CN113701771B - Parking path planning method and device, electronic equipment and storage medium - Google Patents
Parking path planning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113701771B CN113701771B CN202110866458.5A CN202110866458A CN113701771B CN 113701771 B CN113701771 B CN 113701771B CN 202110866458 A CN202110866458 A CN 202110866458A CN 113701771 B CN113701771 B CN 113701771B
- Authority
- CN
- China
- Prior art keywords
- path
- planning
- point
- parking
- algorithm
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a parking path planning method, a device, electronic equipment and a storage medium, wherein the parking path planning method comprises the following steps: determining a starting point and a target point of a parking path in a pre-established parking environment model; planning a parking path by utilizing at least two path planning algorithms based on the starting point and the target point to obtain at least one planning path; when the at least one planned path includes only one planned path, the planned path is a target planned path; and when the at least one planning path comprises at least two planning paths, determining one of the at least two planning paths as the target planning path according to a preset selection algorithm. The invention avoids the limitation of a single path planning algorithm and improves the reliability and rationality of a target planning path.
Description
Technical Field
The invention relates to the technical field of automatic parking, in particular to a parking path planning method, a device, electronic equipment and a storage medium.
Background
The automatic driving parking plan is to plan a collision-free parking track according to the positions of the vehicle, the target parking positions and the current environmental obstacles when the vehicle is near the parking space (park). The current method for automatic driving parking planning mostly adopts three-section type deep learning or mixed A star. The three-section method is simple, the comfort in the parking process is insufficient by adopting a planning mode of fixing the ackerman corner, and the complex parking environment is difficult to face; the planning mode of deep learning has higher calculation force requirement, and is difficult to face complex and changeable parking environments when training data is insufficient; the trajectory generated by the hybrid a star typically includes unnecessary steering operations, requiring a smoothing operation again, etc.
From the above description, it is clear that: the parking path planning method in the prior art realizes parking planning according to a preset path planning algorithm, but with the improvement of complex variability of the actual parking environment, the single path planning algorithm has different applicability, so that the single path planning algorithm cannot use the complex variability of the actual parking environment, and the parking path planning is unreasonable, even the parking path planning is unsuccessful.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a parking path planning method, apparatus, electronic device and storage medium, so as to solve the technical problems that in the prior art, a single path planning algorithm cannot use a complex and diverse actual parking environment, resulting in unreasonable parking path planning and unsuccessful parking planning path planning.
In order to solve the technical problems, the invention provides a parking path planning method, which comprises the following steps:
determining a starting point and a target point of a parking path in a pre-established parking environment model;
planning a parking path by utilizing at least two path planning algorithms based on the starting point and the target point to obtain at least one planning path;
when the at least one planned path includes only one planned path, the planned path plans a path for the target; when the at least one planned path comprises at least two planned paths, determining one of the at least two planned paths as a target planned path according to a preset selection algorithm.
In one possible implementation, the at least two planned paths include a first planned path and a second planned path; the determining that one of the at least two planned paths is the target planned path according to a preset selection algorithm includes:
respectively calculating a first loss value and a second loss value of the first planning path and the second planning path according to a preset loss function;
when the first loss value is larger than the second loss value, the second planning path is a target planning path; and when the first loss value is smaller than the second loss value, the first planned path is a target planned path.
In one possible implementation, the first planned path and the second planned path each include a plurality of path points, and the loss function is:
cost＝λ 1 gmin(p i -p 0 )+λ 2 g∑c i +λ 3 g∑j i +λ 4 g∑s i
wherein cost is the loss function; min () is a minimum function; p is p i -p 0 Is the distance between the ith path point and the obstacle; c i Curvature for the ith path point; j (j) i Curvature change rate for the i-th path point; s is(s) i The length of the movement of the ith path point relative to the (i-1) th path point; lambda (lambda) 1 、λ 2 、λ 3 、λ 4 Is a weight coefficient;
wherein, the liquid crystal display device comprises a liquid crystal display device,
in the formula, h i Heading angle of the path point; x is x i Is the abscissa of the ith path point; x is x i-1 The abscissa of the i-1 th path point; y is i Is the ordinate of the ith path point; y is i-1 Is the ordinate of the i-1 th waypoint.
In one possible implementation, the at least two planned path algorithms include a first planned path algorithm and a second planned path algorithm; planning a parking path by using at least two path planning algorithms based on the starting point and the target point, and obtaining at least one planned path includes:
determining a first iteration threshold number of the first path planning algorithm and a second iteration threshold number of the second path planning algorithm;
planning a parking path by using a first path planning algorithm and a second path planning algorithm based on the starting point and the target point;
when the first path planning algorithm converges within the first iteration threshold number and the second path planning algorithm also converges within the second iteration number, the first planned path and the second planned path are obtained;
when the first path planning algorithm converges within the first iteration threshold number and the second path planning algorithm does not converge within the second iteration number, the first planning path is obtained;
and when the first path planning algorithm is not converged within the first iteration threshold number, and the second path planning algorithm is converged within the second iteration number, the second planning path is obtained.
In one possible implementation, the first path planning algorithm is a Q learning algorithm and the second path planning algorithm is a hybrid a star algorithm.
In one possible implementation manner, the planning the parking path using the first planning path includes:
determining a plurality of path points between the starting point and the target point;
starting from the starting point, determining Q function update values of the starting point, the plurality of path points and the target point according to a Q learning rule;
judging whether the Q function updating value is converged or not, and if so, obtaining the first planning path;
wherein, the Q learning rule is:
Q * (s,a)←Q(s,a)+α*[γ(r+max(Q(s',a'))-Q(s,a)]
wherein, r is instant punishment; gamma is a conversion factor; alpha is a learning factor; s' is the next state; a' is the next action; s is the current state; a is the current action; q (s, a) is the Q function value of the current action under the current state; q (s ', a') is the Q function value for executing the next action in the next state; q (s, a) is the Q function update value.
In one possible implementation manner, the planning the parking path using the second planning path algorithm includes:
acquiring a plurality of passable path points in a preset range of a current path point, and calculating the sum of the distances between each passable path point in the plurality of passable path points and the current path point and the target point; wherein the current path point is the starting point or any one of a plurality of path points between the starting point and the target point;
taking the minimum passable path point and the distance as the next path point of the current path point, judging whether the next path point is the target point, and if so, obtaining the second planning path; and if not, taking the next path point as the current path point.
The invention also provides a parking path planning device, which comprises:
the preprocessing unit is used for determining a starting point and a target point of a parking path in a pre-established parking environment model;
the path planning unit is used for planning a parking path by utilizing at least two path planning algorithms based on the starting point and the target point to obtain at least one planned path;
a target planned path determining unit configured to, when the at least one planned path includes only one planned path, determine that the planned path is the target planned path; when the at least one planned path comprises at least two planned paths, determining one of the at least two planned paths as a target planned path according to a preset selection algorithm.
The invention also provides an electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor is coupled to the memory, and is configured to execute the program stored in the memory, so as to implement the steps in the parking path planning method in any one of the foregoing implementations.
The present invention also provides a computer readable storage medium storing a computer readable program or instructions that, when executed by a processor, enable implementation of the steps in the parking path planning method in any one of the above implementations.
The beneficial effects of adopting the embodiment are as follows: according to the parking path planning method, the parking paths are planned by utilizing at least two path planning algorithms, at least one planned path is obtained, and when the at least one planned path comprises at least two planned paths, one of the at least two planned paths is determined to be a target planned path according to a preset selection algorithm. The target planning algorithm is determined from at least two planning paths through the preset selection algorithm, so that the limitation of a single path planning algorithm can be avoided, and the reliability and rationality of the target planning path are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an embodiment of a parking path planning method according to the present invention;
FIG. 2 is a flow chart of the embodiment of S103 in FIG. 1 according to the present invention;
FIG. 3 is a flow chart illustrating the process of S102 in FIG. 1 according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the process of S302 in FIG. 3 according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a process according to another embodiment of S302 of FIG. 3;
fig. 6 is a schematic structural diagram of an embodiment of a parking path planning apparatus according to the present invention;
fig. 7 is a schematic structural diagram of an embodiment of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, based on the embodiments of the invention, which a person skilled in the art would obtain without making any inventive effort, are within the scope of the invention.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.
The invention provides a parking path planning method, a device, electronic equipment and a storage medium, which are respectively described below.
As shown in fig. 1, a flow chart of an embodiment of a parking path planning method according to an embodiment of the present invention includes:
s101, determining a starting point and a target point of a parking path in a pre-established parking environment model;
s102, planning a parking path by using at least two path planning algorithms based on a starting point and a target point to obtain at least one planned path;
s103, when at least one planning path only comprises one planning path, the planning path is a target planning path; when the at least one planned path comprises at least two planned paths, determining one of the at least two planned paths as a target planned path according to a preset selection algorithm.
In step S101, the parking environment model is a vehicle, obstacle, target point, and parking lot environment model constructed under a 2D plane coordinate system with the ground as a plane, wherein different positions of the vehicle, obstacle, target point, and parking lot are each represented by (x, y).
In particular, the obstacle may be a hydrant, other vehicles that have been parked on a parking space, or the like.
Further, the starting point of the parking path can be determined according to the current position automatically positioned by the GPS positioning module in the vehicle, namely, the starting point of the parking path is the current position point of the target vehicle; the target point of the parking path can be determined according to the target place position to be reached by the target vehicle, namely, the target point of the parking path is the position point of the target parking place of the vehicle. Of course, in order to more accurately determine the start point and the target point of the parking path, in an embodiment, the rear-axis midpoint corresponding to the current position point of the vehicle may be taken as the start point, and the geometric center point of the position point of the target parking space to be reached by the target vehicle may be taken as the target point.
The target point may also be determined in other ways during actual operation. For example, the user may manually click to determine coordinates of the target point directly in the established parking environment model.
Compared with the prior art, the parking path planning method provided by the embodiment of the invention has the advantages that at least one planning path is obtained by planning the parking path by utilizing at least two path planning algorithms, and when the at least one planning path comprises at least two planning paths, one of the at least two planning paths is determined to be a target planning path according to the preset selection algorithm. The target planning algorithm is determined from at least two planning paths through the preset selection algorithm, so that the limitation of a single path planning algorithm can be avoided, and the reliability and the rationality of the target planning path are improved.
In order to avoid the technical problem that when too many planning path algorithms are set to plan the parking path, the parking path is too long to affect the parking efficiency, in some embodiments of the present invention, at least two planning paths include a first planning path and a second planning path, as shown in fig. 2, step S103 includes:
s201, respectively calculating a first loss value and a second loss value of a first planning path and a second planning path according to a preset loss function;
s202, when the first loss value is larger than the second loss value, the second planning path is a target planning path; when the first loss value is smaller than the second loss value, the first planned path is the target planned path.
The target planning path is determined by setting a preset loss function, so that the reliability and parking comfort of the target planning path can be improved.
In a specific embodiment of the present invention, the first planned path and the second planned path each include a plurality of path points, and the loss function is:
cost＝λ 1 ·min(p i -P 0 )+λ 2 ·∑c i +λ 3 ·∑j i +λ 4 ·∑s i
in the formula, cost is a loss function; min () is a minimum function; p is p i -p 0 Is the distance between the ith path point and the obstacle; c i Curvature for the ith path point; j (j) i Curvature change rate for the i-th path point; s is(s) i The length of the movement of the ith path point relative to the (i-1) th path point; lambda (lambda) 1 、λ 2 、λ 3 、λ 4 Is a weight coefficient;
wherein, the liquid crystal display device comprises a liquid crystal display device,
in the formula, h i Heading angle of the path point; x is x i Is the abscissa of the ith path point; x is x i-1 The abscissa of the i-1 th path point; y is i Is the ordinate of the ith path point; y is i-1 Is the ordinate of the i-1 th waypoint.
It should be understood that: lambda (lambda) 1 、λ 2 、λ 3 、λ 4 The setting can be performed according to actual requirements, for example: if the safety of the parking planning path needs to be ensured, lambda is 1 The value of (2) is larger than lambda 2 、λ 3 、λ 4 Is a value of (a). By setting lambda 1 、λ 2 、λ 3 、λ 4 The target planning path can be provided with better comfort and safety.
Further, since the planning of the parking path by the planning path algorithm may fail, at least one planning path may be obtained by at least two planning path algorithms. In some embodiments of the invention, the at least two planned path algorithms include a first planned path algorithm and a second planned path algorithm; as shown in fig. 3, step S102 includes:
s301, determining a first iteration threshold number of a first path planning algorithm and a second iteration threshold number of a second path planning algorithm;
s302, planning a parking path by using a first path planning algorithm and a second path planning algorithm based on a starting point and a target point;
s303, when the first path planning algorithm is converged within the first iteration threshold number and the second path planning algorithm is converged within the second iteration number, a first planning path and a second planning path are obtained;
s304, when the first path planning algorithm converges within the first iteration threshold number and the second path planning algorithm does not converge within the second iteration number, a first planning path is obtained;
s305, when the first path planning algorithm is not converged within the first iteration threshold number and the second path planning algorithm is converged within the second iteration number, a second planning path is obtained.
In some embodiments of the invention, the first path planning algorithm is a Q learning algorithm and the second path planning algorithm is a hybrid a star algorithm.
The Q learning algorithm is an algorithm with lower time complexity and space complexity, and the speed of planning the parking path can be improved and the instantaneity of the target planning path can be improved by setting the first path planning algorithm as the Q learning algorithm. Because the path planning success of the hybrid A star algorithm is higher, by setting the second path planning algorithm as the hybrid A star algorithm, the situation that a target planning path cannot be planned by both path planning algorithms can be avoided, and the reliability of parking path planning is further improved.
In some embodiments of the present invention, as shown in fig. 4, planning a parking path using a first planned path in step S302 includes:
s401, determining a plurality of path points between a starting point and a target point;
s402, starting from a starting point, determining Q function updating values of the starting point, a plurality of path points and target points according to a Q learning rule;
s403, judging whether the Q function updating value is converged, and if so, obtaining a first planning path.
Wherein, the Q learning rule is:
Q * (s,a)←Q(s,a)+α*[γ(r+max(Q(s',a'))-Q(s,a)]
wherein, r is instant punishment; gamma is a conversion factor, and gamma is more than 0 and less than 1; alpha is a learning factor, and alpha is more than 0.5 and less than or equal to 1; s' is the next state; a' is the next action; s is the current state; a is the current action; q (s, a) is the Q function value of the current action under the current state; q (s ', a') is the Q function value for executing the next action in the next state; q (s, a) is the Q function update value.
In particular, the instant prize may include a prize value corresponding to the prize item and a penalty value corresponding to the penalty item. Wherein the bonus item is to reach the target point; the penalty term is length of movement, collision with an obstacle, etc.
Specifically, the actions are displacement of the vehicle running and steering wheel angle. Wherein the displacement of the vehicle running is an integer multiple of the minimum running displacement in unit time; steering wheel angle is an integer multiple of the minimum steering wheel angle per unit time.
In some embodiments of the present invention, as shown in fig. 5, planning a parking path using the second planning path in step S302 includes:
s501, acquiring a plurality of passable path points in a preset range of a current path point, and calculating the sum of the distances between each passable path point in the plurality of passable path points and the current path point and the target point; the current path point is a starting point or any one of a plurality of path points between the starting point and the target point;
s502, taking the distance and the minimum passable path point as the next path point of the current path point, judging whether the next path point is the target point, and if so, obtaining a second planning path; if not, the next path point is taken as the current path point.
In step S501, the parking lot environment model is a raster pattern, and the passable path points are the barrier-removed raster points in the raster pattern.
In order to better implement the parking path planning method in the embodiment of the present invention, correspondingly, as shown in fig. 6, on the basis of the parking path planning method, the embodiment of the present invention further provides a parking path planning device 600, including:
a preprocessing unit 601, configured to determine a start point and a target point of a parking path in a pre-established parking environment model;
a path planning unit 602, configured to plan a parking path by using at least two path planning algorithms based on the starting point and the target point, to obtain at least one planned path;
a target planned path determination unit 603, configured to, when the at least one planned path includes only one planned path, determine that the planned path is a target planned path; when the at least one planned path comprises at least two planned paths, determining one of the at least two planned paths as a target planned path according to a preset selection algorithm.
What needs to be explained here is: the parking path planning device 600 provided in the foregoing embodiment may implement the technical solutions described in the foregoing embodiments of the parking path planning method, and the specific implementation principles of the foregoing modules or units may refer to the corresponding contents in the foregoing embodiments of the parking path planning method, which are not described herein again.
As shown in fig. 7, based on the above-mentioned parking path planning method, the present invention further provides an electronic device 700 accordingly. The electronic device 700 includes a processor 701, a memory 702, and a display 703. Fig. 7 illustrates some of the components of the electronic device 700, but it should be understood that not all of the illustrated components need be implemented, and that more or fewer components may alternatively be implemented.
The memory 702 may be an internal storage unit of the electronic device 700 in some embodiments, such as a hard disk or memory of the electronic device 700. The memory 702 may also be an external storage device of the electronic device 700 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 700.
Further, the memory 702 may also include both internal storage units and external storage devices of the electronic device 700. The memory 702 is used to store application software and various types of data for installing the electronic device 700,
the processor 701 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 702, such as the parking path planning program 704 of the present invention.
The display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 703 is used for displaying information on the electronic device 700 and for displaying a visual user interface. The components 701-703 of the electronic device 700 communicate with each other via a system bus.
In one embodiment, when the processor 701 executes the parking path planning program 704 in the memory 702, the following steps may be implemented:
determining a starting point and a target point of a parking path in a pre-established parking environment model;
planning a parking path by using at least two path planning algorithms based on the starting point and the target point to obtain at least one planning path;
when the at least one planned path includes only one planned path, the planned path is a target planned path; when the at least one planned path comprises at least two planned paths, determining one of the at least two planned paths as a target planned path according to a preset selection algorithm.
It should be understood that: the processor 701 may perform other functions in addition to the above functions when executing the parking path planning program 704 in the memory 702, see in particular the description of the corresponding method embodiments above.
Further, the type of the electronic device 700 is not specifically limited in the embodiment of the present invention, for example: the electronic device 700 may be a component integrated on a vehicle, and may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (personal digital assistant, PDA), a wearable device, a laptop (laptop), etc. that is communicatively connected to the vehicle, and may be used to plan a parking path for the vehicle.
Correspondingly, the embodiment of the application also provides a computer readable storage medium, and the computer readable storage medium is used for storing a computer readable program or instructions, which when executed by a processor, can realize the method steps or functions provided by the above-mentioned embodiments of the parking path planning method.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program that instructs associated hardware, and that the program may be stored in a computer readable storage medium. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The parking path planning method, device, electronic equipment and storage medium provided by the invention are described in detail, and specific examples are applied to illustrate the principle and implementation of the invention, and the description of the above examples is only used for helping to understand the method and core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present invention, the present description should not be construed as limiting the present invention.
Claims (9)
1. A method of parking path planning, comprising:
determining a starting point and a target point of a parking path in a pre-established parking environment model;
planning a parking path by utilizing at least two path planning algorithms based on the starting point and the target point to obtain at least one planning path;
when the at least one planned path includes only one planned path, the planned path is a target planned path; when the at least one planning path comprises at least two planning paths, determining one of the at least two planning paths as the target planning path according to a preset selection algorithm;
the at least two path planning algorithms comprise a first path planning algorithm and a second path planning algorithm; planning a parking path by using at least two path planning algorithms based on the starting point and the target point, and obtaining at least one planned path includes:
determining a first iteration threshold number of the first path planning algorithm and a second iteration threshold number of the second path planning algorithm;
planning a parking path by using a first path planning algorithm and a second path planning algorithm based on the starting point and the target point;
when the first path planning algorithm is converged within the first iteration threshold times, and the second path planning algorithm is converged within the second iteration threshold times, a first planning path and a second planning path are obtained;
when the first path planning algorithm is converged within the first iteration threshold times, and when the second path planning algorithm is not converged within the second iteration threshold times, the first planning path is obtained;
and when the first path planning algorithm is not converged within the first iteration threshold times, and the second path planning algorithm is converged within the second iteration threshold times, the second planning path is obtained.
2. The parking path planning method according to claim 1, wherein the at least two planned paths include a first planned path and a second planned path; the determining that one of the at least two planned paths is the target planned path according to a preset selection algorithm includes:
respectively calculating a first loss value and a second loss value of the first planning path and the second planning path according to a preset loss function;
when the first loss value is larger than the second loss value, the second planning path is a target planning path; and when the first loss value is smaller than the second loss value, the first planning path is a target planning path.
3. The parking path planning method according to claim 2, wherein the first planned path and the second planned path each include a plurality of path points, the loss function being:
in the method, in the process of the invention,costis the loss function;min()as a function of the minimum value;p i -p 0 is the firstiThe distance between each path point and the obstacle;c i is the firstiCurvature of the individual path points;j i is the firstiCurvature change rate of each path point;s i is the firstiThe path point is relative to the firsti- 1The length of the movement of the individual waypoints;λ 1 、λ 2 、λ 3 、λ 4 is a weight coefficient;
wherein, the liquid crystal display device comprises a liquid crystal display device,
in the method, in the process of the invention,h i heading angle of the path point;x i is the firstiThe abscissa of the individual path points;x i-1 is the firsti-1The abscissa of the individual path points;y i is the firstiThe ordinate of each path point;y i-1 is the firsti-1The ordinate of each path point.
4. A parking path planning method according to claim 3, characterized in that the first path planning algorithm is a Q learning algorithm and the second path planning algorithm is a hybrid a star algorithm.
5. The method of parking path planning of claim 4, wherein planning the parking path using the first planned path comprises:
determining a plurality of path points between the starting point and the target point;
starting from the starting point, determining Q function update values of the starting point, the plurality of path points and the target point according to a Q learning rule;
judging whether the Q function updating value is converged or not, and if so, obtaining the first planning path;
wherein, the Q learning rule is:
in the method, in the process of the invention,ris a real-time rewarding and punishing;γis a conversion factor;is a learning factor;s’is the next state;a’the next action;sis the current state;ais the current action;Q(s,a)for performing the current action in the current stateQA function value;Q(s’,a’）the Q function value of the next action is executed in the next state;Q*(s,a)is thatQThe function updates the value.
6. The method of claim 4, wherein the planning the parking path using the second path planning algorithm comprises:
acquiring a plurality of passable path points in a preset range of a current path point, and calculating the sum of the distances between each passable path point in the plurality of passable path points and the current path point and the target point; wherein the current path point is the starting point or any one of a plurality of path points between the starting point and the target point;
taking the minimum passable path point and the distance as the next path point of the current path point, judging whether the next path point is the target point, and if so, obtaining the second planning path; and if not, taking the next path point as the current path point.
7. A parking path planning apparatus, comprising:
the preprocessing unit is used for determining a starting point and a target point of a parking path in a pre-established parking environment model;
the path planning unit is used for planning a parking path by utilizing at least two path planning algorithms based on the starting point and the target point to obtain at least one planned path;
a target planned path determining unit, configured to, when the at least one planned path includes only one planned path, determine that the planned path is a target planned path; when the at least one planning path comprises at least two planning paths, determining one of the at least two planning paths as a target planning path according to a preset selection algorithm;
the at least two path planning algorithms comprise a first path planning algorithm and a second path planning algorithm; planning a parking path by using at least two path planning algorithms based on the starting point and the target point, and obtaining at least one planned path includes:
determining a first iteration threshold number of the first path planning algorithm and a second iteration threshold number of the second path planning algorithm;
planning a parking path by using a first path planning algorithm and a second path planning algorithm based on the starting point and the target point;
when the first path planning algorithm is converged within the first iteration threshold times, and the second path planning algorithm is converged within the second iteration threshold times, a first planning path and a second planning path are obtained;
when the first path planning algorithm is converged within the first iteration threshold times, and when the second path planning algorithm is not converged within the second iteration threshold times, the first planning path is obtained;
and when the first path planning algorithm is not converged within the first iteration threshold times, and the second path planning algorithm is converged within the second iteration threshold times, the second planning path is obtained.
8. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps in the parking path planning method according to any one of the preceding claims 1 to 6.
9. A computer readable storage medium storing a computer readable program or instructions which, when executed by a processor, is capable of carrying out the steps of the parking path planning method according to any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110866458.5A CN113701771B (en) | 2021-07-29 | 2021-07-29 | Parking path planning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110866458.5A CN113701771B (en) | 2021-07-29 | 2021-07-29 | Parking path planning method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113701771A CN113701771A (en) | 2021-11-26 |
| CN113701771B true CN113701771B (en) | 2023-08-01 |
Family
ID=78650892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110866458.5A Active CN113701771B (en) | 2021-07-29 | 2021-07-29 | Parking path planning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113701771B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108562301A (en) * | 2018-05-21 | 2018-09-21 | 北京石油化工学院 | A kind of method and device for planning of driving path |
| CN109405843A (en) * | 2018-09-21 | 2019-03-01 | 北京三快在线科技有限公司 | A kind of paths planning method and device and mobile device |
| CN112606830A (en) * | 2020-12-29 | 2021-04-06 | 吉林大学 | Two-section type autonomous parking path planning method based on mixed A-star algorithm |
| CN113110520A (en) * | 2021-05-26 | 2021-07-13 | 重庆邮智机器人研究院有限公司 | Robot path planning method based on multiple intelligent optimization parallel algorithms |
| CN113129630A (en) * | 2021-03-30 | 2021-07-16 | 中国联合网络通信集团有限公司 | Autonomous parking method, AVP platform and vehicle terminal |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2505464B (en) * | 2012-08-31 | 2019-12-18 | Bae Systems Plc | Route planning |
| US10515321B2 (en) * | 2017-09-11 | 2019-12-24 | Baidu Usa Llc | Cost based path planning for autonomous driving vehicles |
-
2021
- 2021-07-29 CN CN202110866458.5A patent/CN113701771B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108562301A (en) * | 2018-05-21 | 2018-09-21 | 北京石油化工学院 | A kind of method and device for planning of driving path |
| CN109405843A (en) * | 2018-09-21 | 2019-03-01 | 北京三快在线科技有限公司 | A kind of paths planning method and device and mobile device |
| CN112606830A (en) * | 2020-12-29 | 2021-04-06 | 吉林大学 | Two-section type autonomous parking path planning method based on mixed A-star algorithm |
| CN113129630A (en) * | 2021-03-30 | 2021-07-16 | 中国联合网络通信集团有限公司 | Autonomous parking method, AVP platform and vehicle terminal |
| CN113110520A (en) * | 2021-05-26 | 2021-07-13 | 重庆邮智机器人研究院有限公司 | Robot path planning method based on multiple intelligent optimization parallel algorithms |
Non-Patent Citations (2)
| Title |
|---|
| 两种自主泊车路径规划方法的对比研究;王道斌;梁华为;杨妮娜;高航;;电子测量技术;第34卷(第01期);第27-30、38页 * |
| 多约束平行泊车路径规划;侯晓阳;黄勇;孙思;季学武;;汽车技术(09);第48-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113701771A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102292277B1 (en) | LIDAR localization inferring solutions using 3D CNN networks in autonomous vehicles | |
| KR102335389B1 (en) | Deep Learning-Based Feature Extraction for LIDAR Position Estimation of Autonomous Vehicles | |
| CN111290385B (en) | Robot path planning method, robot, electronic equipment and storage medium | |
| CN105608920B (en) | A kind of parking lot car searching method and system | |
| EP3819194B1 (en) | Automatic parking method and apparatus, and electronic device | |
| CN110533943A (en) | Determine that the lane of automatic driving vehicle changes the method for track | |
| CN103109161B (en) | Guider and method | |
| CN109141464A (en) | Navigate lane change reminding method and device | |
| WO2021169993A1 (en) | Method for constructing self-driving map and related device | |
| US11532063B2 (en) | Systems and methods for online to offline service | |
| CN112339747A (en) | Automatic parking track generation method and device, electronic equipment and storage medium | |
| CN106767776A (en) | Mobile device and the method for asking for mobile device attitude | |
| CN110109449A (en) | Speed planning method, apparatus, computer equipment and storage medium | |
| CN112454367B (en) | Trajectory planning method and device and computer storage medium | |
| CN109795492A (en) | Autonomous driving vehicle drives switching method, system, equipment and storage medium | |
| CN112066976A (en) | Self-adaptive expansion processing method and system, robot and storage medium | |
| CN113701771B (en) | Parking path planning method and device, electronic equipment and storage medium | |
| CN112212875B (en) | Vehicle turning track planning method and device, vehicle and storage medium | |
| US20230266763A1 (en) | Method for navigating root through limited space, robot and computer-readable storage medium | |
| JP7478831B2 (en) | Autonomous driving based riding method, device, equipment and storage medium | |
| CN113077652B (en) | Parking space automatic search method and device, electronic device and storage medium | |
| CN113320544B (en) | Vehicle driving behavior planning method and device, electronic equipment and storage medium | |
| CN114723903A (en) | Obstacle risk field environment modeling method and device and related products | |
| CN117542205B (en) | Lane guiding method, device, equipment and storage medium | |
| CN116403455B (en) | Vehicle control method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |