Path planning method, device, equipment and storage medium

Abstract

The present disclosure provides a path planning method, device, equipment and storage medium, which relate to the field of artificial intelligence technology. The method includes: obtaining the current coordinates and current reference line of a moving body in a road coordinate system, and the road coordinate system obtains the longitudinal axis according to the center line of the road; obtaining the planned distance for path planning of the moving body; based on the current coordinates of the moving body, obtaining the boundary point coordinates of multiple obstacles within the planning range corresponding to the planned distance; obtaining the road edge line in the road coordinate system; determining a reference obstacle from multiple obstacles according to the road edge line and the boundary point coordinates of multiple obstacles; obtaining a local reference line of the moving body within the planned distance according to the current reference line and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line. The method realizes planning a more reasonable path for the moving body when it needs to bypass multiple obstacles, thereby improving the working efficiency of the moving body.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a path planning method, device, equipment and readable storage medium. Background Art

[0002] At present, mobile robot technology is developing rapidly. With the continuous expansion of robot application scenarios and modes in recent years, various mobile robots have emerged one after another. For example, unmanned logistics delivery vehicles are one of the widely used mobile robots. Path planning technology is an indispensable part of unmanned logistics delivery vehicle technology. In an environment with lane lines, a reference line for path planning is usually established, and the speed and acceleration of the unmanned vehicle are planned based on the reference line.

[0003] In the case of obstacles on some roads, the relevant technology adopts the method of bypassing the obstacles in front and then returning to the original reference line when planning the path for unmanned logistics delivery vehicles. When there are a series of obstacles along the road and there are gaps between the obstacles, the unmanned logistics delivery vehicle needs to bypass the gaps between the obstacles and then bypass them in order to return to the center line of the lane, resulting in the unmanned logistics delivery vehicle's driving trajectory to be "S" shaped, affecting delivery efficiency.

[0004] As mentioned above, how to provide more flexible reference lines to plan more reasonable routes for unmanned logistics delivery vehicles has become an urgent problem to be solved.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present disclosure is to provide a path planning method, device, equipment and readable storage medium, which at least to a certain extent overcome the problem of low working efficiency of unmanned logistics delivery vehicles caused by the path planning method adopted in the related technology of bypassing the obstacles in front and then returning to the original reference line.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a path planning method is provided, comprising: obtaining current coordinates and a current reference line of a moving body in a road coordinate system, wherein the road coordinate system obtains a longitudinal axis according to a road centerline; obtaining boundary point coordinates of a plurality of obstacles; obtaining a road edge line in the road coordinate system; obtaining a planned distance for path planning of the moving body; based on the current coordinates of the moving body, determining reference obstacles within a planned range corresponding to the planned distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles; obtaining a local reference line of the moving body within the planned distance according to the current reference line and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line.

[0009] According to one embodiment of the present disclosure, the method also includes: obtaining the width and obstacle avoidance distance of the moving body; obtaining the local reference line of the moving body within the planned distance based on the current reference line and the boundary point coordinates of the reference obstacle includes: obtaining the local reference line based on the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving body and the obstacle avoidance distance.

[0010] According to an embodiment of the present disclosure, there are multiple reference obstacles, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle; obtaining the local reference line according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving body and the obstacle avoidance distance includes: for each reference obstacle among the multiple reference obstacles, adding the horizontal axis positive boundary point coordinates of the reference obstacle, half the width of the moving body and the obstacle avoidance distance to obtain the obstacle avoidance reference line of each reference obstacle; selecting the reference line that is farthest from the reference edge line among the current reference line and the obstacle avoidance reference lines of each reference obstacle as the local reference line.

[0011] According to an embodiment of the present disclosure, there are multiple reference obstacles, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle; the obtaining of the local reference line according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving body and the obstacle avoidance distance includes: obtaining a maximum lateral boundary component according to the boundary point coordinates of multiple reference obstacles, the maximum lateral boundary component being the maximum value of the horizontal axis components of the horizontal axis positive boundary point coordinates of multiple reference obstacles in the road coordinate system; adding the maximum lateral boundary component to half the width of the moving body and the obstacle avoidance distance to obtain an obstacle avoidance reference line within the planned distance; selecting a reference line that is farther from the reference edge line from the current reference line and the obstacle avoidance reference line within the planned distance as the local reference line.

[0012] According to an embodiment of the present disclosure, the planned distance includes a forward obstacle avoidance distance and a backward obstacle avoidance distance, the boundary point coordinates of the multiple obstacles include the positive boundary point coordinates and the negative boundary point coordinates of the longitudinal axis of the multiple obstacles, and the current coordinates of the moving body include the current longitudinal coordinates of the moving body; based on the current coordinates of the moving body, determining the reference obstacle within the planned range corresponding to the planned distance from the multiple obstacles according to the road edge line and the boundary point coordinates of the multiple obstacles includes: storing the multiple obstacles in an obstacle set; excluding obstacles that meet a first filtering condition from the obstacle set and updating the obstacle set; determining the reference obstacle from the updated obstacle set; wherein the first filtering condition is that the position is outside the planned range, and the position outside the planned range is that the positive boundary point coordinates of the longitudinal axis are less than the difference between the current longitudinal coordinate of the moving body and the backward obstacle avoidance distance, or the negative boundary point coordinates of the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the forward obstacle avoidance distance.

[0013] According to an embodiment of the present disclosure, the boundary point coordinates of the multiple obstacles also include the positive boundary point coordinates and the negative boundary point coordinates of the multiple obstacles on the horizontal axis; the method also includes: obtaining the minimum positive road width and the minimum negative road width on the horizontal axis according to the road center line and the road edge line; the determining the reference obstacles within the planning range corresponding to the planning distance from the multiple obstacles based on the current coordinates of the moving body according to the road edge line and the boundary point coordinates of the multiple obstacles also includes: excluding obstacles that meet a second filtering condition from the obstacle set and updating the obstacle set, wherein the second filtering condition is that the negative boundary point coordinate of the horizontal axis is greater than the sum of the horizontal coordinate of the current reference line of the moving body and the width of the moving body, or the positive boundary point coordinate of the horizontal axis is less than the inverse of the minimum negative road width on the horizontal axis, or the positive boundary point coordinate of the horizontal axis is greater than the difference between the minimum positive road width on the horizontal axis and the width of the moving body.

[0014] According to an embodiment of the present disclosure, the determining of reference obstacles within the planning range corresponding to the planned distance from the multiple obstacles based on the current coordinates of the moving body and the coordinates of the boundary points of the road edge line and the multiple obstacles also includes: obtaining the distance between the current position of the moving body and the destination along the longitudinal axis according to the current coordinates of the moving body; excluding obstacles that meet a third filtering condition from the obstacle set, and updating the obstacle set, wherein the third filtering condition is that the coordinates of the negative boundary point of the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the distance between the current position of the moving body and the destination along the longitudinal axis.

[0015] According to another aspect of the present disclosure, a path planning device is provided, comprising: a current quantity acquisition module, used to acquire the current coordinates and current reference line of a moving body in a road coordinate system, wherein the road coordinate system acquires a longitudinal axis according to a road centerline; an obstacle boundary acquisition module, used to acquire the boundary point coordinates of a plurality of obstacles; an edge line acquisition module, used to acquire the road edge line in the road coordinate system; a planned distance acquisition module, used to acquire a planned distance for path planning of the moving body; a reference obstacle determination module, used to determine, based on the current coordinates of the moving body, a reference obstacle within a planned range corresponding to the planned distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles; and a local path planning module, used to acquire a local reference line of the moving body within the planned distance according to the current reference line and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line.

[0016] According to one embodiment of the present disclosure, the device also includes: a parameter setting module for obtaining the width and obstacle avoidance distance of the moving body; the local path planning module is also used to obtain the local reference line based on the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving body and the obstacle avoidance distance.

[0017] According to an embodiment of the present disclosure, there are multiple reference obstacles, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle; the local path planning module includes: a first obstacle avoidance reference line acquisition module, which is used to add the horizontal axis positive boundary point coordinates of the reference obstacle to half the width of the moving body and the obstacle avoidance distance for each reference obstacle among the multiple reference obstacles, to obtain the obstacle avoidance reference line of each reference obstacle; a first local reference line determination module, which is used to select the reference line that is farthest from the reference edge line among the current reference line and the obstacle avoidance reference lines of each reference obstacle as the local reference line.

[0018] According to an embodiment of the present disclosure, there are multiple reference obstacles, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the coordinates of the positive boundary points of the reference obstacle on the horizontal axis; the local path planning module includes a lateral boundary acquisition module, which is used to: obtain a maximum lateral boundary component according to the boundary point coordinates of the multiple reference obstacles, and the maximum lateral boundary component is the maximum value of the components of the positive boundary point coordinates of the horizontal axis in the road coordinate system among the multiple reference obstacles; a second obstacle avoidance reference line acquisition module, which is used to add the maximum lateral boundary component to half the width of the mobile body and the obstacle avoidance distance to obtain an obstacle avoidance reference line within the planned distance; a second local reference line determination module, which is used to select a reference line that is farther from the reference edge line from the current reference line and the obstacle avoidance reference lines within the planned distance as the local reference line.

[0019] According to an embodiment of the present disclosure, the planned distance includes a forward obstacle avoidance distance and a backward obstacle avoidance distance, the boundary point coordinates of the multiple obstacles include the positive boundary point coordinates and the negative boundary point coordinates of the longitudinal axis of the multiple obstacles, and the current coordinates of the moving body include the current longitudinal coordinate of the moving body; the reference obstacle determination module includes: an obstacle set acquisition module, used to store the multiple obstacles in an obstacle set; a first obstacle filtering module, used to exclude obstacles that meet a first filtering condition from the obstacle set and update the obstacle set; the reference obstacle determination module is also used to determine the reference obstacle from the updated obstacle set; wherein the first filtering condition is that the position is outside the planned range, and the position outside the planned range is that the positive boundary point coordinates of the longitudinal axis are less than the difference between the current longitudinal coordinate of the moving body and the backward obstacle avoidance distance, or the negative boundary point coordinates of the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the forward obstacle avoidance distance.

[0020] According to an embodiment of the present disclosure, the boundary point coordinates of the multiple obstacles also include the horizontal axis positive boundary point coordinates and the horizontal axis negative boundary point coordinates of the multiple obstacles; the device also includes: a road width acquisition module, used to obtain the horizontal axis positive minimum road width and the horizontal axis negative minimum road width according to the road center line and the road edge line; the reference obstacle determination module also includes: a second obstacle filtering module, used to exclude obstacles that meet the second filtering condition from the obstacle set and update the obstacle set, wherein the second filtering condition is that the horizontal axis negative boundary point coordinate is greater than the sum of the horizontal coordinate of the current reference line of the moving body and the width of the moving body, or the horizontal axis positive boundary point coordinate is less than the inverse of the horizontal axis negative minimum road width, or the horizontal axis positive boundary point coordinate is greater than the difference between the horizontal axis positive minimum road width and the width of the moving body.

[0021] According to an embodiment of the present disclosure, the reference obstacle determination module further includes: a target distance acquisition module, used to obtain the distance between the current position of the moving body and the destination along the longitudinal axis according to the current coordinates of the moving body; a third obstacle filtering module, used to exclude obstacles that meet a third filtering condition from the obstacle set and update the obstacle set, wherein the third filtering condition is that the coordinates of the negative boundary point of the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the distance between the current position of the moving body and the destination along the longitudinal axis.

[0022] According to another aspect of the present disclosure, a device is provided, comprising: a memory, a processor, and executable instructions stored in the memory and executable in the processor, wherein the processor implements any of the above methods when executing the executable instructions.

[0023] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, and when the executable instructions are executed by a processor, any of the above methods is implemented.

[0024] The path planning method provided by the embodiments of the present disclosure determines a reference obstacle within a planning range corresponding to a planning distance for path planning of a moving body from among multiple obstacles according to a road edge line in a road coordinate system and boundary point coordinates of multiple obstacles, obtains a local reference line of the moving body within the planning distance according to the current reference line of the moving body in the road coordinate system and the boundary point coordinates of the reference obstacle, and plans the path of the moving body according to the current coordinates of the moving body in the road coordinate system and the local reference line, thereby planning a more reasonable path for the moving body when it needs to bypass multiple obstacles, thereby improving the working efficiency of the moving body.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0027] Figure 1 A schematic diagram showing a system structure in an embodiment of the present disclosure.

[0028] Figure 2 A flow chart of a path planning method in an embodiment of the present disclosure is shown.

[0029] Figure 3 A schematic diagram of coordinate transformation in an embodiment of the present disclosure is shown.

[0030] Figure 4 A schematic diagram showing the coordinates of a boundary point of an obstacle in a road coordinate system according to an embodiment of the present disclosure.

[0031] Figure 5 A schematic diagram showing a road edge line in a road coordinate system according to an embodiment of the present disclosure.

[0032] Figure 6 A flow chart of an obstacle filtering method in an embodiment of the present disclosure is shown.

[0033] Figure 7 A flow chart showing another obstacle filtering method in an embodiment of the present disclosure is shown.

[0034] Figure 8 A flow chart of another obstacle filtering method in an embodiment of the present disclosure is shown.

[0035] Fig. 9A flow chart of a local reference line generation method in an embodiment of the present disclosure is shown.

[0036] Fig.10 A block diagram of a path planning device in an embodiment of the present disclosure is shown.

[0037] Fig.11 A block diagram of another path planning device in an embodiment of the present disclosure is shown.

[0038] Fig.12 A schematic structural diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The accompanying drawings are only schematic illustrations of the disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0040] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, devices, steps, etc. may be adopted. In other cases, well-known structures, methods, devices, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0041] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present disclosure, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. The symbol " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0042] In this disclosure, unless otherwise clearly specified and limited, terms such as "connection" should be understood in a broad sense, for example, it can be an electrical connection or can communicate with each other; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this disclosure can be understood according to specific circumstances.

[0043] Unmanned logistics delivery vehicles usually travel on non-motorized vehicle lanes or the rightmost motor vehicle lane. The local reference line for path planning of the unmanned logistics delivery vehicle can be the center line of the lane, the right reference line at a certain safe distance from the right edge of the lane, and the like. As described above, when there are a series of obstacles along the lane near the road edge (such as the right edge) and there are gaps between the obstacles, the unmanned logistics delivery vehicle needs to go around into the gap and then go out in order to return to the original reference line, resulting in the unmanned logistics delivery vehicle's driving trajectory being "S" shaped, affecting the delivery efficiency. Therefore, the present disclosure provides a path planning method, by determining a reference obstacle within a planning range corresponding to a planning distance for path planning of a moving body from a plurality of obstacles according to the road edge line in a road coordinate system and the boundary point coordinates of a plurality of obstacles, obtaining a local reference line of the moving body within the planning distance according to the current reference line of the moving body in the road coordinate system and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body in the road coordinate system and the local reference line, so that a more reasonable path can be planned for the moving body when it needs to bypass a plurality of obstacles, thereby improving the working efficiency of the moving body.

[0044] Figure 1 An exemplary system architecture 10 to which the path planning method or path planning device of the present disclosure can be applied is shown.

[0045] like Figure 1 As shown, the system architecture 10 may include a terminal device 102, a network 104, a server 106, and a database 108. The terminal device 102 may be a variety of electronic devices having a display screen and supporting input and output, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, wearable devices, virtual reality devices, smart homes, mobile robots, etc. The network 104 is used to provide a medium for a communication link between the terminal device 102 and the server 106. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. The server 106 may be a server or server cluster that provides various services, etc. The database 108 may be a large database software placed on a server, or a small database software installed on a computer for storing data.

[0046] The terminal device 102 can interact with the server 106 and the database 108 through the network 104 to receive or send data, etc. For example, a user can operate on the terminal device 102 to send the configuration parameters for generating the path planning to the server 106 through the network 104, so that the server 106 can perform path planning for the connected mobile robot according to the configuration parameters. For another example, the server 106 sends the speed and acceleration of the mobile robot planned in real time to the terminal device 102 through the network 104, so that the terminal device 102 can control the movement of the mobile robot. For another example, the real-time movement data of the terminal device 102 can be uploaded to the database 108 through the network 104 for storage, so as to be used for path planning at the next time point.

[0047] The server 106 may also receive data from the database 108 or send data to the database 108 through the network 104. For example, the server 106 may be a background processing server, which is used to obtain the mobile robot's movement data from the database 108 through the network 104 and then perform real-time path planning for the mobile robot. For another example, the server 106 may be used to send the planned speed, acceleration and other data of the mobile robot to the database 108 through the network 104 for storage, so as to be used for path planning at the next time point.

[0048] It should be understood that Figure 1 The number of terminal devices, networks, servers and databases in the embodiment is only for illustration. Any number of terminal devices, networks, servers and databases may be provided as required.

[0049] Figure 2 FIG. 1 is a flow chart of a path planning method according to an exemplary embodiment. Figure 2 The method shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system.

[0050] refer to Figure 2 , the method 20 provided in the embodiment of the present disclosure may include the following steps.

[0051] In step S202, the current coordinates and current reference line of the moving body in the road coordinate system are obtained, and the road coordinate system obtains the longitudinal axis according to the center line of the road. The moving body can be an unmanned robot, such as a cleaning robot, a logistics robot, etc. In actual situations, the road on which the robot travels is usually not straight, but winding, so the robot's driving route is usually a curve. In the Cartesian coordinate system, the representation and calculation of the curve are relatively cumbersome; and even if the position of the moving body in the Cartesian coordinate system is given, it is not known where the road is, it is difficult to know how far the moving body has moved, and it is difficult to determine whether the moving body has deviated from the reference line. Therefore, when planning the path of a moving body such as a robot, a road coordinate system is usually used. The road coordinate system is a rectangular coordinate system. In the road coordinate system, two variables, the distance change along the road (longitudinal displacement) and the left and right position on the road (lateral displacement), are used to describe the position of the point therein. For example, the center line of the road can be used as the longitudinal axis and the normal vector of the center line of the road can be used as the horizontal axis. Path planning can be performed at a certain time period during the driving process of the mobile body. When performing path planning, the coordinates of the current position of the mobile body in the road coordinate system and the equation of the reference line currently used for path planning in the coordinate system are obtained.

[0052] In some embodiments, for example, the road coordinate system may be a Frenet coordinate system, which takes the tangent vector of the road centerline as the vertical axis and the normal vector of the road centerline as the horizontal axis. The Cartesian coordinates of the moving object may be first obtained, and then the coordinates may be transformed to obtain the coordinates of the moving object in the Frenet coordinate system. For a specific implementation, please refer to Figure 3 . refer to Figure 3 , if t represents the current time, 1(t) represents the horizontal coordinate of the reference line at the current time, when the current reference line of the moving body is the center line of the road, the current reference line equation is 1(t) = 0; taking the right-hand traffic as an example, when the current reference line of the moving body is the right reference line, the current reference line equation is l(t) = -(|l right |-0.5×W-d0), where |l right | is the road width on the right side of the road centerline, W is the width of the moving body, and d0 is the set safety distance from the edge of the road.

[0053] In step S204, the coordinates of the boundary points of multiple obstacles are obtained. All obstacles from the perception module of the unmanned logistics delivery vehicle can be obtained, such as all static obstacles, slow dynamic obstacles, etc., which are obstacles that can be considered to be bypassed. Others, such as fast dynamic obstacles, can be considered to follow them by adjusting the speed. When representing the boundary points of obstacles, the obstacles can be approximated as polygons formed by a series of vertices connected in a certain order, and the coordinates of the boundary points of each obstacle can be determined from the vertices of the obstacle.

[0054] In some embodiments, for example, Figure 4 The coordinate diagram of the boundary points of the obstacle in the Frenet coordinate system is shown. Figure 4 .

[0055] In step S206, the road edge line in the road coordinate system is obtained. The road edge line may include a left edge line and a right edge line of the road, which are used to determine the reference obstacle.

[0056] In some embodiments, for example, the representation of the road edge line may refer to Figure 5 .

[0057] In step S208, a planning distance for path planning of the moving body is obtained. The planning distance for path planning of the moving body is used to consider obstacles that are at a set planning distance from the current position of the moving body when performing path planning for the moving body at a certain period.

[0058] In some embodiments, for example, the planned distance can be a preset distance (i.e., a forward obstacle avoidance distance) along the moving body's forward direction (i.e., the positive direction of the longitudinal axis of the road coordinate system), or can be a preset distance (i.e., a backward obstacle avoidance distance) along the reverse direction of the moving body's forward direction (i.e., the negative direction of the longitudinal axis of the road coordinate system). The reason for considering the backward obstacle avoidance distance is that when going around the obstacle, it does not turn immediately after (the tail of the moving body) passes the obstacle (front), but moves forward a certain distance to ensure the safety of the detour. The planned distance can be set to 40 meters, 50 meters, or 60 meters, etc., and the forward obstacle avoidance distance and the backward obstacle avoidance distance can be set to be equal or unequal. For example, the forward obstacle avoidance distance and the backward obstacle avoidance distance can both be set to 50 meters, or the forward obstacle avoidance distance can be set to 45 meters, and the backward obstacle avoidance distance can be set to 55 meters, and so on.

[0059] In step S210, based on the current coordinates of the moving body, reference obstacles within the planning range corresponding to the planning distance are determined from the multiple obstacles according to the road edge line and the boundary point coordinates of the multiple obstacles. According to the relationship between the boundary point coordinates of the obstacle and the road edge line, obstacles that will not affect the driving of the moving body can be filtered out from the multiple obstacles, and only the remaining reference obstacles are considered. When generating the local reference line for obstacle avoidance, the filtered obstacles are not considered to improve the calculation efficiency.

[0060] In some embodiments, for example, obstacles outside the planned range corresponding to the planned distance may be excluded according to the coordinates of the positive boundary point on the longitudinal axis and the negative boundary point on the longitudinal axis of the obstacle. Figure 6 .

[0061] In some embodiments, for example, obstacles that are far from the moving object's route (not blocking the road) and obstacles that cannot be bypassed can be eliminated based on the obstacle's horizontal axis positive boundary point coordinates and horizontal axis negative boundary point coordinates, horizontal axis positive minimum road width and horizontal axis negative minimum road width. Figure 7 .

[0062] In some embodiments, for example, obstacles other than the distance between the current position of the moving body and the destination along the longitudinal axis may also be eliminated. Figure 8 .

[0063] In step S212, a local reference line of the moving body within the planned distance is obtained according to the current reference line and the coordinates of the boundary points of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line. The width w and obstacle avoidance distance db of the moving body can be obtained, and the local reference line is obtained as a line with a fixed preset reference distance from the edge of the road according to the current reference line, the coordinates of the boundary points of the reference obstacle, the width of the moving body and the obstacle avoidance distance. It is expected that the moving body moves along the reference line, and the coordinates of the reference line can be obtained according to the positions of the coordinate axes specified by the road coordinate system, the feasible width of the moving body and the preset reference distance. After the coordinates of the local reference line for obstacle avoidance are calculated, the expected coordinates of the moving body can be obtained according to the coordinates of the local reference line. When the relationship between the speed, acceleration and time of the moving body is obtained according to the real-time coordinates, real-time speed and acceleration, and expected speed and acceleration of the moving body in the road coordinate system, the path planning of the moving body is performed.

[0064] In some embodiments, for example, the number of reference obstacles is multiple, the road edge line includes the reference edge line (for example, the reference edge line is the right edge line of the road when driving on the right), and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates l end , for each reference obstacle among multiple reference obstacles, add the coordinates of the positive boundary point of the horizontal axis of the reference obstacle to half of the width w of the moving body and the obstacle avoidance distance to obtain the obstacle avoidance reference line of each reference obstacle, and then select the reference line with the farthest distance from the reference edge line among the current reference line and the obstacle avoidance reference lines of each reference obstacle as the local reference line. That is, the local reference line l1(t) can be expressed by the following formula:

[0065] l1(t)=max(l(t),l end +0.5*w+d b ) (1)

[0066] In some embodiments, for example, the maximum lateral boundary component l may be obtained according to the boundary point coordinates of a plurality of reference obstacles. end，max, the maximum lateral boundary component is the maximum value of the components of the positive boundary point coordinates of the horizontal axis in the road coordinate system among multiple reference obstacles, and then the maximum lateral boundary component is added to half of the width of the moving body and the obstacle avoidance distance to obtain the obstacle avoidance reference line within the planning distance, and then the reference line with a longer distance from the reference edge line among the current reference line and the obstacle avoidance reference line within the planning distance is selected as the local reference line, that is, the local reference line l2(t) can be expressed by the following formula:

[0067] l2(t)=max(l(t),l end，max +0.5*w+d b ) (2).

[0068] The path planning method provided by the embodiments of the present disclosure determines a reference obstacle within a planning range corresponding to a planning distance for path planning of a moving body from among multiple obstacles according to a road edge line in a road coordinate system and boundary point coordinates of multiple obstacles, obtains a local reference line of the moving body within the planning distance according to the current reference line of the moving body in the road coordinate system and the boundary point coordinates of the reference obstacle, plans the path of the moving body according to the current coordinates of the moving body in the road coordinate system and the local reference line, and can adaptively generate a local reference line in a Frenet coordinate system, so that a more reasonable path can be planned for the moving body when it needs to bypass multiple obstacles, solves the technical problem that the reference line used for path planning of a logistics delivery vehicle cannot be adaptively adjusted according to roadside obstacles, and improves the working efficiency of the moving body.

[0069] Figure 3 A schematic diagram of coordinate system conversion in an embodiment of the present disclosure is shown. Figure 3 As shown, XMY is the Cartesian coordinate system, SOL is the Frenet coordinate system, OS is the longitudinal axis of the Frenet coordinate system, and the positive direction of the longitudinal axis is the direction in which the angle between the straight line OS and the moving direction of the moving body is smaller (such as Figure 3 OL is the horizontal axis of the Frenet coordinate system, and its positive direction is to the left. Figure 3 The road is in an ideal straight state, and the center line of the road is a straight line, so the center line of the road is the longitudinal axis OS. When the center line of the road is a curve, the tangent vector of the center line of the road is the longitudinal axis OS. The center line of the road is composed of a series of discrete points. If the coordinates of the position of the moving body in the Cartesian coordinate system are p(x p ,y p ), then we can find the two discrete points r(x r ,y r ) and e(x e y e ). If the coordinates of point r in the Frenet coordinate system are (s r , 0), the coordinates of point e in the Frenet coordinate system are (se , 0), then the coordinates of point p in the Frenet coordinate system can be derived (s p , l p ) and its coordinates in the Cartesian coordinate system (x p ,y p )

[0070]

[0071] In the formula, is a vector starting from point p and ending at point r, is a vector with point e as the starting point and point r as the end point, δ is the length of the line segment pr and the vector With vector The product of the cosine of the angle between, λ is the ratio of the length of line segment pr to the length of line segment re and the vector With vector The product of the cosine values ​​of the angles between δ and δ. Since the line segment corresponding to δ is the same as the line segment Or (whose length is s e ) is the projection of the point ray Op on the OS axis (its length is s p ), so it can be deduced that s in formula (2) p The expression of p For vector With vector is the height of the parallelogram of adjacent sides, so according to the area formula of the parallelogram, we can deduce that (2) p expression.

[0072] According to the coordinate conversion method between the road coordinate system and the Cartesian coordinate system provided in the embodiment of the present disclosure, by selecting two discrete conversion reference points on the coordinate axis of the road coordinate system, i.e., the road centerline, coordinate conversion is performed according to the geometric relationship, thereby obtaining the coordinates of the moving object in the road coordinate system. This method is applicable to the case where the road centerline is a straight line or a curve, and has strong applicability.

[0073] Figure 4 A schematic diagram of the coordinates of obstacle boundary points is shown in FIG. Figure 4 As shown, the obstacle can be, for example, a quadrilateral, whose four vertices have coordinates in the Frenet coordinate system of (s1, l1), (s2, l2), (s3, l3) and (s4, l4), respectively. The four vertices are projected toward the S axis and the L axis respectively to determine the boundary point coordinates of the obstacle (s start ,s end , l start , l end ),in:

[0074]

[0075] Where i is any positive integer between 1 and 4. It can be seen from the generation rules of obstacle boundary point coordinates in the Frenet coordinate system that it can better describe the distribution of obstacle polygons on the road compared with the Cartesian coordinate system.

[0076] Figure 5 A schematic diagram of a road scene is shown in FIG. Figure 5 As shown in the figure, the two edges (curb) of the road are on both sides of the center line of the road (vertical axis OS), and there are two obstacles on the right side of the road: obstacle 1 (obj1) and obstacle 2 (obj2). The coordinates of the projection point of the left edge line of the road on the horizontal axis OL are (0, l lefft ), the coordinates of the projection point of the right edge line of the road on the horizontal axis OL are (0, l right ).

[0077] Figure 6 FIG. 1 is a flow chart of an obstacle filtering method according to an exemplary embodiment. Figure 6 The method shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system.

[0078] refer to Figure 6 , the method 60 provided in the embodiment of the present disclosure may include the following steps.

[0079] In step S602, the forward obstacle avoidance distance and the backward obstacle avoidance distance are obtained. The forward obstacle avoidance distance can be expressed as d f , the backward obstacle avoidance distance is expressed as d r .

[0080] In step S604, the coordinates of the vertical axis positive boundary points and the vertical axis negative boundary points of the plurality of obstacles are obtained. Figure 4 , the coordinates of the positive boundary point on the longitudinal axis of the obstacle can be expressed as s end , the coordinates of the negative boundary point on the longitudinal axis of the obstacle are expressed as s start .

[0081] In step S606, the current vertical coordinate of the moving object is obtained. The current vertical coordinate of the moving object can be marked as s0.

[0082] In step S608, multiple obstacles are stored in an obstacle set. The coordinates of the positive boundary points of the longitudinal axis of each obstacle in the obstacle set can be obtained as s end and the coordinates of the negative boundary point on the longitudinal axis of the obstacle s start .

[0083] In step S610, obstacles that meet the first filtering condition are excluded from the obstacle set, and the obstacle set is updated. The first filtering condition is that the position is outside the planning range. The position outside the planning range means that the coordinates of the positive boundary point on the longitudinal axis are less than the difference between the current longitudinal coordinate of the moving body and the backward obstacle avoidance distance, or the coordinates of the negative boundary point on the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the forward obstacle avoidance distance. That is, for each obstacle in the obstacle set, if it meets s end <s0-d r ||s start >s0+d f Obstacles are those outside the planning scope and can be ignored when generating local reference lines.

[0084] In step S612, a reference obstacle is determined from the updated obstacle set. The updated obstacle set may be further filtered by other filtering conditions to obtain the remaining reference obstacles. For example, the horizontal boundary point coordinates l may be selected. end , l start Obstacles within a certain range.

[0085] According to the obstacle filtering method provided in the embodiment of the present disclosure, by filtering out obstacles outside the planning range composed of forward obstacle avoidance distance and backward obstacle avoidance distance before generating a local reference line according to the obstacle boundary, the calculation amount of generating the local reference line can be reduced and the efficiency of path planning can be improved.

[0086] Figure 7 is based on Figure 6 FIG. 1 is a flowchart of another obstacle filtering method. Figure 7 The method shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system. Figure 7 For Figure 6 On this basis, the obstacles in the obstacle set are further filtered.

[0087] refer to Figure 7 , the method 70 provided in the embodiment of the present disclosure may include the following steps.

[0088] In step S702, the coordinates of the positive boundary points of the horizontal axis and the negative boundary points of the horizontal axis of the multiple obstacles are calculated. Figure 4 , the coordinate of the positive boundary point of the horizontal axis of the obstacle can be marked as l end , mark the negative boundary point of the obstacle's horizontal axis as l start .

[0089] In step S704, the minimum road width in the positive direction of the horizontal axis and the minimum road width in the negative direction of the horizontal axis are obtained according to the road center line and the road edge line. Figure 5 , the minimum road width in the positive direction of the horizontal axis can be recorded as l right, the minimum road width in the negative direction of the horizontal axis is recorded as l left .

[0090] In step S706, obstacles that meet the second filtering condition are excluded from the obstacle set, and the obstacle set is updated. The second filtering condition is that the coordinates of the negative boundary point on the horizontal axis are greater than the sum of the horizontal coordinates of the current reference line of the moving body and the width of the moving body, or the coordinates of the positive boundary point on the horizontal axis are less than the inverse of the minimum road width on the negative axis, or the coordinates of the positive boundary point on the horizontal axis are greater than the difference between the minimum road width on the positive axis and the width of the moving body. If the width of the moving body is denoted as w, for each obstacle in the obstacle set, if l start >l(t)+w or l end <-l right or end >l left -w obstacles are those outside the planning scope and can be ignored when generating local reference lines. For example, taking the case where the moving body passes on the right side and bypasses the left side of the obstacle, obstacles one width to the left of the current reference line of the moving body, obstacles outside the right edge of the road, and obstacles less than one width away from the left edge of the road will not be considered for bypassing (for example, for dynamic obstacles, following the vehicle can be considered, and for static obstacles, stopping and prompting can be performed).

[0091] According to the obstacle filtering method provided by the embodiment of the present disclosure, by filtering out obstacles that do not block the road laterally and cannot be circumvented before generating local reference lines according to the obstacle boundaries, the calculation amount of generating local reference lines is further reduced and the efficiency of path planning is improved.

[0092] Figure 8 is based on Figure 6 FIG. 1 is a flowchart of another obstacle filtering method. Figure 8 The method shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system. Figure 8 For Figure 6 On this basis, the obstacles in the obstacle set are further filtered.

[0093] refer to Figure 8 , the method 80 provided in the embodiment of the present disclosure may include the following steps.

[0094] In step S802, the distance between the current position of the moving body and the destination along the longitudinal axis is obtained according to the current coordinates of the moving body. The distance between the current position of the moving body and the destination along the longitudinal axis obtained from the current coordinates of the moving body can be recorded as d.

[0095] In step S804, obstacles that meet the third filtering condition are excluded from the obstacle set, and the obstacle set is updated. The third filtering condition is that the coordinate of the negative boundary point on the longitudinal axis is greater than the sum of the current longitudinal coordinate of the moving body and the distance between the current position of the moving body and the destination along the longitudinal axis. If the width of the moving body is recorded as w, for each obstacle in the obstacle set, if it meets s start Obstacles greater than s0+d may be ignored when generating the local reference line, that is, obstacles that are not on the target driving section are not considered for bypassing.

[0096] According to the obstacle filtering method provided by the embodiment of the present disclosure, by filtering out obstacles that are not in the target driving section before generating the local reference line according to the obstacle boundary, the calculation amount of generating the local reference line is further reduced and the efficiency of path planning is improved.

[0097] Fig. 9 According to an embodiment of the present disclosure, a schematic diagram of a process of generating a local reference line is shown. The vertical coordinate of the unmanned logistics delivery vehicle in the Frenet coordinate system is s0, the remaining mileage distance to the destination is d, and the maximum distance to the obstacle is d. f , consider the maximum distance of the obstacle backward to be d r , the width of the vehicle is w, the current reference line coordinate is l(t), the adaptively adjusted local reference line coordinate is l1(t), and the minimum distance between the reference line and the obstacle is d b , the minimum width of the left side of the road in the Frenet coordinate system is l left , the minimum width of the right side of the road is l right .like Fig. 9 As shown, firstly, all static obstacles from the perception module of the unmanned logistics delivery vehicle are obtained, and the boundary point coordinates of each static obstacle are calculated, and the obstacles with the boundary point coordinate information are stored in the set V (S902); all obstacles b in the set V are traversed. j (S904), where j is a positive integer greater than 0 and less than or equal to the total number of obstacles in the set V. If b j Satisfaction start >s0+d holds, then filter out the obstacle and update the set V (continue) (S906); if b j Satisfaction end <s0-d r ||s start >s0+d f If b is true, continue (S906); j Satisfy start >l(t)+w or l end <-l right or end >lleft -w, then continue (S906); calculate the local reference line l1(t) (S908), l1(t) = max(l(t), l end +0.5*w+d b ).

[0098] Fig.10 FIG. 1 is a block diagram of a path planning device according to an exemplary embodiment. Fig.10 The device shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system.

[0099] refer to Fig.10 The path planning device 100 provided in the embodiment of the present disclosure may include a current quantity acquisition module 1002, an obstacle boundary acquisition module 1004, an edge line acquisition module 1006, a planned distance acquisition module 1008, a reference obstacle determination module 1010 and a local path planning module 1012.

[0100] The current quantity acquisition module 1002 may be used to acquire the current coordinates and the current reference line of the moving object in the road coordinate system. The road coordinate system acquires the longitudinal axis according to the center line of the road.

[0101] The obstacle boundary acquisition module 1004 may be used to acquire the coordinates of boundary points of multiple obstacles.

[0102] The edge line acquisition module 1006 may be used to acquire the road edge line in the road coordinate system.

[0103] The planning distance acquisition module 1008 may be used to acquire the planning distance for path planning of the moving object.

[0104] The reference obstacle determination module 1010 may be used to determine a reference obstacle within a planned range corresponding to a planned distance from among multiple obstacles based on the current coordinates of the moving body and according to the road edge line and the boundary point coordinates of the multiple obstacles.

[0105] The local path planning module 1012 may be used to obtain a local reference line of the moving body within a planned distance according to the current reference line and the coordinates of the boundary points of the reference obstacles, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line.

[0106] Fig.11 FIG. 1 is a block diagram of a path planning device according to an exemplary embodiment. Fig.11 The device shown can be applied to the server side of the above system, for example, and can also be applied to the terminal device of the above system.

[0107] refer to Fig.11The path planning device 110 provided in the embodiment of the present disclosure may include a current quantity acquisition module 1102, an obstacle boundary acquisition module 1104, an edge line acquisition module 1106, a planned distance acquisition module 1108, a road width acquisition module 1109, a reference obstacle determination module 1110, a parameter setting module 1111 and a local path planning module 1112, wherein the reference obstacle determination module 1110 may include an obstacle set acquisition module 11102, a first obstacle filtering module 11104, a second obstacle filtering module 11106, a target distance acquisition module 11107, and a third obstacle filtering module 11108, and the local path planning module 1112 may include: a first obstacle avoidance reference line acquisition module 11122, a first local reference line determination module 11124, a lateral boundary acquisition module 11125, a second obstacle avoidance reference line acquisition module 11126, and a second local reference line determination module 11128.

[0108] The current quantity acquisition module 1102 can be used to acquire the current coordinates and current reference line of the moving body in the road coordinate system, and the road coordinate system obtains the longitudinal axis according to the center line of the road. The current coordinates of the moving body include the current longitudinal coordinates of the moving body.

[0109] The obstacle boundary acquisition module 1104 can be used to acquire boundary point coordinates of multiple obstacles, including the vertical axis positive boundary point coordinates and the vertical axis negative boundary point coordinates, the horizontal axis positive boundary point coordinates and the horizontal axis negative boundary point coordinates of the multiple obstacles.

[0110] The edge line acquisition module 1106 may be used to acquire the road edge line in the road coordinate system.

[0111] The planned distance acquisition module 1108 may be used to acquire the planned distance for path planning of the moving object. The planned distance includes a forward obstacle avoidance distance and a backward obstacle avoidance distance.

[0112] The road width obtaining module 1109 may be used to obtain the minimum road width in the positive direction of the horizontal axis and the minimum road width in the negative direction of the horizontal axis according to the road center line and the road edge line.

[0113] The reference obstacle determination module 1110 may be used to determine a reference obstacle within a planned range corresponding to a planned distance from among multiple obstacles based on the current coordinates of the moving body and according to the road edge line and the boundary point coordinates of the multiple obstacles.

[0114] The reference obstacle determination module 1110 may also be configured to determine a reference obstacle from the updated obstacle set.

[0115] The obstacle set obtaining module 11102 may be used to store multiple obstacles into an obstacle set.

[0116] The first obstacle filtering module 11104 can be used to exclude obstacles that meet the first filtering condition from the obstacle set and update the obstacle set. The first filtering condition is that the position is outside the planning range, and the position is outside the planning range when the coordinates of the positive boundary point of the longitudinal axis are less than the difference between the current longitudinal coordinate of the moving body and the backward obstacle avoidance distance, or the coordinates of the negative boundary point of the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the forward obstacle avoidance distance.

[0117] The second obstacle filtering module 11106 can be used to exclude obstacles that meet the second filtering condition from the obstacle set and update the obstacle set, wherein the second filtering condition is that the coordinates of the negative boundary point on the horizontal axis are greater than the sum of the horizontal coordinates of the current reference line of the moving body and the width of the moving body, or the coordinates of the positive boundary point on the horizontal axis are less than the negative number of the minimum road width on the negative axis, or the coordinates of the positive boundary point on the horizontal axis are greater than the difference between the minimum road width on the positive axis and the width of the moving body.

[0118] The target distance obtaining module 11107 may be used to obtain the distance along the longitudinal axis between the current position of the moving body and the destination according to the current coordinates of the moving body.

[0119] The third obstacle filtering module 11108 can be used to exclude obstacles that meet the third filtering condition from the obstacle set and update the obstacle set, wherein the third filtering condition is that the coordinates of the negative boundary point on the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the distance between the current position of the moving body and the destination along the longitudinal axis.

[0120] The parameter setting module 1111 may be used to obtain the width and obstacle avoidance distance of the moving object.

[0121] The local path planning module 1112 can be used to obtain a local reference line of the moving body within the planning distance according to the current reference line and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line. The number of reference obstacles is multiple, the road edge line includes the reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle.

[0122] The first obstacle avoidance reference line obtaining module 11122 may be used to obtain the obstacle avoidance reference line of each reference obstacle among multiple reference obstacles by adding the coordinates of the positive boundary point of the horizontal axis of the reference obstacle to half the width of the moving body and the obstacle avoidance distance.

[0123] The first local reference line determination module 11124 may be used to select a reference line that is farthest from the reference edge line among the current reference line and the obstacle avoidance reference lines of each reference obstacle as the local reference line.

[0124] The lateral boundary acquisition module 11125 can be used to obtain the maximum lateral boundary component according to the boundary point coordinates of multiple reference obstacles. The maximum lateral boundary component is the maximum value of the components of the horizontal axis of the positive boundary point coordinates of the multiple reference obstacles in the road coordinate system.

[0125] The second obstacle avoidance reference line obtaining module 11126 may be used to add the maximum lateral boundary component to half of the width of the moving object and the obstacle avoidance distance to obtain an obstacle avoidance reference line within the planned distance.

[0126] The second local reference line determination module 11128 may be used to select a reference line that is farther from the reference edge line from among the obstacle avoidance reference lines within the planned distance from the current reference line as a local reference line.

[0127] The local path planning module 1112 may also be used to obtain a local reference line according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving body, and the obstacle avoidance distance.

[0128] The specific implementation of each module in the device provided by the embodiment of the present disclosure can refer to the content of the above method, which will not be repeated here.

[0129] Fig.12 The following is a schematic diagram showing the structure of an electronic device in an embodiment of the present disclosure. It should be noted that: Fig.12 The device shown is only an example of a computer system, which should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0130] like Fig.12 As shown, the device 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage part 1208 into a random access memory (RAM) 1203. In the RAM 1203, various programs and data required for the operation of the device 1200 are also stored. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0131] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1212 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1212 as needed, so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0132] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 1209, and / or installed from a removable medium 1211. When the computer program is executed by a central processing unit (CPU) 1201, the above-mentioned functions defined in the system of the present disclosure are executed.

[0133] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0134] The flow charts and block diagrams in the accompanying drawings illustrate the possible 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 flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order 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 flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0135] The modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The modules described may also be set in a processor, for example, may be described as: a processor including a current quantity acquisition module, an obstacle boundary acquisition module, an edge line acquisition module, a planned distance acquisition module, a reference obstacle determination module and a local path planning module. The names of these modules do not, in some cases, constitute a limitation on the modules themselves, for example, the current quantity acquisition module may also be described as a "module for acquiring the current position data and path planning data of the connected mobile body".

[0136] As another aspect, the present disclosure further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0137] The present coordinates and the present reference line of the moving body in the road coordinate system are obtained, and the longitudinal axis of the moving body is obtained according to the center line of the road; the coordinates of the boundary points of the plurality of obstacles are obtained; the edge line of the road in the road coordinate system is obtained; the planning distance for path planning of the moving body is obtained; based on the present coordinates of the moving body, a reference obstacle within the planning range corresponding to the planning distance is determined from the plurality of obstacles according to the edge line of the road and the coordinates of the boundary points of the plurality of obstacles; a local reference line of the moving body within the planning distance is obtained according to the current reference line and the coordinates of the boundary points of the reference obstacles, so as to plan the path of the moving body according to the present coordinates of the moving body and the local reference line.

[0138] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A path planning method, characterized in that: include: Obtaining the current coordinates and the current reference line of the moving body in a road coordinate system, wherein the road coordinate system obtains the longitudinal axis according to the center line of the road; Acquire boundary point coordinates of a plurality of obstacles, wherein the boundary point coordinates of the plurality of obstacles include boundary point coordinates of positive directions of the horizontal axes and boundary point coordinates of negative directions of the horizontal axes of the plurality of obstacles; Acquire a road edge line in the road coordinate system; Acquire a planned distance for path planning of the mobile object; Obtaining the minimum road width in the positive direction of the horizontal axis and the minimum road width in the negative direction of the horizontal axis according to the road center line and the road edge line; Based on the current coordinates of the moving body, determining a reference obstacle within the planning range corresponding to the planning distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles; Obtaining a local reference line of the moving body within the planned distance according to the current reference line and the coordinates of the boundary points of the reference obstacle, so as to plan a path of the moving body according to the current coordinates of the moving body and the local reference line, wherein the moving body passes along the negative side of the horizontal axis of the road coordinate system, and the local reference line bypasses the reference obstacle along the positive side of the horizontal axis of the road coordinate system; The determining, based on the current coordinates of the moving body, a reference obstacle within the planning range corresponding to the planning distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles comprises: Storing the plurality of obstacles into an obstacle set; The obstacles satisfying the second filtering condition are excluded from the obstacle set, and the obstacle set is updated, wherein the second filtering condition is that the coordinates of the negative boundary point on the horizontal axis are greater than the sum of the horizontal coordinates of the current reference line of the moving body and the width of the moving body, or The coordinates of the boundary point on the positive side of the horizontal axis are less than the inverse of the minimum road width on the negative side of the horizontal axis, or The coordinate of the boundary point in the positive direction of the horizontal axis is greater than the difference between the minimum road width in the positive direction of the horizontal axis and the width of the moving body; Determining the reference obstacle from the updated obstacle set; Among them, for an obstacle that meets the second filtering condition that the coordinates of the positive boundary point on the horizontal axis are greater than the difference between the minimum road width on the positive axis and the width of the moving body, if it is a dynamic obstacle, the speed of the moving body is adjusted so that the moving body follows the dynamic obstacle; if it is a static obstacle, the moving body is controlled to stop and a prompt is given for processing.

2. The method according to claim 1, characterized in that: Also includes: Obtaining the width and obstacle avoidance distance of the moving object; The step of obtaining the local reference line of the moving object within the planned distance according to the current reference line and the boundary point coordinates of the reference obstacle comprises: The local reference line is obtained according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving object and the obstacle avoidance distance.

3. The method according to claim 2, characterized in that The number of the reference obstacles is multiple, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle; The obtaining of the local reference line according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving object and the obstacle avoidance distance comprises: For each of the plurality of reference obstacles, adding the coordinates of the positive boundary point of the horizontal axis of the reference obstacle, half the width of the moving object and the obstacle avoidance distance to obtain an obstacle avoidance reference line of each reference obstacle; The reference line which is farthest from the reference edge line among the current reference line and the obstacle avoidance reference lines of each reference obstacle is selected as the local reference line.

4. The method according to claim 2, characterized in that: The number of the reference obstacles is multiple, the road edge line includes a reference edge line, and the boundary point coordinates of the reference obstacle include the horizontal axis positive boundary point coordinates of the reference obstacle; The obtaining of the local reference line according to the current reference line, the boundary point coordinates of the reference obstacle, the width of the moving object and the obstacle avoidance distance comprises: Obtaining a maximum lateral boundary component according to the boundary point coordinates of the plurality of reference obstacles, wherein the maximum lateral boundary component is a maximum value of the components of the coordinates of the positive boundary points of the transverse axes among the plurality of reference obstacles in the road coordinate system; Adding the maximum lateral boundary component, half of the width of the moving object and the obstacle avoidance distance to obtain an obstacle avoidance reference line within the planned distance; A reference line which is farther from the reference edge line among the current reference line and the obstacle avoidance reference lines within the planned distance is selected as the local reference line.

5. The method according to any one of claims 2 to 4, characterized in that The planned distance includes a forward obstacle avoidance distance and a backward obstacle avoidance distance, the boundary point coordinates of the plurality of obstacles include the longitudinal axis positive boundary point coordinates and the longitudinal axis negative boundary point coordinates of the plurality of obstacles, and the current coordinates of the moving body include the current longitudinal coordinates of the moving body; The determining, based on the current coordinates of the moving body, a reference obstacle within the planning range corresponding to the planning distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles also includes: Excluding obstacles that meet the first filtering condition from the obstacle set, and updating the obstacle set; The first filtering condition is that the position is outside the planning range, and the position outside the planning range is that the coordinates of the positive boundary point of the longitudinal axis are less than the difference between the current longitudinal coordinate of the moving body and the backward obstacle avoidance distance, or The coordinate of the negative boundary point of the longitudinal axis is greater than the sum of the current longitudinal coordinate of the moving object and the forward obstacle avoidance distance.

6. The method according to claim 5, characterized in that The determining, based on the current coordinates of the moving body, a reference obstacle within the planning range corresponding to the planning distance from the plurality of obstacles according to the road edge line and the boundary point coordinates of the plurality of obstacles also includes: Obtaining the distance between the current position of the moving body and the destination along the longitudinal axis according to the current coordinates of the moving body; Obstacles satisfying a third filtering condition are excluded from the obstacle set, and the obstacle set is updated, wherein the third filtering condition is that the coordinates of the negative boundary point on the longitudinal axis are greater than the sum of the current longitudinal coordinate of the moving body and the distance between the current position of the moving body and the destination along the longitudinal axis.

7. A path planning device, characterized in that: include: A current quantity acquisition module, used to acquire the current coordinates and current reference line of the moving body in a road coordinate system, wherein the road coordinate system obtains the longitudinal axis according to the center line of the road; An obstacle boundary acquisition module, used to acquire boundary point coordinates of a plurality of obstacles, wherein the boundary point coordinates of the plurality of obstacles include the horizontal axis positive boundary point coordinates and the horizontal axis negative boundary point coordinates of the plurality of obstacles; An edge line acquisition module, used to acquire the road edge line in the road coordinate system; A planning distance acquisition module, used to acquire a planning distance for path planning of the mobile object; A road width obtaining module, used for obtaining the minimum road width in the positive direction of the horizontal axis and the minimum road width in the negative direction of the horizontal axis according to the road center line and the road edge line; A reference obstacle determination module, configured to determine, based on the current coordinates of the moving body and according to the road edge line and the boundary point coordinates of the multiple obstacles, a reference obstacle within a planning range corresponding to the planning distance from the multiple obstacles; An obstacle set obtaining module, used for storing the plurality of obstacles into an obstacle set; A second obstacle filtering module is used to exclude obstacles that meet a second filtering condition from the obstacle set and update the obstacle set, wherein the second filtering condition is that the coordinates of the boundary point in the negative direction of the horizontal axis are greater than the sum of the horizontal coordinates of the current reference line of the moving body and the width of the moving body, or the coordinates of the boundary point in the positive direction of the horizontal axis are less than the negative number of the minimum road width in the negative direction of the horizontal axis, or the coordinates of the boundary point in the positive direction of the horizontal axis are greater than the difference between the minimum road width in the positive direction of the horizontal axis and the width of the moving body; The reference obstacle determination module is further used to determine the reference obstacle from the updated obstacle set; A local path planning module, used for obtaining a local reference line of the moving body within the planned distance according to the current reference line and the boundary point coordinates of the reference obstacle, so as to plan the path of the moving body according to the current coordinates of the moving body and the local reference line, wherein the moving body passes along the negative side of the horizontal axis of the road coordinate system, and the path of the moving body is planned to bypass the obstacle along the positive side of the horizontal axis of the road coordinate system; The local path planning module is also used for, for an obstacle that satisfies the second filtering condition and whose coordinates of the positive boundary point on the horizontal axis are greater than the difference between the minimum positive road width on the horizontal axis and the width of the moving body, if the obstacle is a dynamic obstacle, adjusting the speed of the moving body so that the moving body follows the dynamic obstacle; if the obstacle is a static obstacle, controlling the moving body to stop and prompting processing.

8. A device comprising: A memory, a processor, and executable instructions stored in the memory and executable in the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the executable instructions.

9. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the executable instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images