CN118310536A - A path generation method and device - Google Patents

Abstract

The application discloses a path generation method and device, and belongs to the field of unmanned driving. After first key point information and reversing point information are acquired, a target point is determined, then a target curve fitting strategy is determined based on the relation between the direction of the target point and the direction of the reversing point, and finally the key points corresponding to the first key point information and the reversing points are fitted according to the target curve fitting strategy, so that a target path is obtained. According to the scheme, only the key point information and the reversing point information are needed to be determined, and the target curve fitting strategy can be determined according to the relation between the direction of the target point and the direction of the reversing point, so that the target path is obtained, the acquisition path of a vehicle is not needed to be driven manually, the path generation efficiency is improved, the generated path is closer to the path planning level of manual driving, and the path generation effect is effectively improved.

Description

A path generation method and device

Technical Field

The present application relates to the field of unmanned driving technology, and in particular, to a path generation method and device.

Background technique

At present, there are two main methods for path planning of autonomous vehicles in roadless areas where there is no road division (such as autonomous mining vehicles in mining areas), namely, manually driving vehicles to collect paths and back-end algorithms to generate paths. However, both methods have certain shortcomings in practical applications, which limit the efficiency and continuity of autonomous vehicle operations in roadless areas.

The first method, that is, manually driving a vehicle to collect the path, has certain advantages in adapting to changes in the loading area, but its repeated manual driving operations not only consume time and resources, but also affect the continuity of autonomous driving operations. Every time the structure, obstacle layout or operation requirements in the roadless area change, the path needs to be collected again, which greatly limits the flexibility and efficiency of the operation.

The second method, that is, generating paths by back-end algorithms, overcomes the tedious process of manually collecting paths. However, the existing method is affected by the algorithm capabilities and the generated paths are poor. For example, in some special scenarios, paths with multiple turns may be generated. The more turns there are, the longer it takes for the vehicle to reach the destination. These problems seriously affect the operating efficiency in roadless areas and also threaten the continuity of production operations.

Summary of the invention

In order to overcome the deficiencies of the prior art, the present application provides a path generation method and device to solve the problem that the existing methods for generating paths are either time-consuming and resource-intensive and inflexible, or the generated paths have poor effects.

The technical solution adopted by this application to solve its technical problem is:

In one aspect, a path generation method is provided, comprising:

Acquire first key point information and turning point information; wherein the first key point information includes starting point information and/or end point information, the starting point information includes a starting point position and a starting point orientation of the starting point, the turning point information includes a turning point position and a turning point orientation of the turning point, and the end point information includes an end point position and an end point orientation of the end point;

Determine a target point related to the first key point information, and determine a target curve fitting strategy according to a relationship between an orientation of the target point and an orientation of a reversing point corresponding to the reversing point information;

According to the target curve fitting strategy, the key points corresponding to the first key point information and the turning points corresponding to the turning point information are fitted to obtain a target path.

Further, determining a target curve fitting strategy according to a relationship between the orientation of the target point and the orientation of the reversing point corresponding to the reversing point information includes:

Obtaining an angle difference between a direction corresponding to the direction of the target point and a direction corresponding to the direction of the reversing point;

The target curve fitting strategy is determined according to the angle difference.

Further, the determining the target point related to the first key point information includes:

In the case where the first key point information includes the end point information, determining that the first key point information does not include a reversing waypoint;

An end point corresponding to the end point information is determined as the target point.

Further, the determining the target point related to the first key point information includes:

In a case where the first key point information includes starting point information, determining that the first key point information includes a forward waypoint;

The target point is determined based on the starting point and the forward waypoint.

Further, the determining the target point according to the starting point and the forward path point comprises:

Connecting the starting point and at least one of the forward path points using a preset curve to obtain a guidance path;

At least one target sampling point is determined on the guide path, and the target point is determined according to the target sampling point.

Further, the determining at least one target sampling point on the guide path, and determining the target point according to the target sampling point, comprises:

Determine a point on the guide path that is closest to the reversing point as a first designated sampling point;

The at least one target sampling point is determined according to the first designated sampling point.

Further, determining the at least one target sampling point according to the first designated sampling point includes:

Determining, according to the information of the first designated sampling point and the information of the turning point, whether the first designated sampling point meets the turning requirement of the target autonomous driving vehicle;

In a case where a turning requirement of the target autonomous driving vehicle is met, taking the first designated sampling point as a target sampling point;

When the turning requirement of the target autonomous driving vehicle is not met, on the guidance path, the first designated sampling point is moved a designated distance in the direction of the starting point to obtain a second designated sampling point, wherein the second designated sampling point meets the turning requirement of the target autonomous driving vehicle; and the second designated sampling point is used as a target sampling point.

Further, the determining at least one target sampling point on the guide path, and determining the target point according to the target sampling point, comprises:

The first designated sampling point or the second designated sampling point is used as the target point; or,

Taking the first designated sampling point or the second designated sampling point as a target starting point, sampling is performed on the guide path at a designated distance interval in a direction toward the starting point to obtain the at least one target sampling point, wherein the at least one target sampling point includes the first designated sampling point or the second designated sampling point; and each target sampling point is used as the target point.

Further, determining the target curve fitting strategy according to the angle difference includes:

When the angle difference is greater than or equal to the first preset angle and less than the second preset angle, a fourth target curve is used to fit the target point and the reversing point;

When the angle difference is greater than or equal to the second preset angle and less than the third preset angle, a fifth target curve is used to fit the target point and the reversing point;

The first preset angle is smaller than the second preset angle, the second preset angle is smaller than the third preset angle, and the fourth target curve and the fifth target curve have different constraints on curvature and/or curvature change rate.

Furthermore, the step of determining the target curve fitting strategy according to the angle difference further includes:

When the angle difference is greater than or equal to 0 and less than the first preset angle, a third target curve is used to fit the target point and the reversing point;

When the angle difference is greater than or equal to the third preset angle and less than the fourth preset angle, a sixth target curve is used to fit the target point and the reversing point;

Among them, the first preset angle is greater than 0, the third preset angle is less than the fourth preset angle; the third target curve does not constrain the curvature and the rate of change of curvature, the fourth target curve only constrains the curvature, the fifth target curve only constrains the rate of change of curvature, and the curvature of the sixth target curve is a fixed value.

Furthermore, it also includes:

In the case where the first key point information includes the end point information, determining that the first key point information includes information of a reversing path point; fitting the end point, the reversing path point and the turning point with a first target curve to obtain the target path; or

In the case where the first key point information includes the starting point information, it is determined that the first key point information does not include information of the forward path point; and a second target curve is used to fit the starting point, the forward path point and the turning point to obtain the target path.

Furthermore, it also includes:

Performing smoothing on the target path;

At least one of the following checks is performed on the target path after the smoothing process: a first check process is used to determine whether the target path after the smoothing process is within a preset boundary range; a second check process is used to determine whether the end point of the target path after the smoothing process and the end point position of the end point included in the first key point information meet the distance requirement; a third check process is used to determine whether the orientation of the end point of the target path after the smoothing process and the end point orientation of the end point included in the first key point information meet the orientation requirement;

A verified target path is determined, and the driving of the target autonomous driving vehicle is controlled according to the verified target path.

Furthermore, the reversing point information includes a plurality of reversing points, and further includes:

Acquire a first user instruction, where the first user instruction is used to instruct to generate a first reversal point;

generating the plurality of reversing points according to the first reversing point, wherein the plurality of reversing points includes the first reversing point;

According to a specified order, the target path corresponding to each of the plurality of switching points is verified until at least one target path that passes the verification is obtained.

In another aspect, a path generation device is provided, comprising:

An information acquisition module, used to acquire first key point information and turning point information; wherein the first key point information includes starting point information and/or end point information, the starting point information includes a starting point position and a starting point orientation of the starting point, the turning point information includes a turning point position and a turning point orientation of the turning point, and the end point information includes an end point position and an end point orientation of the end point;

a strategy determination module, configured to determine a target point related to the first key point information, and determine a target curve fitting strategy according to a relationship between an orientation of the target point and an orientation of a reversing point corresponding to the reversing point information;

A path fitting module is used to fit the key points corresponding to the first key point information and the turning points corresponding to the turning point information according to the target curve fitting strategy to obtain a target path.

Beneficial effects:

The technical solution of the present application provides a path generation method and device. After obtaining the first key point information and the turning point information, the target point is determined, and then the target curve fitting strategy is determined based on the relationship between the orientation of the target point and the orientation of the turning point. Finally, the key points and turning points corresponding to the first key point information are fitted according to the target curve fitting strategy to obtain the target path. The present application solution only needs to determine the key point information and the turning point information, and then determine the target curve fitting strategy according to the relationship between the orientation of the target point and the orientation of the turning point, and then obtain the target path. There is no need to manually drive the vehicle to collect the path, which improves the efficiency of path generation, and the generated path is closer to the path planning level of manual driving, which effectively improves the path generation effect.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a flow chart of a path generation method provided in an embodiment of the present application;

FIG2 is a schematic diagram of a generation path provided in an embodiment of the present application;

FIG3 is a schematic diagram of the structure of a path generating device provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

Glossary:

Starting point: the position of the vehicle when it starts moving;

Forward waypoint: the location that the vehicle needs to pass when driving forward;

Reversing point: the position where the vehicle changes from forward driving to reverse driving;

Reversing waypoint: the position that the vehicle needs to pass when reversing;

End point: The location where the vehicle finally stops.

Starting direction: the direction of travel from the starting point;

Reversal point orientation; direction of entry into the reversal point;

Destination direction: the direction of entering the destination.

Referring to FIG. 1 , an embodiment of the present application provides a path generation method, including:

S11: Obtain first key point information and turning point information; wherein, the first key point information includes starting point information and/or end point information, the starting point information includes the starting point position and starting point direction of the starting point, the turning point information includes the turning point position and turning point direction of the turning point, and the end point information includes the end point position and end point direction of the end point.

Wherein, when the first key point information includes the starting point information, it may also include the forward waypoint; when the first key point information includes the end point information, it may also include the reverse waypoint, wherein the forward waypoint and the reverse waypoint may include the position information and/or the orientation information. Preferably, the forward waypoint and the reverse waypoint respectively include only the position information, but not the orientation information.

As a preferred implementation method of the embodiment of the present application, the first key point information and/or the reversal point information are generated by operating on the map platform, for example, the operation can be click, drag, select, or any form of input. The input form is not limited to input through other devices, user input, etc. The input content can be content input of the mouse, voice input, etc. Preferably, this solution can obtain the first key point information and/or the reversal point information by manually controlling the terminal by the user.

S12: Determine a target point related to the first key point information, and determine a target curve fitting strategy according to a relationship between the orientation of the target point and the orientation of the turning point corresponding to the turning point information.

In this step, the target point may be any one or more of the key points included in the first key point information, or may be other points related to any one or more of the key points included in the first key point information. Optionally, the information included in the target point may be the position and/or orientation of the target point.

Optionally, the relationship between the orientation of the target point and the orientation of the turning point corresponding to the turning point information can be obtained based on at least one of the following: the difference between the orientation of the target point and the orientation of the turning point; or the difference between the orientation of the target point and the orientation of the turning point and the standard orientation, respectively. Preferably, the relationship between the orientation of the target point and the orientation of the turning point corresponding to the turning point information includes the angle between the orientation of the target point and the orientation of the turning point.

S13: According to the target curve fitting strategy, the key points corresponding to the first key point information and the turning points corresponding to the turning point information are fitted to obtain a target path.

Optionally, when the first key point information includes end point information, it is determined that the first key point information does not include a reversing path point; and the end point corresponding to the end point information is determined as the target point. According to the relationship between the orientation of the target point and the orientation of the turning point corresponding to the turning point information, a target curve fitting strategy is determined, and then the end point and the turning point are fitted based on the determined target curve fitting strategy to obtain a reversing path, that is, a target path.

Optionally, in the case where the first key point information includes the end point information, if it is determined that the first key point information includes a reversing path point, the target point may also be determined based on the reversing path point and the end point corresponding to the end point information. For example, the reversing path point closest to the turning point may be used as the target point to perform a first curve fitting; then, the latest end point obtained after the first curve fitting is used as the current turning point, and the reversing path point closest to the current turning point is used as the new target point, and a second curve fitting is performed based on the two, and so on, until the end point corresponding to the end point information is reached.

Preferably, when the first key point information includes a reversing path point, the relationship between the direction of the target point and the direction of the turning point corresponding to the reversing point information is no longer examined, but curve fitting is performed on the turning point, the reversing path point and the end point based on other algorithms.

Optionally, when the first key point information includes starting point information, it is determined that the first key point information includes a forward path point; the target point is determined according to the starting point and the forward path point. Then, according to the relationship between the orientation of the target point and the orientation of the turning point corresponding to the turning point information, a target curve fitting strategy is determined, and then the target point and the turning point are fitted based on the determined target curve fitting strategy, and then the path obtained by fitting and the guide path (the guide path between the starting point and the target point) are spliced to obtain a forward path, that is, a target path.

Optionally, determining the target point according to the starting point and the forward path point comprises:

The guide path is obtained by connecting the starting point and at least one of the forward path points using a preset curve; that is, the guide path is obtained by fitting the starting point and the forward path point using a preset curve. At least one target sampling point is determined on the guide path, and the target point is determined based on the target sampling point. Among them, the location on the guide path that meets the preset distance requirement from the turning point can be used as the first designated sampling point. Preferably, the point on the guide path closest to the turning point is determined as the first designated sampling point; based on the first designated sampling point, the at least one target sampling point is determined.

Preferably, based on the information of the first designated sampling point and the information of the turning point, it is determined whether the first designated sampling point meets the turning requirement of the target autonomous driving vehicle; wherein the turning requirement is set according to actual needs, and illustratively, the turning requirement can be determined based on vehicle parameters (e.g., turning radius), for example, the determined turning requirement is greater than the turning radius; it can be determined whether there is a preset turning area near the sampling point; or it can be determined whether the angle between the tangent direction of the sampling point and the direction of the turning point meets a preset angle range.

Optionally, when the turning requirement of the target autonomous driving vehicle is met, the first designated sampling point is used as a target sampling point; when the turning requirement of the target autonomous driving vehicle is not met, on the guidance path, the first designated sampling point is moved a specified distance in the direction of the starting point to obtain a second designated sampling point, wherein the second designated sampling point meets the turning requirement of the target autonomous driving vehicle; and the second designated sampling point is used as a target sampling point.

In one embodiment, at least one target sampling point is determined on the guide path, and the target point is determined according to the target sampling point, including: taking the first designated sampling point or the second designated sampling point as the target point. That is, after obtaining a target sampling point, the target sampling point is directly used as the target point to generate a target path, and then the target path is verified. If the verification passes, no new target point is searched. This method can greatly save the amount of calculation when generating the path. However, the obtained target path may not be the optimal target path.

Therefore, in another embodiment, at least one target sampling point is determined on the guide path, and the target point is determined based on the target sampling point, including: taking the first designated sampling point or the second designated sampling point as the target starting point, sampling in the direction of the starting point at a designated distance interval on the guide path to obtain the at least one target sampling point, wherein the at least one target sampling point includes the first designated sampling point or the second designated sampling point; taking each target sampling point as the target point. That is, all target points are found, and then a target path is obtained based on each target point, and then a verification is performed, and a target path that passes the verification is determined as the final target path according to the preset filtering conditions. The preset filtering conditions are any one or more combinations of the following:

1. The target path that passes through the most forward waypoints is taken as the final target path.

2. The target path with the shortest overall path length is taken as the final target path.

3. The target path with the longest straight path length is taken as the final target path.

Among them, multiple combinations can be used to assign a preset weight to each condition, and then calculate the final weight, and use the target path with the largest final weight as the final target path.

As an optional implementation of the embodiment of the present application, determining a target curve fitting strategy according to a relationship between the orientation of the target point and the orientation of the reversing point corresponding to the reversing point information includes:

Obtain the angle difference between the direction corresponding to the orientation of the target point and the direction corresponding to the orientation of the reversing point; determine the target curve fitting strategy based on the angle difference. Therefore, in actual use, if all angle differences use one curve, it may cause the autonomous driving vehicle to turn too much when driving on the generated path, affecting the vehicle's driving speed, and may even cause the risk of the vehicle overturning. Therefore, the embodiment of the present application uses curves with different constraints to fit the target point and the reversing point for different angle differences.

In some embodiments, determining the target curve fitting strategy according to the angle difference includes:

When the angle difference is greater than or equal to the first preset angle and less than the second preset angle, the fourth target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the second preset angle and less than the third preset angle, the fifth target curve is used to fit the target point and the turning point; wherein the first preset angle is less than the second preset angle, the second preset angle is less than the third preset angle, and the fourth target curve and the fifth target curve have different constraints on curvature and/or curvature change rate. The curvature represents the degree to which the curve deviates from a straight line, which may be related to the angle of the vehicle's turn; and the curvature change rate represents the degree of curvature change, which may be related to whether the vehicle frequently adjusts the turning direction.

In some other embodiments, determining the target curve fitting strategy according to the angle difference includes:

When the angle difference is greater than or equal to 0 and less than the first preset angle, a third target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the first preset angle and less than the second preset angle, a fourth target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the second preset angle and less than the third preset angle, a fifth target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the third preset angle and less than the fourth preset angle, a sixth target curve is used to fit the target point and the turning point;

Among them, the first preset angle is greater than 0, the first preset angle is smaller than the second preset angle, the second preset angle is smaller than the third preset angle, the third preset angle is smaller than the fourth preset angle, and the fourth preset angle is smaller than 180; the third target curve does not constrain the curvature and the rate of change of curvature, the fourth target curve only constrains the curvature, the fifth target curve only constrains the rate of change of curvature, and the curvature of the sixth target curve is a fixed value.

As an optional implementation of the present application, when the first key point information includes the end point information, the first key point information includes the information of the reversing path point; the first target curve is used to fit the end point, the reversing path point and the turning point to obtain the target path. That is, when the user inputs the end point and the reversing path point, the first target curve is used to directly fit the end point, the reversing path point and the turning point to obtain the reversing path, that is, the target path, without determining the target curve fitting strategy according to the angle difference.

As another optional implementation of the present application, when the first key point information includes the starting point information, it is determined that the first key point information does not include the information of the forward path point; the second target curve is used to fit the starting point, the forward path point and the turning point to obtain the target path. That is, when the user inputs the starting point but does not input the forward path point, the second target curve is directly used to fit the starting point, the forward path point and the turning point to obtain the forward path, that is, the target path, without determining the target curve fitting strategy according to the angle difference.

It should be noted that the target paths obtained by the above fitting methods need to be further processed, as follows:

The target path is smoothed; and at least one of the following checks is performed on the smoothed target path:

The first verification process is used to determine whether the target path after smoothing is within a preset boundary range to ensure that the autonomous driving vehicle will not exceed the map boundary or collide with boundaries such as obstacles when traveling on the target path; the second verification process is used to determine whether the end point of the target path after smoothing and the end point position included in the first key point information meet the distance requirement; the third verification process is used to determine whether the direction of the end point of the target path after smoothing and the end point direction of the end point included in the first key point information meet the direction requirement; determine the target path that passes the verification, and control the driving of the target autonomous driving vehicle according to the target path that passes the verification.

Wherein, whether the forward path or the reverse path is generated, it needs to be verified by the first verification step, while the second verification process and the third verification process are only for the generated reverse path.

After the verification is passed, a path as shown in FIG2 is generated, where the gray area is the driving path of the autonomous driving vehicle. The autonomous driving vehicle enters the reversing point from the starting point along the forward path, changes from forward driving to reverse driving at the reversing point, and then enters the end point along the reverse path. The forward path points on the forward path and the reverse path points on the reverse path are schematically shown. Optionally, the driving path shown in this embodiment can be processed for use by the vehicle, and the processing includes but is not limited to smoothing processing, or other corrections.

Optionally, when actually generating a target path, after the user determines a turning point, if the generated target path fails to pass verification, the user can reselect a turning point, but usually the user reselects a position near the turning point selected last time. Therefore, in order to avoid the user from reselecting when the turning point determined by the user cannot obtain the target path or the target path obtained fails to pass verification, the present application provides a solution for automatically generating multiple turning points, that is, the turning point information includes multiple turning points, which are as follows:

A first user instruction is obtained, wherein the first user instruction is used to instruct the generation of a first turning point; based on the first turning point, the plurality of turning points are generated, wherein the plurality of turning points include the first turning point; illustratively, in a target area centered on the turning point, a second turning point is set at a preset distance. The first turning point and all the second turning points are deduplicated to generate turning point information.

According to a specified order, the target path corresponding to each of the plurality of switching points is verified until at least one target path that passes the verification is obtained.

In one embodiment, the target path is generated and verified in the order of the first turning point and then the second turning point, wherein the second turning point is generated and verified in the order of the smaller the distance from the first turning point, the higher the priority. When the target path generated by any turning point passes the verification, the target path generation and verification for the subsequent turning points are no longer performed.

In another embodiment, a target path is generated for all the switching points, and then all are verified. Finally, an optimal target path is selected from the verified target paths according to a preset screening condition as the final target path. The screening condition is referred to the above content and will not be repeated here.

Based on the same inventive concept, as shown in FIG3 , the present application provides a path generation device 20, including:

The information acquisition module 31 is used to acquire first key point information and turning point information; wherein the first key point information includes starting point information and/or end point information, the starting point information includes the starting point position and starting point orientation of the starting point, the turning point information includes the turning point position and turning point orientation of the turning point, and the end point information includes the end point position and end point orientation of the end point. The turning point information includes multiple turning points, and further includes: acquiring a first user instruction, the first user instruction is used to instruct the generation of a first turning point; generating the multiple turning points according to the first turning point, the multiple turning points including the first turning point; and verifying the target path corresponding to each turning point in the multiple turning points in a specified order until at least one target path that passes the verification is obtained.

The strategy determination module 32 is used to determine the target point related to the first key point information, and determine the target curve fitting strategy according to the relationship between the orientation of the target point and the reversing point orientation corresponding to the reversing point information; specifically, the strategy determination module 32 obtains the angle difference between the direction corresponding to the orientation of the target point and the direction corresponding to the reversing point orientation; and determines the target curve fitting strategy according to the angle difference.

In one embodiment, determining the target curve fitting strategy according to the angle difference includes:

When the angle difference is greater than or equal to the first preset angle and less than the second preset angle, the fourth target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the second preset angle and less than the third preset angle, the fifth target curve is used to fit the target point and the turning point; wherein the first preset angle is smaller than the second preset angle, the second preset angle is smaller than the third preset angle, and the fourth target curve and the fifth target curve have different constraints on curvature and/or curvature change rate.

In another embodiment, determining the target curve fitting strategy according to the angle difference further includes:

When the angle difference is greater than or equal to 0 and less than the first preset angle, the third target curve is used to fit the target point and the turning point; when the angle difference is greater than or equal to the third preset angle and less than the fourth preset angle, the sixth target curve is used to fit the target point and the turning point; wherein the first preset angle is greater than 0, and the third preset angle is less than the fourth preset angle; the third target curve does not constrain the curvature and the rate of change of curvature, the fourth target curve only constrains the curvature, the fifth target curve only constrains the rate of change of curvature, and the curvature of the sixth target curve is a fixed value.

In one embodiment, determining the target point related to the first key point information includes: when the first key point information includes end point information, determining that the first key point information does not include a reversing path point; and determining the end point corresponding to the end point information as the target point.

In another embodiment, determining the target point related to the first key point information includes: when the first key point information includes starting point information, determining that the first key point information includes a forward path point; and determining the target point based on the starting point and the forward path point.

Wherein, determining the target point according to the starting point and the forward path point comprises: using a preset curve to connect the starting point and at least one of the forward path points to obtain a guide path; determining at least one target sampling point on the guide path, and determining the target point according to the target sampling point.

Further, determining at least one target sampling point on the guide path and determining the target point according to the target sampling point includes: determining a point on the guide path that is closest to the reversing point as a first designated sampling point; and determining the at least one target sampling point according to the first designated sampling point.

Preferably, determining the at least one target sampling point according to the first designated sampling point includes: determining whether the first designated sampling point meets the turning requirement of the target autonomous driving vehicle according to information of the first designated sampling point and information of the turning point; if the turning requirement of the target autonomous driving vehicle is met, taking the first designated sampling point as a target sampling point; if the turning requirement of the target autonomous driving vehicle is not met, moving the first designated sampling point in the direction of the starting point by a designated distance on the guidance path to obtain a second designated sampling point, wherein the second designated sampling point meets the turning requirement of the target autonomous driving vehicle; and taking the second designated sampling point as a target sampling point.

Further, determining at least one target sampling point on the guide path, and determining the target point according to the target sampling point includes: taking the first designated sampling point or the second designated sampling point as the target point; or taking the first designated sampling point or the second designated sampling point as the target starting point, sampling in a direction toward the starting point at a designated distance interval on the guide path to obtain the at least one target sampling point, wherein the at least one target sampling point includes the first designated sampling point or the second designated sampling point; and taking each target sampling point as the target point.

The path fitting module 33 is used to fit the key points corresponding to the first key point information and the turning points corresponding to the turning point information according to the target curve fitting strategy to obtain a target path.

In addition, when the first key point information includes the end point information, it is determined that the first key point information includes the information of the reversing waypoint; the first target curve is used to fit the end point, the reversing waypoint and the turning point to obtain the target path; or,

In the case where the first key point information includes the starting point information, it is determined that the first key point information does not include information of the forward path point; and a second target curve is used to fit the starting point, the forward path point and the turning point to obtain the target path.

It should be noted that it also includes: smoothing the target path; performing at least one of the following checks on the smoothed target path: a first check process, used to determine whether the smoothed target path is within a preset boundary range; a second check process, used to determine whether the end point of the smoothed target path and the end point position included in the first key point information meet the distance requirement; a third check process, used to determine whether the orientation of the end point of the smoothed target path and the end point orientation of the end point included in the first key point information meet the orientation requirement; determining a target path that passes the check, and controlling the driving of the target autonomous driving vehicle according to the target path that passes the check.

According to the present application, a computer-readable storage medium is also provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the methods described above.

According to the present application, an electronic device is also provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the methods described above.

The above method has been described in detail in the previous embodiments and will not be repeated here.

It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims (14)

1. A path generation method, characterized by comprising: Acquire first key point information and turning point information; wherein the first key point information includes starting point information and/or end point information, the starting point information includes a starting point position and a starting point orientation of the starting point, the turning point information includes a turning point position and a turning point orientation of the turning point, and the end point information includes an end point position and an end point orientation of the end point; Determine a target point related to the first key point information, and determine a target curve fitting strategy according to a relationship between an orientation of the target point and an orientation of a reversing point corresponding to the reversing point information; According to the target curve fitting strategy, the key points corresponding to the first key point information and the turning points corresponding to the turning point information are fitted to obtain a target path. 2. The method according to claim 1, characterized in that the determining of the target curve fitting strategy according to the relationship between the orientation of the target point and the orientation of the reversing point corresponding to the reversing point information comprises: Obtaining an angle difference between a direction corresponding to the direction of the target point and a direction corresponding to the direction of the reversing point; The target curve fitting strategy is determined according to the angle difference. 3. The method according to claim 1, characterized in that the step of determining the target point related to the first key point information comprises: In the case where the first key point information includes the end point information, determining that the first key point information does not include a reversing waypoint; An end point corresponding to the end point information is determined as the target point. 4. The method according to claim 1, characterized in that the step of determining the target point related to the first key point information comprises: In a case where the first key point information includes starting point information, determining that the first key point information includes a forward waypoint; The target point is determined based on the starting point and the forward waypoint. 5. The method according to claim 4, characterized in that the determining the target point according to the starting point and the forward path point comprises: Connecting the starting point and at least one of the forward path points using a preset curve to obtain a guidance path; At least one target sampling point is determined on the guide path, and the target point is determined according to the target sampling point. 6. The method according to claim 5, characterized in that determining at least one target sampling point on the guide path and determining the target point according to the target sampling point comprises: Determine a point on the guide path that is closest to the reversing point as a first designated sampling point; The at least one target sampling point is determined according to the first designated sampling point. 7. The method according to claim 6, wherein determining the at least one target sampling point according to the first designated sampling point comprises: Determining, according to the information of the first designated sampling point and the information of the turning point, whether the first designated sampling point meets the turning requirement of the target autonomous driving vehicle; In a case where a turning requirement of the target autonomous driving vehicle is met, taking the first designated sampling point as a target sampling point; When the turning requirement of the target autonomous driving vehicle is not met, on the guidance path, the first designated sampling point is moved a designated distance in the direction of the starting point to obtain a second designated sampling point, wherein the second designated sampling point meets the turning requirement of the target autonomous driving vehicle; and the second designated sampling point is used as a target sampling point. 8. The method according to claim 7, characterized in that the determining at least one target sampling point on the guide path and determining the target point according to the target sampling point comprises: The first designated sampling point or the second designated sampling point is used as the target point; or, Taking the first designated sampling point or the second designated sampling point as a target starting point, sampling is performed on the guide path at a designated distance interval in a direction toward the starting point to obtain the at least one target sampling point, wherein the at least one target sampling point includes the first designated sampling point or the second designated sampling point; and each target sampling point is used as the target point. 9. The method according to claim 2, characterized in that the step of determining the target curve fitting strategy according to the angle difference comprises: When the angle difference is greater than or equal to the first preset angle and less than the second preset angle, a fourth target curve is used to fit the target point and the reversing point; When the angle difference is greater than or equal to the second preset angle and less than the third preset angle, a fifth target curve is used to fit the target point and the reversing point; The first preset angle is smaller than the second preset angle, the second preset angle is smaller than the third preset angle, and the fourth target curve and the fifth target curve have different constraints on curvature and/or curvature change rate. 10. The method according to claim 9, characterized in that the step of determining the target curve fitting strategy according to the angle difference further comprises: When the angle difference is greater than or equal to 0 and less than the first preset angle, a third target curve is used to fit the target point and the reversing point; When the angle difference is greater than or equal to the third preset angle and less than the fourth preset angle, a sixth target curve is used to fit the target point and the reversing point; Among them, the first preset angle is greater than 0, the third preset angle is less than the fourth preset angle; the third target curve does not constrain the curvature and the rate of change of curvature, the fourth target curve only constrains the curvature, the fifth target curve only constrains the rate of change of curvature, and the curvature of the sixth target curve is a fixed value. 11. The method according to claim 1, further comprising: In the case where the first key point information includes the end point information, determining that the first key point information includes information of a reversing path point; fitting the end point, the reversing path point and the turning point with a first target curve to obtain the target path; or In the case where the first key point information includes the starting point information, it is determined that the first key point information does not include information of the forward path point; and a second target curve is used to fit the starting point, the forward path point and the turning point to obtain the target path. 12. The method according to claim 1, further comprising: Performing smoothing on the target path; At least one of the following checks is performed on the target path after the smoothing process: a first check process is used to determine whether the target path after the smoothing process is within a preset boundary range; a second check process is used to determine whether the end point of the target path after the smoothing process and the end point position of the end point included in the first key point information meet the distance requirement; a third check process is used to determine whether the orientation of the end point of the target path after the smoothing process and the end point orientation of the end point included in the first key point information meet the orientation requirement; A verified target path is determined, and the driving of the target autonomous driving vehicle is controlled according to the verified target path. 13. The method according to claim 1 or 12, characterized in that the reversal point information includes a plurality of reversal points, and further comprising: Acquire a first user instruction, where the first user instruction is used to instruct to generate a first reversal point; generating the plurality of reversing points according to the first reversing point, wherein the plurality of reversing points includes the first reversing point; According to a specified order, the target path corresponding to each of the plurality of switching points is verified until at least one target path that passes the verification is obtained. 14. A path generation device, comprising: An information acquisition module, used to acquire first key point information and turning point information; wherein the first key point information includes starting point information and/or end point information, the starting point information includes a starting point position and a starting point orientation of the starting point, the turning point information includes a turning point position and a turning point orientation of the turning point, and the end point information includes an end point position and an end point orientation of the end point; a strategy determination module, configured to determine a target point related to the first key point information, and determine a target curve fitting strategy according to a relationship between an orientation of the target point and an orientation of a reversing point corresponding to the reversing point information; A path fitting module is used to fit the key points corresponding to the first key point information and the turning points corresponding to the turning point information according to the target curve fitting strategy to obtain a target path.