2, then the time interval is determined to be [t(1), t(2)), and the lane change type corresponding to the time interval [t(1), t(2)) is 2.

[0075] It should be noted that, for the first first path point, the time interval can be determined based on the start time and the first time information corresponding to the first path point, and the lane change type corresponding to the time interval is the lane change type corresponding to the first path point. For the last first path point, the time interval can be determined based on the first time information corresponding to the first path point and the end time, and the lane change type corresponding to the time interval can be a preset lane change type.

[0076] Exemplarily, the correspondence between the pre-configured time interval and the lane change type is that the lane change type corresponding to the time interval not greater than t(1) is 1, the lane change type corresponding to the time interval greater than t(1) and not greater than t(2) is 2, and the lane change type corresponding to the time interval greater than t(2) is 0. Among them, 0 represents the preset lane change type.

[0077] Method three, if the navigation information includes a change distance, the change distance can be determined based on the current time information and the first time information corresponding to each of the path points. Exemplarily, the current time information is obtained. According to the correspondence between the pre-configured time interval and the lane change point, the target lane change point corresponding to the time interval where the current time information is located is determined. Based on the coordinate information of the target lane change point, the change distance is determined.

[0078] In one example, a path point (first path point) that requires lane change is pre-configured, and the lane change type corresponding to the first path point is identified. For each first path point with a lane change type identified, a time interval is determined based on the first time information included in the path point information of the first path point and the first time information included in the path point information of the second path point. Among them, the second path point is a path point that requires lane change after the first path point. Determine that the time interval corresponds to the second path point. For example, the first time information corresponding to the first path point is t(1), and the first time information corresponding to the second path point is t(2), then the time interval is determined to be [t(1), t(2)), and the lane change point corresponding to the time interval [t(1), t(2)) is t(2).

[0079] It should be noted that, for the first first path point, the time interval can be determined based on the start time and the first time information corresponding to the first path point, and the lane change point corresponding to the time interval is the first path point. For the last first path point, the time interval can be determined based on the first time information corresponding to the first path point and the end time, and the lane change point corresponding to the time interval can be a preset lane change point.

[0080] In one example, the change distance may be determined according to the horizontal coordinate in the coordinate information of the target lane change point, for example, by multiplying a preset multiple by the horizontal coordinate.

[0081] In one possible manner, for a preset lane change point, coordinate information corresponding to the preset lane change point can be pre-configured, and the change distance can be determined based on the coordinate information corresponding to the preset lane change point. The change distance corresponding to the preset lane change point can also be pre-configured, thereby reducing the amount of calculation required to determine the change distance.

[0082] Exemplarily, the correspondence between the pre-configured time interval and the lane change point is that the lane change point corresponding to the time interval not greater than t(1) is t(1), the lane change point corresponding to the time interval greater than t(1) and not greater than t(2) is t(2), and the lane change point corresponding to the time interval greater than t(2) is the preset lane change point. After obtaining the current time information t, if it is determined that t≤t(1), the target lane change point is t(1), and based on the coordinate information of the target lane change point t(1), the change distance is determined to be d=Q t(1) *2; If it is determined that t(1)<t≤t(2), the target lane change point is t(2). Based on the coordinate information of the target lane change point t(2), the change distance is determined to be d=Q t(2)*2; if t(2)<t, the target lane change point is null, and the change distance corresponding to the target lane change point null is d=5001, where 5001 is the preset change distance.

[0083] Method four, if the navigation information includes a lane line coefficient, the lane line coefficient can be determined according to the lane line information corresponding to the lanes associated with the target vehicle.

[0084] In one example, the lane line information corresponding to the lanes associated with the target vehicle can be directly determined as the lane line coefficient. For example, the left lane line coefficients A0, A1, A2, and A3 of the first lane can be determined by the following formula:

[0085] A0=LA0;

[0086] A1=LA1;

[0087] A2=LA2;

[0088] A3=LA3;

[0089] Among them, LA0, LA1, LA2, and LA3 are lane line information of the left lane line of the first lane.

[0090] The right lane line coefficients B0, B1, B2, and B3 of the first lane can be determined by the following formula:

[0091] B0=RA0;

[0092] B1=RA1;

[0093] B2=RA2;

[0094] B3=RA3;

[0095] Among them, RA0, RA1, RA2, and RA3 are lane line information of the right lane line of the first lane.

[0096] The lane line coefficients C0, C1, C2, and C3 of the left lane line of the second lane can be determined by the following formula:

[0097] C0 = LLA0;

[0098] C1 = LLA1;

[0099] C2 = LLA2;

[0100] C3 = LLA3;

[0101] Among them, LLA0, LLA1, LLA2, and LLA3 are lane line information of the left lane line of the second lane.

[0102] The lane line coefficients D0, D1, D2, and D3 of the right lane line of the third lane can be determined by the following formula:

[0103] D0 = RRA0;

[0104] D1 = RRA1;

[0105] D2 = RRA2;

[0106] D3 = RRA3;

[0107] Among them, RRAO, RRA1, RRA2, and RRA3 are lane line information of the right lane line of the third lane.

[0108] In another example, the lane line information corresponding to the lanes associated with the target vehicle can be processed through preset mathematical calculations, such as weighted processing, and the processed lane line information can be determined as a lane line coefficient.

[0109] It should be noted that, when the waypoint information includes the first coordinate information of the waypoint and the first time information of the vehicle passing through the waypoint, and the perception information includes the second coordinate information of the target vehicle and the lane line information corresponding to the lanes associated with the target vehicle, when determining the navigation information, the navigation information can be determined by at least two of the above methods, for example, it can be determined by method one and method two, or by method one and method three, or by method two and method four, or by method one, method two and method three, or by method two, method three and method four, or by method one, method two, method three and method four. In the specific implementation process, the method of obtaining navigation information can be flexibly determined according to actual needs, and no specific limitation is made here.

[0110] Case 2: Reference line information includes reference point information.

[0111] In this application, the reference point information includes one or more of the following:

[0112] The heading information of the reference point, the coordinate information of the reference point, the slope information of the reference point, and the curvature information of the reference point.

[0113] In one example, if the reference point information is to be determined, it is necessary to determine the reference path point from the acquired path points. Exemplarily, the reference path point can be determined from the path points based on the path point information corresponding to each path point and a preset screening rule. The screening rule may be the number of reference points and / or the interval distance between two adjacent reference points. For example, the screening rule is to determine 40 reference points, and the interval distance between the first 25 reference points is 2m, and the interval distance between the last 15 reference points is 20m.

[0114] It should be noted that when setting the number of reference points, different values ​​can be set according to different scenarios. If you want to obtain accurate reference point information, you can set the number to be larger. If you want to reduce the amount of calculation consumed in determining the reference point information, you can set the number to be smaller. When setting the number, you can flexibly set it according to actual needs, and no specific limitation is made here.

[0115] Similarly, when setting the interval distance between two adjacent reference points, different values ​​can be set according to different scenarios. If you want to obtain accurate reference point information, you can set the interval distance to be larger. If you want to reduce the amount of calculation consumed in determining the reference point information, you can set the interval distance to be smaller. When setting the interval distance, you can flexibly set it according to actual needs, and no specific limitation is made here.

[0116] Exemplarily, if the reference line information includes reference point information, the manner of determining the reference point information includes the following:

[0117] Mode 1: If the reference point information includes the heading information of the reference point, the heading information of the reference point can be determined according to the first heading information included in the path point information and the second heading information included in the perception information. Exemplarily, for each determined reference path point, the reference heading information of the reference point is determined according to the second heading information and the first heading information corresponding to the reference path point.

[0118] In one example, the heading difference between the second heading information and the first heading information of the reference path point may be determined. The heading information of the reference point may be determined based on the trigonometric function value of the heading difference. Exemplarily, the reference heading information of the reference point may be determined by the following formula:

[0119] H=egoh-point m _h;

[0120] h m = -atan2(sin(H), cos(H));

[0121] Among them, ego_h is the second heading information, point m _h is the reference path point m The first heading information, h m is the reference heading information of the reference point, and H is the heading difference.

[0122] Method 2, if the reference point information includes the coordinate information of the reference point, then for each reference path point, the coordinate information of the reference point can be determined based on the acquired second coordinate information, the first coordinate information corresponding to the reference path point, and the first heading information corresponding to the reference path point.

[0123] In one example, the trigonometric function value of the first heading information corresponding to the reference path point may be determined, such as the sine function value, the cosine function value, and the coordinate difference between the second coordinate information and the first coordinate information, such as the difference between the horizontal coordinate contained in the second coordinate information and the horizontal coordinate contained in the first coordinate information, and the difference between the vertical coordinate contained in the second coordinate information and the vertical coordinate contained in the first coordinate information. Then, the coordinate information of the reference point is determined based on the trigonometric function value and the coordinate difference.

[0124] Exemplarily, the horizontal coordinate of the reference point can be determined by the following formula:

[0125] x m =deta x *cos(point m _h)+deta y *sin(point m _h);

[0126] deta x =point_x m -ego_x;

[0127] deta y =point_y m -ego_y;

[0128] Among them, point m _h is the reference path point m The first heading information, point_x m is the reference path point m The horizontal coordinate in the coordinate information, point_y m is the reference path point m The ordinate in the coordinate information, x m The horizontal coordinate of the reference point, deta x is the horizontal axis difference, deta y is the vertical coordinate difference.

[0129] The ordinate of the reference point can be determined by the following formula:

[0130] x m =-(deta y *cos(point m _h)-deta x *sin(point m _h));

[0131] deta x =point_xm -ego_x;

[0132] deta y =point_y m -ego_y;

[0133] Among them, point m _h is the reference path point m The first heading information, point_x m is the reference path point m The horizontal coordinate in the coordinate information, point_y m is the reference path point m The ordinate in the coordinate information, x m The horizontal coordinate of the reference point.

[0134] Mode 3: If the reference point information includes slope information of the reference point, the slope information of the reference point can be determined for each reference path point according to the first road slope information corresponding to the reference path point.

[0135] In one example, the first road slope information corresponding to the reference path point can be directly determined as the slope information of the reference point. For example, the first lateral slope information corresponding to the reference path point is determined as the lateral slope information of the reference point, and the first road longitudinal slope information corresponding to the reference path point is determined as the longitudinal slope information of the reference point.

[0136] Exemplarily, the slope information of the reference point can be determined by the following formula:

[0137] slope xm =slope_x m ;

[0138] slope ym =slope_y m ;

[0139] Among them, slope_x m is the reference path point m The first transverse slope information, slope_y m is the reference path point m The first longitudinal slope information, slope xm is the transverse slope information of the reference point, slope ym It is the transverse slope information of the reference point.

[0140] In another example, the first road slope information corresponding to the reference path point may also be fine-tuned, and the fine-tuned first road slope information may be determined as the slope information of the reference point.

[0141] Mode 3: If the reference point information includes curvature information of the reference point, the curvature information of the reference point can be determined for each reference path point according to the first road curvature information corresponding to the reference path point.

[0142] In an example, the first road curvature information corresponding to the reference path point may be directly determined as the curvature information of the reference point. For example, the first road curvature information corresponding to the reference path point may be directly determined as the curvature information of the reference point.

[0143] Exemplarily, the curvature information of the reference point can be determined by the following formula:

[0144] landcure xm =cure_point m ;

[0145] slope ym =slope_y m ;

[0146] Among them, cure_point m is the reference path point m The first road curvature information, landcure xm is the curvature information of the reference point.

[0147] In another example, the first road curvature information corresponding to the reference path point may be processed by a preset mathematical calculation, such as weighted processing, and the processed first road curvature information may be determined as the curvature information of the reference point.

[0148] It should be noted that, when the waypoint information includes the first coordinate information of the waypoint, the first heading information of the waypoint passed by the vehicle, the first road slope information at the waypoint, and the first road curvature information at the waypoint, and the perception information includes the second coordinate information of the target vehicle and the second heading information of the target vehicle, when determining the reference point information, the reference point information can be determined by at least two of the above methods, for example, it can be determined by method 1 and method 2, or by method 1 and method 3, or by method 2 and method 4, or by method 1, method 2 and method 3, or by method 2, method 3 and method 4, or by method 1, method 2, method 3 and method 4. In the specific implementation process, the method of obtaining the reference point information can be flexibly determined according to actual needs, and no specific limitation is made here.

[0149] Similarly, the above two situations of determining reference line information can exist at the same time, that is, determining both navigation information and reference point information. It should be noted that the specific manner of determining navigation information and reference point information has been described in the above embodiments, and the repeated parts will not be repeated.

[0150] After the reference line information is obtained based on the above-mentioned embodiment, the control algorithm of the high-level autonomous driving system can be tested based on the obtained reference line information.

[0151] For example, after the navigation information is acquired, at least one socket may be created according to the communication protocol of the regulatory control algorithm to encode, package and send the acquired navigation information to an electronic device used to test the regulatory control algorithm.

[0152] For another example, after the reference point information is obtained, at least one socket may be created according to the communication protocol of the regulation and control algorithm to encode, package and send the obtained reference point information to an electronic device used to test the regulation and control algorithm.

[0153] It should be noted that the electronic device used to test the regulation algorithm may be the same as or different from the electronic device used to determine the reference line.

[0154] Since the path point information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so the accuracy of the reference line information determined based on the measured path point information on the target route and the perception information of the target vehicle is higher, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, realizing the decoupling between the map algorithm and the algorithm for determining the reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic device for determining the reference line, and reduces the cost of the electronic device. In addition, the reference line determination method can be applied to existing electronic devices without the need for additional hardware devices.

[0155] Embodiment 2:

[0156] The reference line determination method provided by the present application is described below through specific embodiments. Figure 2 A specific reference line determination process diagram provided in an embodiment of the present application is provided. Taking the hardware-in-the-Loop (HIL) test of the control algorithm of a high-level autonomous driving system as an example, the process includes:

[0157] S201: The PC obtains second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, and second heading information of the target vehicle by running simulation software.

[0158] The PC can communicate with the real-time simulation machine for determining the reference line through an Ethernet interface.

[0159] It should be noted that the real-time simulator can support the perception information sent by a PC after running common high-level autonomous driving simulation software on the market, such as VTD, Cognata, Carmaker, Carsim, Prescan, etc.

[0160] S202: The real-time simulation machine obtains pre-collected path point information.

[0161] S203: The real-time simulation machine determines navigation information based on the acquired second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, second heading information of the target vehicle, and pre-collected path point information.

[0162] S204: The real-time simulation machine determines reference point information based on the acquired second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, second heading information of the target vehicle, and pre-collected path point information.

[0163] S205: The real-time simulator sends the determined navigation information and reference point information to a controller for testing the regulation and control algorithm through an Ethernet interface.

[0164] Since the path point information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so the accuracy of the reference line information determined based on the measured path point information on the target route and the perception information of the target vehicle is higher, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, realizing the decoupling between the map algorithm and the algorithm for determining the reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements for the electronic equipment that determines the reference line, and reduces the cost of the electronic equipment. In addition, it is also conducive to improving the accuracy of subsequent testing of the regulatory control algorithm.

[0165] According to the heterogeneous distribution characteristics of the PC, real-time simulator and controller in HIL, the Ethernet interface is used for unified information reception and transmission, which saves communication interface resources, meets the demand for high-speed data transmission and improves the accuracy of simulation.

[0166] The reference line determination method provided by the present application is described below through another specific embodiment. Figure 3A schematic diagram of another specific reference line determination process provided in an embodiment of the present application is provided. Taking the model in the loop (MIL) test of the control algorithm of a high-level autonomous driving system as an example, the process includes:

[0167] S301: PC 1 obtains second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, and second heading information of the target vehicle by running simulation software, and sends the obtained information to PC 2.

[0168] The PC 1 can communicate with the PC 2 for determining the reference line through an Ethernet interface.

[0169] It should be noted that the PC 2 can support the perception information sent by the PC 1 after running common high-level autonomous driving simulation software on the market, such as VTD, Cognata, Carmaker, Carsim, Prescan, etc.

[0170] S302: PC 2 obtains pre-collected path point information.

[0171] S303: PC 2 determines navigation information based on the acquired second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, second heading information of the target vehicle, and pre-collected path point information.

[0172] S304: PC 2 determines reference point information based on the acquired second coordinate information of the target vehicle, lane line information corresponding to lanes associated with the target vehicle, second heading information of the target vehicle, and pre-collected path point information.

[0173] S305: The module for testing the regulation and control algorithm in the PC 2 may obtain the determined navigation information and reference point information through the model interface to facilitate subsequent testing of the regulation and control algorithm.

[0174] Since the path point information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so the accuracy of the reference line information determined based on the measured path point information on the target route and the perception information of the target vehicle is higher, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, realizing the decoupling between the map algorithm and the algorithm for determining the reference line information, and no need for complex indexing and path planning operations, greatly reducing the amount of calculation required to determine the reference line information, reducing the hardware computing power requirements for the electronic equipment that determines the reference line, and reducing the cost of the electronic equipment. In addition, it is also conducive to improving the accuracy of subsequent testing of the regulatory control algorithm. And according to the characteristics that the reference line determination method and the regulatory control algorithm run on the same PC, the model interface of simulink is used instead of the Ethernet interface of the physical layer, which saves the hardware of the autonomous driving controller. At the same time, simulation testing can be performed in the early development stage of the algorithm, and algorithm problems can be discovered and solved earlier.

[0175] In the various embodiments of the present application, unless otherwise specified or provided for in any logical conflict, the terms and / or descriptions between the different embodiments are consistent and may be referenced to each other, and the technical features in the different embodiments may be combined to form new embodiments according to their inherent logical relationships.

[0176] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0177] Embodiment 3:

[0178] The present application provides a reference line determination device. Figure 4 A schematic diagram of a reference line determination device provided in an embodiment of the present application, the device comprising:

[0179] An acquisition unit 41 is used to acquire the waypoint information on the target route and the perception information of the target vehicle;

[0180] The processing unit 42 is used to determine reference line information based on the waypoint information and the perception information.

[0181] In some possible implementations, the processing unit 42 is specifically used to determine the target path point from each of the path points according to the second coordinate information and the first coordinate information corresponding to each of the path points if the path point information includes the first coordinate information of the path point and the first time information of the vehicle passing through the path point, and the perception information includes the second coordinate information of the target vehicle and the lane line information corresponding to the lanes associated with the target vehicle, and when the navigation information includes the lane number; determine the reference path point after the target path point from each of the path points according to the first time information corresponding to each of the path points; determine the target straight line passing through the target path point and the reference path point; obtain the distance between the target vehicle and the target straight line; and determine the distance interval corresponding to the distance interval according to the correspondence between the distance interval and the lane number. Lane number; in the case where the navigation information includes a lane change type, obtaining current time information; determining the lane change type corresponding to the time interval in which the current time information is located according to a pre-configured correspondence between the time interval and the lane change type; wherein the time interval is determined according to the first time information corresponding to each of the path points; in the case where the navigation information includes a change distance, obtaining current time information; determining a target lane change point corresponding to the time interval in which the current time information is located according to a pre-configured correspondence between the time interval and the lane change point; determining the change distance based on the coordinate information of the target lane change point; wherein the change distance indicates the distance between the target vehicle and the next lane change point; in the case where the navigation information includes a lane line coefficient, determining the lane line coefficient according to the lane line information corresponding to the lanes associated with the target vehicle.

[0182] In some possible implementations, the processing unit 42 is specifically used to determine a reference path point from each of the path points if the path point information includes first coordinate information of the path point, first heading information of the vehicle passing through the path point, first road slope information at the path point, and first road curvature information at the path point, and the perception information includes second coordinate information of the target vehicle and second heading information of the target vehicle, and if the reference point information includes heading information of the reference point, determine the reference heading information of the reference point for each of the reference path points based on the second heading information and the first heading information corresponding to the reference path point; and if the reference point information includes coordinate information of the reference point, Determine a reference path point from each of the path points; for each of the reference path points, determine the coordinate information of the reference point based on the second coordinate information, the first coordinate information corresponding to the reference path point, and the first heading information corresponding to the reference path point; if the reference point information includes slope information of the reference point, determine the reference path point from each of the path points; for each of the reference path points, determine the slope information of the reference point based on the first road slope information corresponding to the reference path point; if the reference point information includes curvature information of the reference point, determine the reference path point from each of the path points; for each of the reference path points, determine the curvature information of the reference point based on the first road curvature information corresponding to the reference path point.

[0183] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0184] Since the waypoint information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so that the reference line information subsequently determined based on the measured waypoint information on the target route and the perception information of the target vehicle is more accurate, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic equipment for determining the reference line, and reduces the cost of the electronic equipment.

[0185] Embodiment 4:

[0186] like Figure 5 The present invention provides a schematic diagram of an electronic device structure according to an embodiment of the present invention. Based on the above embodiments, the present invention further provides an electronic device, such as Figure 5As shown, it includes: a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52, and the memory 53 communicate with each other through the communication bus 54;

[0187] The memory 53 stores a computer program. When the program is executed by the processor 51, the processor 51 performs the following steps:

[0188] Obtaining the waypoint information on the target route and the perception information of the target vehicle;

[0189] Based on the waypoint information and the perception information, reference line information is determined.

[0190] Since the principle of solving the problem by the above electronic device is similar to the reference line determination method, the implementation of the above electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0191] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0192] The communication interface 52 is used for communication between the above electronic device and other devices.

[0193] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0194] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0195] Since the waypoint information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so that the reference line information subsequently determined based on the measured waypoint information on the target route and the perception information of the target vehicle is more accurate, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic equipment for determining the reference line, and reduces the cost of the electronic equipment.

[0196] Embodiment 5:

[0197] On the basis of the above embodiments, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program executable by a processor, and when the program runs on the processor, the processor implements the following steps when executing:

[0198] Obtaining the waypoint information on the target route and the perception information of the target vehicle;

[0199] Based on the waypoint information and the perception information, reference line information is determined.

[0200] Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the reference line determination method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0201] Since the waypoint information on the target route and the perception information of the target vehicle are generally measured, there is no calculation error in this information, so that the reference line information subsequently determined based on the measured waypoint information on the target route and the perception information of the target vehicle is more accurate, avoiding the influence of the accuracy of the map algorithm on the accuracy of the determined reference line information, and there is no need to perform complex indexing and path planning operations, which greatly reduces the amount of calculation required to determine the reference line information, reduces the hardware computing power requirements of the electronic equipment for determining the reference line, and reduces the cost of the electronic equipment.

[0202] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0203] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0206] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A reference line determination method, characterized in that: The method comprises: Obtaining the waypoint information on the target route and the perception information of the target vehicle; Determine reference line information based on the waypoint information and the perception information; wherein the reference line information includes navigation information and / or reference point information; In a case where the waypoint information includes first coordinate information of the waypoint and first time information of the vehicle passing through the waypoint, and the perception information includes second coordinate information of the target vehicle and lane line information corresponding to lanes associated with the target vehicle, determining the reference line information based on the waypoint information and the perception information includes: In the case where the navigation information includes a lane number, according to the second coordinate information and the first coordinate information corresponding to each of the path points, the path point of the first coordinate information that is closest to the second coordinate information among the path points is determined as the target path point; according to the first time information corresponding to each of the path points, a reference path point after the target path point is determined from the path points; a target straight line passing through the target path point and the reference path point is determined; the distance between the target vehicle and the target straight line is obtained; and according to the correspondence between the distance interval and the lane number, the lane number corresponding to the distance interval in which the distance is located is determined; In the case where the navigation information includes a lane change type, obtaining current time information; determining the lane change type corresponding to the time interval in which the current time information is located according to a pre-configured correspondence between the time interval and the lane change type; wherein the time interval is determined according to the first time information corresponding to each of the path points; In the case where the navigation information includes a lane change distance, current time information is acquired; a target lane change point corresponding to the time interval in which the current time information is located is determined according to a pre-configured correspondence between the time interval and the lane change point; and the lane change distance is determined based on the coordinate information of the target lane change point; wherein the lane change distance indicates the distance between the target vehicle and the next lane change point; In a case where the navigation information includes a lane line coefficient, the lane line coefficient is determined according to lane line information respectively corresponding to lanes associated with the target vehicle.

2. The method according to claim 1, characterized in that The waypoint information includes one or more of the following: The first coordinate information of the waypoint, the first heading information of the vehicle passing the waypoint, the first road slope information at the waypoint, the first time information of the vehicle passing the waypoint, and the first road curvature information at the waypoint.

3. The method according to claim 1 or 2, characterized in that The perception information includes one or more of the following: The second coordinate information of the target vehicle, the lane line information corresponding to the lanes associated with the target vehicle, and the second heading information of the target vehicle.

4. The method according to claim 1, characterized in that In a case where the waypoint information includes first coordinate information of the waypoint, first heading information of the vehicle passing through the waypoint, first road slope information at the waypoint, and first road curvature information at the waypoint, and the perception information includes second coordinate information of the target vehicle and second heading information of the target vehicle, determining the reference line information based on the waypoint information and the perception information includes: In the case where the reference point information includes heading information of the reference point, based on the heading information corresponding to each of the headings and a preset screening rule, a reference heading point is determined from each of the headings; for each of the reference headings, the reference heading information of the reference point is determined according to the second heading information and the first heading information corresponding to the reference heading; In the case where the reference point information includes coordinate information of the reference point, determining a reference path point from each of the path points; for each of the reference path points, determining the coordinate information of the reference point according to the second coordinate information, the first coordinate information corresponding to the reference path point, and the first heading information corresponding to the reference path point; In the case where the reference point information includes the slope information of the reference point, determining a reference path point from the path points; for each reference path point, determining the slope information of the reference point according to the first road slope information corresponding to the reference path point; In the case where the reference point information includes curvature information of the reference point, a reference path point is determined from the path points; and for each reference path point, the curvature information of the reference point is determined according to the first road curvature information corresponding to the reference path point.

5. A reference line determination device, characterized in that: The device comprises: An acquisition unit, used to acquire waypoint information on a target route and perception information of a target vehicle; A processing unit, configured to determine reference line information based on the waypoint information and the perception information; wherein the reference line information includes navigation information and / or reference point information; The processing unit is specifically used for, when the path point information includes the first coordinate information of the path point and the first time information of the vehicle passing through the path point, and the perception information includes the second coordinate information of the target vehicle and the lane line information corresponding to the lanes associated with the target vehicle, and when the navigation information includes the lane number, according to the second coordinate information and the first coordinate information corresponding to each of the path points, determining the path point with the first coordinate information closest to the second coordinate information among each of the path points as the target path point; according to the first time information corresponding to each of the path points, determining the reference path point after the target path point from each of the path points; determining the target straight line passing through the target path point and the reference path point; obtaining the distance between the target vehicle and the target straight line; and determining the lane number corresponding to the distance interval in which the distance is located according to the correspondence between the distance interval and the lane number; In the case where the navigation information includes a lane change type, obtaining current time information; determining the lane change type corresponding to the time interval in which the current time information is located according to a pre-configured correspondence between the time interval and the lane change type; wherein the time interval is determined according to the first time information corresponding to each of the path points; In the case where the navigation information includes a lane change distance, current time information is acquired; a target lane change point corresponding to the time interval in which the current time information is located is determined according to a pre-configured correspondence between the time interval and the lane change point; and the lane change distance is determined based on the coordinate information of the target lane change point; wherein the lane change distance indicates the distance between the target vehicle and the next lane change point; In a case where the navigation information includes a lane line coefficient, the lane line coefficient is determined according to lane line information respectively corresponding to lanes associated with the target vehicle.

6. An electronic device, characterized in that: The electronic device comprises at least a processor and a memory, and the processor is used to implement the steps of the reference line determination method as claimed in any one of claims 1 to 4 when executing a computer program stored in the memory.

7. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the reference line determination method as claimed in any one of claims 1 to 4.

8. A computer program product, characterized in that The computer program product comprises: computer program code, which, when executed on a computer, enables the computer to execute the steps of the reference line determination method as claimed in any one of claims 1 to 4.

Images