CN113008256A - Automatic parking path planning method, automatic parking path planning device, and storage medium - Google Patents
Automatic parking path planning method, automatic parking path planning device, and storage medium Download PDFInfo
- Publication number
- CN113008256A CN113008256A CN202110190169.8A CN202110190169A CN113008256A CN 113008256 A CN113008256 A CN 113008256A CN 202110190169 A CN202110190169 A CN 202110190169A CN 113008256 A CN113008256 A CN 113008256A
- Authority
- CN
- China
- Prior art keywords
- path
- end point
- post
- preset
- planning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000008447 perception Effects 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 25
- 238000013145 classification model Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
Abstract
The invention discloses a planning method, a planning device and a storage medium of an automatic parking path, wherein the method comprises the following steps: acquiring environment perception information of a vehicle; acquiring a preset path planning template, wherein the preset path planning template comprises a preset path; and generating a planning path for automatic parking based on the environment perception information and a preset path planning template. On the one hand, on the basis of the traditional automatic parking path planning method, the preset path planning template is stored in the vehicle in advance, so that the path planning efficiency of the vehicle during automatic parking path planning is greatly improved, the waiting time of a user is reduced, and the user experience is improved; on the other hand, the preset stored path planning template is used repeatedly, so that the user is allowed to start planning the path for automatic parking at a certain distance from the parking space without driving the vehicle to the parking space, the operation freedom of the user is improved, and the accuracy of path planning is improved.
Description
Technical Field
The present invention relates to the field of automatic control technologies, and in particular, to a method and an apparatus for planning an automatic parking path, and a computer-readable storage medium.
Background
In modern life, the application of vehicle is very extensive, provides convenient, swift trip experience for people's life, and along with the continuous development of science and technology, people also are more and more high to the user demand of vehicle. For example, in the field of automobiles, people park automobiles in specific parking spaces, drive the automobiles out of the parking spaces when the automobiles need to be used, and drive the automobiles into the corresponding parking spaces for parking after the automobiles reach destinations.
With the continuous development of automobile technology, more intelligent vehicles are needed, for example, automobiles can automatically park. In the conventional automatic parking technology, after a vehicle is driven to the vicinity of a target parking space, the vehicle detects the relative position of the vehicle and the target parking space through a vehicle-mounted sensor, and plans a parking path of the vehicle according to the detected information to control the vehicle to perform automatic parking.
In the practical application process, on one hand, the traditional path planning algorithm needs to perform operation of a large amount of data according to information detected on site in each parking process to calculate the parking path, so that the calculation amount is huge and the operation pressure is large; on the other hand, in the traditional automatic parking process, the user often needs to drive the vehicle to be close to the target parking space to calculate the parking path, so that the situations that the user drives the vehicle to the target parking space and falls back and the like easily occur, and the user experience is reduced.
Disclosure of Invention
In order to solve the technical problems in the prior art, embodiments of the present invention provide a method and a device for planning an automatic parking path, which perform calculation of a parking path by using a path planning template, thereby greatly reducing the amount of computation, reducing the calculation complexity of the parking path, and allowing a user to start calculation of the parking path at a remote location, thereby effectively solving the technical problems.
In order to achieve the above object, an embodiment of the present invention provides a method for planning an automatic parking path, where the method includes: acquiring environment perception information of a vehicle, wherein the environment perception information comprises a target position of the vehicle, a current position of the vehicle and obstacle information within a preset distance of the target position; acquiring a preset path planning template, wherein the preset path planning template comprises a preset path; and generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
Optionally, the obtaining of the preset path planning template includes: acquiring a relative position between the target position and the current position; acquiring a path classification model; analyzing the relative position based on the path classification model to obtain a matching planning path matched with the relative position; and generating the preset path planning template based on the matched planning path.
Optionally, the obtaining the path classification model includes: obtaining a plurality of complete parking paths, wherein each complete parking path comprises a starting point, an end point and a course angle; clustering the complete parking paths to obtain clustered paths; and acquiring a preset training model, training the preset training model based on the clustered paths, and generating the path classification model.
Optionally, the generating a planned path for automatic parking based on the environment sensing information and the preset path planning template includes: obtaining a first post-operation end point according to the preset path based on the target position; judging whether the end point is matched with the current position after the first operation; and under the condition that the first post-operation end point is matched with the current position, generating the planned path based on the target position, the current position and the obstacle information, wherein the planned path comprises a line segment and/or an arc.
Optionally, the first post-computation end point includes a plurality of point locations, and the method further includes: before judging whether the end point is matched with the current position after the first operation, screening the plurality of point locations according to a preset algorithm to obtain at least one screened point location; and taking the at least one screened point location as the first post-operation end point.
Optionally, the determining whether the first post-operation end point matches the current position includes: judging whether the end point is coincident with the current position after the first operation; determining that the first post-computation end point matches the current position when the first post-computation end point coincides with the current position; or obtaining a third post-operation end point based on the current position according to a preset path planning algorithm; judging whether the first post-operation end point is coincident with the third post-operation end point; and determining that the first post-operation end point is matched with the current position under the condition that the first post-operation end point is coincident with the third post-operation end point.
Optionally, the method further includes: s341) under a condition that the first post-computation end point does not match the current position, obtaining a second post-computation end point according to the preset path based on the first post-computation end point; s342) judging whether the second operated end point is matched with the current position; s343), if yes, generating a corresponding planned path based on the target position, the first post-operation end point, the second post-operation end point and the obstacle information; s344) if not, taking the second post-operation end point as the first post-operation end point, and circularly executing the steps S341) -S344) until the second post-operation end point is matched with the current position.
Optionally, the method further includes: acquiring a preset cycle threshold; judging the number of times of loop execution steps S341) -S344); judging whether the cycle number is greater than the preset cycle threshold value; stopping loop execution of steps S341) -S344) in case the number of loops is larger than the preset loop threshold.
Optionally, the generating a corresponding planned path based on the target position, the current position, and the obstacle information includes: acquiring vehicle body information of the vehicle; generating a movable area based on the obstacle information and the vehicle body information; generating a continuous path in the movable area by taking the target position as a starting point and the current position as an end point, wherein the continuous path is formed by line segments and/or circular arcs; and taking the continuous path as the planning path.
Correspondingly, an embodiment of the present invention further provides a device for planning an automatic parking path, where the device includes: the environment sensing unit is used for acquiring environment sensing information of a vehicle, wherein the environment sensing information comprises a target position of the vehicle, a current position of the vehicle and obstacle information within a preset distance of the target position; the system comprises a template obtaining unit, a path planning unit and a path planning unit, wherein the template obtaining unit is used for obtaining a preset path planning template which comprises a preset path; and the path planning unit is used for generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method provided by the embodiment of the present invention.
Through the technical scheme provided by the invention, the invention at least has the following technical effects:
on the one hand, on the basis of the traditional automatic parking path planning method, the preset path planning template is stored in the vehicle in advance, so that the path planning efficiency of the vehicle during automatic parking path planning is greatly improved, the waiting time of a user is reduced, and the user experience is improved; on the other hand, the preset stored path planning template is used repeatedly, so that the user can start planning the path for automatic parking at a certain distance from the parking space without driving the vehicle to the parking space, the operation freedom of the user is greatly improved, and the accuracy of path planning is improved.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a flowchart of a specific implementation of a method for planning an automatic parking path according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a specific implementation of obtaining a preset path planning template in the method for planning an automatic parking path according to the embodiment of the present application;
fig. 3 is a flowchart illustrating a specific implementation of generating a planned path for automatic parking in the method for planning an automatic parking path according to the embodiment of the present application;
fig. 4 is a schematic diagram illustrating an end point obtained after a first operation in the method for planning an automatic parking path according to the embodiment of the present application;
fig. 5 is a schematic diagram illustrating screening of an end point after a first operation in the method for planning an automatic parking path according to the embodiment of the present application;
fig. 6 is a schematic diagram illustrating bidirectional path planning performed simultaneously at a destination location and a current location in the method for planning an automatic parking path according to the embodiment of the present application;
fig. 7 is a schematic structural diagram of an automatic parking path planning apparatus according to an embodiment of the present application.
Detailed Description
In order to solve the technical problems in the prior art, embodiments of the present invention provide a method and a device for planning an automatic parking path, which perform calculation of a parking path by using a path planning template, thereby greatly reducing the amount of computation, reducing the calculation complexity of the parking path, and allowing a user to start calculation of the parking path at a remote location, thereby effectively solving the technical problems.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The terms "system" and "network" in embodiments of the present invention may be used interchangeably. The "plurality" means two or more, and in view of this, the "plurality" may also be understood as "at least two" in the embodiments of the present invention. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" generally indicates that the preceding and following related objects are in an "or" relationship, unless otherwise specified. In addition, it should be understood that the terms first, second, etc. in the description of the embodiments of the invention are used for distinguishing between the descriptions and are not intended to indicate or imply relative importance or order to be construed.
Referring to fig. 1, an embodiment of the present invention provides a method for planning an automatic parking path, where the method includes:
s10), obtaining environment perception information of a vehicle, wherein the environment perception information comprises a target position of the vehicle, a current position of the vehicle and obstacle information within a preset distance of the target position;
s20), acquiring a preset path planning template, wherein the preset path planning template comprises a preset path;
s30) generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
Referring to fig. 2, in the embodiment of the present invention, the obtaining of the preset path planning template includes:
s21) obtaining a relative position between the target position and the current position;
s22) obtaining a path classification model;
s23) analyzing the relative position based on the path classification model to obtain a matching planning path matched with the relative position;
s24) generating the preset path planning template based on the matching planning path.
Further, in this embodiment of the present invention, the obtaining the path classification model includes: obtaining a plurality of complete parking paths, wherein each complete parking path comprises a starting point, an end point and a course angle; clustering the complete parking paths to obtain clustered paths; and acquiring a preset training model, training the preset training model based on the clustered paths, and generating the path classification model.
In embodiments of the present invention, the vehicle includes, but is not limited to, a family car, a truck, and the like.
In one possible embodiment, a user determines that a destination is about to be reached while driving a vehicle, and therefore issues an instruction to the vehicle to automatically park a vehicle, for example, by pressing a preset button in the vehicle to send the instruction to the vehicle. And after the vehicle acquires the instruction, planning an automatic parking path immediately. The vehicle first obtains environment perception information, for example, the environment perception information includes, but is not limited to, a target location where the vehicle is to park, a current location of the vehicle, and obstacle information within a preset distance of the target location.
In an embodiment of the present invention, the target position may be represented as p _ t ═ (x _ t, y _ t, theta _ t), the current position of the vehicle may be represented as p _ e ═ (x _ e, y _ e, theta _ e), where x _ t and y _ t are coordinates of the target position, theta _ t is a vehicle heading angle of the target position, x _ e and y _ e are coordinates of the current position, and theta _ e is a vehicle heading angle of the current position, and the obstacle information may be generated as the obstacle information according to detected obstacle data, for example, the obstacle data includes, but is not limited to, an obstacle position, an obstacle size, and the like, and the inaccessible area boundary is generated according to the obstacle data. In order to increase the distance of the path planning and the computation amount in the path planning process, a preset path planning template may be stored in the vehicle in advance, and the preset path planning template includes at least one preset path.
For example, in the embodiment of the present invention, the Vehicle may first obtain a target location to be parked and a current location of the Vehicle based on a high-precision map or a high-precision positioning method or V2X (Vehicle-to-electric-parking) technology, and further obtain a relative location between the target location and the current location, for example, in the embodiment of the present invention, the current location of the Vehicle may be 100m away from the target location, that is, the relative location is a linear distance of 100m, and the relative location may also be obtained by establishing a coordinate system with the current location of the Vehicle as an origin, mapping the target location onto the coordinate system, and thereby obtaining a relative location between the current location of the Vehicle and the target location, where the relative location includes, but is not limited to, information such as a distance between the current location and the target location, an orientation, and the like. And at the moment, the vehicle calls a path classification model, and analyzes the relative position between the target position and the current position according to the path classification model so as to obtain a matching planning path corresponding to the relative position.
For example, in the embodiment of the present invention, all path planning data for successful parking may be stored, for example, each complete parking path includes a start point, an end point, and a heading angle of the vehicle, and each complete parking path is mapped in a coordinate system with the start point as an origin. At this time, clustering is performed on all the complete parking paths, and multiple post-clustering paths are obtained, and further, a preset training model is obtained, for example, in the embodiment of the present invention, the preset training model includes but is not limited to a support vector machine or a neural network, and after the post-clustering paths are input into the preset training model for training and learning, a corresponding path classification model is obtained.
In a specific application process, after the current position and the target position of the vehicle are obtained, a coordinate system may be established with the current position of the vehicle as a coordinate origin, the target position is used as a destination to obtain a relative position of the vehicle, and then the current position, the target position and the relative position are input into a path classification model to be analyzed to obtain a probability that the relative position belongs to a certain classification, for example, when the probability that the relative position belongs to a certain classification is greater than a preset probability threshold (for example, greater than 80%), it may be determined that the relative position belongs to a parking path corresponding to the classification, that is, a matching planning path matched with the relative position is obtained. At this time, the parameters of the matching planned path are further fine-tuned according to the current position and the target position of the vehicle, for example, a mesh search may be performed near the matching planned path at a preset resolution to find a required control input, so that a final preset path planning template is generated according to the fine-tuned planned path.
In the embodiment of the invention, the preset path planning template is preset in the vehicle according to the running condition of the vehicle, so that the corresponding automatic parking planning path can be quickly obtained according to the environment perception information in the process that the vehicle needs to be automatically parked, the calculation amount is reduced, the path planning efficiency is greatly improved, and the user experience is improved.
In the embodiment of the invention, the more appropriate preset path planning template is selected according to the relative position between the target position and the current position, so that the automatic parking path can be planned when the vehicle is far away from the target position, instead of detecting the position information of the target position through the vehicle end sensor and planning the automatic parking path after the vehicle passes through the target position, and the user experience is improved.
Furthermore, the embodiment of the invention can be applied to parking spaces of types such as parallel parking spaces, vertical parking spaces, inclined side parking spaces and the like, so that the application compatibility of the method is greatly improved, and the application commercial value of the method provided by the embodiment of the invention is improved.
Referring to fig. 3, in an embodiment of the present invention, the generating a planned path for automatic parking based on the environment sensing information and the preset path planning template includes:
s31) obtaining a first post-operation end point based on the target position according to the preset path;
s32) judging whether the first operated end point is matched with the current position;
s33) generating the planned path based on the target position, the current position, and the obstacle information, the planned path including a line segment and/or a circular arc, in a case where the first post-calculation end point matches the current information.
In an embodiment of the present invention, the first post-operation end point includes a plurality of point locations, and the method further includes: before judging whether the end point is matched with the current position after the first operation, screening the plurality of point locations according to a preset algorithm to obtain at least one screened point location; and taking the at least one screened point location as the first post-operation end point.
In this embodiment of the present invention, the determining whether the end point after the first operation matches the current position includes: judging whether the end point is coincident with the current position after the first operation; determining that the first post-computation end point matches the current position when the first post-computation end point coincides with the current position; or obtaining a third post-operation end point based on the current position according to a preset path planning algorithm; judging whether the first post-operation end point is coincident with the third post-operation end point; and determining that the first post-operation end point is matched with the current position under the condition that the first post-operation end point is coincident with the third post-operation end point.
In an embodiment of the present invention, the method further comprises: s341) under a condition that the first post-computation end point does not match the current position, obtaining a second post-computation end point according to the preset path based on the first post-computation end point; s342) judging whether the second operated end point is matched with the current position; s343), if yes, generating a corresponding planned path based on the target position, the first post-operation end point, the second post-operation end point and the obstacle information; s344) if not, taking the second post-operation end point as the first post-operation end point, and circularly executing the steps S341) -S344) until the second post-operation end point is matched with the current position.
Further, in an embodiment of the present invention, the method further includes: acquiring a preset cycle threshold; judging the number of times of loop execution steps S341) -S344); judging whether the cycle number is greater than the preset cycle threshold value; stopping loop execution of steps S341) -S344) in case the number of loops is larger than the preset loop threshold.
In this embodiment of the present invention, the generating a corresponding planned path based on the target position, the current position, and the obstacle information includes: acquiring vehicle body information of the vehicle; generating a movable area based on the obstacle information and the vehicle body information; generating a continuous path in the movable area by taking the target position as a starting point and the current position as an end point, wherein the continuous path is formed by line segments and/or circular arcs; and taking the continuous path as the planning path.
Referring to fig. 4, in order to determine a position to which a current vehicle should be driven, and to which a parking space can be automatically parked, in one possible embodiment, after the target position is obtained, the target position is reversely calculated as a starting point, for example, in an embodiment of the present invention, a first post-calculation end point is obtained after reverse calculation according to the preset path, and the calculation manner may be expressed as a first post-calculation end point p _1 ═ f (p _ t, t _1, l _1), where t _1 represents a path template for selecting different directions (e.g., an arc path is a steering angle corresponding to the arc), l _1 represents a length of the path template running along the selected direction, f is a path template formula, represents a preset path for driving the vehicle, and may be an arc path (i.e., steering is kept constant), or may be another path expression, and are not intended to be limiting.
And then judging whether the first calculated end point is matched with the current position, and generating a corresponding planned path according to the target position, the current position and the obstacle information under the condition that the first calculated end point is matched with the current position, wherein the planned path comprises but is not limited to a line segment and/or an arc.
Referring to fig. 5, in one possible implementation, the first post-operation endpoint obtained as described above includes a plurality of points. Before the determination, in order to further reduce the amount of calculation in the path planning process and reduce the difficulty of path planning, the multiple point locations are further screened, for example, in the embodiment of the present invention, the multiple point locations may be screened according to a preset algorithm, for example, the multiple point locations may be screened according to a distance between each point location and a current position, or according to whether an obstacle exists near each point location, or according to a distance between each point location and an obstacle, or the like, and at least one screened point location is obtained as a first post-operation end point, and at this time, it is further determined whether the first post-operation end point matches with the current position, so that the amount of calculation in the path planning process can be greatly reduced.
For example, it may be directly determined whether a point that coincides with the current position exists in at least one point in the first post-operation end point, for example, p _ e may be made to be p _1, and a corresponding equation p _ e is solved to be f (p _ t, t _1, l _1), and it is determined whether a corresponding solution exists, if so, it is determined that the first post-operation end point matches the current position, and in a specific solving process, a person skilled in the art may perform solving by using a method such as an analytic or numerical method according to a specific form of the formula f to obtain a lower solving difficulty or a higher solving accuracy, which is not described herein in detail.
However, in practical applications, since the relative position relationship between the parking posture of the vehicle driven by the user and the parking space is very different, the success rate of the direct matching is low, and therefore, referring to fig. 6, in another possible implementation, a third post-calculation end point may be further calculated according to the preset planned path template, with the current position as a starting point (that is, the preset planned path template is applied to the current position and the target position of the current vehicle at the same time to perform a faster position matching operation, so as to accelerate the generation of the planned path), where the third post-calculation end point may also include a plurality of point locations, for example, p _2 ═ f (p _ e, t _ e1, l _ e1), at which time, it is further determined whether there is a point location that coincides with at least one of the third post-calculation end points in the plurality of point locations in the first post-calculation end point, for example, p _2 may be made equal to p _1, that is, f (p _ e, t _ e1, l _ e1) is solved, and whether a corresponding solution exists is determined, and if the solution exists, it is determined that the end point after the first operation matches the end point after the third operation.
In the prior art, when a driver needs to automatically park a vehicle, the driver often needs to drive the vehicle to a position near a corresponding parking space, and at this time, a sensor configured on the vehicle can acquire environment sensing information near the parking space, and further plan an automatic parking path, so that the automatic parking path cannot be planned before the driver drives the parking space. In order to solve the above-mentioned technical problem, in the course of planning the automatic parking path of the current vehicle, the destination position may be used as a starting point to obtain a first post-operation end point according to the preset path planning template, and if the first post-operation end point is not matched with the current position, further using the first post-operation end point as a starting point to obtain a corresponding second post-operation end point according to a preset path in the preset path planning template, and further determining whether the end point after the second operation is matched with the current position, if not, then the steps are continuously and repeatedly executed until the obtained calculated end point is matched with the current position, at the moment, a corresponding planning path is generated based on the target position information, the current position information, the obstacle information and all the calculated end points, for example, in the embodiment of the present invention, all of the calculated end points are the first calculated end point and the second calculated end point.
In other words, in the embodiment of the invention, the automatic parking path can be planned when the vehicle is away from the parking space by a certain distance, and the automatic parking path is planned without driving to the vicinity of the parking space, so that the planned distance for planning the automatic parking path is effectively increased, a user can control the vehicle to plan the automatic parking path at any position close to the parking space, and the user experience is improved.
Further, in order to avoid the occurrence of the situation that the vehicle performs infinite iterative computation during the planning process of the automatic parking path because a good understanding cannot be found, the number of times of repetition of the steps is further monitored during the process of repeating the end point after the calculation of the steps, for example, in the embodiment of the present invention, when the number of times of repetition is greater than a preset loop threshold (for example, the preset loop threshold may be 5), the loop is stopped to perform the steps.
It should be noted that, as is readily known by those skilled in the art, after the end point after the second operation is obtained, point locations in the end point after the second operation may also be screened, or the end point after the second operation and the current position may be simultaneously calculated for planning a path, which should be easily thought by those skilled in the art according to the embodiment of the present invention, and therefore, should all belong to the protection scope of the embodiment of the present invention, and will not be described herein in too much detail.
For example, in the embodiment of the present invention, when a vehicle calls a preset path planning template to perform path planning, the template is only applied once to determine that the terminal after the first operation matches the current position, so that vehicle body information of the vehicle can be obtained, a movable region of the vehicle is generated according to the obstacle information and the vehicle body information, at this time, the preset path in the template is extracted, the current position of the vehicle is taken as a starting point of the planned path, the target position is taken as a terminal point of the preset path to generate a continuous path, the continuous path is located in the movable region, and the continuous path is taken as a planned path for automatic parking of the vehicle.
In the embodiment of the invention, the point positions of the end point after each calculation are screened in a heuristic mode, so that the calculation amount and the calculation difficulty in the subsequent path planning process are greatly reduced, the path planning speed is increased, the long-time waiting of a user is avoided, and the user experience is improved.
In the embodiment of the invention, the bidirectional path planning is carried out on the target position and the current position according to the preset path planning template, so that the planning efficiency of the path planning is greatly improved, the autonomy of the vehicle during automatic parking is further improved, and the calculated amount and the calculation difficulty in the parking path planning process are reduced.
The following describes an automatic parking path planning apparatus according to an embodiment of the present invention with reference to the drawings.
Referring to fig. 7, based on the same inventive concept, an embodiment of the present invention provides an automatic parking path planning apparatus, including: the environment sensing unit is used for acquiring environment sensing information of the vehicle, wherein the environment sensing information comprises a target position, a current position and obstacle information; the system comprises a template obtaining unit, a path planning unit and a path planning unit, wherein the template obtaining unit is used for obtaining a preset path planning template which comprises a preset path; and the path planning unit is used for generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
Further, the embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the method according to the embodiment of the present invention.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention do not describe every possible combination.
Those skilled in the art will understand that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (11)
1. A method for planning an automatic parking route, the method comprising:
acquiring environment perception information of a vehicle, wherein the environment perception information comprises a current position of the vehicle, a target position of the vehicle and obstacle information within a preset distance of the target position;
acquiring a preset path planning template, wherein the preset path planning template comprises a preset path;
and generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
2. The method of claim 1, wherein the obtaining the preset path planning template comprises:
acquiring a relative position between the target position and the current position;
acquiring a path classification model;
analyzing the relative position based on the path classification model to obtain a matching planning path matched with the relative position;
and generating the preset path planning template based on the matched planning path.
3. The method of claim 2, wherein obtaining the path classification model comprises:
obtaining a plurality of complete parking paths, wherein each complete parking path comprises a starting point, an end point and a course angle;
clustering the complete parking paths to obtain clustered paths;
and acquiring a preset training model, training the preset training model based on the clustered paths, and generating the path classification model.
4. The method of claim 1, wherein generating a planned path for automatic parking based on the context awareness information and the preset path planning template comprises:
obtaining a first post-operation end point according to the preset path based on the target position;
judging whether the end point is matched with the current position after the first operation;
and under the condition that the first post-operation end point is matched with the current position, generating the planned path based on the target position, the current position and the obstacle information, wherein the planned path comprises a line segment and/or an arc.
5. The method of claim 4, wherein the first post-computation endpoint comprises a plurality of points, the method further comprising:
before judging whether the end point is matched with the current position after the first operation, screening the plurality of point locations according to a preset algorithm to obtain at least one screened point location;
and taking the at least one screened point location as the first post-operation end point.
6. The method of claim 4, wherein said determining whether the first post-calculation endpoint matches the current location comprises:
judging whether the end point is coincident with the current position after the first operation;
determining that the first post-computation end point matches the current position when the first post-computation end point coincides with the current position; or
Obtaining a third post-operation end point according to a preset path planning algorithm based on the current position;
judging whether the first post-operation end point is coincident with the third post-operation end point;
and determining that the first post-operation end point is matched with the current position under the condition that the first post-operation end point is coincident with the third post-operation end point.
7. The method of claim 4, further comprising:
s341) under a condition that the first post-computation end point does not match the current position, obtaining a second post-computation end point according to the preset path based on the first post-computation end point;
s342) judging whether the second operated end point is matched with the current position;
s343), if yes, generating a corresponding planned path based on the target position, the first post-operation end point, the second post-operation end point and the obstacle information;
s344) if not, taking the second post-operation end point as the first post-operation end point, and circularly executing the steps S341) -S344) until the second post-operation end point is matched with the current position.
8. The method of claim 7, further comprising:
acquiring a preset cycle threshold;
judging the number of times of loop execution steps S341) -S344);
judging whether the cycle number is greater than the preset cycle threshold value;
stopping loop execution of steps S341) -S344) in case the number of loops is larger than the preset loop threshold.
9. The method of claim 4, wherein the generating the planned path based on the target location, the current location, and the obstacle information comprises:
acquiring vehicle body information of the vehicle;
generating a movable area based on the obstacle information and the vehicle body information;
generating a continuous path in the movable area by taking the target position as a starting point and the current position as an end point, wherein the continuous path is formed by line segments and/or circular arcs;
and taking the continuous path as the planning path.
10. An automatic parking path planning apparatus, comprising:
the environment sensing unit is used for acquiring environment sensing information of a vehicle, wherein the environment sensing information comprises a target position of the vehicle, a current position of the vehicle and obstacle information within a preset distance of the target position;
the system comprises a template obtaining unit, a path planning unit and a path planning unit, wherein the template obtaining unit is used for obtaining a preset path planning template which comprises a preset path;
and the path planning unit is used for generating a planning path for automatic parking based on the environment perception information and the preset path planning template.
11. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110190169.8A CN113008256A (en) | 2021-02-18 | 2021-02-18 | Automatic parking path planning method, automatic parking path planning device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110190169.8A CN113008256A (en) | 2021-02-18 | 2021-02-18 | Automatic parking path planning method, automatic parking path planning device, and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113008256A true CN113008256A (en) | 2021-06-22 |
Family
ID=76403387
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110190169.8A Pending CN113008256A (en) | 2021-02-18 | 2021-02-18 | Automatic parking path planning method, automatic parking path planning device, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113008256A (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050102097A1 (en) * | 2003-11-10 | 2005-05-12 | Masaaki Tanizaki | Map information supply device for mobile units |
US20180009477A1 (en) * | 2016-07-07 | 2018-01-11 | Ford Global Technologies, Llc | Vehicle with park assist |
CN108860139A (en) * | 2018-04-11 | 2018-11-23 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN111081064A (en) * | 2019-12-11 | 2020-04-28 | 上海赫千电子科技有限公司 | Automatic parking system and automatic passenger-replacing parking method of vehicle-mounted Ethernet |
CN111098852A (en) * | 2019-12-02 | 2020-05-05 | 北京交通大学 | Parking path planning method based on reinforcement learning |
CN111126598A (en) * | 2019-12-19 | 2020-05-08 | 深圳南方德尔汽车电子有限公司 | Automatic parking method, automatic parking device, computer equipment and storage medium |
CN111982137A (en) * | 2020-06-30 | 2020-11-24 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating route planning model |
CN111976717A (en) * | 2019-11-29 | 2020-11-24 | 长城汽车股份有限公司 | Intelligent parking method and device |
CN112230638A (en) * | 2019-06-28 | 2021-01-15 | 初速度(苏州)科技有限公司 | Parking path planning method and device for vehicle |
CN112298194A (en) * | 2019-07-29 | 2021-02-02 | 初速度(苏州)科技有限公司 | Lane changing control method and device for vehicle |
CN112356830A (en) * | 2020-11-25 | 2021-02-12 | 同济大学 | Intelligent parking method based on model reinforcement learning |
-
2021
- 2021-02-18 CN CN202110190169.8A patent/CN113008256A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050102097A1 (en) * | 2003-11-10 | 2005-05-12 | Masaaki Tanizaki | Map information supply device for mobile units |
US20180009477A1 (en) * | 2016-07-07 | 2018-01-11 | Ford Global Technologies, Llc | Vehicle with park assist |
CN108860139A (en) * | 2018-04-11 | 2018-11-23 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN112230638A (en) * | 2019-06-28 | 2021-01-15 | 初速度(苏州)科技有限公司 | Parking path planning method and device for vehicle |
CN112298194A (en) * | 2019-07-29 | 2021-02-02 | 初速度(苏州)科技有限公司 | Lane changing control method and device for vehicle |
CN111976717A (en) * | 2019-11-29 | 2020-11-24 | 长城汽车股份有限公司 | Intelligent parking method and device |
CN111098852A (en) * | 2019-12-02 | 2020-05-05 | 北京交通大学 | Parking path planning method based on reinforcement learning |
CN111081064A (en) * | 2019-12-11 | 2020-04-28 | 上海赫千电子科技有限公司 | Automatic parking system and automatic passenger-replacing parking method of vehicle-mounted Ethernet |
CN111126598A (en) * | 2019-12-19 | 2020-05-08 | 深圳南方德尔汽车电子有限公司 | Automatic parking method, automatic parking device, computer equipment and storage medium |
CN111982137A (en) * | 2020-06-30 | 2020-11-24 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating route planning model |
CN112356830A (en) * | 2020-11-25 | 2021-02-12 | 同济大学 | Intelligent parking method based on model reinforcement learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107480638B (en) | Vehicle obstacle avoidance method, controller, device and vehicle | |
CN108140319B (en) | Parking assistance method and parking assistance device | |
US10319233B2 (en) | Parking support method and parking support device | |
JP6528857B2 (en) | Parking support method and apparatus | |
JP5301448B2 (en) | Analysis method around the vehicle | |
CN112180921B (en) | Automatic driving algorithm training system and method | |
CN106314423A (en) | Vehicle traveling control device | |
KR20180069854A (en) | Display method of parking support information and parking support device | |
US10755117B2 (en) | Obstacle determination method, parking support method, dispatch support method, and obstacle determination device | |
CN111511610B (en) | Parking control method and parking control device | |
CN113324554B (en) | Automatic driving route planning method and device, readable storage medium and electronic equipment | |
CN109212572B (en) | Positioning drift detection method, device and equipment and computer readable storage medium | |
JPWO2017187592A1 (en) | Parking support method and apparatus | |
JP2021187248A (en) | Parking support device and control method of parking support device | |
CN109844670A (en) | For running the method and motor vehicle of motor vehicle in navigational environment | |
JPWO2019123587A1 (en) | Parking control method and parking control device | |
CN113096433A (en) | Autonomous parking method and device based on vehicle-road cooperation and storage medium | |
CN110678914A (en) | Vehicle control apparatus and method for control of autonomous vehicle | |
CN112477850A (en) | Parking path planning method and device, vehicle-mounted equipment and storage medium | |
US11814072B2 (en) | Method and system for conditional operation of an autonomous agent | |
CN109204315A (en) | Method, apparatus, storage medium and the electronic equipment of changing Lane | |
CN111256719A (en) | Obstacle detouring method and device | |
CN111626164A (en) | Vehicle collision information acquisition method, device, equipment and storage medium | |
CN110626349B (en) | Control method and device for automatic driving vehicle, automobile controller and storage medium | |
CN113008256A (en) | Automatic parking path planning method, automatic parking path planning device, and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |