CN115060279B - Path planning method, path planning device, electronic equipment and computer readable medium - Google Patents

Abstract

The present invention discloses a path planning method, device, electronic device and computer-readable medium, and relates to the field of autonomous driving technology. The method includes: determining information about obstacles between the current position of a vehicle and the destination of the vehicle; generating a grid area around the destination, and determining the first cost of each grid according to a preset first rule and information about obstacles; determining multiple alternative destinations around the destination, and determining the second cost of each alternative destination according to a preset second rule and the first cost of the grid; judging in order from small to large the trajectory curve between the alternative destination and the current position of the vehicle whether it meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the driving path of the vehicle. The method can ensure driving safety while ensuring accurate parking at the station, with a small amount of calculation, and ensures the real-time nature of path planning.

Description

Path planning method, device, electronic device and computer readable medium

Technical Field

The present invention relates to the field of autonomous driving technology, and in particular to a path planning method, device, electronic device and computer-readable medium.

Background technique

In the autonomous driving scenario, unmanned vehicle parking stations are a common task scenario, especially in the field of unmanned taxis and unmanned buses. In the autonomous driving scenario, it is necessary to plan the driving path for the unmanned vehicle based on the environmental information. In related technologies, path planning can be divided into global path planning and local path planning according to the degree of understanding of environmental information. Global path planning requires the mastery of all environmental information and path planning based on all information in the environmental map; local path planning only requires sensors to collect environmental information in real time, understand environmental map information, and then determine the location of the map and its local obstacle distribution, so that the optimal path from the current node to a sub-target node can be selected.

Summary of the invention

In view of this, the embodiments of the present invention provide a path planning method, device, electronic device and computer-readable medium, which can ensure driving safety while ensuring the smooth completion of the docking task, effectively reduce the amount of calculation, and ensure the real-time nature of path planning.

To achieve the above object, according to one aspect of an embodiment of the present invention, a path planning method is provided, comprising:

Determining information about obstacles between a current location of a vehicle and a destination of the vehicle;

Generate a grid area around the destination, and determine a first cost of each grid in the grid area according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid;

Determine a plurality of candidate destinations around the destination, and determine a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid;

In order of the second costs from small to large, determine whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and use the trajectory curve that meets the preset conditions as the vehicle's driving path.

Optionally, generating a grid area around the destination includes: determining a trajectory curve between the current position of the vehicle and the destination of the vehicle; detecting, based on information about the obstacle, whether the trajectory curve collides with the obstacle; if so, generating a grid area around the destination; if not, using the trajectory curve between the current position of the vehicle and the destination of the vehicle as the driving path of the vehicle.

Optionally, the information of the obstacle includes location information of the obstacle;

Determine the first cost of each grid in the grid area according to a preset first rule and the information of the obstacle, including: for each grid, determine whether the grid collides with the obstacle according to the information of the obstacle; if so, determine the first cost of the grid to be a preset value; if not, determine the first distance between the grid and the obstacle according to the position information of the obstacle; determine the second distance between the grid and the destination; and determine the first cost of the grid according to the first distance and the second distance.

Optionally, determining the first cost of the grid based on the first distance and the second distance includes: when there are multiple obstacles, determining the minimum first distance from multiple first distances between the grid and the multiple obstacles; and determining the first cost of the grid based on the minimum first distance and the second distance.

Optionally, a plurality of candidate destinations are determined around the destination, including: generating a target graph centered on the destination, wherein a range covered by the target graph overlaps with a range covered by the grid area; sampling on the target graph, and using the sampling points as the candidate destinations.

Optionally, the second cost of each of the alternative destinations is determined based on a preset second rule and the first cost of the grid, including: for each alternative destination, determining the first cost of the grid where the alternative destination is located; determining the third distance between the alternative destination and the current position of the vehicle; and determining the second cost of the alternative destination based on the first cost and the third distance.

Optionally, the method further includes: before determining whether a trajectory curve between the alternative destination and the current position of the vehicle satisfies a preset condition, determining invalid alternative destinations among the multiple alternative destinations and screening out the invalid alternative destinations.

Optionally, determining an invalid alternative destination among the multiple alternative destinations includes: for each alternative destination, determining whether a grid where the alternative destination is located collides with the obstacle; if so, determining that the alternative destination is an invalid alternative destination.

Optionally, the method also includes: if the trajectory curves between all the alternative destinations and the current position of the vehicle do not meet the preset conditions, a new alternative destination is determined, and whether the trajectory curve between the new alternative destination and the current position of the vehicle meets the preset conditions in order of the second costs of the new alternative destinations from small to large.

Optionally, the method further includes: determining whether an obstacle moves while the autonomous driving vehicle is driving along the driving path; if so, replanning the driving path of the vehicle based on information about the moved obstacle.

To achieve the above object, according to one aspect of an embodiment of the present invention, a path planning device is provided, comprising:

An obstacle determination module, used to determine information of obstacles between the current position of the vehicle and the destination of the vehicle;

A first calculation module is used to generate a grid area around the destination, and determine a first cost of each grid in the grid area according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid;

A second calculation module, used for determining a plurality of candidate destinations around the destination, and determining a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid;

The path determination module is used to determine whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions in the order of the second cost from small to large, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the vehicle's driving path.

Optionally, the first calculation module is also used to: determine a trajectory curve between the current position of the vehicle and the destination of the vehicle; detect whether the trajectory curve collides with the obstacle based on the information of the obstacle; if so, generate a grid area around the destination; if not, use the trajectory curve between the current position of the vehicle and the destination of the vehicle as the driving path of the vehicle.

Optionally, the information of the obstacle includes location information of the obstacle;

The first calculation module is also used to: for each grid, determine whether the grid collides with the obstacle based on the information of the obstacle; if so, determine the first cost of the grid to be a preset value; if not, determine the first distance between the grid and the obstacle based on the position information of the obstacle; determine the second distance between the grid and the destination; and determine the first cost of the grid based on the first distance and the second distance.

Optionally, the first calculation module is also used to: when there are multiple obstacles, determine a minimum first distance from multiple first distances between the grid and the multiple obstacles; and determine the first cost of the grid based on the minimum first distance and the second distance.

Optionally, the second calculation module is further used to: generate a target graphic centered on the destination, where a range covered by the target graphic overlaps with a range covered by the grid area; and perform sampling on the target graphic, using the sampling points as the candidate destinations.

Optionally, the second calculation module is also used to: determine, for each alternative destination, a first cost of the grid where the alternative destination is located; determine a third distance between the alternative destination and the current position of the vehicle; and determine a second cost of the alternative destination based on the first cost and the third distance.

Optionally, the device further comprises a screening module, which is used to: determine invalid alternative destinations among the multiple alternative destinations, and screen out the invalid alternative destinations.

Optionally, the screening module is further used to: for each candidate destination, determine whether the grid where the candidate destination is located collides with the obstacle; if so, determine that the candidate destination is an invalid candidate.

Optionally, the device also includes a retry module, which is used to: if the trajectory curves between all the alternative destinations and the current position of the vehicle do not meet the preset conditions, determine a new alternative destination, and judge whether the trajectory curve between the new alternative destination and the current position of the vehicle meets the preset conditions in order of the second costs of the new alternative destinations from small to large.

Optionally, the retry module is also used to: determine whether an obstacle moves while the autonomous driving vehicle is driving along the driving path; if so, replan the driving path of the vehicle based on information about the moved obstacle.

To achieve the above-mentioned purpose, according to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device 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 implement the path planning method of an embodiment of the present invention.

To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the path planning method of the embodiment of the present invention is implemented.

One embodiment of the above invention has the following advantages or beneficial effects:

A grid area is generated around a vehicle destination, and the first cost of each grid in the grid area is determined according to information about obstacles between the vehicle's current position and the destination and a preset first rule; wherein the first cost is used to indicate the feasibility of the grid, and the smaller the first cost, the higher the feasibility and the safer the driving, thereby determining the safe area and the dangerous area in the grid area; then multiple alternative destinations are determined around the destination, and the second cost of each alternative destination is determined according to a preset second rule and the first cost of the grid; according to the order of the second costs from small to large, it is judged in turn whether the trajectory curve between the alternative destination and the vehicle's current position meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the vehicle's driving path, thereby ensuring accurate parking at the station while ensuring driving safety, with less calculation and ensuring the real-time nature of path planning.

The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

FIG1 schematically shows a flow chart of a path planning method according to an embodiment of the present invention;

FIG2 is a schematic diagram showing a grid area in a path planning method according to an embodiment of the present invention;

FIG3 is a schematic diagram showing an alternative destination in a path planning method according to an embodiment of the present invention;

FIG4 schematically shows a flow chart of a path planning method according to another embodiment of the present invention;

FIG5 schematically shows a schematic diagram of the structure of a path planning device according to an embodiment of the present invention;

FIG6 schematically shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed ways

The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

FIG1 schematically shows a flow chart of a path planning method according to an embodiment of the present invention. The path planning method according to the embodiment of the present invention can be applied to a vehicle-mounted control unit of a vehicle or to a server. After determining the driving path of the vehicle, the server can send the driving path to the vehicle. As shown in FIG1 , the method includes:

Step 101: Determine information about obstacles between a current position of a vehicle and a destination of the vehicle.

In this embodiment, the destination of the vehicle can be determined according to the specific scenario. For example, the parking and picking-up task can obtain the task end point (i.e., the destination) on the map and send it to the vehicle through the cloud. The current position of the vehicle can be obtained from the positioning information of the vehicle-mounted combined navigation module pre-set on the vehicle. The information of the obstacle can be obtained through the vehicle-mounted sensor, such as a single/binocular camera, a fisheye camera, a millimeter-wave radar, an ultrasonic radar, a laser radar, etc. Obstacles can include pedestrians, objects on the road, and can also include construction sections, bumpy roads, etc., and the present invention is not limited here. The information of the obstacle may include, but is not limited to: the location of the obstacle, the state of the obstacle (e.g., stationary or moving), and the category of the obstacle (e.g., pedestrians, objects, construction sections, etc.). The information of the obstacle can also be obtained from the map. For example, if there is a construction section on the section where the destination is located, the information of the construction section can be obtained through the annotation information on the map. The vehicle in the embodiment of the present invention can be an autonomous driving vehicle (also known as an unmanned vehicle), such as an unmanned taxi, an unmanned bus, etc., and the present invention is not limited here.

Step 102: Generate a grid area around the destination, and determine a first cost of each grid in the grid area according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid.

Among them, the grid area generated around the destination can be a positive direction, a rectangle or a circle, etc., and the present invention is not limited here. As an example, as shown in Figure 2, the grid area is a square, and the grid within the grid area is also a square. In an embodiment of the present invention, the size of the grid area and the size of the grid can be flexibly set according to vehicle parameters, scene tasks and the environment of the destination, and are not limited here. As an example, in a parking and picking up scenario, the side length of the grid can be set to 0.5 meters to take into account both the speed and driving safety of the vehicle. After the grid area is generated, obstacles between the current position of the vehicle and the destination can be marked in the grid area.

After the grid area is generated, the first cost of each grid in the grid area is calculated. The first cost is used to indicate the feasibility of the grid. The lower the cost, the higher the feasibility and the more suitable it is for vehicle driving. If the grid collides with an obstacle, the grid is determined to be dangerous, and the first cost of the grid is set to a preset value, such as infinity. When judging whether the grid collides with an obstacle, the obstacle can be converted into a rectangle (the obstacle falls completely within the rectangle), and then the hyperplane partition theorem is used to determine whether the grid and the rectangle have overlapping parts. If the grid and the rectangle have overlapping parts, it is determined that the grid collides with the obstacle.

For the mesh that has not collided with the obstacle, its first cost can be determined according to the following process:

Determining a first distance between the grid and the obstacle according to the position information of the obstacle;

determining a second distance between the grid and the destination;

A first cost of the grid is determined according to the first distance and the second distance.

The first distance between the grid and the obstacle may be the distance between the center of the grid and the center of the obstacle. The smaller the first distance, the more dangerous it is for the vehicle to travel on this grid. The second distance between the grid and the destination may be the distance between the center of the grid and the destination. The smaller the second distance, the higher the efficiency. After determining the first distance and the second distance, the first cost of the grid may be calculated according to a preset cost function.

As an example, the preset cost function can be shown as the following formula (1):

cost_net = obstacle_distance - target_distance (1)

Among them, cost_net represents the first cost of the grid, obstacle_distance represents the first distance, and target_distance represents the second distance.

In an optional embodiment of the present invention, when calculating the first cost of the grid, a weight coefficient corresponding to the first distance and/or the second distance may be set, as shown in the following formula (2):

cost_net = k_obstacle*obstacle_distance-k_target*target_distance(2)

Among them, k_obstacle represents the weight coefficient corresponding to the first distance, and k_target represents the weight coefficient corresponding to the second distance. Since obstacle_distance and target_distance have the same unit, k_obstacle = k_target = 1 can be set by default, indicating that the obstacle and target have the same weight, and then adjusted according to the specific details of the task. For example, if you want to ensure safety as much as possible, you can reduce k_obstacle, and if you want to reach the end point as soon as possible, you can reduce k_target.

Step 103: Determine a plurality of candidate destinations around the destination, and determine a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid.

Among them, the alternative destination can be determined according to the following process:

Generate a target graphic centered on the destination, where a range covered by the target graphic overlaps with a range covered by the grid area;

Sampling is performed on the target graph, and the sampling points are used as the candidate destinations.

The target graphic centered on the destination may fall completely within the grid area or may fall partially within the grid area. The target graphic may be a circle, a square, a rectangle, etc., which is not limited in the present invention. In an optional embodiment, as shown in FIG3 , a circle may be generated with the destination as the center and the side length of the grid as the radius (assuming the side length of the grid is r). After generating a circle centered on the destination, uniform sampling may be performed on the circle, and the sampling points may be used as candidate destinations.

Step 104: In order of the second cost from small to large, determine whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and use the trajectory curve that meets the preset conditions as the vehicle's driving path.

The preset conditions may include but are not limited to a minimum turning radius of the vehicle.

In an optional embodiment, the candidate destinations may be sorted in ascending order of the second cost, and then the following process is looped according to the sorting until the vehicle's driving path is determined or all candidate destinations are traversed:

Generate a trajectory curve between a current position of the vehicle and an alternative destination using a cubic polynomial, a quintic polynomial, or a septic polynomial;

Determine whether the trajectory curve meets the preset conditions;

If the trajectory curve meets the preset conditions, the trajectory curve is used as the driving path of the vehicle;

If not satisfied, determine the next alternative destination.

In an optional embodiment, a trajectory curve of the vehicle's current position and the alternative destination may also be generated based on the Reed-Shepps curve. If the trajectory curve can be successfully generated, the trajectory curve is determined to be the vehicle's driving path.

The path planning method of the embodiment of the present invention generates a grid area around the vehicle destination, and determines the first cost of each grid in the grid area according to the information of the obstacles between the current position of the vehicle and the destination and the preset first rule; wherein the first cost is used to indicate the feasibility of the grid, and the smaller the first cost, the higher the feasibility and the safer the driving, so that the safe area and the dangerous area in the grid area can be determined; then, multiple alternative destinations are determined around the destination, and the second cost of each alternative destination is determined according to the preset second rule and the first cost of the grid; according to the second cost in ascending order, it is judged in turn whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the driving path of the vehicle, so that it can ensure accurate parking at the station while ensuring driving safety, with less calculation amount, and ensuring the real-time nature of path planning.

The path planning method of the embodiment of the present invention can be based on different trigger conditions or trigger methods, for example, the trigger method can be determined according to the specific sensor configuration and task scenario, and when the trigger condition is met, the path for the vehicle can be planned according to the method. As an example, path planning can be triggered in the following two ways: one is to trigger a path planning task after the environmental status near the destination is updated, which is common in tasks of picking up passengers in complex environments; the other is to trigger the path planning task at a fixed period, such as running a local path planning task every 100 milliseconds, which is often used in scenarios where the update frequency of multiple sensors is inconsistent.

FIG4 schematically shows a flow chart of a path planning method according to another embodiment of the present invention. As shown in FIG4 , the method includes:

Step 401: Determine information about obstacles between a current position of a vehicle and a destination of the vehicle;

Step 402: Determine a trajectory curve between the current position of the vehicle and the destination of the vehicle;

Step 403: Detecting whether the trajectory curve collides with the obstacle according to the information of the obstacle;

Step 404: If not, taking the trajectory curve as the driving path of the vehicle;

Step 405: If yes, a grid area is generated around the destination, and a first cost of each grid in the grid area is determined according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid;

Step 406: determining a plurality of candidate destinations around the destination, and determining a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid;

Step 407: In order of the second cost from small to large, determine whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and use the trajectory curve that meets the preset conditions as the vehicle's driving path.

Among them, steps 401 and 405-407 are the same as those in the embodiment shown in FIG. 1 , and to avoid repetition, the present invention will not be described again here.

For steps 402-403, a cubic polynomial, a quintic polynomial or a septad polynomial can be used to generate a trajectory curve between the current position of the vehicle and the destination. Then, the posture of the vehicle on the trajectory curve can be predicted, and then based on the posture of the vehicle on the trajectory curve and the information of the obstacle, it is determined whether the vehicle will collide with the obstacle when traveling on the trajectory curve. If so, it is determined that the trajectory curve collides with the obstacle. In determining whether the vehicle will collide with the obstacle when traveling on the trajectory curve, it can be determined whether the coverage range of the vehicle in the posture overlaps with the coverage range of the obstacle. If there is an overlap, it is determined that the vehicle will collide with the obstacle when traveling on the trajectory curve. If the trajectory curve does not collide with the obstacle, the trajectory curve can be used as the vehicle's driving path, thereby eliminating the subsequent steps, effectively reducing the amount of calculation, and ensuring driving safety while completing the docking task.

In an optional embodiment, before determining whether the trajectory curve between the candidate destination and the current position of the vehicle satisfies a preset condition, the path planning method further includes: determining invalid candidate destinations among the multiple candidate destinations, and filtering out the invalid candidate destinations. The process of determining invalid candidate destinations among the multiple candidate destinations may include:

For each candidate destination, determining whether the grid where the candidate destination is located collides with the obstacle; that is, determining whether the first cost of the grid where the candidate destination is located is a preset value;

If so, the alternative destination is determined to be an invalid alternative destination.

This embodiment can avoid the planned driving path from colliding with obstacles by screening out invalid alternative destinations, thereby ensuring the driving safety of the vehicle.

In an optional embodiment, the path planning method further includes: if the trajectory curves between all the alternative destinations and the current position of the vehicle do not meet the preset conditions, a new alternative destination is determined, and it is judged whether the trajectory curve between the new alternative destination and the current position of the vehicle meets the preset conditions. For example, a new target graph can be generated with the destination as the center, and sampling can be performed on the new target graph to obtain a new alternative destination. Taking Figure 3 as an example, a new circle can be generated with the destination as the center and 2r as the radius, and a new alternative destination can be obtained by sampling on the new circle. After the new alternative destination is determined, the second cost of each new alternative destination is calculated, and then the trajectory curve between the new alternative destination and the current position of the vehicle is judged in order from the smallest to the largest second cost to determine whether it meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the vehicle's driving path.

In an optional embodiment, the path planning method further includes: determining whether an obstacle moves while the autonomous driving vehicle is driving along the driving path; if so, replanning the driving path of the vehicle based on the information of the moved obstacle, that is, re-executing steps 101-104 or steps 401-407. The obstacle movement includes one or more of the following: an obstacle moves from a first grid to a second grid, an obstacle moves from within a grid area to outside a grid area, and a new obstacle moves from outside a grid area to within a grid area. The path planning method of this embodiment detects in real time whether an obstacle moves during the driving of the vehicle. If an obstacle moves, the driving path of the vehicle is replanned to ensure that the vehicle can safely drive to the destination.

FIG5 schematically shows a schematic diagram of the structure of a path planning device 500 according to an embodiment of the present invention. As shown in FIG5 , the path planning device 500 includes:

The obstacle determination module 501 is used to determine information of obstacles between the current position of the vehicle and the destination of the vehicle;

A first calculation module 502 is used to generate a grid area around the destination, and determine a first cost of each grid in the grid area according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid;

A second calculation module 503 is used to determine a plurality of candidate destinations around the destination, and determine a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid;

The path determination module 504 is used to determine whether the trajectory curve between the candidate destination and the current position of the vehicle meets a preset condition in the order of the second cost from small to large, and if so, use the trajectory curve as the driving path of the vehicle.

The path planning device of the embodiment of the present invention generates a grid area around the vehicle destination, and determines the first cost of each grid in the grid area according to the information of the obstacles between the current position of the vehicle and the destination and the preset first rule; wherein the first cost is used to indicate the feasibility of the grid, and the smaller the first cost, the higher the feasibility and the safer the driving, so that the safe area and the dangerous area in the grid area can be determined; then, multiple alternative destinations are determined around the destination, and the second cost of each alternative destination is determined according to the preset second rule and the first cost of the grid; according to the second cost in ascending order, it is judged in turn whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and the trajectory curve that meets the preset conditions is used as the driving path of the vehicle, so that it can ensure accurate parking at the station while ensuring driving safety, with less calculation amount, and ensuring the real-time nature of path planning.

Optionally, the first calculation module is also used to: determine a trajectory curve between the current position of the vehicle and the destination of the vehicle; detect whether the trajectory curve collides with the obstacle based on the information of the obstacle; if so, generate a grid area around the destination.

Optionally, the information of the obstacle includes location information of the obstacle;

The first calculation module is also used to: determine, for each grid, a second distance between the grid and the destination; determine a first distance between the grid and the obstacle based on the location information of the obstacle; and determine a first cost of the grid based on the first distance and the second distance.

Optionally, the first calculation module is also used to: when there are multiple obstacles, determine a minimum first distance from multiple first distances between the grid and the multiple obstacles; and determine the first cost of the grid based on the minimum first distance and the second distance.

Optionally, the second calculation module is further used to: generate a target graphic centered on the destination, where a range covered by the target graphic overlaps with a range covered by the grid area; and perform sampling on the target graphic, using the sampling points as the candidate destinations.

Optionally, the second calculation module is also used to: determine, for each alternative destination, a first cost of the grid where the alternative destination is located; determine a third distance between the alternative destination and the current position of the vehicle; and determine a second cost of the alternative destination based on the first cost and the third distance.

Optionally, the device further comprises a screening module, which is used to: determine invalid alternative destinations among the multiple alternative destinations, and screen out the invalid alternative destinations.

Optionally, the screening module is further used to: for each candidate destination, determine whether the grid where the candidate destination is located collides with the obstacle; if so, determine that the candidate destination is an invalid candidate.

Optionally, the device also includes a retry module, which is used to: if the trajectory curves between all the alternative destinations and the current position of the vehicle do not meet the preset conditions, determine a new alternative destination, and judge whether the trajectory curve between the new alternative destination and the current position of the vehicle meets the preset conditions in order of the second costs of the new alternative destinations from small to large.

Optionally, the retry module is also used to: determine whether an obstacle moves while the autonomous driving vehicle is driving along the driving path; if so, replan the driving path of the vehicle based on information about the moved obstacle.

The above device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

The embodiment of the present invention further provides an electronic device, as shown in FIG6 , comprising one or more processors 601, a communication interface 602, a storage device 603 and a communication bus 604, wherein the processor 601, the communication interface 602, and the storage device 603 communicate with each other via the communication bus 604.

Storage device 603, used to store one or more programs;

The processor 601 is used to implement the following steps when executing the program stored in the storage device 603:

Determining information about obstacles between a current location of a vehicle and a destination of the vehicle;

Generate a grid area around the destination, and determine a first cost of each grid in the grid area according to a preset first rule and information about the obstacle; wherein the first cost is used to indicate the feasibility of the grid;

Determine a plurality of candidate destinations around the destination, and determine a second cost of each of the candidate destinations according to a preset second rule and the first cost of the grid;

In order of the second costs from small to large, determine whether the trajectory curve between the alternative destination and the current position of the vehicle meets the preset conditions, until a trajectory curve that meets the preset conditions is determined, and use the trajectory curve that meets the preset conditions as the vehicle's driving path.

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

The communication interface is used for communication between the above electronic device and other devices.

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

The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In another embodiment provided by the present invention, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the path planning method described in any one of the above embodiments.

In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the path planning method described in any one of the above embodiments.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims (11)

1. A method of path planning, comprising:

determining information of an obstacle between a current location of a vehicle and a destination of the vehicle;

generating a grid area around the destination, and determining a first cost of each grid in the grid area according to a preset first rule and information of the obstacle; wherein the first price is used to indicate the feasibility of the grid;

determining a plurality of alternative destinations around the destination, and determining a second cost for each of the alternative destinations according to a preset second rule and the first cost of the grid;

sequentially judging whether the track curve between the alternative destination and the current position of the vehicle meets a preset condition according to the order from the low cost to the high cost until the track curve meeting the preset condition is determined, and taking the track curve meeting the preset condition as the running path of the vehicle;

Wherein determining a plurality of alternative destinations around the destination comprises:

generating a target graph taking the destination as a center, wherein the coverage range of the target graph is overlapped with the coverage range of the grid area;

sampling is carried out on the target graph, and sampling points are used as the alternative destinations;

determining a second cost of each alternative destination according to a preset second rule and the first cost of the grid, including:

for each alternative destination, determining a first cost of a grid in which the alternative destination is located;

determining a third distance between the alternative destination and the current location of the vehicle;

and determining a second cost of the alternative destination according to the first cost and the third distance.

2. The method of claim 1, wherein generating a mesh region around the destination comprises:

determining a trajectory curve between a current location of the vehicle and a destination of the vehicle;

detecting whether the track curve collides with the obstacle according to the information of the obstacle;

if yes, generating a grid area around the destination;

If not, taking a track curve between the current position of the vehicle and the destination of the vehicle as a running path of the vehicle.

3. The method of claim 1, wherein the information of the obstacle comprises position information of the obstacle;

according to a preset first rule and information of the obstacle, determining a first cost of each grid in the grid area comprises the following steps:

determining, for each mesh, whether the mesh collides with the obstacle according to information of the obstacle;

if yes, determining that the first cost of the grid is a preset value;

if not, determining a first distance between the grid and the obstacle according to the position information of the obstacle; determining a second distance between the mesh and the destination; and determining a first cost of the grid according to the first distance and the second distance.

4. A method according to claim 3, wherein determining the first cost of the grid from the first distance and the second distance comprises:

determining a minimum first distance from among a plurality of first distances between the mesh and a plurality of the obstacles in the case where the number of the obstacles is plural;

And determining the first cost of the grid according to the minimum first distance and the second distance.

5. The method according to claim 1, wherein the method further comprises:

before determining whether a trajectory curve between the candidate destination and a current position of the vehicle satisfies a preset condition, determining an invalid candidate among the plurality of candidate destinations, and screening out the invalid candidate.

6. The method of claim 5, wherein determining an invalid alternative of the plurality of alternative destinations comprises:

determining, for each alternative destination, whether a mesh in which the alternative destination is located collides with the obstacle;

if so, determining the alternative destination as an invalid alternative.

7. The method according to any one of claims 1-6, further comprising:

if the track curves between all the alternative destinations and the current position of the vehicle do not meet the preset condition, determining a new alternative destination, and judging whether the track curve between the new alternative destination and the current position of the vehicle meets the preset condition according to the order of the second cost of the new alternative destination from small to large.

8. The method of claim 7, wherein the method further comprises:

determining whether an obstacle movement occurs during the running of the vehicle according to the running path;

if yes, the running path of the vehicle is planned again according to the information of the moved obstacle.

9. A path planning apparatus for performing the path planning method according to any one of claims 1 to 8, the path planning apparatus comprising:

an obstacle determination module for determining information of an obstacle between a current position of a vehicle and a destination of the vehicle;

the first calculation module is used for generating a grid area around the destination and determining a first cost of each grid in the grid area according to a preset first rule and information of the obstacle; wherein the first price is used to indicate the feasibility of the grid;

a second calculation module, configured to determine a plurality of alternative destinations around the destination, and determine a second cost of each of the alternative destinations according to a preset second rule and the first cost of the grid;

and the path determining module is used for sequentially judging whether the track curve between the alternative destination and the current position of the vehicle meets a preset condition according to the order from the low cost to the high cost until the track curve meeting the preset condition is determined, and taking the track curve meeting the preset condition as the running path of the vehicle.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-8.

11. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-8.