CN111653113B

CN111653113B - Method, device, terminal and storage medium for determining local path of vehicle

Info

Publication number: CN111653113B
Application number: CN202010310653.5A
Authority: CN
Inventors: 许康熙; 邓堃; 孙伟
Original assignee: Zhejiang Geely Holding Group Co Ltd; Zhejiang Geely Automobile Research Institute Co Ltd
Current assignee: Zhejiang Geely Holding Group Co Ltd; Zhejiang Geely Automobile Research Institute Co Ltd
Priority date: 2020-04-20
Filing date: 2020-04-20
Publication date: 2022-09-27
Anticipated expiration: 2040-04-20
Also published as: CN111653113A

Abstract

The method comprises the steps of determining a local path set according to acquired vehicle surrounding environment information and vehicle information, wherein the local path set comprises a lane changing path, an in-lane adjusting path, a main return path and a parking path; the main road in the path of the main loop is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point; meanwhile, a path selection instruction is generated according to the surrounding environment information of the vehicle and the vehicle information, and the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path; and determining a target local path from the local path set according to the path selection instruction. Therefore, when the vehicle encounters an obstacle, a plurality of local adjusting paths can be planned in time, and a proper path is selected from the local adjusting paths, so that the safety of the vehicle is improved.

Description

Method, device, terminal and storage medium for determining local path of vehicle

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for determining a local path of a vehicle.

Background

With the development of technology, automatic driving will slowly advance people's life, and the fatigue of driving for a long distance prompts people to look forward and longish to automatic driving. The automatic driving automobile can be divided into four grades of L1 to L4 according to the use scene, technical capability and the like of the automatic driving automobile. The automatic driving with the condition below the L3 level can reduce the driving load of the driver, but all decisions and responsibilities are still responsible for the driver. The L4 rating is fully autonomous driving, enabling autonomous decision making for most scenarios.

In order to ensure that passengers can be safely delivered to a destination after automatic driving at a given starting point and ending point, the vehicle is required to have environment sensing, path planning and execution capabilities.

In the path planning method in the prior art, after a starting point and an end point are given, a global path from the starting point to the end point is planned through algorithms such as a-search and a Rapid-Replication Random Tree (RRT). When the automatic driving vehicle runs along the global path, the conditions of front road construction, traffic accidents or other obstacles are unknown, so that the vehicle is required to be capable of planning a reasonable local adjustment path when encountering the obstacle based on a sensing system so as to complete overtaking, bypassing and other actions, thereby ensuring the safe running of the vehicle.

Disclosure of Invention

The embodiment of the application provides a method, a device, a terminal and a storage medium for determining a local path of a vehicle, so that a local adjustment path can be planned in time when the vehicle encounters an obstacle, and the driving safety and the passing efficiency of an automatic driving vehicle can be improved.

In one aspect, an embodiment of the present application provides a local path determining method for a vehicle, including:

determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; the main road in the main loop road paths is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point;

generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path;

and determining a target local path from the local path set according to the path selection instruction.

In another aspect, an embodiment of the present application provides a local path determining apparatus for a vehicle, including:

the first determining module is used for determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; the main road in the path of the return main road is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point;

the generating module is used for generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path;

and the second determining module is used for determining a target local path from the local path set according to the path selection instruction.

In another aspect, an embodiment of the present application provides a terminal, where the terminal includes a processor and a memory, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded by the processor and executes the above-mentioned method for determining a local path of a vehicle.

In another aspect, an embodiment of the present application provides a computer storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the above-mentioned local path determining method for a vehicle.

The method, the device, the terminal and the storage medium for determining the local path of the vehicle have the following beneficial effects:

determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information, wherein the local path set comprises a lane changing path, an in-lane adjusting path, a return path and a parking path; the main road in the path of the main loop is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point; meanwhile, a path selection instruction is generated according to the surrounding environment information of the vehicle and the vehicle information, and the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path; and determining a target local path from the local path set according to the path selection instruction. Therefore, when the vehicle encounters an obstacle, a plurality of local adjustment paths can be planned in time, and a proper path is selected from the local adjustment paths, so that the safety of the vehicle can be improved; the method has small calculation amount and can improve the efficiency of the output path, thereby improving the traffic efficiency.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart diagram illustrating a method for determining a local path of a vehicle according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a Frenet coordinate system according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a left lane change path according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of an in-lane adjusted path plan according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of another adjusted path plan in a lane according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of another adjusted path plan in a lane according to an embodiment of the present application;

fig. 8 is a schematic diagram of a main loop path provided in an embodiment of the present application;

fig. 9 is a schematic diagram of another main loop path provided in an embodiment of the present application;

FIG. 10 is a schematic diagram of an in-lane scene provided by an embodiment of the present application;

FIG. 11 is a diagram illustrating various functional images provided by an embodiment of the present application;

FIG. 12 is a schematic view of another in-lane scene provided by an embodiment of the present application;

FIG. 13 is a schematic diagram of a multi-lane scenario provided by an embodiment of the present application;

FIG. 14 is a schematic view of another in-lane scenario provided by an embodiment of the present application;

fig. 15 is a schematic structural diagram of a local path determining apparatus of a vehicle according to an embodiment of the present application;

fig. 16 is a hardware block diagram of a server of a local path determining method for a vehicle according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Referring to fig. 1, fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application, including a vehicle 101, where the vehicle 101 includes a path planning module 1011, a path decision module 1012, and a sensing module 1013. The sensing module 1013 sends the sensed vehicle surrounding environment information to the path planning module 1011 and the path decision module 1012, respectively.

The path planning module 1011 determines a local path set according to the vehicle surrounding environment information sent by the sensing module 1013 and the vehicle information acquired from other modules; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; wherein the main road in the main loop road paths is determined by the global path planning system of the vehicle 101 according to the preset starting point and the preset end point. Meanwhile, the path decision module 1012 generates a path selection instruction according to the vehicle surrounding environment information sent by the sensing module 1013 and the vehicle information acquired from other modules; the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path. Finally, the vehicle 101 determines a target local path from the local path set according to the path selection instruction.

In this embodiment, the Vehicle 101 may further receive a path instruction sent by a road end computing unit of an Intelligent Vehicle Infrastructure Cooperative Systems (IVICS), and determine a target local path from the local path set according to the path instruction. Specifically, the road-end calculating unit generates a path instruction based on the road-end sensing system or the sensing module 1013 of the vehicle 101, and sends the path instruction to the vehicle 101, and the vehicle 101 determines the target local path from the local path set based on the path instruction and the vehicle surrounding environment information.

Optionally, the other module for acquiring the Vehicle information from the other module may be a Vehicle Control Unit (VCU) module of the Vehicle 101.

Alternatively, the sensing module 1013 may be a set of sensors disposed on the vehicle 101, including a camera sensor, a lidar sensor, and a millimeter-wave radar sensor.

In the embodiment of the present application, the path planning module 1011, the path decision module 1012, and the sensing module 1013 may be disposed in the same device, such as a vehicle-mounted terminal or a similar operation device; alternatively, the path planning module 1011, the path decision module 1012 and the sensing module 1013 may be provided in a plurality of devices, which are in one system; alternatively, the path planning module 1011, the path decision module 1012 and the sensing module 1013 may be provided on one platform. Therefore, the execution subject of the embodiment of the present application may be a mobile terminal, a computer terminal, a server, or a similar operation device; may be a system or a platform.

While specific embodiments of a method for determining a local path of a vehicle according to the present application are described below, fig. 2 is a schematic flow chart of a method for determining a local path of a vehicle according to an embodiment of the present application, and the present specification provides the method operation steps according to the embodiments or the flow chart, but more or less operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In actual system or server product execution, sequential execution or parallel execution (e.g., parallel processor or multithreaded processing environments) may occur according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 2, the method may include:

s201: determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; the main road in the main loop path is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point.

In the embodiment of the application, the global path planning system of the vehicle plans a main road from the starting point to the end point according to the given starting point and the given end point, and the main road can be regarded as that the vehicle runs along the road center line of the lane level path to be run. In the process that the vehicle runs along the main road, the vehicle can acquire the surrounding environment information of the vehicle through a sensing system of the vehicle and then send the surrounding environment information to a path planning module, and the path planning module plans a plurality of local adjusting paths, namely a local path set, by combining with the vehicle information of the vehicle. The set of local paths may include a lane-change path, an in-lane adjustment path, a return road path, and a parking path.

In the embodiment of the application, the vehicle information may include the current speed of the vehicle, and may also include a vehicle heading angle and a vehicle lateral acceleration; the vehicle surrounding environment information includes a current lane width and current position coordinates of the vehicle. In the embodiment of the present application, a Frenet coordinate system is used when planning a path, as shown in fig. 3, an origin of the Frenet coordinate system is a preset starting point of a main road, an S-axis of the Frenet coordinate system represents a lateral range of the vehicle traveling along a road center line, a D-axis represents a longitudinal distance from all targets in the vehicle surrounding environment information to the road center line, and the targets may be obstacles such as vehicles, pedestrians, road barriers, and the like. The vehicle current position coordinates refer to coordinates based on a Frenet coordinate system, and if the vehicle surrounding environment information acquired by the vehicle sensing system is based on the cartesian coordinate system XYZ, all the vehicle surrounding environment information based on the cartesian coordinate system needs to be mapped into the Frenet coordinate system. After determining the set of local paths based on the Frenet coordinate system, the set of local paths is mapped into a Cartesian coordinate system. The conversion method between the cartesian coordinate system and the Frenet coordinate system belongs to the prior art, and therefore, the present application is not described in detail.

In an optional embodiment of determining a local path set according to the acquired vehicle surrounding environment information and vehicle information, the method for determining a road change path includes: determining a route starting point coordinate and a route end point coordinate of a lane changing route according to the current position coordinate of the vehicle, the current speed of the vehicle, the first preset time, the second preset time and the current lane width; establishing a road changing path function to be solved; and solving a road changing path function according to the path starting point coordinate and the path end point coordinate of the road changing path, the preset longitudinal acceleration and the preset course angle of the path starting point of the road changing path, and the preset longitudinal acceleration and the preset course angle of the path end point of the road changing path to obtain the road changing path. Specifically, the lane change path may include a left lane change path and a right lane change path. Only the determination process of the left lane change path is described below, please refer to fig. 4, and fig. 4 is a schematic diagram of a left lane change path according to an embodiment of the present application. As shown in FIG. 4(a), assume that a vehicle isThe current position coordinates of the vehicle are the starting point (origin) of the main road according to a first preset time (T) ₁ ) And the current speed (v) of the vehicle is determined as a first time interval S ₁ (S ₁ ＝T ₁ V) taking the first time interval as a transverse coordinate of a path starting point coordinate of the left lane changing path, and taking the transverse coordinate on the main path as S ₁ The longitudinal coordinate corresponding to the point is used as the longitudinal coordinate of the path starting point coordinate of the left lane changing path, and the path starting point coordinate is obtained as A (S) ₁ ，D ₁ ) (ii) a According to a second preset time (T) ₂ ) And the current speed (v) of the vehicle determines a second time interval as S ₂ (S ₂ ＝T ₂ V), determining the second time interval as the transverse coordinate of the path end point coordinate of the left lane changing path, and taking the current lane width as the longitudinal coordinate of the path end point coordinate, namely the path end point coordinate can be expressed as B (S) ₂ ，D ₂ ). The first preset time is set according to the actual situation, namely the vehicle runs according to the main road in the first preset time, and the left road changing path is adjusted to the main road after the first preset time; the second preset time is according to the perception distance S of the vehicle perception system ₃ Is determined with the current vehicle speed and satisfies T ₁ *v＜T ₂ *v＜S ₃ The relationship (2) of (c). Secondly, a left-hand road changing path function to be solved is established, and the left-hand road changing path function to be solved can be a fifth-order polynomial, such as formula (1):

d＝a0+a1*s+a2*s ² +a3*s ³ +a4*s ⁴ +a5*s ⁵ ……(1)

a0 and a1... a5 represent polynomial coefficients. A first derivative of formula (1) represents a heading angle; the second derivative of equation (1) represents the longitudinal acceleration.

Secondly, according to the path starting point coordinate A of the left lane changing path (S) ₁ ，D ₁ ) And path end point coordinates B (S) ₂ ，D ₂ ) Setting the preset longitudinal acceleration and the preset course angle of the path starting point of the left lane changing path and the preset longitudinal acceleration and the preset course angle of the path ending point of the lane changing path as 0, thus solving coefficients a0 and a1... a5 of the formula (1) to obtain the left lane changing path based on the Frenet coordinate system as shown in the figure 4 (a); as shown in FIG. 4(b), the base is substitutedThe left-hand road path in the Frenet coordinate system is mapped into the Cartesian coordinate system. The solving mode of the right lane changing path is the same as that of the left lane changing path, and only the longitudinal coordinate of the path end point coordinate of the right lane changing path is changed into-D ₂ Therefore, it is not described in detail.

In the embodiment of the application, the coordinates of the starting point of the path of the adjusting path in the lane, the coordinates of the starting point of the path of the return path, the coordinates of the starting point of the path of the parking path and the coordinates of the starting point of the path of the lane changing path are the same, the coordinates of the starting points of the paths are all at the first time interval of the current position of the vehicle, and the first time interval is the product of the first preset time and the current speed of the vehicle.

In an optional embodiment of determining the local path set according to the acquired vehicle surrounding environment information and vehicle information, determining the in-lane adjustment path includes: if the obstacle information is determined to exist in the vehicle surrounding environment information, determining key obstacle information from the obstacle information; the key obstacle information includes a set of key obstacle coordinates based on a Frenet coordinate system; the obstacle information includes a set of obstacle coordinates based on a Frenet coordinate system; determining a key path point coordinate set based on the key obstacle coordinate set; each key path point coordinate in the key path point coordinate set corresponds to each key obstacle coordinate in the key obstacle coordinate set one by one; establishing an in-lane adjustment path function set to be solved; and solving an in-lane adjustment path function set according to the path starting point coordinates of the in-lane adjustment path, the key path point coordinate set, and the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set to obtain the in-lane adjustment path. It should be noted that the obstacle coordinate set may include one coordinate of each obstacle, or may include a plurality of coordinates of each obstacle; one coordinate may be a center position coordinate of the obstacle, and a plurality of coordinates may be a plurality of coordinates of the obstacle, for example, four vertex coordinates of a bounding box (bounding box) of the obstacle.

Specifically, the determination of the existence of the obstacle from the vehicle surrounding environment information may be implemented by establishing a relevant neural network model or algorithm through machine learning.

Specifically, the determining the key obstacle information from the obstacle information may specifically include: firstly, dividing a plurality of obstacles into a plurality of subsets based on an obstacle coordinate set, wherein each subset comprises one or more obstacles; and the longitudinal coordinates of all the obstacles in each subset are positive or negative. Assuming that the lateral distance between any two laterally adjacent obstacles in each subset is less than 10 meters; secondly, defining all subsets with positive longitudinal coordinates as positive clusters, and defining all subsets with negative longitudinal coordinates as negative clusters; the transverse distance between every two subsets in the positive cluster is larger than or equal to 10 meters, and the transverse distance between every two subsets in the negative cluster is larger than or equal to 10 meters; secondly, determining the longitudinal coordinate with the minimum absolute value from each subset, and determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle to obtain a key obstacle coordinate set. It should be noted that the above 10 meters can be reset according to actual conditions.

Specifically, the determining the coordinate set of the critical path point based on the coordinate set of the critical obstacle includes: shifting the longitudinal coordinate of each key obstacle by a preset distance, and keeping the transverse coordinate unchanged to obtain the corresponding key path point coordinate; the offset direction is opposite to the longitudinal coordinate, the preset distance is set according to the actual condition, and the width of the current lane can be obtained. And if the absolute value of the longitudinal coordinate after the deviation of the preset distance exceeds a preset parameter, updating the longitudinal coordinate of the key path point based on the preset parameter. Wherein the preset parameter may refer to 1/4 of a distance between two lane preset boundaries, which is larger than the current lane width. And (3) assuming that the transverse distance between one key obstacle in the positive cluster and one key obstacle in the negative cluster is less than 5 meters, taking the middle point between the two key obstacles as a key path point to obtain the corresponding key path point coordinates. It should be noted that the above 5 meters can be reset according to actual conditions.

The above-described embodiments are explained below by three specific examples.

Referring to fig. 5, fig. 5 is a schematic diagram of an in-lane adjustment route planning according to an embodiment of the present disclosure. Assuming that the current position coordinates of the vehicle are the starting point (the origin) of the main road, the vehicle acquires the surrounding environment information of the vehicle through a millimeter wave radar sensor, and determines that the obstacle information exists from the surrounding environment information of the vehicle based on a correlation algorithm. Secondly, determining a subset I and a subset II based on the coordinate set of the obstacle; the longitudinal coordinates of all the obstacles in the subset I and the subset II are positive, and the distance between any two transversely adjacent obstacles in the subset I is less than 10 meters; determining the subset I and the subset II as a forward cluster, wherein the transverse distance between the subset I and the subset II is more than or equal to 10 meters; secondly, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle P from the subset (I) ₁ Determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle P from the subset II ₂ Obtaining a set of coordinates { P of key obstacles ₁ (s1，d1)，P ₂ (s2, d2) }; secondly, key obstacles P are respectively arranged ₁ 、P ₂ The longitudinal coordinate deviates the current lane width w, the transverse coordinate is unchanged, and the corresponding key path point coordinate M is obtained ₁ (s1，d1-w)、M ₂ (s2, d 2-w); secondly, judging a key obstacle P ₁ Whether the absolute value of the shifted longitudinal coordinate exceeds a preset parameter or not; if a critical obstacle P ₁ The absolute value of the shifted longitudinal coordinate exceeds a preset parameter (| d1-w |)>0.25L), M is updated ₁ Coordinates (s1, -0.25L); wherein, L represents the distance between the preset boundaries of the current lane; secondly, it can also be at M ₂ Plus a first time interval (S) to the transverse coordinates of ₁ ) Taking the longitudinal coordinate as 0 to obtain the coordinate M of the key path point ₃ (s2+S ₁ ，0)，M ₃ The coordinate of the path end point of the path can be adjusted in the lane; thus, the obtained coordinate set of the key path point is { M } ₁ (s1，-0.25L)，M ₂ (s2，d2-w)，M ₃ (s2+S ₁ 0) }; secondly, establishing a set of lane internal adjustment path functions to be solved, wherein the lane internal adjustment path functions to be solvedThe set may comprise three quintic polynomials, each for solving a path between two adjacent critical path points; next, the route start point coordinate a of the route is adjusted according to the inside of the lane (S) ₁ ，D ₁ ) And a key path point coordinate set, and setting the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set and the preset longitudinal acceleration and the preset course angle of the path starting point coordinate of the adjustment path in the lane to 0, so that coefficients of three fifth-order polynomials can be solved to obtain the adjustment path in the lane based on the Frenet coordinate system as shown in fig. 5 (a); as shown in fig. 5(b), the in-lane adjustment route based on the Frenet coordinate system is mapped into a cartesian coordinate system.

Referring to fig. 6, fig. 6 is a schematic diagram of another adjusted path plan in a lane according to an embodiment of the present application. Assuming that the current position coordinates of the vehicle are the starting point (the origin) of the main road, the vehicle acquires the surrounding environment information of the vehicle through the millimeter wave radar sensor, and determines that the obstacle information exists in the surrounding environment information of the vehicle based on a correlation algorithm. Secondly, determining a subset I, a subset II and a subset III 3 based on the obstacle coordinate set; the longitudinal coordinates of all obstacles in the subset (0) and the subset (1) are positive, the longitudinal coordinates of all obstacles in the subset (3) are negative, and the distance between any two transversely adjacent obstacles in the subset (4) is less than 10 meters; determining the subset (i) and the subset (2) as positive clusters and the subset (iii) as negative clusters, wherein the transverse distance between the subset (i) and the subset (ii) is greater than or equal to 10 meters, and the transverse distance between the subset (ii) and the subset (iii) is greater than or equal to 5 meters; secondly, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle P from the subset (r) ₁ Determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value from the subset as a key obstacle P ₂ Determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value from the subset as a key obstacle P ₃ Obtaining a set of coordinates { P of key obstacles ₁ (s1，d1)，P ₂ (s2，d2)，P ₃ (s3, d3) }; secondly, key obstacles are respectively arrangedP ₁ 、P ₂ And P ₃ The longitudinal coordinate deviates the current lane width w, the transverse coordinate is unchanged, and the corresponding key path point coordinate M is obtained ₁ (s1，d1-w)、M ₂ (s2, d2-w) and M ₃ (s3, d3+ w); secondly, judging a key obstacle P ₁ The absolute value of the shifted longitudinal coordinate exceeds a preset parameter; if a critical obstacle P ₁ The absolute value of the shifted longitudinal coordinate exceeds a preset parameter (| d1-w |)>0.25L), M is updated ₁ Coordinates (s1, -0.25L); secondly, it can also be at M ₃ Plus a first time interval (S) to the transverse coordinates of ₁ ) Taking the longitudinal coordinate as 0 to obtain the coordinate M of the key path point ₄ (s3+S ₁ ，0)，M ₄ The coordinate of the path end point of the path can be adjusted in the lane; thus, the obtained coordinate set of the key path point is { M } ₁ (s1，-0.25L)，M ₂ (s2，d2-w)，M ₃ (s3，d3+w)，M ₄ (s3+S ₁ 0) }; secondly, establishing a lane internal adjustment path function set to be solved, wherein the lane internal adjustment path function set to be solved can comprise four quintic polynomials, and each quintic polynomial is used for solving a path between two adjacent key path points; next, the route start point coordinate a of the route is adjusted according to the inside of the lane (S) ₁ ，D ₁ ) And a key path point coordinate set, wherein the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set and the preset longitudinal acceleration and the preset course angle of the path starting point coordinate of the adjustment path in the lane are both set to be 0, so that the coefficients of four fifth-order polynomials can be solved to obtain the adjustment path in the lane based on the Frenet coordinate system as shown in fig. 6 (a); as shown in fig. 6(b), the in-lane adjustment route based on the Frenet coordinate system is mapped into a cartesian coordinate system.

Referring to fig. 7, fig. 7 is a schematic diagram of another adjusted path plan in a lane according to an embodiment of the present application. Assuming that the current position coordinates of the vehicle are the starting point (the origin) of the main road, the vehicle acquires the surrounding environment information of the vehicle through the millimeter wave radar sensor, and determines that the obstacle information exists in the surrounding environment information of the vehicle based on a correlation algorithm. Secondly, based on obstaclesDetermining a subset (i), a subset (ii) and a subset (ii) 3 by the coordinate set; the longitudinal coordinates of all obstacles in the subset (0) and the subset (1) are positive, the longitudinal coordinates of all obstacles in the subset (three) are negative, and the distance between any two transversely adjacent obstacles in the subset (4) is less than 10 meters; determining the first subset (i) and the second subset (2) as positive clusters and the third subset (i) as negative clusters, wherein the transverse distance between the first subset (i) and the second subset (ii) is greater than or equal to 10 meters, and the transverse distance between the second subset (ii) and the third subset (iii) is less than 5 meters; secondly, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle P from the subset (r) ₁ Determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a key obstacle P from the subset II ₂ Determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value from the subset as a key obstacle P ₃ Obtaining a set of coordinates { P of key obstacles ₁ (s1，d1)，P ₂ (s2，d2)，P ₃ (s3, d3) }; secondly, a key obstacle P is arranged ₁ The longitudinal coordinate deviates from the current lane width w, the transverse coordinate is unchanged, and the corresponding key path point coordinate M is obtained ₁ (s1, d 1-w); secondly, judging a key obstacle P ₁ The absolute value of the shifted longitudinal coordinate exceeds a preset parameter; if a critical obstacle P ₁ The absolute value of the shifted longitudinal coordinate exceeds a preset parameter (| d1-w |)>0.25L), M is updated ₁ Coordinates (s1, -0.25L); secondly, there is a critical obstacle P in the forward cluster ₂ With a key obstacle P in the negative direction cluster ₃ The transverse distance between the two key obstacles is less than 5 meters, the middle point between the two key obstacles is taken as a key path point, and the corresponding key path point coordinate M is obtained ₂ ((s1+ s2)/2, (d1+ d 2)/2); secondly, it can also be at M ₂ Plus a first time interval (S) to the transverse coordinates of ₁ ) Taking the longitudinal coordinate as 0 to obtain the coordinate M of the key path point ₃ ((s1+s2)/2+S ₁ ，0)，M ₃ The coordinate of the path end point of the path can be adjusted in the lane; thus, the obtained coordinate set of the key path point is { M } ₁ (s1，-0.25L)，M ₂ ((s1+s2)/2，(d1+d2)/2)，M ₃ ((s1+s2)/2+S ₁ 0) }; secondly, establishing a lane internal adjustment path function set to be solved, wherein the lane internal adjustment path function set to be solved can comprise three quintic polynomials, and each quintic polynomial is used for solving a path between two adjacent key path points; next, the route start point coordinate a of the route is adjusted according to the inside of the lane (S) ₁ ，D ₁ ) And a key path point coordinate set, and setting the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set and the preset longitudinal acceleration and the preset course angle of the path starting point coordinate of the adjustment path in the lane to 0, so that coefficients of three fifth-order polynomials can be solved to obtain the adjustment path in the lane based on the Frenet coordinate system as shown in fig. 7 (a); as shown in fig. 7(b), the in-lane adjustment path based on the Frenet coordinate system is mapped into the cartesian coordinate system.

In an optional embodiment of determining the local path set according to the acquired vehicle surrounding environment information and vehicle information, determining the return main path includes: determining a path end point coordinate of the path of the return road according to the current position coordinate of the vehicle, the current speed of the vehicle and second preset time; establishing a loop main path function to be solved; and obtaining the main return path according to the path starting point coordinates and the path end point coordinates of the main return path, the preset longitudinal acceleration and the preset course angle of the path starting point of the main return path, and the preset longitudinal acceleration and the preset course angle of the path end point of the main return path. Specifically, please refer to fig. 8, fig. 8 is a schematic diagram of a main loop path according to an embodiment of the present disclosure. Suppose that the current position coordinate of the vehicle is the position coordinate at the first time, i.e., the route start point coordinate of the return route is C (S) ₃ ，D ₃ ) The second time interval (S) ₂ ) Taking the transverse coordinate on the main road as S as the transverse coordinate of the path end point coordinate of the path of the main loop road ₂ The corresponding longitudinal coordinate of point (S) is taken as the longitudinal coordinate of the end point coordinate of the path of the return main path, and the end point coordinate of the path of the return main path can be expressed as E (S) ₂ ，D ₄ ) (ii) a Secondly, establishing a loop main path function to be solved; path starting point coordinates C from the main loop path(S ₃ ，D ₃ ) And path end point coordinates E (S) ₂ ，D ₄ ) Setting the preset longitudinal acceleration and the preset course angle of the path starting point of the main loop path and the preset longitudinal acceleration and the preset course angle of the path end point of the main loop path as 0, solving a main loop path function, wherein the solving method can refer to the method for solving the left-hand road changing path function; after the echo path based on the Frenet coordinate system shown in fig. 8(a) is obtained, the left-hand road path based on the Frenet coordinate system is mapped into the cartesian coordinate system shown in fig. 8 (b). Referring to fig. 9, fig. 9 is a schematic diagram of another main loop path according to the embodiment of the present application. When the current position coordinates of the vehicle are on the path of the previous moment, the first time interval (S) ₁ ) The lateral coordinate of the path starting point coordinate of the return path is S ₁ The corresponding longitudinal coordinate of point (S) is taken as the longitudinal coordinate of the path start point coordinate of the echo path, and the path start point coordinate of the echo path can be expressed as F (S) ₁ ，D ₅ ) (ii) a Secondly, the second time interval (S) ₂ ) Taking the transverse coordinate on the main road as S as the transverse coordinate of the path end point coordinate of the path of the main loop road ₂ The corresponding longitudinal coordinate of point (S) is taken as the longitudinal coordinate of the end point coordinate of the path of the return main path, and the end point coordinate of the path of the return main path can be expressed as G (S) ₂ ，D ₆ ) (ii) a Secondly, establishing a loop main path function to be solved; from the path starting point coordinates F (S) of the loop path ₁ ，D ₅ ) And path end point coordinates G (S) ₂ ，D ₆ ) Setting the preset longitudinal acceleration and the preset course angle of the path starting point of the main loop path and the preset longitudinal acceleration and the preset course angle of the path end point of the main loop path as 0, solving a main loop path function, wherein the solving method can refer to the method for solving the left-hand road changing path function; after the echo path based on the Frenet coordinate system shown in fig. 9(a) is obtained, the left-hand road path based on the Frenet coordinate system is mapped into the cartesian coordinate system shown in fig. 9 (b).

Optional implementation of determining local path set according to acquired vehicle surrounding environment information and vehicle informationIn the method, determining the parking path includes: according to a first preset time (T) ₁ ) And determining a first time interval from the current speed (v) of the vehicle, and decelerating at a preset acceleration from the first time interval until the vehicle speed is 0. Wherein the preset acceleration is determined according to the current speed of the vehicle.

S203: generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path.

S205: and determining a target local path from the local path set according to the path selection instruction.

In the embodiment of the application, the path decision module of the vehicle can also generate a path selection instruction according to the surrounding environment information of the vehicle and the vehicle information of the vehicle, wherein the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a main loop path and a parking path; the path decision module sends the generated path selection instruction to the path planning module, the path planning module determines a target local path from the local path set according to a path identifier carried by the path selection instruction and outputs the target local path to a control system of the vehicle, the control system outputs corresponding steering wheel torque or a corresponding steering angle to an actuator, and the actuator controls the vehicle to run according to the target local path.

In an optional embodiment, the method for generating the routing instruction according to the vehicle surrounding environment information and the vehicle information comprises the following steps: and if the obstacle information is determined not to exist in the vehicle surrounding environment information, generating a path selection instruction carrying the main loop path identifier.

Specifically, the determination of whether the obstacle information exists from the vehicle surrounding environment information may be implemented by establishing a relevant neural network model or algorithm through machine learning.

Another optional implementation of generating the routing instruction according to the vehicle surrounding environment information and the vehicle information includes: determining a current passing threshold value of a first vehicle according to the current speed of the vehicle; determining reference obstacle information from the obstacle information; the reference obstacle information includes a referenceA set of obstacle coordinates; each transverse coordinate in the reference obstacle coordinate set is within a preset transverse range; determining the distance between each reference obstacle and a lane preset boundary according to the reference obstacle coordinate set to obtain a passable distance set; generating a routing instruction based on the current speed of the vehicle, the set of passable distances, the current passing threshold of the first vehicle, and the set of reference obstacle coordinates. Here, the preset lateral range refers to a perceived distance S from the first time distance to the vehicle perception system ₃ The first time interval is the product of the current speed of the vehicle and the first preset time.

Specifically, the determining the current passing threshold of the first vehicle according to the current speed of the vehicle may include: determining a current passing threshold of the first vehicle according to equation (2):

wherein D _ threshold _ average represents the minimum transverse distance that the vehicle passes, namely the current passing threshold of the first vehicle; v denotes the current speed of the vehicle.

Specifically, the determining the reference obstacle information from the obstacle information includes: and if all the longitudinal coordinates in the obstacle coordinate set are positive coordinates or negative coordinates, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a reference obstacle to obtain the coordinates of the reference obstacle.

Correspondingly, the determining the distance between each reference obstacle and the preset boundary of the lane according to the reference obstacle coordinate set to obtain a passable distance set specifically includes: and determining the distance between the reference obstacle and the preset boundary of the lane according to the coordinates of the reference obstacle to obtain the passable distance.

Correspondingly, the generating of the path selection instruction based on the current speed of the vehicle, the passable distance set, the current passing threshold of the first vehicle and the reference obstacle coordinate set specifically includes: and if the passable distance is greater than or equal to the current passing threshold of the first vehicle, generating a path selection instruction carrying the adjustment path identifier in the lane.

The above is explained below by a specific example. Referring to fig. 10, fig. 10 is a schematic view of a scene in a lane according to an embodiment of the present disclosure. Assuming that the current speed of the vehicle is 10km/h, the current passing threshold value of the first vehicle is 2.6 m; secondly, all the longitudinal coordinates in the obstacle coordinate set are forward coordinates, and the obstacle P corresponding to the longitudinal coordinate with the minimum absolute value is used ₁ Determining as a reference obstacle with coordinates P ₁ (S1, d1), and S ₁ ＜s1＜S ₃ Wherein S is ₁ Represents a first time interval, S ₃ Representing a perceived distance; secondly, according to the coordinate P of the reference obstacle ₁ (s1, d1), determining the reference obstacle P ₁ The passable distance from the distance between the lane preset boundaries is D1; secondly, judging the size of the D1 and the current passing threshold of the first vehicle; and if D1 is more than or equal to 2.6m, generating a path selection instruction carrying the in-lane adjustment path mark.

Specifically, in the above embodiment of generating a routing instruction based on the current speed of the vehicle, the passable distance set, the current passing threshold of the first vehicle, and the reference obstacle coordinate set, the method includes: if the reference obstacle coordinate set comprises at least one positive longitudinal coordinate and one negative longitudinal coordinate, and the positive longitudinal coordinate and the negative longitudinal coordinate are not the same coordinate of the reference obstacle, determining a longitudinal deviation set based on all longitudinal coordinates in the reference obstacle coordinate set; determining a second vehicle current passing threshold value set according to the vehicle current speed and a reference obstacle coordinate set; each second vehicle current passing threshold value in the second vehicle current passing threshold value set corresponds to each longitudinal deviation in the longitudinal deviation set one by one; and if each longitudinal deviation in the longitudinal deviation set is greater than or equal to the corresponding current passing threshold of the second vehicle, and each passable distance in the passable distance set is greater than or equal to the current passing threshold of the first vehicle, generating a path selection instruction carrying the adjustment path identifier in the lane.

Specifically, the determining, according to the current speed of the vehicle and the reference obstacle coordinate set, the current passing threshold set of the second vehicle includes: determining each second vehicle current passing threshold value in the second vehicle current passing threshold value set according to equations (3) - (5):

Dmax＝f ₁ (v)……(3)

Dmin＝f ₂ (v)……(4)

D_threshold_sparse＝f ₃ (Dmax,Dmin,ΔS)……(5)

wherein D _ threshold _ spark represents the current passing threshold of the second vehicle; Δ S represents the lateral distance between the reference obstacles; v represents the current speed of the vehicle. The function image of formula (3) may refer to fig. 11(a), where fig. 11(a) describes the relationship between the current speed of the vehicle and the parameter Dmax; the function image of formula (4) may refer to fig. 11(b), where fig. 11(b) describes the relationship between the current speed of the vehicle and the parameter Dmin; the functional image of equation (5) may refer to fig. 11(c), which depicts the relationship of the lateral distance between the reference obstacles and the current passing threshold of the second vehicle. It should be noted that, the parameters in the functional relationship diagram of fig. 11 may be calibrated again according to the actual situation. The longitudinal deviation set and the value of Δ S describe the sparseness of the reference obstacle, and the larger the value of both the longitudinal deviation set and the Δ S, the more sparse and the denser the value of both the longitudinal deviation set and the Δ S.

The embodiments of the previous paragraph are described below by way of a specific example. Referring to fig. 12, fig. 12 is a schematic view of another scene in a lane according to an embodiment of the present disclosure. Assuming that the current speed of the vehicle is 80km/h, the current passing threshold value of the first vehicle is 3.0336 m; secondly, if the barrier coordinates in the barrier information have positive longitudinal coordinates and negative longitudinal coordinates at the same time, determining a reference barrier coordinate set as { P } from the barrier information ₁ (s1，d1)，P ₂ (s2，d2)，P ₃ (S3, d3) }, and S ₁ ＜s1＜s2＜s3＜S ₃ Wherein S is ₁ Represents a first time interval, S ₃ Representing a perceived distance; secondly, determining the distance between each reference obstacle and a lane preset boundary according to the reference obstacle coordinate set to obtain a passable distance set { D1, D2 and D3 }; secondly, since d1 and d2 in the reference obstacle coordinate set are positive longitudinal coordinates and d3 is negative longitudinal coordinates, the reference obstacle coordinate set is based on the reference obstacleThe longitudinal deviation set determined by all the longitudinal coordinates in the object coordinate set is { Delta D ₁ ,ΔD ₂ In which Δ D ₁ ＝D1+D3-L，ΔD ₂ D3+ D2-L, L representing the distance between preset boundaries of the current lane; next, it is determined that the second vehicle currently passes through the threshold satisfying D _ threshold _ coarse ═ f based on the function image of fig. 11 according to the vehicle current speed 80km/h ₃ (3.5,1.5,. DELTA.S), assuming P ₂ And P ₃ Δ S therebetween is 20m, the current passing threshold of the second vehicle is about 2.1667 m; secondly, judging the size of each longitudinal deviation in the longitudinal deviation set and the corresponding current passing threshold of the second vehicle, and judging the size of each passable distance in the passable distance set and the current passing threshold of the first vehicle; if Δ D ₂ And when the distance is larger than or equal to 2.1667m, D1 is larger than or equal to 3.0336m, D2 is larger than or equal to 3.0336m, and D3 is larger than or equal to 3.0336m, generating a path selection instruction carrying the adjustment path mark in the lane. It should be noted that, in some cases, only the lateral distance between two adjacent reference obstacles with opposite longitudinal coordinates may be calculated to obtain the current passing threshold of the second vehicle, and only P may be calculated in this example ₂ And P ₃ And obtaining a current passing threshold value of the second vehicle according to the delta S between the first vehicle and the second vehicle.

Another specific embodiment of generating the routing instruction based on the current speed of the vehicle, the set of passable distances, the current passing threshold of the first vehicle, and the set of reference obstacle coordinates includes: and if the passable distance set comprises at least one passable distance smaller than the current passing threshold of the first vehicle, or the longitudinal deviation set comprises at least one longitudinal deviation smaller than the current passing threshold of the corresponding second vehicle, judging whether a path selection instruction carrying the road path changing identifier can be generated according to the obstacle information.

Correspondingly, the above-mentioned judging whether can generate the route selection instruction carrying the road changing path identifier according to the obstacle information specifically includes: if it is determined from the obstacle information that no moving target exists in the adjacent lane of the current lane of the vehicle and the lane line of the current lane where the vehicle is located is a dotted line, generating a path selection instruction carrying a left road path changing mark; or if the moving target exists in the adjacent left lane and the lane line of the current lane where the vehicle is located is a dotted line, determining the relative distance and the relative speed between the moving target and the vehicle; if the relative distance is greater than or equal to the preset distance and the relative speed is greater than or equal to the preset speed, generating a path selection instruction carrying a left road path changing identifier; if the relative distance is smaller than the preset distance or the relative speed is smaller than the preset speed, determining whether a moving target exists in the adjacent right lane or not from the obstacle information; if the moving target exists in the adjacent right lane determined from the obstacle information, determining the relative distance and the relative speed between the moving target and the vehicle; and if the relative distance is greater than or equal to the preset distance and the relative speed is greater than or equal to the preset speed, generating a path selection instruction carrying a right-hand road path changing identifier. The preset distance and the preset speed can be determined according to the category of the moving object, and the category of the moving object comprises a vehicle and a pedestrian.

Correspondingly, if the relative distance is smaller than the preset distance or the relative speed is smaller than the preset speed, a path selection instruction carrying the parking path identifier is generated.

Continuing with the above example, if Δ D is as shown in FIGS. 12 and 13 ₂ <2.1667m or D1<3.0336m or D2<3.0336m or D3<3.0336m, judging whether a path selection instruction carrying a road changing path identifier can be generated according to the obstacle information. Determining the moving target 1 in the adjacent left lane and the moving target 2 in the adjacent right lane from the obstacle information, and then respectively determining the relative distance and the relative speed between the moving targets 1 and 2 and the vehicle; if the types of the moving targets 1 and 2 are vehicles, determining that the preset speed is 0 and the preset distance is 20 m; as shown in fig. 13, in the first case, the relative distance Δ S1 between the moving object 1 and the own vehicle is 20m, the vehicle speed of the moving object 1 is 70km/h, and the relative speed Δ V1 between the moving object 1 and the own vehicle is 10 km/h; since the relative distance Δ S1 is 20m, the relative speed Δ V1>0, generating a path selection instruction carrying a left road path changing identifier; in the second case, when the relative distance Δ S1 between the moving object 1 and the host vehicle is 10m and the vehicle speed of the moving object 1 is 100km/h, the moving object 1 movesThe relative speed delta V1 between the target 1 and the self-vehicle is-20 km/h; due to the relative distance deltas 1<20m, relative velocity DeltaV 1<0, if the vehicle cannot change lanes to the left, determining whether the adjacent right lane meets lane changing conditions from the obstacle information; if the relative distance Δ S2 between the moving object 2 and the host vehicle is 30m and the vehicle speed of the moving object 2 is 80km/h, the relative speed Δ V2 between the moving object 2 and the host vehicle is 0; due to the relative distance deltas 2>20m, the relative speed Δ V2 is equal to 0, and a path selection instruction carrying a right-changing road path identifier can be generated; in the third case, the relative distance Δ S2 between the moving object 2 and the own vehicle is 20m, the vehicle speed of the moving object 2 is 70km/h, and the relative speed Δ V2 between the moving object 2 and the own vehicle is-10 m/h; since the relative distance Δ α 2 is 20m, the relative speed Δ V2<And 0, if the vehicle cannot change lanes to the right, generating a path selection instruction carrying the parking path identifier.

In the embodiment provided by the application, if the obstacle information is determined to exist in the vehicle surrounding environment information, whether a path selection instruction carrying the adjustment path identifier in the lane can be generated is judged; if the condition for generating the path selection instruction carrying the road mark for adjusting the path in the lane is not met, judging whether the path selection instruction carrying the road changing path mark can be generated or not; if the condition for generating the path selection instruction with the road changing path identifier mentioned in the above embodiment is not met, the path selection instruction with the parking path identifier is generated.

It should be noted that, embodiments only changing the above judgment logic belong to the protection scope of the present application. For example, if it is determined from the vehicle surrounding environment information that there is obstacle information and the vertical coordinate of an obstacle in the obstacle coordinate set is within a preset vertical coordinate range, it is directly determined whether a path selection instruction represented by a portable road changing path can be generated; this can further improve the driving safety, as shown in fig. 14, the preset ordinate range is [ -0.1m,0.1m]The longitudinal coordinate d1 of the obstacle coordinate P (s1, d1) is at [ -0.1m,0.1m]And if so, directly judging whether a path selection instruction represented by the road changing path can be generated or not. For example, if it is determined that the adjustment path in the carrying lane can be generatedThe path selection instruction of the path identifier can also judge whether the path selection instruction carrying the road changing path identifier can be generated or not; under the condition of simultaneously generating a path selection instruction carrying the adjustment path identifier in the lane and a path selection instruction carrying the road changing path identifier, a final path selection instruction can be determined from the path selection instruction carrying the adjustment path identifier in the lane and the path selection instruction carrying the road changing path identifier according to the information of the obstacles in front of the current lane; as shown in fig. 13, it is assumed that the vehicle simultaneously generates a route selection command carrying an in-lane adjustment route sign and a route selection command carrying a road change route sign, based on the obstacle information { P ] in front of the current lane ₁ (s1，d1)，P ₂ (s2，d2)，P ₃ (s3, d3) }, if the vehicle judges that the number of the obstacles exceeds the preset number, determining the path selection instruction carrying the road path changing identifier as a final path selection instruction.

In the embodiment of the application, the vehicle can receive not only the path selection instruction output by the vehicle path decision module, but also the path instruction sent by the road end computing unit in the vehicle-road cooperation system, and determines the target local path from the local path set according to the path instruction. For example, the road end calculation unit receives the environmental information given by the road end sensing system or the vehicle end sensing system, then performs information processing, and sends the path instruction to the vehicle end; and the vehicle end analyzes and decides the path instruction given by the road end according to the surrounding environment information of the vehicle, if the vehicle end finds that the condition is met after verification, the path instruction given by the road end is executed, otherwise, the path selection instruction output by the vehicle path decision module is executed, and the abnormal condition is sent to the road end. As shown in fig. 13, when a vehicle runs on a certain highway, the road-end sensing system detects that a traffic accident exists in a certain lane, the road-end computing unit informs the vehicle that the traffic accident occupies an intermediate lane and a subsequent vehicle should run on a first lane through the vehicle cooperation system in advance, so that the vehicle can change lanes in advance, the sensing capability of the vehicle-end sensor is made up, and the traffic efficiency of the vehicle can be improved; secondly, the vehicle end verifies a path instruction which is given by the road end and is supposed to run on a first lane, a moving object 1 in the first lane (an adjacent left lane) is determined according to the vehicle environment information, and based on the first condition in the embodiment, if the vehicle meets the condition of changing lanes to the left, the vehicle executes the path instruction given by the road section, so that the decision-making accuracy can be improved, and the calculation amount of the vehicle-end equipment can be reduced; if the vehicle cannot change lanes to the left based on the second condition in the above embodiment, the vehicle outputs a path selection instruction according to the vehicle path decision module.

An embodiment of the present application further provides a local path determining apparatus for a vehicle, and fig. 15 is a schematic structural diagram of the local path determining apparatus for a vehicle provided in the embodiment of the present application, and as shown in fig. 15, the apparatus includes:

a first determining module 1501, configured to determine a local path set according to the acquired vehicle surrounding environment information and vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; the main road in the main loop road paths is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point;

a generating module 1502 for generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return road path and a parking path;

a second determining module 1503, configured to determine a target local path from the local path set according to the path selecting instruction.

In the embodiment of the application, the vehicle information comprises the current speed of the vehicle; the vehicle surrounding environment information includes a current lane width and a current position coordinate of the vehicle based on a Frenet coordinate system; the origin of the Frenet coordinate system is a predetermined starting point.

In an alternative embodiment, the apparatus further comprises:

the first determining module 1501 is specifically configured to: determining a route starting point coordinate and a route end point coordinate of a lane changing route according to the current position coordinate of the vehicle, the current speed of the vehicle, the first preset time, the second preset time and the current lane width; establishing a road changing path function to be solved; solving a road changing path function according to the coordinates of the path starting point and the path end point of the road changing path, the preset longitudinal acceleration and the preset course angle of the path starting point of the road changing path and the preset longitudinal acceleration and the preset course angle of the path end point of the road changing path to obtain a road changing path; the coordinates of the starting point of the adjusting path, the coordinates of the starting point of the return path, and the coordinates of the starting point of the parking path in the lane are the same as the coordinates of the starting point of the switching path.

In an alternative embodiment, the apparatus further comprises:

the first determining module 1501 is specifically configured to: if the obstacle information is determined to exist in the vehicle surrounding environment information, determining key obstacle information from the obstacle information; the key obstacle information includes a set of key obstacle coordinates based on a Frenet coordinate system; the obstacle information includes a set of obstacle coordinates based on a Frenet coordinate system; determining a key path point coordinate set based on the key obstacle coordinate set; each key path point coordinate in the key path point coordinate set corresponds to each key obstacle coordinate in the key obstacle coordinate set one by one; establishing an in-lane adjustment path function set to be solved; and solving an in-lane adjustment path function set according to the path starting point coordinates of the in-lane adjustment path, the key path point coordinate set, and the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set to obtain the in-lane adjustment path.

In an alternative embodiment, the apparatus further comprises:

the first determining module 1501 is specifically configured to: determining a path end point coordinate of the path of the return road according to the current position coordinate of the vehicle, the current speed of the vehicle and second preset time; establishing a loop main path function to be solved; and obtaining the main loop path according to the path starting point coordinate and the path end point coordinate of the main loop path, the preset longitudinal acceleration and the preset course angle of the path starting point of the main loop path, and the preset longitudinal acceleration and the preset course angle of the path end point of the main loop path.

In an alternative embodiment, the apparatus further comprises:

the generating module 1502 is specifically configured to: and if the obstacle information is determined not to exist in the vehicle surrounding environment information, generating a path selection instruction carrying the main loop path identifier.

In an alternative embodiment, the apparatus further comprises:

the generating module 1502 is specifically configured to: determining a current passing threshold value of a first vehicle according to the current speed of the vehicle; determining reference obstacle information from the obstacle information; the reference obstacle information includes a set of reference obstacle coordinates; each transverse coordinate in the reference obstacle coordinate set is in a preset transverse range; determining the distance between each reference obstacle and a lane preset boundary according to the reference obstacle coordinate set to obtain a passable distance set; generating a routing instruction based on the current speed of the vehicle, the set of passable distances, the current passing threshold of the first vehicle, and the set of reference obstacle coordinates.

In an alternative embodiment, the apparatus further comprises:

the generating module 1502 is specifically configured to: if all the longitudinal coordinates in the obstacle coordinate set are positive coordinates or negative coordinates, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a reference obstacle to obtain the coordinates of the reference obstacle; determining the distance between the reference obstacle and a lane preset boundary according to the coordinates of the reference obstacle to obtain a passable distance; and if the passable distance is greater than or equal to the current passing threshold of the first vehicle, generating a path selection instruction carrying the adjustment path identifier in the lane.

In an alternative embodiment, the apparatus further comprises:

the generating module 1502 is specifically configured to: if the reference obstacle coordinate set comprises at least one positive longitudinal coordinate and one negative longitudinal coordinate, and the positive longitudinal coordinate and the negative longitudinal coordinate are not the same coordinate of the reference obstacle, determining a longitudinal deviation set based on all longitudinal coordinates in the reference obstacle coordinate set; determining a second vehicle current passing threshold value set according to the vehicle current speed and a reference obstacle coordinate set; each second vehicle current passing threshold value in the second vehicle current passing threshold value set corresponds to each longitudinal deviation in the longitudinal deviation set one by one; and if each longitudinal deviation in the longitudinal deviation set is greater than or equal to the corresponding current passing threshold of the second vehicle, and each passable distance in the passable distance set is greater than or equal to the current passing threshold of the first vehicle, generating a path selection instruction carrying the adjustment path identifier in the lane.

The device and method embodiments in the embodiments of the present application are based on the same application concept.

The method provided by the embodiment of the application can be executed in a computer terminal, a server or a similar operation device. Taking the example of the server running on the server, fig. 16 is a hardware structure block diagram of the server of the method for determining a local path of a vehicle according to the embodiment of the present application. As shown in fig. 16, the server 1600 may have relatively large differences in configuration or performance, and may include one or more Central Processing Units (CPUs) 1610 (the processors 1610 may include but are not limited to a Processing device such as a microprocessor NCU or a programmable logic device FPGA), a memory 1630 for storing data, and one or more storage media 1620 (e.g., one or more mass storage devices) for storing applications 1623 or data 1622. Memory 1630 and storage media 1620 may be transient or persistent storage, among others. The program stored in the storage medium 1620 may include one or more modules, and each module may include a series of instruction operations in a server. Further, the central processor 1610 may be configured to communicate with the storage medium 1620, and execute a series of instruction operations in the storage medium 1620 on the server 1600. The server 1600 may also include one or more power supplies 1660, one or more wired or wireless network interfaces 1650, one or more input-output interfaces 1640, and/or one or more operating systems 1621, such as Windows, Mac OS, Unix, Linux, FreeBSD, etc.

The input/output interface 1640 may be used to receive or transmit data over a network. Specific examples of such networks may include wireless networks provided by the communications provider of server 1600. In one example, i/o Interface 1640 includes a Network adapter (NIC) that may connect to other Network devices through a base station to communicate with the internet. In one example, the input/output interface 1640 may be a Radio Frequency (RF) module, which is used to communicate with the internet via wireless.

It will be understood by those skilled in the art that the structure shown in fig. 16 is merely illustrative and is not intended to limit the structure of the electronic device. For example, server 1600 may also include more or fewer components than shown in FIG. 16, or have a different configuration than shown in FIG. 16.

The embodiment of the application also provides a computer storage medium, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or the at least one program is loaded and executed by a processor to realize the local path determination method of the vehicle.

Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

As can be seen from the embodiments of the method, the apparatus, the terminal, and the storage medium for determining a local path of a vehicle provided by the present application, in the present application, a local path set is determined according to the acquired vehicle surrounding environment information and vehicle information, where the local path set includes a lane change path, an in-lane adjustment path, a return path, and a parking path; the main road in the path of the main loop is determined by a global path planning system of the vehicle according to a preset starting point and a preset end point; meanwhile, a path selection instruction is generated according to the surrounding environment information of the vehicle and the vehicle information, and the path selection instruction carries the identification of any one of a lane changing path, an in-lane adjusting path, a return main path and a parking path; and determining a target local path from the local path set according to the path selection instruction. Therefore, when the vehicle encounters an obstacle, a plurality of local adjustment paths can be planned in time, and a proper path is selected from the local adjustment paths, so that the safety of the vehicle can be improved; the method has small calculation amount and can improve the efficiency of the output path, thereby improving the traffic efficiency.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages or disadvantages of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk.

The above description is only a preferred embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A local path determination method for a vehicle, comprising:

determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; wherein the vehicle information includes a current speed of the vehicle; the vehicle surrounding environment information comprises the current lane width and the current position coordinate of the vehicle based on a Frenet coordinate system; the coordinates of the starting point of the adjusting path in the lane, the coordinates of the starting point of the path of the return path, and the coordinates of the starting point of the path of the parking path are the same as the coordinates of the starting point of the path of the lane changing path; the main road in the main road return paths is a lane level path determined by a global path planning system of the vehicle according to a preset starting point and a preset end point; the origin of the Frenet coordinate system is the preset starting point;

wherein, the determining of the lane change path in the local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information includes:

determining a route starting point coordinate and a route end point coordinate of the lane changing route according to the current position coordinate of the vehicle, the current speed of the vehicle, first preset time, second preset time and the current lane width;

establishing a road changing path function to be solved;

solving the lane change path function according to the coordinates of the path starting point and the path end point of the lane change path, the preset longitudinal acceleration and the preset course angle of the path starting point of the lane change path, and the preset longitudinal acceleration and the preset course angle of the path end point of the lane change path to obtain the lane change path;

wherein, the determining the lane inner adjustment path in the local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information comprises:

determining key obstacle information from the obstacle information if the obstacle information is determined to exist from the vehicle surrounding environment information; the critical obstacle information includes a set of critical obstacle coordinates based on the Frenet coordinate system; the obstacle information includes a set of obstacle coordinates based on the Frenet coordinate system;

determining a set of key path point coordinates based on the set of key obstacle coordinates; each key path point coordinate in the key path point coordinate set corresponds to each key obstacle coordinate in the key obstacle coordinate set in a one-to-one mode;

establishing an in-lane adjustment path function set to be solved;

solving the adjustment path function set in the lane according to the path starting point coordinates of the adjustment path in the lane, the key path point coordinate set, and the preset longitudinal acceleration and the preset course angle of each key path point in the key path point coordinate set, so as to obtain the adjustment path in the lane;

generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries the identifier of any one of the lane changing path, the in-lane adjusting path, the return main path and the parking path;

wherein the generating a routing instruction according to the vehicle surrounding environment information and the vehicle information includes:

determining a current passing threshold of a first vehicle according to the current speed of the vehicle;

determining reference obstacle information from the obstacle information; the reference obstacle information comprises a set of reference obstacle coordinates; each transverse coordinate in the reference obstacle coordinate set is within a preset transverse range;

determining the distance between each reference obstacle and a preset boundary of the lane according to the reference obstacle coordinate set to obtain a passable distance set;

generating the routing instructions based on the vehicle current speed, the set of traversable distances, the first vehicle current pass threshold, and the set of reference obstacle coordinates;

wherein the generating the routing instructions based on the vehicle current speed, the set of passable distances, the first vehicle current pass threshold, and the set of reference obstacle coordinates comprises:

if the reference obstacle coordinate set comprises at least one positive longitudinal coordinate and one negative longitudinal coordinate, and the positive longitudinal coordinate and the negative longitudinal coordinate are not the same coordinate of the reference obstacle, determining a longitudinal deviation set based on all longitudinal coordinates in the reference obstacle coordinate set;

determining a second vehicle current passing threshold set according to the vehicle current speed and the reference obstacle coordinate set; each second vehicle current passing threshold value in the second vehicle current passing threshold value set corresponds to each longitudinal deviation in the longitudinal deviation set one by one;

if each longitudinal deviation in the longitudinal deviation set is greater than or equal to a corresponding second vehicle current passing threshold value, and each passable distance in the passable distance set is greater than or equal to the first vehicle current passing threshold value, generating a path selection instruction carrying an in-lane adjustment path identifier;

2. The method of claim 1, wherein determining the return road path in the set of local paths from the obtained vehicle surroundings information and vehicle information comprises:

determining a path end point coordinate of the return main path according to the current position coordinate of the vehicle, the current speed of the vehicle and the second preset time;

establishing a loop main path function to be solved;

and obtaining the main return path according to the path starting point coordinates and the path end point coordinates of the main return path, the preset longitudinal acceleration and the preset course angle of the path starting point of the main return path, and the preset longitudinal acceleration and the preset course angle of the path end point of the main return path.

3. The method of claim 1, wherein generating routing instructions based on the vehicle ambient information and the vehicle information comprises:

and if the obstacle information is determined not to exist in the vehicle surrounding environment information, generating a path selection instruction carrying the return main path identifier.

4. The method of claim 1, wherein the determining reference obstacle information from the obstacle information comprises:

if all the longitudinal coordinates in the obstacle coordinate set are positive coordinates or negative coordinates, determining the obstacle corresponding to the longitudinal coordinate with the minimum absolute value as a reference obstacle to obtain the coordinates of the reference obstacle;

determining the distance between each reference obstacle and a lane preset boundary according to the reference obstacle coordinate set to obtain a passable distance set, wherein the method comprises the following steps:

determining the distance between the reference obstacle and a lane preset boundary according to the coordinate of the reference obstacle to obtain a passable distance;

the generating the routing instructions based on the vehicle current speed, the set of traversable distances, the first vehicle current pass threshold, and the set of reference obstacle coordinates comprises:

and if the passable distance is larger than or equal to the current passing threshold of the first vehicle, generating a path selection instruction carrying the adjustment path identifier in the lane.

5. A local path determining apparatus of a vehicle, characterized by comprising:

the first determining module is used for determining a local path set according to the acquired vehicle surrounding environment information and the acquired vehicle information; the local path set comprises a lane changing path, an in-lane adjusting path, a return road path and a parking path; wherein the vehicle information includes a current speed of the vehicle; the vehicle surrounding environment information comprises the current lane width and the current position coordinate of the vehicle based on a Frenet coordinate system; the coordinates of the path starting point of the in-lane adjustment path, the coordinates of the path starting point of the return path, and the coordinates of the path starting point of the parking path are the same as the coordinates of the path starting point of the lane change path; the main road in the main road return paths is a lane level path determined by a global path planning system of the vehicle according to a preset starting point and a preset end point; the origin of the Frenet coordinate system is the preset starting point;

determining a route starting point coordinate and a route end point coordinate of the lane changing route according to the current position coordinate of the vehicle, the current speed of the vehicle, a first preset time, a second preset time and the current lane width;

establishing a road changing path function to be solved;

determining key obstacle information from the obstacle information if the obstacle information is determined to exist from the vehicle surrounding environment information; the key obstacle information includes a set of key obstacle coordinates based on the Frenet coordinate system; the obstacle information includes a set of obstacle coordinates based on the Frenet coordinate system;

determining a set of critical path point coordinates based on the set of critical obstacle coordinates; each key path point coordinate in the key path point coordinate set corresponds to each key obstacle coordinate in the key obstacle coordinate set one by one;

establishing an in-lane adjustment path function set to be solved;

the generating module is used for generating a path selection instruction according to the vehicle surrounding environment information and the vehicle information; the path selection instruction carries an identifier of any one of the lane changing path, the in-lane adjusting path, the main loop path and the parking path;

determining the distance between each reference obstacle and a lane preset boundary according to the reference obstacle coordinate set to obtain a passable distance set;

generating the routing instructions based on the current vehicle speed, the set of passable distances, the first current vehicle passing threshold, and the set of reference obstacle coordinates;

if the reference obstacle coordinate set comprises at least one positive longitudinal coordinate and one negative longitudinal coordinate, and the positive longitudinal coordinate and the negative longitudinal coordinate are not the same coordinate of the reference obstacle, determining a longitudinal deviation set based on all the longitudinal coordinates in the reference obstacle coordinate set;

determining a second vehicle current passing threshold value set according to the vehicle current speed and the reference obstacle coordinate set; each second vehicle current passing threshold value in the second vehicle current passing threshold value set corresponds to each longitudinal deviation in the longitudinal deviation set in a one-to-one mode;

6. A terminal characterized in that it comprises a processor and a memory in which at least one instruction or at least one program is stored, which is loaded by the processor and which performs the method for determining the local path of a vehicle according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that at least one instruction or at least one program is stored in the storage medium, which is loaded and executed by a processor to implement the local path determination method of a vehicle according to any one of claims 1 to 4.