CN115465266A - Parking path planning method, device, equipment and storage medium - Google Patents

Parking path planning method, device, equipment and storage medium Download PDF

Info

Publication number
CN115465266A
CN115465266A CN202211402839.9A CN202211402839A CN115465266A CN 115465266 A CN115465266 A CN 115465266A CN 202211402839 A CN202211402839 A CN 202211402839A CN 115465266 A CN115465266 A CN 115465266A
Authority
CN
China
Prior art keywords
pose
path
vehicle
target
parking
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.)
Granted
Application number
CN202211402839.9A
Other languages
Chinese (zh)
Other versions
CN115465266B (en
Inventor
刘世蔷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jidu Technology Co Ltd
Original Assignee
Jidu Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jidu Technology Co ltd filed Critical Jidu Technology Co ltd
Priority to CN202211402839.9A priority Critical patent/CN115465266B/en
Publication of CN115465266A publication Critical patent/CN115465266A/en
Application granted granted Critical
Publication of CN115465266B publication Critical patent/CN115465266B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/06Automatic manoeuvring for parking
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00Road transport of goods or passengers
    • Y02T10/10Internal combustion engine [ICE] based vehicles
    • Y02T10/40Engine management systems

Abstract

The application provides a parking path planning method, a parking path planning device, parking path planning equipment and a parking path planning storage medium, which are applicable to the field of parking. Wherein, in response to a parking request, a first parking path for the vehicle to travel forward from a start pose to an end pose is determined; under the condition that the first parking path does not meet the driving requirement, at least two target poses are searched by taking the driving requirement as an optimization target so as to determine a second parking path for the vehicle to drive forwards from the starting pose to the first target pose, a third parking path for the vehicle to drive forwards from the last target pose to the ending pose, and at least one fourth parking path for the vehicle to drive forwards or backwards between two adjacent target poses in the at least two target poses; the target parking path is formed by the second parking path, at least one fourth parking path and the third parking path. The technical scheme provided by the application solves the problem that the route based on vehicle tail parking is not suitable for the scene of vehicle head parking, and realizes the parking route planning based on vehicle head parking.

Description

Parking path planning method, device, equipment and storage medium
Technical Field
The embodiment of the application relates to the field of parking, in particular to a parking path planning method, device, equipment and storage medium.
Background
With the development of vehicle intellectualization, the automatic parking function is widely applied, and automatic parking and warehousing can be realized according to a planned parking path.
Therefore, how to plan the parking route is an urgent problem to be solved.
Disclosure of Invention
The embodiment of the application provides a parking path planning method, a parking path planning device, equipment and a storage medium, which are used for realizing parking path planning.
In a first aspect, an embodiment of the present application provides a parking path planning method, including:
determining a first parking path for the vehicle to travel forward from a start pose to an end pose in response to the parking request;
in the case that the first parking path does not meet a driving requirement, taking the driving requirement as an optimization target, finding at least two target poses to determine a second parking path for the vehicle to drive forwards from the starting pose to a first target pose, a third parking path for the vehicle to drive forwards from a last target pose to the ending pose, and at least one fourth parking path for the vehicle to drive forwards or backwards between two adjacent target poses of the at least two target poses;
and the second parking path, at least one fourth parking path and the third parking path form a target parking path.
In a second aspect, an embodiment of the present application provides a parking path planning apparatus, including:
a first determination module for determining a first parking path for the vehicle to travel forward from a start pose to an end pose in response to a parking request;
a finding module, configured to find at least two target poses with the driving requirement as an optimization target to determine a second parking path for the vehicle to travel forward from the start pose to a first target pose, a third parking path for the vehicle to travel forward from a last target pose to the end pose, and at least one fourth parking path for the vehicle to travel forward or backward between two adjacent target poses of the at least two target poses, if the first parking path does not meet the driving requirement;
and the second determining module is used for forming a target parking path by the second parking path, at least one fourth parking path and the third parking path.
In a third aspect, an embodiment of the present application provides a computing device, including a storage component and a processing component; the storage component stores one or more computer program instructions, which are invoked for execution by the processing component, and the processing component executes the one or more computer program instructions to implement the parking path planning method according to the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a computer, implements the parking path planning method according to the first aspect.
In the embodiment of the application, after responding to a parking request, a first parking path for a vehicle to travel forwards from a starting position to an ending position can be determined, and in the case that the first parking path does not meet the travel requirement, at least two target positions are searched by taking the travel requirement as an optimization target, a second parking path for the vehicle to travel forwards from the starting position to the first target position, a third parking path for the vehicle to travel forwards from the last target position to the ending position, and at least one fourth parking path for the vehicle to travel forwards or backwards between two adjacent target positions in the at least two target positions can be determined, and the target parking paths are formed by the second parking path, the at least one fourth parking path and the third parking path. Therefore, the vehicle can automatically run from the starting position to the ending position according to the target parking path, so that automatic parking is realized.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following descriptions are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart illustrating one embodiment of a parking path planning method provided by the present application;
FIG. 2 is a schematic diagram illustrating one embodiment of a parking scenario provided by the present application;
FIG. 3 is a schematic diagram illustrating another embodiment of a parking scenario provided by the present application;
4-1 illustrates a schematic diagram of one embodiment of a first target pose provided herein;
4-2 illustrate a schematic view of one embodiment of a second target pose provided herein;
fig. 5 is a schematic structural diagram illustrating an embodiment of a parking path planning apparatus provided in the present application;
FIG. 6 illustrates a schematic structural diagram of one embodiment of a computing device provided herein.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
In some of the flows described in the specification and claims of this application and in the above figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, the order of the operations being 101, 102, etc. merely to distinguish between various operations, the order of which does not itself denote any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical scheme is suitable for parking scenes, particularly automatic parking scenes. With the development of vehicle intellectualization, the automatic parking function is widely applied, and automatic parking and warehousing can be realized according to a planned parking path.
In the traditional scheme, a parking path is usually realized based on a car tail storage mode, for a scene that part of car heads are parked in, such as a parking space close to a wall, a car cannot drive through the parking space to park, a car can be reversely parked in an inclined parking space, and the like, and a good parking path realization method is not provided. Therefore, how to plan the parking path based on the locomotive is an urgent problem to be solved.
In order to solve the above technical problem, the inventor provides a parking path planning method, including: in response to a parking request, determining a first parking path for a vehicle to travel forward from an initial pose to an end pose; in the case that the first parking path does not meet a driving requirement, taking the driving requirement as an optimization target, finding at least two target poses to determine a second parking path for the vehicle to drive forwards from the starting pose to a first target pose, a third parking path for the vehicle to drive forwards from a last target pose to the ending pose, and at least one fourth parking path for the vehicle to drive forwards or backwards between two adjacent target poses of the at least two target poses; and the second parking path, at least one fourth parking path and the third parking path form a target parking path.
According to the scheme, the vehicle can automatically run from the starting position to the ending position according to the target parking path, so that automatic parking is achieved. And the target parking path is planned based on a parking mode, and is suitable for a parking scene of parking.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As shown in fig. 1, a flowchart of an embodiment of a parking path planning method provided by the embodiment of the present application may include the following steps:
101: in response to a parking request, a first parking path for a vehicle to travel forward from an initial pose to an end pose is determined.
The embodiment of the application is suitable for parking scenes, in particular parking scenes of parking at the car head. In response to a parking request for a certain vehicle, a target parking path of the vehicle can be determined, so that the vehicle can automatically park according to the target parking path. The parking request may be triggered by a user, and the triggering manner may include key triggering, voice triggering, and the like, without limitation.
In response to the parking request, a starting pose and an ending pose of the vehicle may be determined. The starting pose may include a starting position and an initial pose where the vehicle requests parking, and the ending pose may include an ending position and an ending pose where the vehicle requests parking, for example, when the vehicle requests parking in a certain parking space, the ending position may refer to a certain position of the parking space. Fig. 2 shows a schematic diagram of an exemplary parking scenario, in which the start position Os and the end position Oe of the vehicle are marked. The coordinates of the start pose Os in the world coordinate system may be represented as (xs, ys, θ s), the coordinates of the end pose Oe in the world coordinate system may be represented as (xe, ye, θ e), the position coordinates (xs, ys) of the start pose Os may refer to the midpoint coordinates of the rear axle of the vehicle body at the start position, the attitude angle θ s may refer to an included angle between the central axis L1 of the vehicle at the start position and the y-axis of the world coordinate system (determined based on the moving direction of the vehicle at the start position, such as the vehicle moving downward to the right in fig. 2, and the degree of rightward movement is greater, so the y-axis of the world coordinate system is the horizontal rightward direction), the position coordinates (xe, ye) of the end pose Oe may refer to the central axis coordinates of the rear axle of the vehicle body at the end position, and the attitude angle θ e may refer to an included angle between the central axis L2 of the vehicle at the end position and the y-axis of the world coordinate system.
According to the starting pose and the ending pose, a first parking path from the starting pose to the ending pose of the vehicle in a forward driving mode can be determined according to a preset path planning mode. Forward travel may refer to travel from the rear of the vehicle to the front of the vehicle. The path planning mode may include a geometric path planning mode, a hybrid a-star algorithm, and the like, and may be set according to an actual application scenario. A manner of determining the first parking path will be described in the following embodiments, and will not be described herein.
Optionally, in order to ensure that the vehicle can park smoothly according to the determined parking path, whether the first parking path meets the driving requirement may be determined.
The driving requirements can include requirements of both sport realization and safe driving. For the motion realization aspect, the determined first parking path will typically include a circular arc path. In order to achieve that the vehicle can follow a circular arc path, the radius of the circular arc path needs to be larger than the minimum turning radius of the vehicle. The minimum turning radius refers to the radius of a track circle which is turned by the center of a rear axle when the steering wheel is turned to the limit position and the automobile is steered and driven at the lowest stable speed.
Thus, the travel request may include: the radius of the circular arc path in the parking path is larger than the minimum turning radius of the vehicle.
Alternatively, in response to a parking request for a vehicle, the requesting vehicle may be determined, and the minimum turning radius of the vehicle may be determined. And judging whether the radius of the arc path in the parking path is larger than the minimum turning radius or not.
For safe driving, the vehicle needs to avoid collision with the obstacle during driving. Therefore, the travel request may further include: the vehicle is located at any position of the road surface corresponding to the parking path and does not overlap with the obstacle.
Specifically, the detection device such as an ultrasonic radar or a laser radar may be used to detect obstacles in the space corresponding to the parking path, such as vehicles and pedestrians on the road surface corresponding to the parking path, pillars in the parking space, and the like, so as to obtain the position and size information of the obstacles. And judging whether the vehicle collides with the obstacle or not by combining any position of the vehicle on the road surface corresponding to the parking path and the vehicle size information.
In practical application, other driving requirements can be set, and the first parking path is correspondingly judged, which is not limited in the application.
102: in the case where the first parking path does not meet the driving requirement, at least two target poses are sought with the driving requirement as an optimization goal to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a third parking path for the vehicle to travel forward from the last target pose to the end pose, and at least one fourth parking path for the vehicle to travel forward or backward between two adjacent target poses of the at least two target poses.
The first parking path is determined under the condition that the vehicle only carries out forward driving once, when the first parking path is judged to be not in accordance with the driving requirement, the vehicle cannot drive from the initial position to the end position when only carrying out forward driving once, at the moment, backward driving, namely the driving process of backing can be added, and the parking path comprising multiple driving processes is determined.
Specifically, the driving requirement can be used as an optimization target to search at least two target poses as intermediate parking poses, so that the vehicle can drive from the starting pose to the ending pose through the intermediate parking poses.
The number of target poses can be set according to the actual application scene. For example, the target poses may be set to two, at which time two target poses are sought with the travel requirement as the optimization target to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a fourth parking path for the vehicle to travel backward from the first target pose to the second target pose, and a third parking path for the vehicle to travel forward from the second target pose to the end pose. For another example, the target poses may be set to four, at which time, four target poses may be found with the travel requirement as the optimization target to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, travel backward from the first target pose to the second target pose, travel forward from the second target pose to the third target pose, and a plurality of fourth parking paths for travel backward from the third target pose to the fourth target pose, and a third parking path for travel forward from the fourth target pose to the end pose.
The above-mentioned process of finding the target pose will be described in detail in the following embodiments, and will not be described herein.
103: the target parking path is formed by the second parking path, at least one fourth parking path and the third parking path.
The determined second parking path, the at least one fourth parking path and the third parking path may be connected end to obtain a complete target parking path.
In this embodiment, after responding to a parking request, a first parking path for a vehicle to travel forward from a start pose to an end pose may be determined, and in the case where the first parking path does not meet the travel requirement, at least two target poses may be found with the travel requirement as an optimization target to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a third parking path for the vehicle to travel forward from the last target pose to the end pose, and at least one fourth parking path for the vehicle to travel forward or backward between two adjacent target poses among the at least two target poses, and the target parking paths are configured by the second parking path, the at least one fourth parking path, and the third parking path. Therefore, the vehicle can automatically drive from the initial pose to the final pose according to the target parking path so as to realize automatic parking. And the target parking path is planned based on a parking mode, and is suitable for a parking scene of parking.
Optionally, when it is determined that the first parking path meets the driving requirement, it indicates that the vehicle may drive forward from the start pose to the end pose according to the first parking path, and at this time, the first parking path may be directly used as a target parking path, so as to improve the path planning efficiency.
The following describes a process for determining a first parking path for a vehicle traveling forward from a start position to an end position by using a geometric path planning method.
In some embodiments, a method of determining a first parking path for a vehicle to travel forward from a starting pose to an ending pose may comprise:
and determining a first parking path from the starting pose to the ending pose of the vehicle, wherein the vehicle alternately travels forwards according to a straight path and a circular path.
The first parking path may include a straight path and an arc path. With reference to the schematic diagram of fig. 2, the radius R of the circular arc path may be preferentially determined based on the first distance le from the position point of the ending pose Oe to the vehicle central axis L1 at the start position, the attitude angle θ s of the starting pose Os, and the attitude angle θ e of the ending pose Oe. Specifically, the calculation can be performed according to the following radius formula.
The radius formula may be:
Figure DEST_PATH_IMAGE001
(ii) a Where R represents a radius of the circular arc path, le represents a first distance from a position point of the end pose Oe to the central axis L1 of the vehicle at the start position, θ s represents a pose angle of the start pose Os, and θ e represents a pose angle of the end pose Oe.
After the radius R of the circular arc path is determined, the distance of the straight line path which is driven forwards in a straight line by the initial pose Os can be determined based on the radius R of the circular arc path, the second distance ls from the position point of the initial pose Os to the central axis L2 of the vehicle at the ending position, the attitude angle theta s and the attitude angle theta e. Specifically, the calculation can be performed according to the following distance formula of the straight path.
The distance formula for this straight path may be:
Figure 903774DEST_PATH_IMAGE002
(ii) a Where dl denotes a distance of the straight path, and ls denotes a second distance from the position point of the start attitude Os to the vehicle central axis L2 at the end position.
After the distance dl of the straight path is determined, the intersection Oc of the straight path and the circular arc path can be determined by combining the distance of the straight path, the attitude angle θ s, and the attitude angle θ e. Specifically, the calculation may be performed according to the following first coordinate formula.
The first coordinate formula may be;
Figure DEST_PATH_IMAGE003
(ii) a Wherein xs represents the abscissa of the initial pose Os, and ys represents the ordinate of the initial pose Os.
Then, a straight line path with the start pose Os as a starting point and the intersection Oc as an end point, and an arc path with the end pose Oe as an end point and the radius R may be determined, and a first parking path composed of the straight line path and the arc path may be determined.
The first distance le and the second distance ls may be obtained by coordinate transformation. Specifically, the distance may be calculated according to the following first distance formula and second distance formula.
The first distance formula may be:
Figure 243751DEST_PATH_IMAGE004
(ii) a Where le denotes the first distance, xe denotes the abscissa of the ending pose Oe, xs denotes the abscissa of the starting pose Os, ye denotes the ordinate of the ending pose Oe, and ys denotes the ordinate of the starting pose Os.
The second distance formula may be:
Figure DEST_PATH_IMAGE005
(ii) a Where ls denotes the second distance.
The first parking path is obtained based on the planning of the driving process of the straight path and the circular arc path in the schematic diagram shown in fig. 2. In practical application, the driving process can also be realized as an arc path and a straight path, and at this time, the first parking path can also be determined according to the above geometric path planning mode, which is not described again.
The first parking path formed by the straight path and the circular arc path is determined by using a geometric programming mode, so that the data operation processing process in the determination of the first parking path is simplified, the determination efficiency of the first parking path is improved, and the determination process is visual, clear, simple and easy to implement.
In some embodiments, before the first parking path planning is performed, the driving sequence of the straight path and the circular arc path may be determined based on the numerical relationship between the first distance le and the second distance ls. Specifically, the vehicle can travel in the order of the straight-line path and the circular-arc path if the first distance le is smaller than the second distance ls, and travel in the order of the circular-arc path and the straight-line path if the first distance le is larger than the second distance ls.
Alternatively, the first parking path may include only a straight path or an arc path, for example, if the distance of the straight path is determined to be 0, the first parking path includes only an arc path, and is not limited.
In practical applications, after the first parking path is determined, in order to improve the problem of discontinuous curvature between the straight path and the circular arc path, the method may further include:
determining a transition path comprising an intersection point of a straight path and a circular arc path;
and performing curvature smoothing processing on the transition path.
Curvature smoothing may be achieved using a third order bezier curve. Specifically, a first starting point far from the intersection point in the quarter straight line path including the intersection point and a second starting point far from the intersection point in the quarter circular arc path including the intersection point may be determined based on the intersection point of the straight line path and the circular arc path, and a path between the first starting point and the second starting point may be used as a transition path. Determining a tangent corresponding to the first starting point and a tangent corresponding to the second starting point respectively, taking the midpoint of each segment in two segments obtained by the intersection of the two tangents (a first segment formed by the intersection of the first starting point and the two tangents and a second segment formed by the intersection of the second starting point and the two tangents), and performing curvature smoothing processing by using a third-order Bessel curve based on the two control points, the first starting point and the second starting point.
In practical applications, the curvature smoothing may also be implemented by other implementations, such as a convolution line, a B-spline curve, and the like, without limitation.
The following specifically describes a procedure for determining the parking path in the case where the first parking path does not meet the travel requirement.
To shorten the parking process and improve the parking efficiency, in some embodiments, two target poses may be found to determine a parking path. The driving requirement is used as an optimization target, a first target pose and a second target pose are searched, and a second parking path of the vehicle driving from the starting pose to the first target pose forwards, a fourth parking path of the vehicle driving from the first target pose to the second target pose backwards and a third parking path of the vehicle driving from the second target pose forwards to the ending pose are determined.
In the embodiment, two target poses are set, and the vehicle travels from the starting pose to the ending pose through three travel processes of forward travel, backward travel and forward travel, corresponding to three travel paths. For ease of understanding, fig. 3 is a schematic diagram of another embodiment of a parking scene, with a first object pose Ot and a second object pose Ot2 labeled. The vehicle travels forward from the start pose Os to the first target pose Ot, backward from the first target pose Ot to the second target pose Ot2, and forward from the second target pose Ot2 to the end pose Oe.
In general, the first target pose may be set around the ending pose and away from the side of the starting pose, for example, the second target pose may be set at the side of the parking space away from the starting pose.
There are various ways to find the first target pose and the second target pose. As an optional implementation manner, the first target pose and the second target pose may be found at the same time, so that the second parking path, the third parking path, and the fourth parking path all meet the driving requirement. For example, any one of the first predicted pose and any one of the second predicted pose may be selected from the plurality of first predicted poses and the plurality of second predicted poses, and a predicted path for the vehicle to travel forward from the start pose to the first predicted pose, a predicted path for the vehicle to travel backward from the first predicted pose to the second predicted pose, and a predicted path for the vehicle to travel forward from the second predicted pose to the end pose may be determined to determine whether the predicted paths meet the travel requirement. And when the plurality of predicted paths meet the driving requirement, determining the corresponding first predicted pose and second predicted pose as the first target pose and the second target pose, otherwise, selecting another first predicted pose and/or second predicted pose to re-determine the predicted paths and judging whether the predicted paths meet the driving requirement. Alternatively, the plurality of first predicted poses and the plurality of second predicted poses may be obtained from parking data. For example, the historical parking data may include a plurality of first historical predicted poses and a plurality of second historical predicted poses, and a preset number of first historical predicted poses may be selected as the plurality of first predicted poses, and a preset number of second historical predicted poses may be selected as the plurality of second predicted poses, where the preset number may be 3, 5, 10, and the like, without limitation. Optionally, the plurality of first predicted poses may be determined by combining an end pose, a plurality of first preset distances from the central axis of the vehicle at the end position, a plurality of second preset distances from the perpendicular to the central axis of the vehicle at the end position, preset parameters, and a pose angle of the start pose, where a specific determination manner is described in the following description, and the plurality of second predicted poses may be obtained from historical parking data and are not described again.
As another optional implementation manner, the first target pose and the second target pose may be sequentially searched, for example, the first target pose is preferentially searched, and after the first target pose is determined, the second target pose is searched and determined. Specifically, the method may include:
searching a first target pose so that a second parking path of the vehicle from the starting pose to the first target pose forwards meets the driving requirement;
the second target pose is found so that a fourth parking path for the vehicle to travel backward from the first target pose to the second target pose and a third parking path for the vehicle to travel forward from the second target pose to the end pose meet the travel requirements.
By sequentially searching the first target pose and the second target pose, the data processing pressure in the path planning process can be reduced, the path planning process is shortened, and the path planning efficiency is improved.
In some embodiments, the method of finding the first target pose such that the second parking path for the vehicle to travel forward from the start pose to the first target pose meets the travel requirement may include:
determining a second parking path which meets the driving requirement in a plurality of parking paths corresponding to the plurality of first prediction poses and is formed by forward driving of the vehicle from the starting pose;
and taking the first predicted pose corresponding to the second parking path as a first target pose.
Optionally, before determining the second parking path, a plurality of first predicted poses may also be determined.
As an alternative implementation manner, a plurality of historical parking data of forward driving from the starting position to the ending position may be obtained, the historical parking data may include a first historical position, and a plurality of first predicted positions may be determined based on the first historical position. For example, the plurality of first historical poses can be directly taken as the plurality of first predicted poses; alternatively, the coordinate range in the first predicted pose may be determined based on coordinate data in a plurality of first historical poses, such as the range of the abscissa of the first predicted pose based on the minimum and maximum values of the abscissa in the plurality of first historical poses, and the range of the attitude angle in the first predicted pose based on the attitude angles in the plurality of first historical poses, and any number of first predicted poses may be set based on the determined coordinate range and attitude angle range, and so on.
As another optional implementation manner, a plurality of first predicted poses may be determined by combining the termination pose, a plurality of first preset distances from the central axis of the vehicle at the termination position, a plurality of second preset distances from the perpendicular line to the central axis of the vehicle at the termination position, preset parameters, and the pose angle of the start pose. The first preset distance may refer to a distance from the first predicted pose to a central axis of the vehicle at the end position, and the second preset distance may refer to a distance from the first predicted pose to a perpendicular line from the central axis of the vehicle at the end position. As shown in fig. 4-1, a schematic diagram of an embodiment of a first target pose provided by the present application is marked with a first preset distance dx and a second preset distance dy.
Specifically, the abscissa and the ordinate of the first predicted pose may be determined according to the following second coordinate formula.
The second coordinate formula may be:
Figure 961171DEST_PATH_IMAGE006
(ii) a Wherein xt represents the abscissa of the first predicted pose, yt represents the ordinate of the first predicted pose, dx represents the first preset distance, dy represents the second preset distance, θ e represents the pose angle of the termination pose Oe, xe represents the abscissa of the termination pose Oe, and ye represents the ordinate of the termination pose Oe.
And, the pose angle of the first predicted pose may be determined according to the pose angle formula as follows.
The attitude angle formula may be:
Figure DEST_PATH_IMAGE007
(ii) a Wherein θ t represents a pose angle of the first predicted pose, θ s represents a pose angle of the start pose Os, θ e represents a pose angle of the end pose Oe, and α represents a preset parameter.
The first preset distance, the second preset distance and the preset parameters can be determined according to historical parking data. The historical parking data may include a historical first preset distance, a historical second preset distance and a historical preset parameter. For example, the first preset distance may be 0.2m, 0.5m, 0.8m, the second preset distance may be a vehicle length +0.15m, a vehicle length +0.35m, a vehicle length +0.55m, and the preset parameter may be 0.33,0.43,0.5. At this time, three first predicted poses may be determined, so that a second parking path that meets the driving requirements among three parking paths corresponding to the three first predicted poses to which the vehicle has traveled forward from the start pose, respectively, may be determined, and the first predicted pose corresponding to the second parking path may be taken as the first target pose.
In the scheme, the first preset distance, the second preset distance and the preset parameters are determined according to historical parking data, namely empirical data in an actual parking scene can be achieved, the accuracy is high, the transverse and longitudinal coordinates in the first prediction pose are determined by setting a plurality of first preset distances and second preset distances and combining the first preset distances and the second preset distances, the preset parameters are set, and the attitude angle in the first prediction pose is determined based on the preset parameters, so that the accuracy of determining the first prediction pose is further improved, the number of times of judging a parking path from an initial pose to the first prediction pose is reduced, and the path planning efficiency is improved.
And determining that the vehicle respectively forwards travels from the initial pose to a plurality of parking paths corresponding to the first prediction poses, wherein the second parking path meeting the travel requirement can also have various implementation modes. As an optional implementation manner, for the plurality of first prediction poses, it may be determined that the vehicle travels forward from the start pose to all parking paths corresponding to the plurality of first prediction poses, and a determination is made whether all parking paths meet the travel requirement, so as to determine one or more parking paths meeting the travel requirement, and at this time, one parking path may be selected as the second parking path.
As another optional implementation manner, a parking path that the vehicle travels forward from the starting position to a certain first prediction position may be determined, whether the parking path meets the travel requirement or not is determined, and if the parking path meets the travel requirement, the parking path is determined to be a second parking path, and determination of parking paths corresponding to other first prediction positions is not performed. And if the current parking path corresponding to the first prediction pose does not meet the driving requirement, continuing to judge the next parking path corresponding to the first prediction pose until one parking path meeting the driving requirement is determined, and ending the judging process so as to reduce the data processing pressure in the path planning process, shorten the path planning process and improve the path planning efficiency.
In order to further improve the path planning efficiency, a preset number of first predicted poses can be determined from the multiple first predicted poses according to a preset condition, and then the second parking path and the first target poses are determined according to the preset number of first predicted poses. For example, a preset number of first predicted poses that do not overlap with the obstacle may be determined from the plurality of first predicted poses based on the position and size information of the obstacle in the detected space. For example, three first predicted poses may be provided, the first preset distance of the first predicted pose being 0.2m, the first preset distance of the second first predicted pose being 0.5m, and the first preset distance of the third first predicted pose being 0.8m. And when the first preset distance is judged to be 0.8m based on the detected position and size information of the obstacle in the space, the obstacle is overlapped with a pillar at the far end of the parking space, at the moment, a first prediction pose and a second first prediction pose can be screened out from the three first prediction poses, and the parking path is determined only based on the first prediction pose and the second first prediction pose, so that the path planning process is further shortened, and the path planning efficiency is improved.
In some embodiments, a method of finding a second target pose such that a fourth parking path of the vehicle traveling backward from the first target pose to the second target pose and a third parking path of the vehicle traveling forward from the second target pose to an end pose meet travel requirements may comprise:
determining a second predicted pose according to the first target pose and the termination pose;
judging whether a first prediction path from the first target pose to the second prediction pose when the vehicle runs backwards and a second prediction path from the second prediction pose to the termination pose meet the running requirement or not;
if so, taking the second predicted pose as a second target pose;
if not, the minimum turning radius of the vehicle is taken as the predicted arc radius, the distance between the minimum turning radius of the vehicle and the third preset distance is taken as the distance of the predicted arc path, and the second predicted pose is determined again;
judging whether a first predicted path from the first target pose to the second predicted pose and a second predicted path from the second predicted pose to the end pose which are determined again meet the driving requirements or not;
if so, taking the second predicted pose determined again as a second target pose;
if not, the second predicted pose which is determined again is adjusted to obtain a first predicted path and a second predicted path which meet the driving requirements, the adjusted second predicted pose is used as a second target pose, the first predicted path which meets the driving requirements is used as a fourth parking path, and the second predicted path which meets the driving requirements is used as a third parking path.
In the process, the second predicted pose can be preliminarily determined according to the first target pose and the termination pose. As shown in fig. 4-2, a schematic diagram of an embodiment of a second object pose provided by the present application is shown. With reference to fig. 4-2, a circle may be determined with the first target pose as the first tangent point, the vehicle central axis L4 at the first target pose as the first tangent line, and the vehicle central axis L2 at the termination position as the second tangent line, and the second tangent point on the second tangent line on the circle may be used as the second predicted pose.
The second predicted pose is preliminarily determined by a geometric planning method, the determination process is visual and clear, and the method is simple and easy to implement.
After the second predicted pose is determined, the radius of the circle can be used as the radius of the arc path, the arc path from the first target pose to the second predicted pose after backward driving is used as a first predicted path, and the path from the second predicted pose to the ending pose before forward driving is used as a second predicted path, wherein the determination mode of the second predicted path can be consistent with the determination mode of the first parking path, and is not repeated. And judging whether the first predicted path and the second predicted path meet the driving requirement, if so, taking the second predicted pose as a second target pose, and ending the process.
And if the first predicted path and/or the second predicted path do not meet the driving requirement, re-determining the second predicted pose and judging whether the second predicted pose meets the driving requirement or not by taking the minimum turning radius of the vehicle as the predicted arc radius and the third preset distance as the distance of the predicted arc path. Wherein the third preset distance may be set to 0.4m, for example.
If the first predicted path and the second predicted path corresponding to the second re-determined predicted pose both meet the driving requirement, the second re-determined predicted pose may be used as the second target pose, and the process is ended.
If the first predicted path and/or the second predicted path corresponding to the re-determined second predicted pose still do not meet the driving requirement, the re-determined second predicted pose can be adjusted.
Optionally, the operation of adjusting the re-determined second predicted pose may include:
sequentially increasing a fourth preset distance on the basis of the distance of the current circular arc path, and adjusting the re-determined second predicted pose until the attitude angle of the second predicted pose is the same as the attitude angle of the ending pose; wherein the fourth preset distance may be set to 0.4m, for example.
Judging whether a second prediction path from the adjusted second prediction pose to the end pose of the vehicle forwards meets the driving requirement or not;
if so, taking the first predicted path meeting the driving requirement as a fourth parking path, taking the second predicted path meeting the driving requirement as a third parking path, and taking the corresponding adjusted second predicted pose as a second target pose.
Taking the case that the distance of the current arc path is 0.4m, the radius of the current arc path is the minimum turning radius, and the predicted path corresponding to the currently determined second predicted pose does not meet the driving requirement, the following adjustment operations can be performed:
and (3) increasing 0.4m on the basis of the distance of the current circular arc path, namely determining a second predicted pose and judging whether the second predicted pose meets the driving requirement or not by taking the distance of the circular arc path as 0.8m and the radius of the circular arc path as the minimum turning radius, and taking the second predicted pose as a second target pose if the second predicted pose meets the driving requirement and ending the process. Otherwise, continuously increasing 0.4m on the basis of the distance of the current circular arc path, namely determining a second predicted pose and judging whether the second predicted pose meets the driving requirement or not by taking the second predicted pose as a second target pose by taking the distance of the circular arc path as 1.2m and the radius of the circular arc path as the minimum turning radius, and finishing the process if the second predicted pose meets the driving requirement. And if not, continuously increasing 0.4m on the basis of the distance of the current circular arc path to determine a second predicted pose and judge whether the second predicted pose meets the driving requirement or not until the second predicted pose meets the driving requirement, and taking the corresponding second predicted pose as a second target pose, or until the attitude angle of the second predicted pose is the same as the attitude angle of the ending pose.
In the adjusting process, if the attitude angle of the second predicted pose is the same as the attitude angle of the termination pose until the attitude angle of the second predicted pose is not in accordance with the requirements, a fifth preset distance can be increased on the basis of the current arc radius, and the second predicted pose is adjusted for the second time according to the step of sequentially increasing a fourth preset distance on the basis of the distance of the current arc path until the attitude angle of the second predicted pose is the same as the attitude angle of the termination pose; wherein the fifth preset distance may be set to 0.5m, for example.
Judging whether a second predicted path of the vehicle from the second predicted pose after the secondary adjustment to the end pose forwards meets the driving requirement or not;
and under the condition of meeting the requirements, taking the first prediction path meeting the driving requirements as a fourth parking path, taking the second prediction path meeting the driving requirements as a third parking path, and taking the corresponding second prediction pose after secondary adjustment as a second target pose.
Taking the example that the radius of the current circular arc path is the minimum turning radius, and the attitude angle adjusted to the second predicted pose according to the adjustment operation is the same as the attitude angle of the ending pose, the predicted path corresponding to the second predicted pose does not meet the requirement, the following secondary adjustment operation can be performed:
and (3) increasing 0.5m on the basis of the radius of the current circular arc path, namely, taking the minimum turning radius increased by 0.5m as the radius of the circular arc path, taking the distance of the circular arc path as 0.4m, determining a second predicted pose and judging whether the second predicted pose meets the driving requirement, taking the second predicted pose as a second target pose if the second predicted pose meets the driving requirement, and ending the process. Otherwise, 0.4m is added on the basis of the distance of the current circular arc path, namely the distance of the circular arc path is 0.8m, the radius of the circular arc path is the radius of the minimum turning radius increased by 0.5m, a second prediction pose is determined, whether the second prediction pose meets the driving requirement or not is judged, if the second prediction pose meets the driving requirement, the second prediction pose is used as a second target pose, and the process is ended. And if not, continuously increasing 0.4m on the basis of the distance of the current circular arc path to determine a second predicted pose and judge whether the second predicted pose meets the driving requirement or not until the second predicted pose meets the driving requirement, and taking the corresponding second predicted pose as a second target pose, or until the attitude angle of the second predicted pose is the same as the attitude angle of the ending pose.
Optionally, after the secondary adjustment operation, if the predicted path corresponding to the second predicted pose still does not meet the requirement, the fifth preset distance may be continuously increased on the basis of the radius of the current arc path for prediction, which is not described again.
By sequentially adjusting the second predicted pose, the pose adjustment and path judgment process can be finished when the second predicted path meeting the driving requirement is determined, the data processing pressure in the path planning process is reduced, the path planning process is shortened, and the path planning efficiency is further improved.
In practical application, if a parking path cannot be obtained according to the planning method, the situation that the driving requirement cannot be met by setting two target poses possibly due to more obstacles in a space is considered. At this time, the number of target poses can be increased.
In some embodiments, more than two target poses may be found to determine a parking path. Taking the finding of four target poses as an example, a third target pose, a fourth target pose, a fifth target pose, and a sixth target pose may be found with the driving requirements as the optimization targets to determine a second parking path for the vehicle to travel forward from the start pose to the third target pose, a backward travel from the third target pose to the fourth target pose, a forward travel from the fourth target pose to the fifth target pose, and a backward travel from the fifth target pose to the sixth target pose, as well as a third parking path for the vehicle to travel forward from the sixth target pose to the end pose.
In the embodiment, four target poses are set, and the vehicle travels from the starting pose to the ending pose through five travel processes of forward travel, backward travel, forward travel, backward travel and forward travel, which correspond to five travel paths.
Wherein the third target pose may be preferentially determined. And determining a target pose which is forwards driven to a sixth preset distance from the nearest barrier according to the minimum turning radius from the starting pose by combining the position information of the barrier in the space, and determining the target pose as a third target pose. The sixth preset distance may be set to 30cm, for example.
And determining a fourth target pose traveling backwards from the third target pose, a fifth target pose traveling forwards from the fourth target pose and a sixth target pose traveling backwards from the fifth target pose by taking the third target pose as an initial pose, wherein the fourth target pose traveling backwards from the third target pose can be realized by referring to the steps of a vertical parking mode in the traditional scheme, namely the process of advancing after backing and backing again is not repeated. Then, the third parking path, which is traveled forward from the sixth object pose to the termination pose, may be determined according to the method for determining the first parking path in the above-described embodiment.
By arranging a plurality of target poses, the parking is easier and smoother to realize and the success rate of parking is improved.
It can be understood that if a parking path is still unavailable and the automatic parking is not considered to be suitable, corresponding prompt information can be output to inform a user, so that the user can conveniently adopt manual parking or replace the starting pose and/or the ending pose.
In one or more embodiments, a first parking path is preferentially determined from a starting position to a stopping position, two target positions are preferentially searched for when the first parking path does not meet a driving requirement, so that the vehicle is preferentially determined to travel from the starting position to the first target position, the vehicle is preferentially determined to travel from the first target position to the second target position, the vehicle is moved from the second target position to the stopping position, and a planning method for continuing to increase the target positions and determining the parking path is provided when the two target positions cannot meet the driving requirement, so that a path planning process is finished when a current parking path meets the driving requirement, and planning efficiency is improved.
In addition, the embodiment of the present application further provides another parking path planning method, which may include:
determining a starting pose and an ending pose of the vehicle in response to the parking request;
with the driving requirement as an optimization target, searching a first target pose and a second target pose to determine a second parking path for the vehicle to drive forwards from the starting pose to the first target pose, a fourth parking path for the vehicle to drive backwards from the first target pose to the second target pose, and a third parking path for the vehicle to drive forwards from the second target pose to the ending pose;
the second parking path, the fourth parking path, and the third parking path constitute a target parking path.
In this embodiment, the finding method of the first target pose and the second pose is described in the foregoing embodiments, and is not described again.
By directly taking the driving requirement as an optimization target, searching the first target pose and the second target pose and determining the parking path, the success rate of parking path planning is improved, the parking requirements of all vehicles can be met to a greater extent, and automatic parking is realized.
Optionally, the embodiment of the present application further provides another parking path planning method, which may include:
determining a starting pose and an ending pose of the vehicle in response to the parking request;
with the driving requirement as an optimization target, finding a third target pose, a fourth target pose, a fifth target pose and a sixth target pose to determine a second parking path for the vehicle to travel forward from the start pose to the third target pose, travel backward from the third target pose to the fourth target pose, travel forward from the fourth target pose to the fifth target pose, and travel backward from the fifth target pose to the sixth target pose, and a third parking path for travel forward from the sixth target pose to the end pose;
the target parking path is formed by the second parking path, the three fourth parking paths, and the third parking path.
By directly taking the driving requirement as an optimization target, searching a third target pose, a fourth target pose, a fifth target pose and a sixth pose, and determining a parking path, the success rate of parking path planning is further improved.
Optionally, it may also be determined according to the information of the obstacle between the start pose and the end pose of the vehicle, whether to preferentially determine a first parking path from the start pose to the end pose of the vehicle, or to directly find two target poses for path planning, or to directly find four target poses for path planning, or the like.
For example, it is possible to preferentially determine a first parking path for the vehicle to travel forward from the start pose to the end pose when the obstacle information between the start pose and the end pose of the vehicle is small, such as the number of obstacles is less than a first threshold, and to find two target poses to perform parking path planning with the travel requirement as an optimization target when the number of obstacles is greater than the first threshold and less than a second threshold, and to find four target poses to perform parking path planning with the travel requirement as an optimization target when the number of obstacles is greater than the second threshold, and so on.
Or, the determination may be performed according to size information, type information, and the like of the obstacle, and the setting may be performed according to an actual application scenario, which is not described again.
As shown in fig. 5, for a schematic structural diagram of an embodiment of a parking path planning apparatus provided by the present application, the method may include the following modules:
a first determining module 501, configured to determine a first parking path for a vehicle to travel forward from a start pose to an end pose in response to a parking request;
a finding module 502, configured to find at least two target poses with the driving requirement as an optimization target in case the first parking path does not meet the driving requirement, to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a third parking path for the vehicle to travel forward from the last target pose to the end pose, and at least one fourth parking path for the vehicle to travel forward or backward between two adjacent target poses of the at least two target poses;
a second determining module 503 is configured to form a target parking path from the second parking path, the at least one fourth parking path, and the third parking path.
The parking path planning apparatus of this embodiment may be used to implement the parking path planning method shown in fig. 1, and may determine, after responding to a parking request, a first parking path in which a vehicle travels forward from a start pose to an end pose, and in a case where the first parking path does not meet a travel requirement, find at least two target poses with the travel requirement as an optimization target, to determine a second parking path in which the vehicle travels forward from the start pose to a first target pose, a third parking path in which the vehicle travels forward from a last target pose to the end pose, and at least one fourth parking path in which the vehicle travels forward or backward between two adjacent target poses of the at least two target poses, and constitute a target parking path from the second parking path, the at least one fourth parking path, and the third parking path. Therefore, the vehicle can automatically run from the starting position to the ending position according to the target parking path, so that automatic parking is realized. And the target parking path is planned based on a parking-in mode, and is suitable for a parking scene of parking-in.
In some embodiments, the finding module 502 may be specifically configured to find the first target pose and the second target pose with the travel requirement as an optimization objective to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a fourth parking path for the vehicle to travel backward from the first target pose to the second target pose, and a third parking path for the vehicle to travel forward from the second target pose to the end pose.
In some embodiments, the finding module 502 may include;
the first searching unit is used for searching a first target pose so as to enable a second parking path of the vehicle to forwards travel from the starting pose to the first target pose to meet the travel requirement;
and a second finding unit for finding the second target pose so that a fourth parking path for the vehicle to travel backward from the first target pose to the second target pose and a third parking path for the vehicle to travel forward from the second target pose to the end pose meet the travel requirement.
In some embodiments, the first finding unit may be specifically configured to determine a second parking path that meets the driving requirement, from among the plurality of parking paths corresponding to the plurality of first predicted poses, to which the vehicle travels forward from the start pose, respectively; and taking the first predicted pose corresponding to the second parking path as a first target pose.
In some embodiments, the finding module 502 may further include:
the first determining unit is used for determining a plurality of first predicted poses based on the termination pose, a plurality of first preset distances from the central axis of the vehicle at the termination position, a plurality of second preset distances from the vertical line of the central axis of the vehicle at the termination position, preset parameters and the pose angle of the starting pose.
In some embodiments, the second finding unit may include:
the first determining subunit is used for determining a second predicted pose according to the first target pose and the termination pose;
the first judgment subunit is used for judging whether a first predicted path from the first target pose to the second predicted pose and a second predicted path from the second predicted pose to the end pose of the vehicle are both in accordance with the driving requirements;
the second determining subunit takes the second predicted pose as a second target pose when the first judging subunit results in yes;
the third determining subunit, when the first judging subunit result is negative, using the minimum turning radius of the vehicle as the predicted arc radius, and using the third preset distance as the distance of the predicted arc path, and re-determining the second predicted pose;
a fourth determination subunit configured to, in a case where both of the first predicted path along which the vehicle travels backward from the first target pose to the second predicted pose that is newly determined and the second predicted path along which the vehicle travels forward from the second predicted pose that is newly determined to the end pose meet the travel requirement, take the second predicted pose that is newly determined as the second target pose;
and the fifth determining subunit is used for adjusting the re-determined second predicted pose to obtain a first predicted path and a second predicted path which meet the driving requirement, taking the adjusted second predicted pose as a second target pose, taking the first predicted path which meet the driving requirement as a fourth parking path, and taking the second predicted path which meet the driving requirement as a third parking path.
In some embodiments, the first determining subunit may be specifically configured to determine a circle with the first target pose as a first tangent point, the central axis of the vehicle at the first target pose as a first tangent line, and the central axis of the vehicle at the end position as a second tangent line, and take a second tangent point on the second tangent line on the circle as a second predicted pose;
the fifth determining subunit may be specifically configured to increase a fourth preset distance on the basis of the distance of the current arc path in sequence, and adjust the second predicted pose determined again until the pose angle of the second predicted pose is the same as the pose angle of the termination pose; judging whether a second prediction path from the adjusted second prediction pose to the end pose of the vehicle forwards meets the driving requirement or not; if so, taking the first prediction path meeting the driving requirement as a fourth parking path, taking the second prediction path meeting the driving requirement as a third parking path, and taking the adjusted second prediction pose as a second target pose; if not, increasing a fifth preset distance on the basis of the current arc radius, and secondarily adjusting the second predicted pose according to the step of sequentially increasing the fourth preset distance on the basis of the distance of the current arc path until the attitude angle of the second predicted pose is the same as the attitude angle of the ending pose; judging whether a second predicted path from the second predicted pose after secondary adjustment to the ending pose of the vehicle forwards meets the driving requirement or not; and under the condition of meeting the requirement, taking a first prediction path meeting the driving requirement as a fourth parking path, taking a second prediction path meeting the driving requirement as a third parking path, and taking a corresponding second prediction pose after secondary adjustment as a second target pose.
In some embodiments, the first determining module 501 may be specifically configured to determine a first parking path for the vehicle to travel alternately forward from the start pose to the end pose according to a straight path and a circular path.
In some embodiments, the first determining module 501 may be specifically configured to determine the radius of the circular arc path based on a first distance from the ending location to a central axis of the vehicle at the starting location, an attitude angle of the vehicle at the starting location, and an attitude angle of the vehicle at the ending location; determining the distance of the straight line path based on the radius of the circular arc path, the second distance from the starting position to the central axis of the vehicle at the ending position, the attitude angle of the vehicle at the starting position and the attitude angle of the vehicle at the ending position; determining the intersection point of the straight line path and the circular arc path based on the distance of the straight line path, the attitude angle of the vehicle at the initial position and the attitude angle of the vehicle at the final position; and determining a straight line path taking the initial pose as a starting point and the intersection point as an end point, and determining an arc path taking the intersection point as a starting point and the end pose as an end point, and determining a first parking path consisting of the straight line path and the arc path.
In some embodiments, the first determining module 501 may also be configured to determine a transition path including an intersection of a straight-line path and a circular-arc path; and performing curvature smoothing processing on the transition path.
The parking path planning apparatus shown in fig. 5 may execute the parking path planning method described in the embodiment shown in fig. 1, and the implementation principle and technical effects are not described again. The specific manner in which each module and unit of the parking path planning apparatus in the above-described embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail here.
An embodiment of the present application further provides a computing device, as shown in fig. 6, the computing device may include a storage component 601 and a processing component 602;
the storage component 601 stores one or more computer program instructions, wherein the one or more computer program instructions are invoked by the processing component 602 for execution to implement the parking path planning method shown in fig. 1.
Of course, the computing device described above may also necessarily include other components, such as input/output interfaces, communication components, and so forth.
The input/output interface provides an interface between the processing components and peripheral interface modules, which may be output devices, input devices, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, and the like.
An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the parking path planning method shown in fig. 1 may be implemented. The computer readable medium may be embodied in the computing device described in the above embodiments; or may exist separately and not be assembled into the computing device.
Embodiments of the present application also provide a computer program product, which includes a computer program loaded on a computer-readable storage medium, and when the computer program is executed by a computer, the computer program can implement the parking path planning method shown in fig. 1.
In such embodiments, the computer program may be downloaded and installed from a network, and/or installed from a removable medium. The computer program, when executed by a processor, performs various functions defined in the system of the present application.
It should be noted that the computing device may be a physical device or a flexible computing host provided by a cloud computing platform. It can be implemented as a distributed cluster consisting of a plurality of servers or terminal devices, or as a single server or a single terminal device.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.

Claims (13)

1. A parking path planning method, comprising:
determining a first parking path for the vehicle to travel forward from a start pose to an end pose in response to the parking request;
in the case that the first parking path does not meet a driving requirement, taking the driving requirement as an optimization target, finding at least two target poses to determine a second parking path for the vehicle to drive forwards from the starting pose to a first target pose, a third parking path for the vehicle to drive forwards from a last target pose to the ending pose, and at least one fourth parking path for the vehicle to drive forwards or backwards between two adjacent target poses of the at least two target poses;
and the second parking path, at least one fourth parking path and the third parking path form a target parking path.
2. The method of claim 1, wherein the finding at least two target poses with the travel requirement as an optimization objective comprises:
with the driving request as an optimization objective, finding a first target pose and a second target pose to determine a second parking path for the vehicle to travel forward from the start pose to the first target pose, a fourth parking path for the vehicle to travel backward from the first target pose to the second target pose, and a third parking path for the vehicle to travel forward from the second target pose to the end pose.
3. The method of claim 2, wherein the finding operation for the first target pose and the second target pose comprises:
finding a first target pose so that a second parking path for the vehicle to travel forward from the starting pose to the first target pose meets the travel requirement;
a second target pose is sought such that a fourth parking path for the vehicle to travel from the first target pose back to the second target pose and a third parking path for the vehicle to travel from the second target pose forward to the end pose meet the travel requirements.
4. The method of claim 3, wherein the finding a first target pose such that a second parking path for the vehicle to travel forward from the starting pose to the first target pose conforms to the travel requirements comprises:
determining a second parking path which meets the driving requirement in a plurality of parking paths corresponding to a plurality of first prediction poses and is formed by forward driving of the vehicle from the starting pose;
and taking the first predicted pose corresponding to the second parking path as a first target pose.
5. The method of claim 4, wherein the starting pose comprises a starting position and a pose angle of the vehicle at the starting position, and the ending pose comprises an ending position and a pose angle of the vehicle at the ending position;
the method further comprises the following steps:
determining a plurality of first predicted poses based on the termination pose, a plurality of first preset distances from the central axis of the vehicle at the termination position, a plurality of second preset distances from the perpendicular to the central axis of the vehicle at the termination position, a plurality of preset parameters, and the pose angle of the vehicle at the starting position.
6. The method of claim 3, wherein the finding the second target pose such that a fourth parking path traveled by the vehicle from the first target pose back to the second target pose and a third parking path traveled from the second target pose forward to the end pose conform to the travel requirement comprises:
determining a second predicted pose according to the first target pose and the termination pose;
judging whether a first predicted path of the vehicle from the first target pose to the second predicted pose and a second predicted path from the second predicted pose to the termination pose both meet the driving requirement;
if so, taking the second predicted pose as a second target pose;
if not, the minimum turning radius of the vehicle is taken as the predicted arc radius, the third preset distance is taken as the distance of the predicted arc path, and the second predicted pose is determined again;
taking the second predicted pose as a second target pose if both the first predicted path for the vehicle to travel backward from the first target pose to the second predicted pose as determined anew and the second predicted path for the vehicle to travel forward from the second predicted pose as determined anew meet the travel requirements;
otherwise, adjusting the redetermined second predicted pose to obtain a first predicted path and a second predicted path which meet the driving requirement, taking the adjusted second predicted pose as a second target pose, taking the first predicted path which meet the driving requirement as a fourth parking path, and taking the second predicted path which meet the driving requirement as a third parking path.
7. The method of claim 6, wherein determining a second predicted pose from the first target pose and an end pose comprises:
determining a circle by taking the first target pose as a first tangent point, the central axis of the vehicle at the first target pose as a first tangent line and the central axis of the vehicle at the termination position as a second tangent line, and taking a second tangent point on the second tangent line on the circle as a second predicted pose;
the adjustment operation of the re-determined second predicted pose includes:
sequentially increasing a fourth preset distance on the basis of the distance of the current circular arc path, and adjusting the re-determined second prediction pose until the attitude angle of the second prediction pose is the same as the attitude angle of the termination pose;
judging whether a second predicted path of the vehicle from the adjusted second predicted pose to the end pose forwards meets the driving requirement or not;
if so, taking the first prediction path meeting the driving requirement as a fourth parking path, taking the second prediction path meeting the driving requirement as a third parking path, and taking the corresponding adjusted second prediction pose as a second target pose;
if not, increasing a fifth preset distance on the basis of the current arc radius, and secondarily adjusting the re-determined second predicted pose according to the step of sequentially increasing a fourth preset distance on the basis of the distance of the current arc path until the pose angle of the second predicted pose is the same as the pose angle of the termination pose;
and under the condition that second prediction paths of the vehicle from the second prediction pose after secondary adjustment to the termination pose all meet the requirements, taking the first prediction path meeting the driving requirements as a fourth parking path, taking the second prediction path meeting the driving requirements as a third parking path, and taking the corresponding second prediction pose after secondary adjustment as a second target pose.
8. The method of claim 1, wherein determining the first parking path for the vehicle to travel forward from the starting pose to the ending pose comprises:
and determining a first parking path from the starting pose to the ending pose of the vehicle, wherein the vehicle alternately travels forwards according to a straight path and a circular path.
9. The method of claim 8, wherein the starting pose comprises a starting position and a pose angle of the vehicle at the starting position, and the ending pose comprises an ending position and a pose angle of the vehicle at the ending position;
the determining of the first parking path of the vehicle from the starting pose to the ending pose alternately along the straight path and the circular path comprises the following steps:
determining the radius of the circular arc path based on a first distance from the ending position to a central axis of the vehicle at the starting position, an attitude angle of the vehicle at the starting position and an attitude angle of the vehicle at the ending position;
determining a distance of a straight line path based on the radius of the circular arc path, a second distance from the starting position to the central axis of the vehicle at the ending position, the attitude angle of the vehicle at the starting position and the attitude angle of the vehicle at the ending position;
determining an intersection point of the straight line path and the circular arc path based on the distance of the straight line path, the attitude angle of the vehicle at the starting position and the attitude angle of the vehicle at the ending position;
and determining a straight line path taking the starting pose as a starting point and the intersection point as an end point, and determining a circular arc path taking the intersection point as a starting point and the ending pose as an end point, and determining a first parking path formed by the straight line path and the circular arc path.
10. The method of claim 9, further comprising:
determining a transition path including an intersection point of the straight path and the circular arc path;
and performing curvature smoothing processing on the transition path.
11. A parking path planning apparatus, comprising:
a first determination module for determining a first parking path for the vehicle to travel forward from a start pose to an end pose in response to a parking request;
a finding module, configured to find at least two target poses with the driving requirement as an optimization target to determine a second parking path for the vehicle to travel forward from the start pose to a first target pose, a third parking path for the vehicle to travel forward from a last target pose to the end pose, and at least one fourth parking path for the vehicle to travel forward or backward between two adjacent target poses of the at least two target poses, if the first parking path does not meet the driving requirement;
and the second determining module is used for forming a target parking path by the second parking path, at least one fourth parking path and the third parking path.
12. A computing device comprising a storage component and a processing component; the storage component stores one or more computer program instructions for the processing component to call and execute, and the processing component executes the one or more computer program instructions to realize the parking path planning method according to any one of claims 1 to 10.
13. A computer-readable storage medium, in which a computer program is stored, which when executed by a computer implements a parking path planning method according to any one of claims 1 to 10.
CN202211402839.9A 2022-11-10 2022-11-10 Parking path planning method, device, equipment and storage medium Active CN115465266B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211402839.9A CN115465266B (en) 2022-11-10 2022-11-10 Parking path planning method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211402839.9A CN115465266B (en) 2022-11-10 2022-11-10 Parking path planning method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN115465266A true CN115465266A (en) 2022-12-13
CN115465266B CN115465266B (en) 2023-03-21

Family

ID=84338278

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211402839.9A Active CN115465266B (en) 2022-11-10 2022-11-10 Parking path planning method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115465266B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111409625A (en) * 2020-04-02 2020-07-14 北京四维智联科技有限公司 Parking track determination method and device
CN112172799A (en) * 2020-10-15 2021-01-05 吉林大学 Narrow vertical parking path planning method
CN112677959A (en) * 2020-12-23 2021-04-20 广州小鹏自动驾驶科技有限公司 Parking method and device
CN112714729A (en) * 2019-11-29 2021-04-27 华为技术有限公司 Vehicle path planning method and vehicle path planning device
CN113320527A (en) * 2021-06-29 2021-08-31 惠州华阳通用电子有限公司 Automatic parking method based on vehicle head parking
CN113696886A (en) * 2021-09-17 2021-11-26 中国第一汽车股份有限公司 Parking track automatic determination method, device, medium and electronic equipment
CN113830079A (en) * 2021-10-19 2021-12-24 同济大学 Online planning method and system for continuous curvature parking path with any initial pose
CN114523958A (en) * 2022-02-28 2022-05-24 重庆长安汽车股份有限公司 Path planning method, device and storage medium for parking space at head of vehicle
CN114684111A (en) * 2020-12-31 2022-07-01 华为技术有限公司 Parking method, device and system with vehicle head entering first
CN115218916A (en) * 2022-07-14 2022-10-21 清华大学 Safety path planning method and device

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112714729A (en) * 2019-11-29 2021-04-27 华为技术有限公司 Vehicle path planning method and vehicle path planning device
CN111409625A (en) * 2020-04-02 2020-07-14 北京四维智联科技有限公司 Parking track determination method and device
CN112172799A (en) * 2020-10-15 2021-01-05 吉林大学 Narrow vertical parking path planning method
CN112677959A (en) * 2020-12-23 2021-04-20 广州小鹏自动驾驶科技有限公司 Parking method and device
CN114684111A (en) * 2020-12-31 2022-07-01 华为技术有限公司 Parking method, device and system with vehicle head entering first
WO2022142592A1 (en) * 2020-12-31 2022-07-07 华为技术有限公司 Front-first parking method, device and system
CN113320527A (en) * 2021-06-29 2021-08-31 惠州华阳通用电子有限公司 Automatic parking method based on vehicle head parking
CN113696886A (en) * 2021-09-17 2021-11-26 中国第一汽车股份有限公司 Parking track automatic determination method, device, medium and electronic equipment
CN113830079A (en) * 2021-10-19 2021-12-24 同济大学 Online planning method and system for continuous curvature parking path with any initial pose
CN114523958A (en) * 2022-02-28 2022-05-24 重庆长安汽车股份有限公司 Path planning method, device and storage medium for parking space at head of vehicle
CN115218916A (en) * 2022-07-14 2022-10-21 清华大学 Safety path planning method and device

Also Published As

Publication number Publication date
CN115465266B (en) 2023-03-21

Similar Documents

Publication Publication Date Title
CN111923910B (en) Method for planning lane change of vehicle, autonomous vehicle and storage medium
CN112758084B (en) Parking trajectory planning method, device, equipment and storage medium
WO2019042295A1 (en) Path planning method, system, and device for autonomous driving
CN113916246A (en) Unmanned obstacle avoidance path planning method and system
CN111731269B (en) Automatic parking path planning method and system
JP6854095B2 (en) Parking support device
JP6750365B2 (en) Parking assistance method and parking assistance device
CN110488816B (en) Automatic driving longitudinal planning method and related equipment
CN112590775B (en) Automatic parking method and device, vehicle and storage medium
CN111830979A (en) Trajectory optimization method and device
JP2019064466A (en) Parking support device
CN111746517A (en) Vehicle parking-out control method and device
CN113895463B (en) Path planning method suitable for turning around of automatic driving vehicle
CN114791288B (en) Method and device for planning driving path of mine vehicle and computer equipment
CN113296118B (en) Unmanned obstacle detouring method and terminal based on laser radar and GPS
CN111746518A (en) Vehicle parking-out control method and device
CN112141091A (en) Secondary parking method and system for solving parking space deviation and positioning deviation and vehicle
CN113670305A (en) Parking trajectory generation method and device, computer equipment and storage medium
CN113335270B (en) Parking path planning method and device
CN116476840B (en) Variable-lane driving method, device, equipment and storage medium
CN115465266B (en) Parking path planning method, device, equipment and storage medium
US20230202471A1 (en) Method and apparatus for controlling lane changing, and storage medium
CN114506314A (en) Vehicle parallel parking method, device, equipment and storage medium
CN114750782A (en) Path planning method, device and equipment and vehicle control method, device and equipment
CN114670876A (en) Method and device for turning around unmanned vehicle in lane and electronic equipment

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
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230828

Address after: Room 844, Floor 8, Building 1, No. 10, Hongda North Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing 100176 (Yizhuang Cluster, High end Industrial Zone, Beijing Free Trade Zone)

Patentee after: Beijing Jidu Technology Co.,Ltd.

Address before: Room 611, 6/F, Zone 2, Building A, No. 12, Hongda North Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing 102101 (Yizhuang Cluster, High end Industrial Zone, Beijing Pilot Free Trade Zone)

Patentee before: Jidu Technology Co.,Ltd.