Path planning method and apparatus, electronic device, medium, and autonomous vehicle

Abstract

A path planning method and apparatus, an electronic device, a medium, and an autonomous vehicle. The path planning method comprises: determining a path planning area comprising a starting point and a destination point, wherein there are obstacles in the path planning area (S210); determining M reference lines, wherein the reference lines include reference lines between the obstacles and / or reference lines between the obstacles and boundaries of the path planning area, and M is a positive integer (S220); determining at least one sampling point from each reference line to obtain a sampling point set (S230); and generating a planned path from the starting point to the destination point on the basis of the sampling point set (S240).

Description

Path planning method, device, electronic device, medium and autonomous driving vehicle

[0001] This application claims priority to Chinese patent application No. 202311465563.3 filed on November 6, 2023, the contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the fields of computer technology and autonomous driving, and more specifically, to a path planning method, device, electronic device, medium, and autonomous driving vehicle. Background Art

[0003] With the advancement of computer technology, autonomous vehicles (AVs) have emerged. Autonomous vehicles can be defined as motor vehicles that are automatically controlled by computers, leveraging the collaborative efforts of artificial intelligence, visual computing, radar, monitoring systems, and the Global Positioning System (GPS). Autonomous vehicles can follow a planned route toward their destination while avoiding obstacles along the way.

[0004] In the process of realizing the concepts disclosed herein, the inventors discovered that there are at least the following problems in the related art: the planned path determined in a simplified autonomous driving vehicle scenario is inaccurate, resulting in insufficient lateral distance between the autonomous driving vehicle and obstacles during actual driving, leading to collisions. Summary of the Invention

[0005] In view of the above problems, the present disclosure provides a path planning method, device, electronic device, medium and autonomous driving vehicle.

[0006] A first aspect of the present disclosure provides a path planning method, comprising:

[0007] Determining a path planning area including a starting point and a destination point, wherein obstacles exist in the path planning area;

[0008] Determine M reference lines, where the reference lines include reference lines between obstacles and / or reference lines between obstacles and a boundary of a path planning area, and M is a positive integer;

[0009] Determine at least one sampling point from each reference line to obtain a sampling point set; and

[0010] Based on the set of sample points, a planned path is generated from the starting point to the target point.

[0011] According to an embodiment of the present disclosure, there are multiple obstacles in the path planning area, each obstacle corresponds to at least one edge position information and at least one angular position information, the edge position information includes the position information of the edge constituting the obstacle, the angular position information represents the position information of the angle formed by the intersection of two edges of the obstacle, and the path planning area corresponds to at least one boundary position information;

[0012] Determine M reference lines, including:

[0013] Determine the foot of the perpendicular from each corner to the edge of each obstacle and the foot of the perpendicular position information based on the corner position information and the edge position information;

[0014] Determine the foot of the perpendicular from each corner to the boundary of the path planning area and the position information of the foot of the perpendicular based on the angular position information and the boundary position information; and

[0015] Among them, the angle corresponding to the foot of the perpendicular and the line connecting the foot of the perpendicular are the reference lines.

[0016] According to an embodiment of the present disclosure, determining the foot of a perpendicular from each corner to the side of each obstacle and the foot of perpendicular position information based on the corner position information and the side position information includes:

[0017] Calculate the slope of each obstacle's edge based on the edge position information;

[0018] Determine the calculation mode that matches the slope; and

[0019] The edge position information and the corner position information are calculated based on the calculation mode to obtain the perpendicular position information from each corner to the edge of each obstacle.

[0020] According to an embodiment of the present disclosure, determining at least one sampling point on each reference line to obtain a sampling point set includes:

[0021] Taking at least one point on the reference line other than the two end points of the reference line as a sampling point to obtain a sampling point set;

[0022] Each sampling point corresponds to sampling point position information, and the sampling point position information is determined based on the vertical position information and the angular position information.

[0023] According to an embodiment of the present disclosure, determining the sampling point location information includes:

[0024] The midpoint of the reference line is used as the sampling point, and the position information of the midpoint of each reference line is calculated based on the perpendicular position information and the angular position information.

[0025] According to an embodiment of the present disclosure, it further includes:

[0026] Calculate the length of each reference line based on the corner position information, the side position information, and the boundary position information;

[0027] Filtering N reference lines from the M reference lines whose lengths are greater than a distance threshold, where the distance threshold is related to the size of the target autonomous vehicle, the target autonomous vehicle traveling along a planned path from the starting point to the target point, where N is greater than or equal to 1 and N is less than or equal to M; and

[0028] At least one sampling point is determined from each reference line after screening to obtain a sampling point set.

[0029] According to an embodiment of the present disclosure, generating a planned path from a starting point to a target point based on a set of sampling points includes:

[0030] Taking multiple sampling points in the sampling point set as initial sampling points, determine the initial planning path with the shortest distance from the starting point to the target point;

[0031] Filtering at least one sampling point located on the initial planned path from the sampling point set, and using the at least one sampling point located on the initial planned path as a path point to obtain a path point set; and

[0032] Using the smooth path algorithm, a planning path including all path points in the path point set is generated.

[0033] According to an embodiment of the present disclosure, it further includes:

[0034] Deleting the sampling points that fall within the obstacle from the sampling point set to obtain an updated sampling point set; and

[0035] Taking multiple sampling points in the updated sampling point set as initial sampling points, an initial planning path with the shortest distance from the starting point to the target point is determined.

[0036] According to an embodiment of the present disclosure, the method further includes: processing image information of the path planning area to determine edge position information and corner position information.

[0037] A second aspect of the present disclosure provides a path planning device, comprising:

[0038] A first determining module is used to determine a path planning area including a starting point and a target point, wherein obstacles exist in the path planning area;

[0039] A second determining module is configured to determine M reference lines, wherein the reference lines include reference lines between obstacles and / or reference lines between obstacles and a boundary of a path planning area, and M is a positive integer;

[0040] A third determining module is configured to determine at least one sampling point on each reference line to obtain a sampling point set; and

[0041] The generation module is used to generate a planned path from the starting point to the target point based on a set of sampling points.

[0042] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned path planning method.

[0043] A fourth aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned path planning method.

[0044] The fifth aspect of the present disclosure further provides a computer program product, including a computer program, which implements the above-mentioned path planning method when executed by a processor.

[0045] The sixth aspect of the present disclosure also provides an autonomous driving vehicle, comprising the above-mentioned electronic device. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0047] FIG1 schematically illustrates an exemplary system architecture to which the method and apparatus for path planning disclosed herein may be applied;

[0048] FIG2 schematically shows a flow chart of a path planning method according to an embodiment of the present disclosure;

[0049] FIG3A schematically shows a reference line diagram established according to the first embodiment of the present disclosure;

[0050] FIG3B schematically shows a reference line diagram established according to the second embodiment of the present disclosure;

[0051] FIG3C schematically shows a reference line diagram established according to the third embodiment of the present disclosure;

[0052] FIG4 schematically shows a flow chart of a method for determining vertical foot position information according to a specific embodiment of the present disclosure;

[0053] FIG5 schematically shows a flow chart of generating a planned path from a starting point to a target point based on a set of sampling points according to an embodiment of the present disclosure;

[0054] FIG6A schematically shows a schematic diagram of a path planning area and an angle of an obstacle determined by simulation;

[0055] FIG6B schematically shows a schematic diagram of the perpendicular foot of each corner to the edge of the obstacle and to the boundary of the path planning area determined by simulation;

[0056] FIG6C schematically shows a schematic diagram of multiple sampling points in a path planning area determined by simulation;

[0057] FIG6D schematically shows an initial planned path determined by simulation, and a schematic diagram of multiple path points located on the initial planned path;

[0058] FIG6E schematically shows a comparison diagram between a square earthquake planning path generated according to an embodiment of the present disclosure and an existing planning path;

[0059] FIG7 schematically shows a structural block diagram of a path planning device according to an embodiment of the present disclosure; and

[0060] FIG8 schematically shows a block diagram of an electronic device suitable for a path planning method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0062] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0063] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0064] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0065] In the embodiments of this disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of all data involved (including, but not limited to, user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard the security of user personal information, network security, and national security.

[0066] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0067] Numerous existing path planning methods exist, including cubic polynomial models, artificial potential field models, improved artificial potential field models based on regression search methods, particle swarm optimization, Dijkstra's algorithm, rapid exploration random tree path planning, subgoal networks, and the A* algorithm. However, most of these algorithms simplify the autonomous vehicle into a point or a pre-set geometric shape, ignoring its dimensions.

[0068] Because existing path planning algorithms ignore the size of the autonomous vehicle itself, at certain path points near obstacles, the lateral distance between the autonomous vehicle and the obstacle is insufficient, increasing the risk of collision.

[0069] To at least partially address the technical problems in the related art, the present disclosure provides a path planning method, comprising: determining a path planning area including a starting point and a target point, wherein obstacles exist in the path planning area; determining M reference lines, wherein the reference lines include reference lines between obstacles and / or reference lines between obstacles and a boundary of the path planning area, and M is a positive integer; determining at least one sampling point on each reference line to obtain a sampling point set; and generating a planned path from the starting point to the target point based on the sampling point set.

[0070] It should be noted that the path planning method and apparatus provided in the embodiments of the present disclosure can be used in the fields of computer technology and autonomous driving technology, for example, in the fields of positioning and navigation. The path planning method and apparatus provided in the embodiments of the present disclosure can also be used in any field other than computer technology and autonomous driving technology, for example, in the field of warehouse management, by planning the path of a mobile robot to retrieve and install goods. The application fields of the path planning method and apparatus provided in the embodiments of the present disclosure are not limited.

[0071] Figure 1 schematically illustrates an exemplary system architecture to which the path planning method and apparatus of the present disclosure may be applied. It should be noted that Figure 1 is merely an example of a system architecture to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, and does not imply that the embodiments of the present disclosure may not be applied to other devices, systems, environments, or scenarios.

[0072] As shown in Figure 1, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include a wired communication network and a wireless communication network.

[0073] For example, a wireless communication network may include vehicle-to-everything (V2X) wireless communications. For example, the vehicle-to-everything (V2X) wireless communications may include at least one of the following: vehicle-to-everything (V2X) wireless communications based on dedicated short-range communication (DSRC) and vehicle-to-everything (V2X) wireless communications based on cellular mobile communications (C-V2X). Vehicle-to-everything (V2X) wireless communications based on cellular mobile communications may include at least one of the following: vehicle-to-everything (V2X) wireless communications based on LTE-V2X (Long Term Evolution V2X), vehicle-to-everything (V2X) wireless communications based on the fourth generation mobile communication technology (4G), and vehicle-to-everything (V2X) wireless communications based on the fifth generation mobile communication technology (5G).

[0074] A user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various navigation applications, web browser applications, search applications, entertainment applications, and instant messaging applications (for example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0075] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens, support for web browsing, support for positioning and navigation, including but not limited to self-driving vehicles, smart phones, tablet computers, laptop computers and desktop computers, etc.

[0076] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0077] It should be noted that the path planning method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the path planning device provided in the embodiment of the present disclosure can generally be set in the server 105. The path planning method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the path planning device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0078] Alternatively, the path planning method provided in the embodiment of the present disclosure may also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may also be executed by another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the path planning apparatus provided in the embodiment of the present disclosure may also be provided in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may be provided in another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0079] It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative and any number of terminal devices, networks, and servers may be provided as required.

[0080] It should be noted that the sequence numbers of the operations in the following method are only used to indicate the operation for the purpose of description, and should not be regarded as indicating the order in which the operations should be performed. Unless explicitly stated, the method does not need to be performed in the order shown.

[0081] FIG2 schematically shows a flow chart of a path planning method according to an embodiment of the present disclosure.

[0082] As shown in FIG. 2 , the method 200 includes operations S210 to S240 .

[0083] In operation S210 , a path planning area including a start point and a target point is determined, wherein an obstacle exists in the path planning area.

[0084] In operation S220 , M reference lines are determined, where the reference lines include reference lines between obstacles and / or reference lines between obstacles and a boundary of a path planning area, and M is a positive integer.

[0085] In operation S230 , at least one sampling point is determined on each reference line to obtain a sampling point set.

[0086] In operation S240 , a planned path from the starting point to the target point is generated based on the set of sampling points.

[0087] According to an embodiment of the present disclosure, the starting point may be the current location of the autonomous driving vehicle, and the target point may be the destination of the user or the autonomous driving vehicle.

[0088] According to embodiments of the present disclosure, a path planning area includes a starting point and a destination point. For example, the path planning area may be defined as a minimum rectangular area encompassing the starting point and the destination point. The path planning area may be a high-precision map encompassing the starting point and the destination point, or it may be an image captured by the autonomous vehicle.

[0089] According to an embodiment of the present disclosure, a route planning area including a starting point and a destination point can be determined based on the location information of the starting point and the destination point. The location information of the starting point and the destination point can be determined through user interaction. For example, the location information of the starting point and the destination point can be determined through voice interaction, interaction on an operation interface, gesture interaction, etc.

[0090] Alternatively, the starting point's location information can be determined by the autonomous vehicle's positioning system, such as the Global Positioning System (GPS), BeiDou Navigation Satellite System (BDS), Global Navigation Satellite System (GNSS), or GLONASS. Alternatively, the starting point can be determined by an inertial measurement unit (IMU), visual sensor, vehicle-side lidar, or vehicle-side radar installed in the autonomous vehicle.

[0091] According to an embodiment of the present disclosure, the path planning area may include at least one obstacle, which may be a static obstacle in the environment surrounding the autonomous driving vehicle, or a dynamic obstacle such as a pedestrian or other vehicle.

[0092] According to an embodiment of the present disclosure, for a larger obstacle, the boundary of the path planning area divides the obstacle into two parts, namely, the part within the path planning area and the part outside the path planning area. In the above case, the part within the path planning area can be regarded as one obstacle.

[0093] According to an embodiment of the present disclosure, a reference line is used to assist an autonomous vehicle in determining at least one sampling point before path planning. The two ends of the reference line can be located on two obstacles, or on the edge of an obstacle and the boundary of the path planning area.

[0094] According to an embodiment of the present disclosure, the reference line includes a reference line between obstacles and / or a reference line between an obstacle and a boundary of a path planning area. At least one reference line may exist between multiple obstacles, and at least one reference line may also exist between an obstacle and a boundary of a path planning area.

[0095] For example, there can be only one reference line between two obstacles, or two, three, or four reference lines. There can be one or more reference lines between a single obstacle and multiple boundaries of the path planning area. There can also be no reference line between a single obstacle and any boundary of the path planning area.

[0096] According to an embodiment of the present disclosure, at least one sampling point may be determined from each reference line, thereby determining a set of sampling points corresponding to the entire path planning area.

[0097] According to an embodiment of the present disclosure, during the path planning process, path planning can be performed based on the sampling points in the sampling point set to obtain a non-smoothed planned path from the starting point and the target point; then, a smoothing operation is performed on the non-smoothed planned path to obtain the final planned path.

[0098] In the embodiments of the present disclosure, since the sampling points are determined from the reference lines between obstacles in the path planning area and / or the reference lines between the obstacles and the boundary of the path planning area, the sampling points themselves can reflect the distance characteristics between obstacles and between obstacles and the boundary of the path planning area. As a result, the planned path generated based on the sampling points can integrate the obstacle avoidance distance characteristics to ensure the lateral safety distance between the planned path and the obstacles, thereby avoiding collisions with obstacles during driving and improving the safety of the autonomous driving process. In addition, since the sampling points are pre-determined before path planning, the embodiments of the present disclosure can also circumvent the problems of insufficient lateral safety distance and inaccurate path planning caused by random sampling, further reducing the risk of collision and improving the safety of the autonomous driving process.

[0099] According to an embodiment of the present disclosure, there are multiple obstacles in the path planning area, and each obstacle corresponds to at least one edge position information and at least one angular position information. The edge position information includes the position information of the edges constituting the obstacle, and the angular position information represents the position information of the angle formed by the two edges of the obstacle at the intersection. The path planning area corresponds to at least one boundary position information.

[0100] In an embodiment of the present disclosure, each obstacle in the path planning area is mapped to a polygon that characterizes the shape of the obstacle, and the intersection between two sides can be regarded as a corner. Each obstacle can include multiple sides and multiple corners.

[0101] According to an embodiment of the present disclosure, the corner of an obstacle may be referred to as a corner point. A corner point may also be considered as an extreme point, that is, a point with particularly prominent attributes in a certain aspect.

[0102] For example, when the obstacle is a street lamp, the obstacle may be mapped as a polygon in the shape of the street lamp, wherein the lampshade of the street lamp is a trapezoid; when the obstacle is an irregular bicycle, the obstacle may be mapped as a polygon with the outline of the bicycle.

[0103] According to an embodiment of the present disclosure, each side corresponds to side position information, and each corner corresponds to corner position information. The side position information and corner position information can be represented by coordinates in a coordinate system, and the coordinate system is established based on the path planning area.

[0104] For example, the angular position information may include the coordinates of the corners of the obstacle in the coordinate system, and the edge position information may include the coordinates of the two endpoints of the edge of the obstacle in the coordinate system. The edge position information may also include the edge length. Table 1 schematically shows the edge position information of the obstacle:

[0105] Table 1

[0106]

[0107] Among them, endpoint 1 may be the starting point of the edge of the obstacle, and endpoint 2 may be the end point of the edge of the obstacle.

[0108] According to an embodiment of the present disclosure, the boundary position information is similar to the edge position information, and includes the coordinates of the two endpoints of the boundary of the path planning area in the coordinate system. The boundary position information may also include the boundary length.

[0109] According to an embodiment of the present disclosure, when there is one obstacle in the path planning area, the M reference lines are only the reference lines between the obstacle and the boundary of the path planning area. When there are multiple obstacles in the path planning area, the M reference lines may only include the reference lines between the obstacles; or the M reference lines may include both the reference lines between the obstacle and the boundary of the path planning area and the reference lines between the obstacles.

[0110] According to an embodiment of the present disclosure, the path planning method further includes: processing image information of the path planning area to determine edge position information and corner position information.

[0111] According to an embodiment of the present disclosure, the path planning area can be processed by utilizing an image-based corner detection algorithm to obtain the angular position information of all obstacles in the path planning area.

[0112] According to embodiments of the present disclosure, image-based corner detection algorithms include: grayscale image-based corner detection algorithms, binary image-based corner detection algorithms, and contour curve-based corner detection algorithms. Grayscale image-based corner detection algorithms include gradient methods, template methods, and template gradient methods. Template methods include: Kitchen-Rosenfeld corner detection algorithm, Harris corner detection algorithm, KLT algorithm, and SUSAN corner detection algorithm.

[0113] For example, the Harris corner detection algorithm can be used to process the path planning area to obtain the angular position information of all obstacles in the path planning area.

[0114] According to an embodiment of the present disclosure, a method for determining edge location information includes simplifying the edges of an obstacle into straight lines and detecting straight line segments within the simplified path planning area to determine the edge location information. For example, a line segment detector (LSD) algorithm can be used. The location information of the obstacle's edges, i.e., edge location information, is obtained without adjusting the image parameters of the path planning area and while minimizing the number of false positives.

[0115] According to an embodiment of the present disclosure, M reference lines are determined, including: determining the foot of the perpendicular from each corner to the edge of each obstacle and the position information of the foot of the perpendicular based on the angular position information and the edge position information; determining the foot of the perpendicular from each corner to the boundary of the path planning area and the position information of the foot of the perpendicular based on the angular position information and the boundary position information; wherein the angle corresponding to the foot of the perpendicular and the line between the foot of the perpendicular are reference lines.

[0116] According to an embodiment of the present disclosure, the reference line may be a perpendicular line from a corner of an obstacle to a side of another obstacle, or a perpendicular line from a corner of an obstacle to a boundary of a path planning area.

[0117] According to an embodiment of the present disclosure, for reference lines between obstacles, the intersection of a perpendicular from each corner to the edge of another obstacle and the edge of the aforementioned obstacle is the foot of the perpendicular. For perpendiculars between an obstacle and the boundary of the path planning area, the intersection of a perpendicular from each corner to the boundary of the path planning area and the boundary of the aforementioned path planning area is the foot of the perpendicular. Each foot of the perpendicular is associated with foot of the perpendicular position information, which can be the coordinates of the foot of the perpendicular.

[0118] According to an embodiment of the present disclosure, the foot position information of the perpendicular from each corner to the edge of another obstacle can be calculated based on the coordinates of the two endpoints and the coordinates of the corner in the edge position information. The foot position information of the perpendicular from each corner to the boundary of the path planning area can be calculated based on the coordinates of the two endpoints and the coordinates of the corner in the boundary position information.

[0119] FIG3A schematically shows a reference line diagram established according to the first embodiment of the present disclosure, FIG3B schematically shows a reference line diagram established according to the second embodiment of the present disclosure, and FIG3C schematically shows a reference line diagram established according to the third embodiment of the present disclosure.

[0120] As shown in Figure 3A , scenario 300A involves path planning from starting point A to target point B. Two rectangular obstacles exist within the path planning area encompassing starting point A and target point B. Rectangular obstacle 1, located above the path planning area, includes corners C1 and C3, while rectangular obstacle 2, located below the path planning area, includes corners C2 and C4.

[0121] The perpendicular line between corner C2 and the side of rectangular obstacle 1 is line C2-C1, and the foot position information is the coordinates of corner C1; the perpendicular line between corner C4 and the side of rectangular obstacle 1 is line C4-C3, and the foot position information is the coordinates of corner C3; the perpendicular line between corner C1 and the side of rectangular obstacle 2 is line C1-C2, and the foot position information is the coordinates of corner C2; the perpendicular line between corner C3 and the side of rectangular obstacle 2 is line C3-C4, and the foot position information is the coordinates of corner C4.

[0122] Since the C2-C1 line and the C1-C2 line coincide with each other, the C2-C1 line and the C1-C2 line can also be used as the same reference line.

[0123] As shown in Figure 3B , scenario 300B involves path planning from starting point A to target point B. Within the path planning area encompassing starting point A and target point B, there are a triangular obstacle and a rectangular obstacle. Rectangular obstacle 3, located above the path planning area, intersects with the boundary of the path planning area at a corner. Triangular obstacle 4, located below the path planning area, includes corner D1. The perpendicular line between corner D1 and the edge of rectangular obstacle 3 is line C1-E1, with the foot of the perpendicular at E1. The foot of the perpendicular is the coordinates of E1.

[0124] As shown in Figure 3C , scenario 300C involves path planning from starting point A to target point B. An irregular obstacle 5 and a trapezoidal obstacle 6 exist in the path planning area encompassing starting point A and target point B. Irregular obstacle 5, located above the path planning area, includes corner D4, while trapezoidal obstacle 6, located below the path planning area, includes corners D2 and D3.

[0125] The perpendicular line between angle D2 and the side of irregular obstacle 5 is line D2-E2, with its foot at E2 and its coordinates at the foot of the perpendicular. The perpendicular line between angle D3 and the side of irregular obstacle 5 is line D3-E3, with its foot at E3 and its coordinates at the foot of the perpendicular. The perpendicular line between angle D4 and the side of trapezoidal obstacle 6 is line D4-E4, with its foot at E4 and its coordinates at the foot of the perpendicular.

[0126] According to an embodiment of the present disclosure, since the reference line is the line segment with the smallest relative distance between the corner and the edge of the obstacle or the boundary of the path planning area, using the perpendicular line as the reference line helps to determine the sampling point at the position with the shortest relative distance, so as to avoid collision at the place where the obstacles on both sides are closest.

[0127] According to an embodiment of the present disclosure, taking the calculation of the foot position information of the perpendicular from a corner to the side of an obstacle as an example, determining the foot of the perpendicular from each corner to the side of each obstacle and the foot position information based on the angle position information and the side position information includes: calculating the slope of the side of each obstacle based on the side position information; determining a calculation mode that matches the slope; and calculating the edge position information and the angle position information based on the calculation mode to obtain the foot position information of the perpendicular from each corner to the side of each obstacle.

[0128] According to an embodiment of the present disclosure, the slope of the edge of the current obstacle can be determined by the ratio of the difference between the ordinates and the abscissas of the two endpoints, for example, the slope k is 3.

[0129] According to an embodiment of the present disclosure, slopes at different value ranges correspond to different calculation modes. Specifically, for the case where the absolute value of the slope is greater than or equal to 100, the side to which the above-mentioned slope belongs can be regarded as a side perpendicular to the horizontal coordinate, and the foot position coordinates of the angle to the side to which the current slope belongs are calculated according to the first calculation mode. For the case where the absolute value of the slope is less than or equal to 0.01, the side to which the above-mentioned slope belongs can be regarded as a side parallel to the horizontal coordinate, and the foot position coordinates of the angle to the side to which the current slope belongs are calculated according to the third calculation mode. For the case where the absolute value of the slope is between 0.01 and 100, there is an angle between the side to which the above-mentioned slope belongs and the horizontal coordinate, and the foot position coordinates of the angle to the side to which the current slope belongs are calculated according to the second calculation mode.

[0130] For example, the slope of the obstacle side is k. When |k| ≥ 100, the first calculation mode is as shown in formula (1):

[0131] x p =x1,y p =y c (1)

[0132] Among them, x p The horizontal coordinate of the foot of the perpendicular, y p represents the vertical coordinate of the foot of the perpendicular, x1 represents the horizontal coordinate of the starting point of the edge, y c Indicates the vertical coordinate of the angle.

[0133] When |k|≤0.01, the third calculation mode is as shown in formula (2):

[0134] x p =x c ,y p =y1 (2)

[0135] Among them, x p The horizontal coordinate of the foot of the perpendicular, y p The vertical coordinate of the foot of the perpendicular, x c represents the horizontal coordinate of the angle, and y1 represents the vertical coordinate of the starting point of the side.

[0136] When 0.01<|k|<100, the second calculation mode is as shown in formulas (3) and (4):

[0137] k p = -1 / k (3)

[0138] (4)

[0139] Among them, k p represents the slope of the vertical line, x p The horizontal coordinate of the foot of the perpendicular, y p The vertical coordinate of the foot of the perpendicular, xc The horizontal coordinate of the angle, y c represents the vertical coordinate of the angle, x1 represents the horizontal coordinate of the starting point of the side, and y1 represents the vertical coordinate of the starting point of the side.

[0140] As another embodiment of the present disclosure, when calculating the perpendicular position information, the coordinates of the other end point of the edge or boundary may also be used.

[0141] According to an embodiment of the present disclosure, calculating the perpendicular position information from the corner to the boundary of the path planning area is similar to calculating the perpendicular position information from the edge of the obstacle, and will not be repeated here.

[0142] FIG4 schematically shows a flow chart of a method for determining vertical foot position information according to a specific embodiment of the present disclosure.

[0143] 4 , the method 400 for determining perpendicular foot position information includes edge position information / boundary position information 401, slope 402, calculation mode 403, angular position information 404, and perpendicular foot position information 405. The calculation mode 403 includes a first calculation mode 4031, a second calculation mode 4032, and a third calculation mode 4033.

[0144] The slope 402 of the obstacle edge or the path planning area boundary can be calculated based on the edge position information / boundary position information 401. Based on the relationship between the calculated slope 402 and the slope range, the perpendicular position information used to calculate the angle to edge or angle to boundary is determined.

[0145] After determining that the calculation mode is one of the first calculation mode 4031 , the second calculation mode 4032 or the third calculation mode 4033 , the edge position information / boundary position information 401 and the angular position information 404 are calculated using the determined calculation mode to obtain the perpendicular foot position information 405 .

[0146] According to an embodiment of the present disclosure, determining at least one sampling point on each reference line to obtain a sampling point set includes: using at least one point on the reference line other than two endpoints of the reference line as a sampling point to obtain the sampling point set; wherein each sampling point is associated with sampling point position information, and the sampling point position information is determined based on the perpendicular position information and the angular position information.

[0147] For example, one or more sampling points can be randomly selected within a line segment that is more than a preset distance from both endpoints of the reference line. For example, if the reference line is 10 meters long, a sampling point can be randomly selected within a line segment that is more than 3 meters away from both endpoints of the reference line.

[0148] According to an embodiment of the present disclosure, the preset distance is related to the size of the autonomous driving vehicle.

[0149] According to an embodiment of the present disclosure, since the two endpoints of the reference line are located on the sides of two obstacles, or one endpoint is located on the side of an obstacle and the other endpoint is located on the boundary of the path planning area, when determining sampling points from the reference line, points other than the two endpoints of the reference line and located on the reference line can be used as sampling points to avoid collisions between the autonomous driving vehicle and obstacles on both sides or the single-sided boundary of a single-sided obstacle during actual driving.

[0150] As a specific embodiment of the present disclosure, determining the sampling point position information includes: taking the midpoint of the reference line as the sampling point, and calculating the position information of the midpoint of each reference line according to the perpendicular position information and the angular position information.

[0151] For example, the coordinates of the midpoint of the reference line can be calculated using the following formula (5):

[0152] (5)

[0153] Among them, x p The horizontal coordinate of the foot of the perpendicular, y p The vertical coordinate of the foot of the perpendicular, x c The horizontal coordinate of the angle, y c The vertical coordinate of the angle, x m Indicates the horizontal coordinate of the sampling point, y m Indicates the vertical coordinate of the sampling point.

[0154] In the embodiments of the present disclosure, since the sampling points used to generate the planned path in path planning have an impact on whether the planned path is close to obstacles, by using the midpoint of the vertical line with the smallest relative distance between the obstacles on both sides as the sampling point, it is possible to ensure to the greatest extent that the autonomous driving vehicle maintains a safe lateral distance from the obstacles on both sides at the corner of the obstacle, thereby avoiding collisions.

[0155] According to an embodiment of the present disclosure, before determining the sampling points from the reference lines, the established reference lines may be screened first, and the method further includes: calculating the length of each reference line based on the angular position information, the side position information, and the boundary position information; screening out N reference lines whose lengths are greater than a distance threshold from the M reference lines, where the distance threshold is related to the size of the target autonomous driving vehicle, and the target autonomous driving vehicle travels along a planned path from the starting point to the target point, where N is greater than or equal to 1 and N is less than or equal to M; and determining at least one sampling point from each reference line after screening to obtain a sampling point set.

[0156] According to an embodiment of the present disclosure, the length of each reference line may be calculated by referring to the following formula (6):

[0157] (6)

[0158] Where d represents the length of the reference line, x p The horizontal coordinate of the foot of the perpendicular, y p The vertical coordinate of the foot of the perpendicular, x c The horizontal coordinate of the angle, y c The vertical coordinate of the angle, x m Indicates the horizontal coordinate of the sampling point.

[0159] According to an embodiment of the present disclosure, the distance threshold is used to screen out areas that are actually impassable or prone to collisions. In actual use, the distance threshold can be slightly larger than the size of the autonomous vehicle, for example, the distance threshold can be 6 meters.

[0160] According to the embodiments of the present disclosure, since most existing path planning algorithms simplify the control of the vehicle itself, the generated planned path can meet the requirements of continuity and smoothness, but ignores the size of the vehicle itself, resulting in the planned path being very close to obstacles at some locations, increasing the risk of collision in actual applications.

[0161] In an embodiment of the present disclosure, by calculating the length of each reference line and screening the reference lines based on the comparison relationship between the length of the reference line and the distance threshold, inaccessible areas during actual driving are filtered out during the path planning process. Therefore, the risk of collision caused by not considering the actual size of the autonomous driving vehicle can be avoided.

[0162] According to embodiments of the present disclosure, when determining the foot of a perpendicular from a corner to an obstacle's edge or the boundary of a path planning area, it is possible that the foot of a perpendicular from one obstacle's edge to another obstacle's edge may overlap with a corner of the other obstacle, as shown in Figure 3A. While the proximity or even overlap of some perpendiculars does not affect the subsequent determination of sampling points, to avoid repeated selection of sampling points of the same value, a threshold can be set to filter the foot of perpendiculars close to obstacle corners, ensuring that the remaining perpendiculars belong to different corners.

[0163] For example, for each corner, the vertical legs whose distance to the corner is less than a preset threshold are deleted, where the preset threshold represents the degree of proximity to the corner. For example, the preset threshold may be 0.1 m.

[0164] According to an embodiment of the present disclosure, generating a planned path from a starting point to a target point based on a sampling point set includes: determining an initial planned path with the shortest distance from the starting point to the target point using multiple sampling points in the sampling point set as initial sampling points; selecting at least one sampling point on the initial planned path from the sampling point set, and using the at least one sampling point on the initial planned path as a path point to obtain a path point set; and generating a planned path including all path points in the path point set using a smooth path algorithm.

[0165] According to an embodiment of the present disclosure, a sampling-based path planning algorithm is used to generate an initial planned path from a starting point to a destination point, using multiple sampling points from a sampling point set as initial sampling points. The initial planned path can be considered a shortest distance solution from the starting point to the destination point, calculated based on the multiple sampling points from the sampling point set. The initial planned path may include at least one sampling point from the sampling point set.

[0166] For example, sampling-based path planning algorithms may include: Rapidly-exploring Random Tree (RRT) algorithm and Probabilistic Road Map (PRM) algorithm.

[0167] According to embodiments of the present disclosure, when a PRM algorithm is used to calculate an initial planned path using multiple sampling points from a sampling point set as initial sampling points, the PRM algorithm can filter and delete sampling points that fall within obstacle areas. Furthermore, the PRM algorithm calculates the initial planned path with the shortest distance from the starting point to the target point through repeated relaxation operations.

[0168] According to embodiments of the present disclosure, generating an initial planned path further eliminates sampling points that contribute little to the final planned path, namely, sampling points outside the initial planned path. Furthermore, sampling points used to locate the final planned path are obtained, namely, sampling points on the initial planned path with the shortest distance from the starting point to the destination point. At least one sampling point on the initial planned path can be used as a path point to obtain a path point set for generating the final planned path.

[0169] According to an embodiment of the present disclosure, after determining the set of waypoints, the initial planned path is directly processed using a smooth path algorithm to generate a planned path including all the waypoints in the set of waypoints.

[0170] As another embodiment of the present disclosure, a smooth planned path may be regenerated based on all the path points in the path point set.

[0171] According to an embodiment of the present disclosure, the following methods can be used to generate a smooth planned path: a path planning algorithm based on interpolation (Quadratic Polynomial and Membership Interpolation, QPMI), a Floyd algorithm, a path smoothing algorithm based on special curves, etc. Special curves include Bezier curves, cubic spline curves, B-spline curves, Dubin's curves, etc.

[0172] In the embodiments of the present disclosure, since the process of establishing a reference line and selecting sampling points can ensure that the selected sampling points maintain a safe lateral distance from obstacles on both sides, and the path points after screening through the initial planned path can fix the final planned path on the path with the shortest distance from the starting point to the target point, the planned path including the path points in the path point set can not only avoid collisions between the autonomous driving vehicle and obstacles on both sides, but also ensure the accuracy of the planned path.

[0173] FIG5 schematically shows a flow chart of generating a planned path from a starting point to a target point based on a set of sampling points according to an embodiment of the present disclosure.

[0174] As shown in FIG5 , an embodiment 500 of generating a planned path from a starting point to a target point based on a sampling point set includes a starting point position 501 , a target point position 502 , a sampling point set 503 , an initial planned path 504 , a path point set 505 , and a planned path 506 .

[0175] For example, all sampling points in sampling point set 503 are used as initial sampling points, and an initial planned path 504 is calculated based on starting point position 501 and target point position 502 using the PRM algorithm. Based on the generated initial planned path 504, sampling points on initial planned path 504 are filtered from sampling point set 503 and used as path points to generate path point set 505. Subsequently, a planned path 506 including all path points in path point set 505 can be generated using a smooth path algorithm.

[0176] According to an embodiment of the present disclosure, the path planning method further includes: deleting sampling points that fall within obstacles from the sampling point set to obtain an updated sampling point set; and determining an initial planned path with the shortest distance from the starting point to the target point using multiple sampling points in the updated sampling point set as initial sampling points.

[0177] According to an embodiment of the present disclosure, for an algorithm that is unable to filter and delete sampling points that fall within an obstacle area, before calculating the initial planned path, sampling points that fall within the obstacle are deleted from the sampling point set based on the edge position information of the obstacle to obtain an updated sampling point set. The initial planned path with the shortest distance from the starting point to the target point is determined based on the updated sampling point set.

[0178] Figure 6A schematically shows a schematic diagram of the path planning area and the corners of obstacles determined by simulation; Figure 6B schematically shows a schematic diagram of the perpendiculars of each corner to the edge of the obstacle and to the boundary of the path planning area determined by simulation; Figure 6C schematically shows a schematic diagram of multiple sampling points in the path planning area determined by simulation; Figure 6D schematically shows an initial planned path determined by simulation, and a schematic diagram of multiple path points located on the initial planned path; Figure 6E schematically shows a comparison diagram of the Fangzhen planned path generated according to an embodiment of the present disclosure and the existing planned path.

[0179] As shown in Figure 6A, a 100×100 coordinate system was constructed using the lower boundary of the path planning area as the x-axis and the left boundary of the path planning area as the y-axis. The four shaded areas in the coordinate system represent the four obstacles in the path planning area, with the topmost obstacle intersecting with the upper boundary of the path planning area.

[0180] The Harris algorithm is used to detect corner points of the path planning area including the coordinate system, and the corners (corner points) of the obstacles represented by the dots in FIG6A are obtained.

[0181] According to an embodiment of the present disclosure, a coordinate system is constructed based on the path planning area, whereby the side position information, angular position information of the obstacle, and the boundary position information of the path planning area can all be represented by coordinates in the coordinate system.

[0182] FIG6B shows the foot of the perpendicular from each corner to the edge of the obstacle and the foot of the perpendicular from each corner to the path planning area determined based on the edge position information, corner position information, and boundary position information of the path planning area of ​​the obstacle.

[0183] In Figure 6B, the square points on the obstacle are the feet of the perpendicular from the corner to the edge of the obstacle; the square points on the left and bottom boundaries of the path planning area are the feet of the perpendicular from the corner to the boundary of the path planning area, such as the square points between (0, 15) and (0, 20) on the y-axis.

[0184] The midpoint of the line connecting the angle and the perpendicular foot can be used as a sampling point, and sampling points throughout the path planning area are obtained, such as the triangular points shown in FIG6C .

[0185] Based on the sampling points determined in Figure 6C, the initial planned path from the starting point to the target point generated by the PRM algorithm is shown in Figure 6D. As shown in Figure 6D, the sampling points on the initial planned path are path points.

[0186] Figure 6E (a) includes the initial planned path generated in Figure 6D and the simulated planned path including all path points on the initial planned path. Figure 6E (b) shows the initial planned path generated based on random sampling points in the prior art and the simulated planned path generated based on random sampling points.

[0187] As can be seen from Figure 6E (b), when the size of the autonomous driving vehicle is simplified, the autonomous driving vehicle will collide when passing the two corners of the leftmost obstacle in the path planning area.

[0188] On the contrary, as can be seen from Figure 6E (a), by determining the sampling points on the reference line and determining the path points based on the sampling points and the initial planned path, the planned path can be fixed to the path points at the corner of the obstacle, thereby avoiding the autonomous driving vehicle from colliding with obstacles on both sides at the corner.

[0189] In existing technologies, when randomly sampling points to determine and then perform path planning, insufficient sampling points can result in a path failure. Even with a sufficient number of sampling points, the shortest planned path created during path generation cannot avoid collision risks at corners. Furthermore, random sampling results in different sampling points for different operations, making the resulting planned path non-unique. This increases the risk of collisions during subsequent smoothing and actual application. Furthermore, the inherent randomness of path planning and smoothing algorithms makes it difficult to mitigate collision risks.

[0190] The planned path generated based on the embodiments of the present disclosure can avoid obstacles on both sides at obstacle corners, ensuring that the planned path meets the safety requirements of practical applications and reducing collision risks. Furthermore, because the path points used for path planning are unique, the planned path generated using the embodiments of the present disclosure is also unique, making the planned path easier to control in practical applications and improving the safety and controllability of autonomous driving in practical applications.

[0191] FIG7 schematically shows a structural block diagram of a path planning device according to an embodiment of the present disclosure.

[0192] As shown in FIG. 7 , the path planning device 700 of this embodiment includes a first determination module 710 , a second determination module 720 , a third determination module 730 and a generation module 740 .

[0193] The first determining module 710 is configured to determine a path planning area including a starting point and a target point, wherein obstacles exist in the path planning area.

[0194] The second determining module 720 is configured to determine M reference lines, where the reference lines include reference lines between obstacles and / or reference lines between obstacles and a boundary of the path planning area, and M is a positive integer.

[0195] The third determining module 730 is configured to determine at least one sampling point on each reference line to obtain a sampling point set.

[0196] The generation module 740 is configured to generate a planned path from the starting point to the target point based on the sampling point set.

[0197] According to an embodiment of the present disclosure, there are multiple obstacles in the path planning area, and each obstacle corresponds to at least one edge position information and at least one angular position information. The edge position information includes the position information of the edge constituting the obstacle, and the angular position information represents the position information of the angle formed by the two edges of the obstacle at the intersection. The path planning area corresponds to at least one boundary position information.

[0198] The second determining module 720 includes a first determining unit and a second determining unit.

[0199] The first determining unit is configured to determine the foot of a perpendicular from each corner to the side of each obstacle and the position information of the foot of the perpendicular based on the corner position information and the side position information.

[0200] The second determining unit is used to determine the foot of the perpendicular from each corner to the boundary of the path planning area and the position information of the foot of the perpendicular according to the angular position information and the boundary position information.

[0201] According to an embodiment of the present disclosure, the angle corresponding to the foot of the perpendicular and the line connecting the foot of the perpendicular are reference lines.

[0202] According to an embodiment of the present disclosure, the first determining unit includes a first determining subunit, a second determining subunit, and a third determining subunit.

[0203] The first determining subunit is configured to calculate the slope of the edge of each obstacle according to the edge position information.

[0204] The second determining subunit is used to determine a calculation mode that matches the slope.

[0205] The third determining subunit is configured to calculate the edge position information and the corner position information based on the calculation mode to obtain the perpendicular position information from each corner to the edge of each obstacle.

[0206] According to an embodiment of the present disclosure, the third determining module 730 includes a third determining unit.

[0207] The third determining unit is configured to select at least one point on the reference line other than the two endpoints of the reference line as a sampling point to obtain a set of sampling points, wherein each sampling point has corresponding sampling point position information, and the sampling point position information is determined based on the perpendicular position information and the angular position information.

[0208] According to an embodiment of the present disclosure, the third determining module 730 further includes a fourth determining unit.

[0209] The fourth determining unit is configured to use the midpoint of the reference line as a sampling point, and calculate the position information of the midpoint of each reference line according to the perpendicular position information and the angular position information.

[0210] According to an embodiment of the present disclosure, the third determination module 730 further includes a length calculation unit, a screening unit, and a sampling unit.

[0211] The length calculation unit is used to calculate the length of each reference line according to the corner position information, the side position information and the boundary position information.

[0212] The screening unit is used to screen out N reference lines whose lengths are greater than a distance threshold from M reference lines. The distance threshold is related to the size of the target autonomous driving vehicle. The target autonomous driving vehicle travels along a planned path from a starting point to a target point. N is greater than or equal to 1 and N is less than or equal to M.

[0213] The sampling unit is used to determine at least one sampling point from each reference line after screening to obtain a sampling point set.

[0214] According to an embodiment of the present disclosure, the generation module 740 includes a first planning unit, a waypoint determination unit, and a smoothing unit.

[0215] The first planning unit is configured to determine an initial planning path with the shortest distance from a starting point to a target point by using a plurality of sampling points in the sampling point set as initial sampling points.

[0216] The path point determination unit is used to filter out at least one sampling point located on the initial planned path from the sampling point set, and use the at least one sampling point located on the initial planned path as a path point to obtain a path point set.

[0217] The smoothing unit is used to generate a planned path including all path points in the path point set by using a smoothing path algorithm.

[0218] According to an embodiment of the present disclosure, the generation module 740 further includes a sampling point screening unit and a second planning unit.

[0219] The sampling point screening unit is used to delete the sampling points that fall within the obstacle from the sampling point set to obtain an updated sampling point set.

[0220] The second planning unit is configured to determine an initial planning path with the shortest distance from the starting point to the target point by using multiple sampling points in the updated sampling point set as initial sampling points.

[0221] According to an embodiment of the present disclosure, the path planning device 700 further includes a position determination module for processing image information of the path planning area to determine edge position information and corner position information.

[0222] According to the embodiments of the present invention, any number of modules, sub-modules, units, and sub-units, or at least part of the functions of any number of them, can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, sub-modules, units, and sub-units can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, sub-modules, units, and sub-units can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, sub-modules, units, and sub-units can be at least partially implemented as a computer program module, which can perform the corresponding functions when the computer program module is executed.

[0223] For example, any multiple of the first determination module 710, the second determination module 720, the third determination module 730, and the generation module 740 can be combined into a single module / unit / sub-unit, or any one of these modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functionality of one or more of these modules / units / sub-units can be combined with at least part of the functionality of other modules / units / sub-units and implemented in a single module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the first determination module 710, the second determination module 720, the third determination module 730, and the generation module 740 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware by any other reasonable means of circuit integration or packaging, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the first determination module 710 , the second determination module 720 , the third determination module 730 and the generation module 740 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0224] It should be noted that the path planning device part in the embodiment of the present disclosure corresponds to the path planning method part in the embodiment of the present disclosure. The description of the path planning device part specifically refers to the path planning method part and will not be repeated here.

[0225] FIG8 schematically shows a block diagram of an electronic device suitable for a path planning method according to an embodiment of the present disclosure.

[0226] As shown in FIG8 , an electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 802 or programs loaded from a storage unit 808 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or related chipsets and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)). The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for executing the different actions of the method flow according to the embodiment of the present disclosure.

[0227] Various programs and data required for the operation of the electronic device 800 are stored in the RAM 803. The processor 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. The processor 801 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 802 and / or the RAM 803. It should be noted that the programs may also be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 may also execute the various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0228] According to an embodiment of the present disclosure, electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to bus 804. Electronic device 800 may also include one or more of the following components connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 808 including a hard disk; and a communication section 809 including a network interface card such as a LAN card or modem. Communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. Removable media 811, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 810 as needed, so that computer programs read from the removable media can be installed into storage section 808 as needed.

[0229] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0230] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 802 and / or RAM 803 described above, and / or one or more memories other than ROM 802 and RAM 803.

[0231] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the above-mentioned method provided in the embodiments of the present disclosure.

[0232] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 801 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0233] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0234] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 809, and / or installed from a removable medium 811. When the computer program is executed by the processor 801, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0235] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0236] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0237] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or couplings are intended to fall within the scope of this disclosure.

[0238] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present disclosure. It should be understood that the above are only specific embodiments of the present disclosure and are not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A path planning method, comprising: Determine a path planning area including a starting point and a target point, wherein obstacles exist in the path planning area; Determine M reference lines, wherein the reference lines include reference lines between the obstacles and / or reference lines between the obstacles and a boundary of the path planning area, and M is a positive integer; Determine at least one sampling point from each of the reference lines to obtain a sampling point set; and Based on the sampling point set, a planned path from the starting point to the target point is generated.

2. The method according to claim 1, wherein: There are multiple obstacles in the path planning area, each obstacle corresponds to at least one edge position information and at least one corner position information, the edge position information includes the position information of the edge constituting the obstacle, the corner position information represents the position information of the angle formed by the two edges of the obstacle at the intersection, and the path planning area corresponds to at least one boundary position information; The determining of M reference lines comprises: Determine the foot of a perpendicular from each corner to the side of each obstacle and the foot of the perpendicular position information according to the corner position information and the side position information; Determine the foot of a perpendicular from each corner to the boundary of the path planning area and the foot position information according to the angular position information and the boundary position information; The angle corresponding to the foot of the perpendicular and the line connecting the foot of the perpendicular are the reference lines.

3. The method according to claim 2, wherein: Determining the foot of a perpendicular from each corner to the side of each obstacle and the foot of the perpendicular position information according to the corner position information and the side position information comprises: Calculating the slope of each edge of the obstacle according to the edge position information; determining a calculation mode that matches the slope; and The edge position information and the corner position information are calculated based on the calculation mode to obtain the perpendicular position information from each corner to the edge of each obstacle.

4. The method according to claim 2, wherein: The step of determining at least one sampling point from each of the reference lines to obtain a sampling point set includes: Taking at least one point on the reference line other than the two end points of the reference line as a sampling point to obtain the sampling point set; Each of the sampling points corresponds to sampling point position information, and the sampling point position information is determined according to the perpendicular position information and the angular position information.

5. The method according to claim 4, wherein: Determining the sampling point location information includes: The midpoint of the reference line is used as the sampling point, and the position information of the midpoint of each reference line is calculated according to the perpendicular position information and the angular position information.

6. The method according to any one of claims 2 to 5, further comprising: Calculating the length of each reference line according to the angular position information, the side position information and the boundary position information; Filtering N reference lines whose lengths are greater than a distance threshold from the M reference lines, the distance threshold being related to a size of a target autonomous driving vehicle, the target autonomous driving vehicle traveling along a planned path from the starting point to the target point, N being greater than or equal to 1 and N being less than or equal to M; as well as At least one sampling point is determined from each of the reference lines after screening to obtain a sampling point set.

7. The method according to claim 1, wherein: The generating a planned path from the starting point to the target point based on the sampling point set includes: Taking a plurality of the sampling points in the sampling point set as initial sampling points, determining an initial planning path with the shortest distance from the starting point to the target point; Filtering at least one sampling point located on the initial planned path from the sampling point set, and using the at least one sampling point located on the initial planned path as a path point to obtain a path point set; and A smooth path algorithm is used to generate a planned path including all the path points in the path point set.

8. The method according to claim 7, further comprising: Deleting the sampling points that fall within the obstacles from the sampling point set to obtain an updated sampling point set; as well as Taking the plurality of sampling points in the updated sampling point set as initial sampling points, an initial planning path with the shortest distance from the starting point to the target point is determined.

9. The method according to claim 2, further comprising: The image information of the path planning area is processed to determine the edge position information and the corner position information.

10. A path planning device, comprising: A first determination module is used to determine a path planning area including a starting point and a target point, wherein obstacles exist in the path planning area; A second determination module, configured to determine M reference lines, wherein the reference lines include reference lines between the obstacles and / or reference lines between the obstacles and a boundary of the path planning area, and M is a positive integer; A third determining module is used to determine at least one sampling point from each of the reference lines to obtain a sampling point set; and A generation module is used to generate a planned path from the starting point to the target point based on the sampling point set.

11. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 10.

12. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 10.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

14. An autonomous driving vehicle comprising the electronic device described in claim 11.

Images