Detour path planning method, automatic driving method, vehicle-mounted equipment and storage medium

Abstract

The present application discloses a detour path planning method, which is applied to an autonomous driving vehicle. The path planning method includes: receiving a detour instruction; in response to the detour instruction, obtaining a detour path of the autonomous driving vehicle starting from the initial position of the autonomous driving vehicle, so that the autonomous driving vehicle can detour at the initial position, wherein the detour path includes a first path and a second path connected to each other, the first path is obtained by planning based on a first sampling method of a preset coordinate system, and the second path is obtained by planning based on a second sampling method of the preset coordinate system, and the first sampling method is different from the second sampling method. The present application also discloses an autonomous driving method, an on-board device, and a storage medium. The present application can achieve safe and efficient detours.

Description

Technical Field

[0001] The disclosed embodiments of the present application relate to the field of autonomous driving technology, and more specifically, to a detour path planning method, an autonomous driving method, a vehicle-mounted device, and a storage medium. Background Art

[0002] Autonomous vehicles, also known as driverless vehicles, computer-driven vehicles, or wheeled mobile robots, are intelligent vehicles that are unmanned by computer systems. With the popularization of autonomous vehicles, autonomous vehicles can be used as public transportation.

[0003] When passengers use self-driving vehicles, they often encounter situations where the self-driving vehicle is too close to the vehicle in front or an obstacle and cannot complete the detour. This can easily lead to low driving efficiency of the self-driving vehicle and hinder the normal passage of road traffic. Summary of the invention

[0004] According to the embodiments of the present application, the present application provides a detour path planning method, an automatic driving method, a vehicle-mounted device and a storage medium to solve the above-mentioned problems.

[0005] In a first aspect, the present application provides a detour path planning method, which is applied to an autonomous driving vehicle. The method comprises: receiving a detour instruction; in response to the detour instruction, obtaining a detour path of the autonomous driving vehicle starting from an initial position of the autonomous driving vehicle, so that the autonomous driving vehicle can detour at the initial position, wherein the detour path comprises a first path and a second path connected to each other, the first path is obtained by planning based on a first sampling method of a preset coordinate system, and the second path is obtained by planning based on a second sampling method of the preset coordinate system, and the first sampling method is different from the second sampling method.

[0006] In some embodiments, obtaining a detour path of the autonomous driving vehicle starting from an initial position of the autonomous driving vehicle includes: determining whether a vehicle speed of the autonomous driving vehicle at the initial position satisfies a preset condition; and obtaining the detour path in response to the vehicle speed at the initial position satisfying the preset condition.

[0007] In some embodiments, the preset condition includes the vehicle speed being less than or equal to a preset value.

[0008] In some embodiments, acquiring the first path includes: determining a first sampling point sampled by the first sampling method corresponding to the detour instruction; and determining the detour path based on the first sampling point.

[0009] In some embodiments, determining the first sampling point sampled by the first sampling method corresponding to the bypass instruction includes: obtaining a sampling point layer sampled by the first sampling method, wherein the sampling point layer is parallel to the first sampling point layer sampled by the second sampling method and includes a plurality of uniformly distributed sampling points; and determining the first sampling point corresponding to the bypass instruction from the sampling point layer sampled by the first sampling method.

[0010] In some embodiments, the values ​​represented by the multiple sampling points in the sampling point layer sampled by the first sampling method decrease successively from one side to the other side, wherein the maximum value represented by the multiple sampling points is determined by the maximum steering wheel angle of the autonomous driving vehicle, and the minimum value is determined by the minimum steering wheel angle of the autonomous driving vehicle.

[0011] In some embodiments, obtaining the second path includes: determining multiple sampling point layers sampled by the second sampling method corresponding to the first path, wherein the multiple sampling point layers are evenly distributed along the driving direction of the autonomous driving vehicle, and multiple sampling points in each sampling point layer in the multiple sampling point layers are evenly distributed along a direction perpendicular to the driving direction; determining multiple second sampling points corresponding to the end point of the first path from the multiple sampling point layers, wherein the multiple second sampling points are located in the same straight line; and obtaining the second path based on the multiple second sampling points.

[0012] A second aspect of the present application provides an autonomous driving method, the method comprising: obtaining a detour path; performing autonomous driving according to the detour path; wherein the detour path is obtained by the detour path planning method for controlling an autonomous driving vehicle in the first aspect mentioned above.

[0013] A third aspect of the present application provides an electronic device, comprising a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned bypass path planning method or automatic driving method.

[0014] A fourth aspect of the present application provides a non-volatile computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned detour path planning method or autonomous driving method when executed by a processor.

[0015] The beneficial effects of the present application are as follows: by responding to a detour instruction, a detour path of the autonomous driving vehicle starting from the initial position of the autonomous driving vehicle is obtained, so that the autonomous driving vehicle can detour at the initial position. The detour path includes a first path and a second path connected to each other, the first path is obtained by planning based on a first sampling method of a preset coordinate system, and the second path is obtained by planning based on a second sampling method of a preset coordinate system, and the first sampling method is different from the second sampling method, thereby achieving safe and efficient detour of the autonomous driving vehicle, and even when the autonomous driving vehicle is too close to the vehicle or obstacle in front, the detour can be completed safely and efficiently.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present application will be further described below in conjunction with the accompanying drawings and implementation methods, in which:

[0018] Figure 1 is a flowchart of a detour path planning method according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of an autonomous driving vehicle used in an embodiment of the present application when in a turning state;

[0020] Figure 3 Schematic diagram of the sampling of the curvature sampling method and the sl sampling method based on the Frenet coordinate system used in the embodiments of the present application;

[0021] Figure 4 is a flowchart of an automatic driving method according to an embodiment of the present application;

[0022] Figure 5 is a schematic structural diagram of a vehicle-mounted device according to an embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of the structure of the non-volatile computer-readable storage medium of an embodiment of the present application. DETAILED DESCRIPTION

[0024] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] The term "and / or" in this application is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, and can mean including any one or more elements selected from the set consisting of A, B, and C. In addition, the terms "first", "second", and "third" in this application are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features.

[0026] In order to enable those skilled in the art to better understand the technical solution of the present application, the technical solution of the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0027] See also Figure 1 , Figure 1 is a flowchart of a detour path planning method according to an embodiment of the present application. The method can be applied to an autonomous driving vehicle, such as an autonomous driving vehicle equipped with an on-board device having computing and other functions. It should be noted that if there are substantially the same results, the method of the present application is not limited to the above. Figure 1 The process sequence shown is limited.

[0028] In some possible implementations, the method may be implemented by a processor calling computer-readable instructions stored in a memory, such as Figure 1 As shown, the method may include the following steps:

[0029] S11: receiving a detour instruction.

[0030] The detour instruction received by the autonomous driving vehicle may be an instruction triggered when a detour is required, for example, when there is a vehicle or obstacle in front of the autonomous driving vehicle. For example, in response to the distance between the autonomous driving vehicle and the vehicle or obstacle in front of it in the current environment reaching a preset condition, the detour instruction is triggered. For another example, in response to the current speed of the autonomous driving vehicle reaching a preset speed threshold, the detour instruction is triggered.

[0031] The environment in which the autonomous driving vehicle is currently located can be monitored by sensor equipment, wherein the sensor equipment includes a speed sensor, a camera sensor, and a radar sensor. The speed sensor can be an infrared sensor, and the speed sensor can be used to collect the distance data of the autonomous driving vehicle. The radar sensor can be a radar device used for autonomous driving and meeting the accuracy requirements for providing point cloud perception, wherein the laser radar can include a mechanical laser radar, a semi-solid laser radar, or a solid-state laser radar, etc. For example, the radar sensor includes a millimeter wave radar, a laser radar, etc., and the radar sensor can be used to collect point cloud data. The camera sensor can be a 3D depth camera sensor, which can collect the depth data of the autonomous driving vehicle. The speed sensor, the camera sensor, and the radar sensor can be installed on the autonomous driving vehicle.

[0032] In one application scenario, an autonomous vehicle is driving on a road, and a speed sensor installed on the autonomous vehicle obtains distance data used to describe the environment space where the autonomous vehicle is located, thereby obtaining an initial data set. A radar sensor is used to obtain point cloud data used to describe the environment space where the vehicle-mounted equipment is located, thereby obtaining another initial data set. Thus, through these two initial data sets, it is determined whether the distance between the autonomous vehicle and the vehicle or obstacle in front of it in the current environment meets the preset conditions.

[0033] S12: In response to the detour instruction, a detour path of the autonomous driving vehicle starting from the initial position of the autonomous driving vehicle is obtained, so that the autonomous driving vehicle can detour at the initial position. The detour path includes a first path and a second path connected to each other, the first path is obtained by planning based on a first sampling method of a preset coordinate system, and the second path is obtained by planning based on a second sampling method of the preset coordinate system, and the first sampling method is different from the second sampling method.

[0034] That is, the first path and the second path are continuous paths planned by different sampling methods based on a preset coordinate system. For example, when there is a vehicle or obstacle in front of the autonomous driving vehicle, a detour instruction is triggered. In response to the detour instruction, the autonomous driving vehicle plans the first path and the second path to avoid the vehicle or obstacle in front. The first path is the path of the autonomous driving vehicle from the initial position to bypass the vehicle or obstacle in front, and the second path is the path of the autonomous driving vehicle after bypassing the vehicle or obstacle in front.

[0035] The preset coordinate system may be a Frenet coordinate system. In the Frenet coordinate system, the longitudinal direction s represents the direction of travel of the autonomous driving vehicle along the road, and the lateral direction l represents the direction perpendicular to the road (where the left side is positive). Different sampling methods based on the Frenet coordinate system include an sl sampling method and a curvature sampling method. The sl sampling method is to scatter points in the s direction and the l direction to obtain multiple sampling point layers in the s direction and the l direction, wherein each point is an sl sampling point. When the sl sampling method is used for path planning, the position of the rear axle center of the autonomous driving vehicle is taken as the starting point, and the sl sampling points between different layers are connected in the form of an sl quintic curve, thereby obtaining a path planned using the sl sampling method, wherein the first-order derivative and the second-order derivative of the coordinate in the l direction at the sl sampling point with respect to the coordinate in the s direction are 0.

[0036] The curvature sampling method is to determine different curvature sampling points, each curvature sampling point represents a curvature, and the curvature can determine the steering wheel angle of the autonomous driving vehicle. The different curvature sampling points determined by the curvature sampling method can be set into a curvature sampling point layer and arranged according to the size of the curvature value of the curvature sampling point.

[0037] To illustrate the relationship between curvature and the steering wheel angle of an autonomous vehicle, the following describes an autonomous vehicle. Figure 2 , which is a schematic diagram of the autonomous driving vehicle used in the embodiment of the present application in a turning state. The autonomous driving vehicle is in a turning state, which can indicate that the autonomous driving vehicle is detouring. The wheelbase L is the distance between the front and rear tires of the autonomous driving vehicle, the front wheel turning angle a is the angle formed by the front wheel and the vehicle body, and the turning radius R is the degree of turning caused by the front wheel turning angle a.

[0038] from Figure 2 It can be seen that the turning radius R, wheelbase L, and front wheel angle a can be described by the trigonometric tangent relationship. Therefore, combined with the steering ratio ratio between the steering wheel angle steer and the front wheel angle a, and the curvature k and the turning radius R are reciprocals, the relationship between the curvature and the steering wheel angle can be obtained, as shown in the following formula:

[0039] Steer=ratio*arctan(k*L),

[0040] Among them, steer is the steering wheel angle, ratio is the steering ratio between the steering wheel angle and the front wheel angle, and k is the curvature.

[0041] From the above formula, it can be seen that the steering wheel angle of the autonomous driving vehicle can be determined based on the curvature sampling points.

[0042] In this embodiment, by responding to a detour instruction, a first path and a second path of the autonomous driving vehicle starting from an initial position of the autonomous driving vehicle are obtained, so that the autonomous driving vehicle can detour at the initial position, wherein the detour path includes a first path and a second path that are connected to each other, the first path is planned based on a first sampling method of a preset coordinate system, and the second path is planned based on a second sampling method of the preset coordinate system, and the first sampling method is different from the second sampling method, thereby achieving safe and efficient detour of the autonomous driving vehicle, and even being able to complete the detour safely and efficiently when the vehicle or obstacle ahead is too close.

[0043] As described above, when a detour instruction is received, a detour path of the autonomous driving vehicle starting from the initial position of the autonomous driving vehicle is obtained. In some embodiments, obtaining a detour path of the autonomous driving vehicle starting from the initial position of the autonomous driving vehicle may include: determining whether the speed of the autonomous driving vehicle at the initial position meets a preset condition; in response to the speed of the autonomous driving vehicle at the initial position meeting the preset condition, obtaining the detour path.

[0044] When the speed of the autonomous driving vehicle at the initial position meets the preset condition, the detour path is obtained. That is, when a detour instruction is received, the detour path is obtained, that is, path planning is performed to obtain the detour path, on the premise that the speed of the autonomous driving vehicle at the initial position meets the preset condition.

[0045] The preset condition can be set according to the actual situation, for example, it can include that the vehicle speed is less than or equal to the preset value. The speed of the autonomous driving vehicle at the initial position is less than or equal to the preset value, indicating that the autonomous driving vehicle is stationary or at a low speed at the initial position. The preset value can be set according to the actual situation, for example, the preset value can be 0.1m / s.

[0046] Furthermore, in some embodiments, the above-mentioned preset condition may include that the vehicle speed is less than or equal to a preset value.

[0047] As mentioned above, the first path and the second path in the detour path are planned based on different sampling methods of a preset coordinate system, wherein the first path is planned based on a first sampling method of a preset coordinate system, and the second path is planned based on a second sampling method of a preset coordinate system, and the first sampling method is different from the second sampling method.

[0048] In the example where the preset coordinate system is the Frenet coordinate system, the first sampling method may be the curvature sampling method, and the second sampling method may be the sl sampling method, wherein the sl sampling method and the curvature sampling method have been described in detail in the above embodiment and will not be described again here.

[0049] In some embodiments, acquiring the first path includes: determining a first sampling point sampled by the first sampling method corresponding to the detour instruction; and determining the detour path based on the first sampling point.

[0050] Taking the first sampling method as the curvature sampling method and the second sampling method as the sl sampling method as an example, the first sampling point corresponding to the detour instruction is determined, that is, one of the curvature sampling points is determined in the curvature sampling point layer obtained by the curvature sampling method. Then, as described above, the steering wheel angle of the autonomous driving vehicle can be determined according to the curvature sampling point. Then, since the steering wheel angle is known, the first path can be obtained.

[0051] The first sampling point sampled by the first sampling method corresponding to the detour instruction indicates that the detour instruction itself contains relevant information of the first sampling point, for example, the detour instruction itself indicates the curvature value range of the first sampling point. When receiving the detour instruction, the autonomous driving vehicle can determine the curvature value range of the first sampling point according to the detour instruction, and can achieve successful detour. Specifically, the first sampling point sampled by the first sampling method corresponding to the detour instruction can represent the maximum curvature value sampled by the curvature sampling method, or can represent other curvature values ​​sampled by the curvature sampling method. This application is not limited to this, as long as the autonomous driving vehicle can successfully detour. In other words, the relevant information of the first sampling point contained in the detour instruction itself has indicated that a successful detour can be achieved, and the relevant information of the first sampling point contained in the detour instruction itself has been judged whether a successful detour can be achieved before being sent to the autonomous driving vehicle upstream such as the cloud. If the relevant information of the first sampling point contained in the detour instruction itself cannot enable the autonomous driving vehicle to successfully detour, the detour instruction will not be sent to the autonomous driving vehicle.

[0052] As described above, when acquiring the first path, it is necessary to determine the first sampling point sampled by the first sampling method corresponding to the detour instruction. In some embodiments, determining the first sampling point sampled by the first sampling method corresponding to the detour instruction includes: acquiring a sampling point layer sampled by the first sampling method, wherein the sampling point layer is parallel to the first sampling point layer sampled by the second sampling method and includes a plurality of uniformly distributed sampling points; and determining the first sampling point corresponding to the detour instruction from the sampling point layer sampled by the first sampling method.

[0053] Continuing with the example of the first sampling method being the curvature sampling method and the second sampling method being the sl sampling method, and combining Figure 3 To explain, Figure 3 It is a sampling schematic diagram of the curvature sampling method and the sl sampling method based on the Frenet coordinate system used in the embodiments of the present application.

[0054] like Figure 3 As shown, when there is a vehicle or obstacle in front of the autonomous driving vehicle, the sl sampling method is used to perform sampling before path planning, and multiple sampling point layers on the longitudinal direction s are obtained, including the first sampling point layer, the second sampling point layer...the nth sampling point layer. Of course, the multiple sampling point layers on the longitudinal direction s can also be regarded as multiple sampling point layers on the horizontal direction l. When used, this is not performed in the horizontal direction l, so it is not explained. The curvature sampling method is used to perform sampling before path planning, and a sampling point layer, namely the curvature sampling point layer, is obtained. This sampling point layer is parallel to the first sampling point layer of the sl sampling method and includes multiple uniformly distributed sampling points (i.e., curvature sampling points).

[0055] In the process of determining the first sampling point corresponding to the detour instruction, the curvature sampling point layer sampled by the curvature sampling method is first obtained, and then the first sampling point corresponding to the detour instruction is determined from the curvature sampling point layer. Then, the steering wheel angle of the autonomous driving vehicle is determined based on the first sampling point, that is, as described above Figure 2 As shown, according to the curvature sampling points, the steering wheel angle of the autonomous driving vehicle can be determined. After the steering wheel angle is determined, the first path can be obtained. Figure 3 In FIG. 1 , the first sampling point is the leftmost curvature sampling point, and accordingly, the first path is indicated by a curved arrow.

[0056] In some embodiments, the values ​​represented by multiple sampling points in the sampling point layer sampled by the first sampling method decrease successively from one side to the other side, wherein the values ​​represented by the multiple sampling points are determined by the maximum steering wheel angle of the autonomous driving vehicle, and the minimum value is determined by the minimum steering wheel angle of the autonomous driving vehicle.

[0057] The maximum value is determined by the maximum steering wheel angle of the autonomous vehicle, and the minimum value is determined by the minimum steering wheel angle of the autonomous vehicle, and the maximum steering wheel angle and the minimum steering wheel angle are determined by the physical limits of the steering wheel of the autonomous vehicle. In other words, the value range represented by the sampling point layer sampled by the first sampling method is related to the steering wheel angle range of the autonomous vehicle.

[0058] Continuing with the example of the first sampling method being the curvature sampling method and the second sampling method being the sl sampling method, and combining Figure 3 For explanation. Figure 3 As shown, the values ​​represented by the multiple sampling points in the curvature sampling point layer decrease successively from one side to the other side, that is, in the curvature sampling point layer, the curvature represented by the sampling points decreases successively from one side to the other side, and accordingly, the steering wheel angle corresponding to the value represented by the sampling points decreases successively from one side to the other side.

[0059] As described above, the first path and the second path are obtained by planning based on different sampling methods of the preset coordinate system. The first path is obtained by planning based on the first sampling method of the preset coordinate system, and the second path is obtained by planning based on the second sampling method of the preset coordinate system, wherein the first sampling method is different from the second sampling method.

[0060] In the example where the preset coordinate system is the Frenet coordinate system, the first sampling method may be the curvature sampling method, and the second sampling method may be the sl sampling method, wherein the sl sampling method and the curvature sampling method have been described in detail in the above embodiment and will not be described again here.

[0061] At this time, in some embodiments, obtaining the second path includes: determining a plurality of sampling point layers sampled by the second sampling method corresponding to the first path, wherein the plurality of sampling point layers are evenly distributed along the driving direction of the autonomous driving vehicle, and a plurality of sampling points in each sampling point layer in the plurality of sampling point layers are evenly distributed along a direction perpendicular to the driving direction; determining a plurality of second sampling points corresponding to the end point of the first path from the plurality of sampling point layers, wherein the plurality of second sampling points are located in the same straight line; and obtaining the second path based on the plurality of second sampling points.

[0062] Take the first sampling method as the curvature sampling method and the second sampling method as the sl sampling method as an example, and combine Figure 3 To explain, Figure 3 It is a sampling schematic diagram of the curvature sampling method and the sl sampling method based on the Frenet coordinate system used in the embodiments of the present application.

[0063] like Figure 3 As shown, when there is a vehicle or obstacle in front of the autonomous driving vehicle, the SL sampling method is used to perform sampling before path planning, and multiple sampling point layers uniformly distributed in the longitudinal direction s (the driving direction of the autonomous driving vehicle) are obtained, including a uniformly distributed first sampling point layer, a second sampling point layer...nth sampling point layer, and multiple sampling points in each sampling point layer are uniformly distributed along the horizontal direction l (i.e., the vertical driving direction). Of course, the multiple sampling point layers in the longitudinal direction s can also be regarded as multiple sampling point layers in the horizontal direction l. When used, this is not performed in the horizontal direction l, so it is not explained. The curvature sampling method is used to perform sampling before path planning, and a sampling point layer, i.e., a curvature sampling point layer, is obtained. This sampling point layer is parallel to the first sampling point layer of the SL sampling method, and includes multiple uniformly distributed sampling points (i.e., curvature sampling points).

[0064] Determine a plurality of sampling point layers sampled by the second sampling method corresponding to the first path, that is, perform s1 sampling before planning, and obtain a plurality of sampling point layers. Then, determine a plurality of second sampling points corresponding to the end point of the first path from the plurality of sampling point layers. If the plurality of second sampling points are located on the same straight line or the same curve, the plurality of second sampling points are a sampling point layer in the vertical direction. For example, Figure 3 As shown in FIG. 1 , the end point of the first path is the leftmost sampling point, and the plurality of second sampling points corresponding to the end point are the leftmost sampling point layer in the vertical direction. Subsequently, the second path is obtained based on the plurality of second sampling points. For example, the plurality of second sampling points can be determined by a polynomial such as a quintic curve to connect them into a line, thereby forming a second path, as shown in FIG. Figure 3 Indicated by the straight arrow on the left.

[0065] See also Figure 4 , Figure 4 is a flowchart of an automatic driving method according to an embodiment of the present application. The method can be applied to an on-board device with computing and other functions installed on an automatic driving vehicle. In some possible implementations, the method can be implemented by a processor calling a computer-readable instruction stored in a memory, such as Figure 4 As shown, the method may include the following steps:

[0066] S41: Obtain a detour path.

[0067] The detour path may be a path of the autonomous driving vehicle obtained by using the detour path planning method of the above embodiment, and the detour path includes a first path and a second path. The detour path planning method of the above embodiment may refer to the specific implementation process of the above embodiment, and this application will not repeat it here.

[0068] S42: Execute automatic driving according to the detour path.

[0069] Automatic driving is performed according to the detour path obtained by the above-mentioned detour path planning method.

[0070] In this embodiment, by acquiring a detour path obtained by utilizing the detour path planning method of the above embodiment, automatic driving is implemented according to the detour path, thereby achieving safe and efficient detour of the automatic driving vehicle, and even being able to complete the detour safely and efficiently when the vehicle ahead or an obstacle is too close.

[0071] 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.

[0072] The specific implementation of this embodiment can refer to the implementation process of the above embodiment, which will not be repeated here.

[0073] See also Figure 5 , Figure 5 The vehicle-mounted device 500 includes a memory 501 and a processor 502 coupled to each other, and the processor 502 is used to execute program instructions stored in the memory 501 to implement the steps of any embodiment of the above-mentioned detour path planning method or the automatic driving method.

[0074] In a specific implementation scenario, the vehicle-mounted device 500 may include, but is not limited to: a microcomputer and a server, which are not limited here.

[0075] Specifically, the processor 502 is used to control itself and the memory 501 to implement the steps of any embodiment of the above-mentioned detour path planning method and / or the automatic driving method. The processor 502 can also be called a CPU (Central Processing Unit), and the processor 502 may be an integrated circuit chip with signal processing capabilities. The processor 502 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 502 can be implemented by an integrated circuit chip.

[0076] The specific implementation of this embodiment can refer to the implementation process of the above embodiment, which will not be repeated here.

[0077] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of a non-volatile computer-readable storage medium in an embodiment of the present application. The non-volatile computer-readable storage medium 600 is used to store program instructions 601. When the program instructions 601 are executed by the processor, they are used to implement the steps in any embodiment of the above-mentioned detour path planning method or the automatic driving method.

[0078] The non-volatile computer-readable storage medium 600 may be a medium that can store program instructions 601, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or may be a server that stores the program instructions 601. The server may send the stored program instructions 601 to other devices for execution, or may execute the stored program instructions 601 by itself.

[0079] The specific implementation of this embodiment can refer to the implementation process of the above embodiment, which will not be repeated here.

[0080] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed methods and related devices can be implemented in other ways. For example, the above-described related device implementations are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication disconnection shown or discussed can be through some interfaces, indirect coupling or communication disconnection of devices or units, which can be electrical, mechanical or other forms.

[0082] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0084] It is easy for a person skilled in the art to know that many modifications and changes can be made to the device and method while maintaining the teaching content of the present application. Therefore, the above disclosure should be considered as limited only by the scope of the appended claims.

Claims

1. A detour path planning method, characterized in that: Applications in autonomous vehicles include: receiving a detour instruction; In response to the detour instruction, a detour path of the autonomous driving vehicle starting from an initial position of the autonomous driving vehicle is obtained, so that the autonomous driving vehicle can detour at the initial position, wherein the detour path includes a first path and a second path connected to each other, the first path is obtained by planning based on a first sampling method of a preset coordinate system, and the second path is obtained by planning based on a second sampling method of the preset coordinate system; Wherein, obtaining the first path includes: Acquire a sampling point layer sampled by the first sampling method, wherein the sampling point layer is parallel to the first sampling point layer sampled by the second sampling method and includes a plurality of sampling points that are evenly distributed, and the first sampling method includes determining different curvature sampling points; Determining the first sampling point corresponding to the detour instruction from the sampling point layer sampled by the first sampling method; Determining the first path according to the first sampling point; Acquiring the second path includes: Determine a plurality of sampling point layers sampled by the second sampling method corresponding to the first path; Determining, from the plurality of sampling point layers, a plurality of second sampling points corresponding to end points of the first path, wherein the plurality of second sampling points are located on the same straight line; The second path is obtained according to the plurality of second sampling points.

2. The method according to claim 1, characterized in that: The obtaining of a detour path of the autonomous driving vehicle starting from an initial position of the autonomous driving vehicle includes: Determining whether the speed of the autonomous driving vehicle at the initial position meets a preset condition; In response to the vehicle speed at the initial position satisfying a preset condition, the detour path is acquired.

3. The method according to claim 2, characterized in that The preset condition includes that the vehicle speed is less than or equal to a preset value.

4. The method according to claim 1, characterized in that: The values ​​represented by the multiple sampling points in the sampling point layer sampled by the first sampling method decrease successively from one side to the other side, wherein the maximum value represented by the multiple sampling points is determined by the maximum steering wheel angle of the autonomous driving vehicle, and the minimum value is determined by the minimum steering wheel angle of the autonomous driving vehicle.

5. The method according to claim 1, characterized in that The multiple sampling point layers are evenly distributed along the driving direction of the autonomous driving vehicle, and the multiple sampling points in each sampling point layer in the multiple sampling point layers are evenly distributed along a direction perpendicular to the driving direction.

6. An automatic driving method, characterized in that: include: Get the detour path; Execute automatic driving according to the detour path; The detour path is obtained by executing the detour path planning method as described in any one of claims 1-5.

7. A vehicle-mounted device, characterized in that: It includes a memory and a processor coupled to each other, and the processor is used to execute program instructions stored in the memory to implement the detour path planning method described in any one of claims 1 to 5 or the automatic driving method described in claim 6.

8. A non-volatile computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by the processor, the detour path planning method described in any one of claims 1 to 5 or the automatic driving method described in claim 6 is implemented.

Images