CN115195706A - Parking path planning method and device - Google Patents
Parking path planning method and device Download PDFInfo
- Publication number
- CN115195706A CN115195706A CN202210823970.6A CN202210823970A CN115195706A CN 115195706 A CN115195706 A CN 115195706A CN 202210823970 A CN202210823970 A CN 202210823970A CN 115195706 A CN115195706 A CN 115195706A
- Authority
- CN
- China
- Prior art keywords
- pose point
- pose
- point
- collision
- free
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 claims abstract description 24
- 238000005381 potential energy Methods 0.000 claims description 50
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W30/00—Purposes 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
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W30/00—Purposes 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
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The present application relates to a parking path planning method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: firstly, acquiring collision-free pose points in a preset area to which target parking pose points belong; wherein the collision-free pose point is a pose point at which a collision-free path exists with the target parking pose point. And then determining whether a collision-free path exists from the middle pose point to the collision-free pose point. And if so, generating a final parking path according to a collision-free path from the current pose point to the middle pose point, a collision-free path from the middle pose point to the collision-free pose point and a collision-free path from the collision-free pose point to the target parking pose point. By the method, the efficiency of parking path planning is improved under the condition that the obstacles near the target parking pose point are complex.
Description
Technical Field
The present application relates to the field of path planning technologies, and in particular, to a parking path planning method and apparatus.
Background
With the development of the automatic driving technology, a path planning technology appears, the most widely used path planning technology is a path planning strategy based on the a-x algorithm, the path planning strategy based on the hybrid a-x algorithm is further improved on the path planning strategy based on the a-x algorithm, and the path at the planning position is more consistent with the vehicle kinematics. In the path planning strategy planning path process based on the hybrid A-x algorithm, the search pose points are generally gradually expanded forwards from the current pose points to form a traveling path.
However, in practical application, in a scene of parking, because more obstacles are often found near the parking point, when the path planning strategy based on the hybrid a-star algorithm reaches the extended search pose point near the parking point, the search difficulty is greatly increased, so that the search efficiency near the parking point is low.
Disclosure of Invention
In view of the above, it is necessary to provide a parking path planning method, apparatus, computer device, computer readable storage medium and computer program product capable of improving the efficiency of parking path planning.
In a first aspect, the present application provides a parking path planning method. The method comprises the following steps:
acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
determining whether a collision-free path exists from the middle pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if so, generating a parking path according to a collision-free path from the current pose point to the middle pose point, a collision-free path from the middle pose point to the collision-free pose point and a collision-free path from the collision-free pose point to the target parking pose point.
In one embodiment, the method further comprises:
and if no collision path exists from the middle pose point to the collision-free pose point, re-determining the middle pose point according to the path search strategy, and executing the step of determining whether the collision-free path exists from the middle pose point to the collision-free pose point.
In one embodiment, the obtaining collision-free pose points in a preset area to which the target parking pose points belong includes:
in a preset area where the target parking pose points belong, determining a plurality of first candidate pose points by a preset pose point selection strategy;
for each first candidate pose point, taking the first candidate pose point as a collision-free pose point if there is a collision-free path from the first candidate pose point to the target parking pose point.
In one embodiment, the determining, in a preset region to which the target parking pose point belongs, a plurality of first candidate pose points by a preset pose point selection strategy includes:
determining a plurality of position points in the preset area based on a preset position selection strategy;
and determining a pose point corresponding to each position point based on a preset pose angle as a first candidate pose point.
In one embodiment, the acquiring collision-free pose points in a preset area to which the target parking pose point belongs includes:
determining a plurality of first candidate pose points by a preset pose point selection strategy in a preset area to which the target parking pose point belongs;
for each first candidate pose point, taking the first candidate pose point as a second candidate pose point when a collision-free path exists from the first candidate pose point to the target parking pose point;
for each second candidate pose point, determining a driving cost value of the second candidate pose point to drive to the target parking pose point;
and taking the second candidate pose point with the minimum driving cost value as a collision-free pose point.
In one embodiment, the determining, for each second candidate pose point, a travel cost value for the candidate pose point to travel to the target parking pose point comprises:
for each second candidate pose point, acquiring a running cost parameter of the second candidate pose point: wherein the driving cost parameter comprises one or more of a Voronoi potential energy value of the second candidate pose point, a gradient value of Voronoi potential energy along a pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point;
and determining the driving cost value of the second candidate pose point according to the acquired driving cost parameter of the second candidate pose point.
In a second aspect, the application further provides a parking path planning device. The device comprises:
the acquisition module is used for acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
a determining module, configured to determine whether a collision-free path exists from the intermediate pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if the collision-free path exists, generating a parking path according to the collision-free path from the current pose point to the middle pose point, the collision-free path from the middle pose point to the collision-free pose point and the collision-free path from the collision-free pose point to the target parking pose point.
In a third aspect, the application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
determining whether a collision-free path exists from the intermediate pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if the target parking position point exists, generating a parking path according to a collision-free path from the current position point to the middle position point, a collision-free path from the middle position point to the collision-free position point and a collision-free path from the collision-free position point to the target parking position point.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
determining whether a collision-free path exists from the middle pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if so, generating a parking path according to a collision-free path from the current pose point to the middle pose point, a collision-free path from the middle pose point to the collision-free pose point and a collision-free path from the collision-free pose point to the target parking pose point.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
determining whether a collision-free path exists from the middle pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if the target parking position point exists, generating a parking path according to a collision-free path from the current position point to the middle position point, a collision-free path from the middle position point to the collision-free position point and a collision-free path from the collision-free position point to the target parking position point.
According to the parking path method, the parking path device, the computer equipment, the storage medium and the computer program product, in the scene of parking path planning, the last parking path is planned in advance, so that the path planning efficiency near the parking position point is effectively accelerated.
Drawings
Fig. 1 is a basic flow diagram illustrating a hybrid a-based path planning strategy according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for planning a parking path according to one embodiment of the present application;
fig. 3 is a schematic diagram illustrating target parking pose points in a preset area to which the target parking pose points belong, according to an embodiment of the present application;
FIG. 4 is a flow chart diagram illustrating a method for parking path planning in accordance with another embodiment;
fig. 5 is a block diagram illustrating a parking path planning apparatus according to an embodiment of the present application;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the related art, the path planning strategy based on the hybrid a-algorithm considers the actual motion constraint of the object on the basis of the algorithm path planning strategy based on a. The basic flow of the hybrid a algorithm path planning strategy is shown in fig. 1.
1. Firstly, determining a current pose point and a target pose point to which a vehicle with a planned path runs, and initializing an open set as the current pose point, wherein a closed set is empty.
2. And judging whether the open set is empty or not. If the path is empty, the path search is failed; if not, continue to execute step 3.
3. And determining the total cost f of each pose point in the open set, selecting the pose point with the minimum substitution value in the open set as an intermediate pose point, and adding the intermediate pose point into the closed set. The total cost f of each pose point comprises two parts, namely a motion cost item g and a heuristic cost item h, wherein the motion cost item g is used for representing the driving cost value from the current pose point to the pose point, and the heuristic cost item h is used for representing the heuristic cost value from the pose point to the target pose point.
4. And detecting whether the intermediate pose point and the target pose point have collision-free paths or not. If the path exists, taking the planned path from the current pose point to the middle pose point and the non-collision path from the middle pose point to the target pose point as the final planned path; if not, continue to step 5.
5. And determining and selecting an adjacent pose point of the middle pose points according to a kinematic formula.
6. And judging whether a collision-free path exists from the adjacent pose point to the middle pose point. If yes, continuing to execute the step 7; if not, return to step 5.
7. And judging whether the adjacent pose point is in a closed set. If yes, returning to the step 5; if not, continue to step 8.
8. And calculating the motion cost g from the current pose point to the adjacent pose point according to the motion cost from the current pose point to the intermediate pose point and the motion cost from the intermediate pose point to the adjacent pose point.
9. And judging whether the adjacent pose point is in an open set or not. If yes, executing step 10; if not, step 12 is performed.
10. And judging the motion cost g of the adjacent pose point and the motion cost g of the adjacent pose point stored in the opening set. And if the motion cost g of the adjacent pose point is not less than the motion cost g of the adjacent pose point stored in the opening set, directly returning to the step 2. If the motion cost g of the adjacent pose point is less than the motion cost g of the adjacent pose point saved in the opening set, step 11 is executed.
11. And updating the motion cost g of the adjacent pose point in the opening set, the parent node of the adjacent pose point and the total cost f of the adjacent pose point, and returning to the step 2.
12. And calculating the heuristic cost h of the adjacent pose point, calculating the total cost f of the adjacent pose point according to the motion cost g and the heuristic cost h of the adjacent pose point, recording the father node of the adjacent pose point as an intermediate pose point, and adding the adjacent pose point into the open set. And returning to the step 2.
According to the basic flow of the path planning strategy of the hybrid A-algorithm, when the hybrid A-algorithm approaches to a target pose point, in order to be connected to the target pose as low as possible and improve the searching speed, the hybrid A-algorithm tries to search for a path by using a mode without considering obstacles, so that if the number of the obstacles near the target pose point is large, particularly the obstacles in a U shape under a parking scene, the difficulty of searching for the adjacent pose point near the target pose point is greatly improved, and the efficiency is greatly reduced.
Based on the method, a complicated path planning method aiming at the obstacles near the target pose point is shown on the basis of a path planning strategy based on a hybrid A-star algorithm, namely a parking path planning method. Firstly, acquiring collision-free pose points in a preset area to which target parking pose points belong; wherein the collision-free pose point is a pose point at which a collision-free path exists with the target parking pose point. And then determining whether a collision-free path exists from the middle pose point to the collision-free pose point. And if so, generating a final parking path according to a collision-free path from the current pose point to the middle pose point, a collision-free path from the middle pose point to the collision-free pose point and a collision-free path from the collision-free pose point to the target parking pose point.
According to the method provided by the embodiment of the application, the parking path planning with the most obstacles in the last section is completed according to the collision-free pose points near the target parking pose points, so that when the parking path planning is performed, only the path from the current pose point to the starting pose point (collision-free pose point) of the parking path in the last section needs to be planned, and the obstacles near the collision-free pose points are far less than the obstacles near the target parking pose points, so that the overall efficiency of parking path planning is improved.
First, the parking path planning method according to the present application will be described in detail. The parking path planning method provided by the embodiment of the application can be applied to personal computers, notebook computers, smart phones, tablet computers, internet of things devices, portable wearable devices, independent servers or a server set consisting of a plurality of servers.
As shown in fig. 2, a flow chart of a parking path planning method according to an embodiment of the present application is provided, which includes the following steps:
The collision-free pose point is located in a preset area where the target parking pose point belongs, and a collision-free path exists between the collision-free pose point and the target parking pose point. The preset area to which the target parking pose point belongs may be a fixed-length and fixed-width area, such as an area with a length of 11 meters and a width of 5 meters, defined by taking the target parking pose point as a center, or a fixed-length and fixed-width area, defined by dividing the device according to an obstacle near the target parking pose point, so that the target parking pose point is close to one side of the area, and the obstacle on the side is the most.
In one embodiment, each pose point comprises three pieces of information, and the abscissa in the map, the ordinate in the map, and the orientation of the vehicle, that is, the position of the same abscissa and ordinate may have a plurality of pose points. For example, the pose point may include three dimensions (x, y, θ) representing a position (x, y) in the plane xOy coordinate system, and a vehicle heading angle θ.
In one embodiment, the device stores map data containing obstacle information and specifies a current pose point and a target parking pose point of a parking path plan, and specifies basic parameters of an actually traveling vehicle of the path plan, such as a length, a width, and the like of the actually traveling vehicle, vehicle kinematics-related parameters, such as a wheel base, a distance between a rear axle and a front end, a minimum steering radius, and the like. Therefore, the apparatus, when determining whether there is a collision-free path between two pose points, may generate a travel path conforming to the kinematics of the vehicle based on a preset path generation strategy and kinematic parameters of the vehicle (e.g., a minimum steering radius), and then determine whether the vehicle will collide along the generated path based on basic parameters of the vehicle, such as a vehicle length, a vehicle width, and the like. If collision occurs, the equipment determines that no collision-free path exists between the two pose points; if no collision occurs, the device determines that a collision-free path exists between the two pose points.
The preset path generation strategy can be an RS curve path generation strategy or a Dubins curve path generation strategy, the RS curves are similar to the Dubins curves and are all circular and linear paths, and the difference is that the RS curves allow the vehicle to back up, and the Dubins curves only allow the vehicle to advance.
As shown in fig. 3, for the schematic diagram of each pose point in the preset area to which the target parking pose point belongs, the position of a solid hexagram indicates the position of the target parking pose point, the arrow to which the solid hexagram belongs indicates the direction of the target parking pose point, the dotted line near the target parking pose point is an obstacle of the target parking pose point, the positions of other solid original points indicate the positions of a certain pose point, and the arrow to which the solid hexagram belongs indicates the direction of the pose point. The position points circled by the circles are collision-free position points, lines from the collision-free position points to the target parking position points represent collision-free paths from the collision-free position points to the target parking position points, and no collision-free paths exist from other position points not circled by the circles to the target parking position points.
And step 203, determining whether a collision-free path exists from the middle pose point to the collision-free pose point.
The intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy, and when the pose point is expanded according to the preset path search strategy, the intermediate pose point is continuously updated according to the path search condition. Taking a preset path search strategy as the path planning based on the hybrid A-x algorithm as an example, a pose point with the minimum total cost f is selected from the set as an intermediate pose point until step 3 is executed in a circulating manner, and a collision-free path exists between the intermediate pose point and a target pose point.
In one embodiment, the apparatus, when determining whether there is a collision-free path from the intermediate pose point to the collision-free pose point, first determines whether there is a path that conforms to the kinematics of the vehicle without considering the obstacle information in the map, and if it is determined that there is a path that conforms to the kinematics of the vehicle from the intermediate pose point to the collision-free pose point, the apparatus further determines whether there is an obstacle in the path according to the obstacle information in the map data, and determines whether there is a collision in actual travel according to the basic information of the vehicle actually traveling. And the equipment determines that a collision-free path exists from the middle pose point to the collision-free pose point under the condition that the path is determined not to collide.
The method includes the steps that whether a path which accords with vehicle kinematics exists between an intermediate pose point and a non-collision pose point or not is determined without considering obstacle information in a map, the path can be a preset path generation strategy, for example, the path can be an RS curve path generation algorithm or a Dubins curve path generation algorithm, RS curves are similar to Dubins curves and are paths of circles and straight lines, and the difference is that the RS curves allow a vehicle to reverse and the Dubins curves only allow the vehicle to advance. If a path which accords with vehicle kinematics can be generated from the middle pose point to the collision-free pose point according to a preset path generation strategy, a path which accords with the vehicle kinematics exists from the middle pose point to the collision-free pose point; if a path conforming to the kinematics of the vehicle cannot be generated for the intermediate pose point to the non-collision pose point according to a preset path generation strategy, no path conforming to the kinematics of the vehicle exists from the intermediate pose point to the non-collision pose point.
And step 205, if the target parking position point exists, generating a parking path according to a collision-free path from the current position point to the middle position point, a collision-free path from the middle position point to the collision-free position point and a collision-free path from the collision-free position point to the target parking position point.
In one embodiment, the parking path planned by the device for the current pose point to the target parking pose point comprises three parts, the first part is a path from the current pose point to an intermediate pose point planned according to a preset path search strategy, the second part is a collision-free path from the intermediate pose point to a collision-free pose point generated according to a preset path generation strategy, the third part is a collision-free path from the collision-free pose point to the target parking pose point generated according to the preset path generation strategy, and the paths of the three parts are combined, so that the device can generate the parking path planned from the current pose point to the target parking pose point.
For example, if the current pose point is A, the intermediate pose point is D, the collision-free pose point is X, and the target parking pose point is Y, the device plans a path from the current pose point A to the intermediate pose point D to be A-B-C-D according to a preset path search strategy, determines that the collision-free path D-X exists between the intermediate pose point D and the collision-free pose point X, and determines that the collision-free path X-Y exists between the collision-free pose point X and the target parking pose point Y, the path generated by the device is A-B-C-D-X-Y.
The device may use the path planning strategy based on the hybrid a × algorithm or the path planning strategy based on the a × algorithm when planning the path from the current pose point to the intermediate pose point according to a preset path search strategy, which is not limited in the present application.
According to the embodiment, the last part of the parking path, namely the third part of the parking path, is independently planned, and the difficulty in planning the second part of the parking path is reduced, so that the overall efficiency of parking path planning, especially the planning efficiency of the second part and the third part of the parking path is improved.
In one embodiment, there may be no collision-free path from the intermediate pose point to the collision-free pose point, and in this case, the method may further include:
and step 207, if no collision-free path exists from the intermediate pose point to the collision-free pose point, re-determining the intermediate pose point according to a path search strategy, and executing step 203.
In one embodiment, if no collision-free path exists from the intermediate pose point to the collision-free pose point, the device may determine that a path needs to be continuously searched forward according to a preset path search strategy, and extend a new pose point forward, that is, update the pose of the intermediate point. And then determining whether a collision-free path exists between the intermediate pose and the collision-free pose according to the updated intermediate point pose.
In an embodiment, taking the example that the preset path search strategy is the path planning strategy based on the hybrid a-algorithm, after the device determines that no collision-free path exists between the intermediate pose point and the collision-free pose point, it indicates that more pose points need to be continuously expanded according to the preset path search strategy, and then according to the total cost f of each pose point, the one with the smallest total cost f is selected as the intermediate pose point.
In the related art, a path planning strategy based on a hybrid A-x algorithm has many obstacles near a target parking pose point, so that the device can extend to a pose point having a collision-free path with the target parking pose point only when the device reaches the vicinity of the target parking pose point, and the device can extend to a pose point having a collision-free path with the target parking pose point only when the device needs to update the intermediate pose point repeatedly for many times.
In this embodiment, since there are relatively fewer obstacles near the collision-free pose point, it is possible to extend the pose point to a pose point at a far distance where there is a collision-free path with the collision-free pose point, and therefore the apparatus does not need to repeat step 207 many times to update and extend the intermediate pose point to a pose point where there is a collision-free path with the collision-free pose point. The method greatly improves the path planning efficiency under the scene that the obstacles near the target parking pose point are complex.
In one embodiment, when determining collision-free pose points near the target parking pose points, a candidate pose point selection strategy can be used to determine a plurality of first candidate pose points in a preset area to which the target parking pose points belong, and then pose points meeting the condition that a collision-free path exists with the target parking pose points are further screened out to serve as the collision-free pose points.
Therefore, in an embodiment, the step 201 may specifically include:
step 201a, in a preset area where the target parking pose point belongs, determining a plurality of first candidate pose points according to a preset pose point selection strategy.
The preset candidate pose point selection strategy is not limited in the application, and a plurality of first candidate pose points which accord with the preset area around the target parking pose point can be selected.
In one embodiment, the preset candidate pose point selection strategy may be to randomly select a plurality of first candidate pose points located in a preset area to which the target parking pose point belongs. The candidate pose point selection strategy can also be to obtain a plurality of first candidate pose points which are uniformly distributed in a preset area where the target parking pose point belongs according to the length direction step length and the width direction step length.
And step 201b, regarding each first candidate pose point, and taking the first candidate pose point as a collision-free pose point under the condition that a collision-free path exists between the first candidate pose point and the target parking pose point.
In one embodiment, after the device determines a plurality of first candidate pose points, for each first candidate pose point, it may directly determine that there is a collision-free path between the first candidate pose point and the target parking pose point, and if it is determined that there is a collision-free path between the first candidate pose point and the target parking pose point, the device may regard the first candidate pose point as a collision-free pose point; if it is determined that no collision-free path exists between the first candidate pose point and the target parking pose point, the device directly discards the first candidate pose point.
In one embodiment, after the apparatus determines a plurality of first candidate pose points, for each first candidate pose point, the apparatus may further determine, according to stored map data including obstacle information, whether an obstacle exists at a position of the first candidate pose point and whether a vehicle collides with the first candidate pose point, so as to screen out first candidate pose points for which it is unnecessary to determine whether a collision-free path exists. If the position of the first candidate pose point is determined to have an obstacle or the vehicle can collide with the first candidate pose point, the first candidate pose point is necessarily the pose point where the vehicle can not stay, and the equipment directly discards the first candidate pose point so as to reduce the consumption of computing resources for determining whether a collision-free path exists for the first candidate pose point. If the position of the first candidate pose point is determined to have no obstacle and the vehicle does not collide at the first candidate pose point, the device further determines whether a collision-free path exists between the first candidate pose point and the target parking pose point. If it is determined that a collision-free path exists between the first candidate pose point and the target parking pose point, the device may take the first candidate pose point as a collision-free pose point; if the first candidate pose point and the target parking pose point are determined to have no collision-free path, the equipment directly abandons the first candidate pose point.
In this embodiment, each first candidate pose point near the target parking pose point is selected through a preset candidate pose point selection strategy, and then collision-free pose points are further obtained by screening among the first candidate pose points.
In an embodiment, the preset candidate pose point selection strategy is to obtain a plurality of first candidate pose points which are uniformly distributed in a preset area to which the target parking pose point belongs according to a length direction step length and a width direction step length, where the step 201a specifically includes:
step a1, determining a plurality of position points in a preset area where a target parking pose point belongs based on a preset position selection strategy.
In one embodiment, a length direction step length and a width direction step length may be defined, and position points (length/length direction step length of the preset region + 1) × (width/width direction step length of the preset region + 1) are determined in the preset region to which the target parking pose point belongs. For example, the length and width of the preset region to which the target parking pose points belong are 10m and 8m respectively, and the length-direction step size and the width-direction step size are both 1m, so that 11 × 9=99 pose points can be determined.
And a2, determining a pose point corresponding to each position point based on a preset pose angle to serve as a first candidate pose point.
In one embodiment, each position point has a plurality of directions, step length in the angle direction is defined, orientation angles (2 pi/step length in the angle direction) can be obtained, and the equipment obtains position and position points (2 pi/step length in the angle direction) at the position point according to the determined orientation angle of 0 degree.
In one embodiment, a preset area with the length W and the width H determined near the target parking pose point is assumed to be within the range of theta epsilon (-pi, pi)]The definition domain representing the orientation angle is (res) in each of the length direction step size, the width direction step size, and the angle direction step size in the three-dimensional state space of W × H × θ x ,res y ,res θ ) Then the device depends on the parameter (res) x ,res y ,res θ ) And generating discrete three-dimensional pose points in a preset area where the target parking pose points belong, and forming a first candidate pose state set S by the points. For example, if W is 10m and H is 5 m, then (res) x ,res y ,res θ ) If 11 discrete points are produced in length, 6 discrete points are produced in width, and 6 discrete points are produced in orientation angles, the apparatus will determine 11 x 6=396 three-dimensional pose points, i.e., 396 discrete first candidate pose points, in total.
By the embodiment, different length direction step lengths, width direction step lengths and angle direction step lengths can be set according to actual needs, and different numbers of first candidate pose points which are uniformly distributed are selected from the preset area to which the target parking pose point belongs.
In practical applications, there may be a plurality of pose points near the target parking pose point that have no collision path with the target parking pose point, so in one embodiment, a pose point corresponding to the optimal collision-free path of the target parking pose point may be selected as the collision-free pose point. Namely, the collision-free path from the collision-free pose point to the target parking pose point is the collision-free path with the lowest driving cost value in the collision-free paths from the pose points to the target parking pose point in the preset area.
Therefore, in an embodiment, the step 201 may specifically include:
and 2011, determining a plurality of first candidate pose points by using a preset pose point selection strategy in a preset area where the target parking pose point belongs.
The description of this step can refer to the description of step 201 a.
Step 2013, regarding each first candidate pose point, and taking the first candidate pose point as a second candidate pose point under the condition that a collision-free path exists between the first candidate pose point and the target parking pose point.
The description of this step can refer to the description of step 201 b.
Step 2015, determining, for each second candidate pose point, a driving cost value of the second candidate pose point driving to the target parking pose point.
In one embodiment, for each second candidate pose point, when the apparatus determines the travel cost of the second candidate pose point traveling to the target parking pose point, the length of a collision-free path between the second candidate pose point and the target parking pose point may be directly used as the travel cost value, and the longer the length of the collision-free path, the larger the travel cost value.
In one embodiment, for each second candidate pose point, when the device acquires one or more driving cost parameters of the second candidate pose point driving to the target parking pose point, the device determines the driving cost value of the second candidate pose point driving to the target parking pose point according to the acquired one or more driving cost parameters.
And 2017, taking the second candidate pose point with the minimum driving cost as a collision-free pose point.
In one embodiment, after the apparatus determines the travel cost for each of the second candidate pose points to travel to the target parking pose point, the second candidate pose point having the smallest travel cost is determined as the collision-free pose point by comparison.
In one embodiment, the driving costs of the second candidate pose points may be the same, so that the device may determine a plurality of second candidate pose points with the smallest driving costs, and select one of the second candidate pose points as the collision-free pose point.
According to the embodiment, the optimal one of the multiple last collision-free paths of the parking path is selected, so that the last collision-free path of the parking path obtained by the equipment planning is quicker and safer in driving.
In one embodiment, for each second candidate pose point, a Voronoi potential energy value for the second candidate pose point may be calculated as a travel cost value for the second candidate pose point.
The Voronoi potential energy of the grid point can reflect the distance between the grid point and the peripheral obstacle, and the higher the potential energy is, the closer the grid point is to the peripheral obstacle, and the danger is increased from the viewpoint of collision avoidance safety. Compared with a common artificial potential field, the Voronoi potential field has an advantage in potential energy calculation of a narrow passage area formed by similar obstacles. When two obstacles are close to each other, a narrow passage is formed between the two obstacles, if the general potential field is used for calculation, the potential energy in the narrow passage is generally higher (because a point in the narrow passage is close to the obstacle), so that the search process which tends to have low potential energy is not easy to cross the narrow passage, and if the Voronoi potential energy is used for calculating the potential energy in the narrow passage area, a low potential energy area (generally, a position with the same distance with the two obstacles) close to 0 always exists in the narrow passage area, so that the path search is convenient to cross the narrow passage.
Voronoi potential energy ρ v (x, y) the calculation formula at point (x, y) is:
wherein, d o Is the closest distance of point (x, y) to the obstacle, d v Is the closest distance between the point (x, y) and the generalized Voronoi polygon edge (the generalized Voronoi polygon edge can be directly found by MATLAB function Voronoi (x, y)), alpha is a positive constant,
maximum effective distance of potential field when
Time, potential energy value rho v (x, y) =0. It can also be seen from the calculation formula that when point (x, y) is located on the edge of the generalized Voronoi polygon (i.e., d) v (x, y) = 0), potential energy value ρ v (x, y) =0.Voronoi potential energy ρ v (x, y) is in the range of [0,1]Maximum Voronoi potential energy value at the point of the obstacle, i.e. p v (x, y) =1. Determining a specific potential field parameter alpha,
Then, the Voronoi potential value can be calculated.
Noting that the Voronoi potential value of a second candidate pose point r is f1, then
f1＝Voronoi(r x ,r y )
Wherein r is x ,r y Is the position coordinate of the pose point r.
In one embodiment, for each second candidate pose point, a gradient value of Voronoi potential energy at the second candidate pose point along an orientation direction of the second candidate pose point may be calculated as a travel cost value of the second candidate pose point.
The gradient value of the Voronoi potential energy along the orientation direction of the second candidate pose point can be obtained by calculating the Voronoi potential energy and then performing discrete differential numerical calculation. The effect of reducing the gradient value of the Voronoi potential energy along the direction of the second candidate pose point is to make the path pointed by the orientation angle of the selected second candidate pose point as far away from the surrounding obstacle as possible. For example, in a corridor, a point is located at the right middle of the corridor, and the Voronoi potential energy gradient value is 0 along the corridor direction, which indicates that walking along the direction is without obstacles and is more and more far away from the obstacles; the Voronoi potential energy gradient values will be larger and larger along the vertical and corridor directions, which indicates that the obstacle is present and the obstacle is closer and closer along the direction.
Noting that the gradient value of the Voronoi potential energy of a certain second candidate pose point r along the direction of the second candidate pose point r is f2, then
Where r θ is the orientation angle of the second candidate pose point r.
In one embodiment, for each second candidate pose point, a Voronoi potential energy integrated value on a collision-free path from the second candidate pose point to the target parking pose point may be calculated as a travel cost value of the second candidate pose point.
The Voronoi potential energy integrated value on the non-collision path from the second candidate pose point to the target parking pose point is the sum of Voronoi potential energy of discrete points on the non-collision path from the second candidate pose point to the target parking pose point, and the Voronoi potential energy integrated value on the non-collision path from the second candidate pose point to the target parking pose point is reduced, so that the safety of the selected non-collision path from the non-collision pose point to the target parking pose point of the non-collision pose point can be improved.
Recording the Voronoi potential energy integral value on a non-collision path from a certain second candidate pose point r to the target parking pose point as f3, then
f3＝∑ p RS r Voronoi(p x ,p y )
Wherein, RS r Is a collision-free path from the second candidate pose point r to the target parking pose point, p is a discrete point on the collision-free path, p x ,p y Is the x, y position coordinate value of the point p.
In one embodiment, for each second candidate pose point, a difference value of the orientation angles of the intermediate pose point and the second candidate pose point may be calculated as the travel cost value of the second candidate pose point.
Reducing the difference value of the orientation angles of the intermediate pose point and the second candidate pose point, enabling the selected collision-free pose point to reduce the searching difficulty of a collision-free path directly reaching the collision-free pose point from the intermediate pose point. The smaller the orientation difference value between the intermediate pose point and the non-collision pose point is, the more likely the intermediate pose point and the non-collision pose point are to plan a non-collision path approaching to a straight line.
The difference value of the orientation angle of a second candidate pose point r and the intermediate pose point is recorded as f4, and then
Where r θ is the orientation angle of the second candidate pose point, and q θ is the orientation angle of the intermediate pose point q.
In one embodiment, for each second candidate pose point, the device may acquire at least two of the following travel cost parameters for that second candidate pose point:
the Voronoi potential energy value of the second candidate pose point, the gradient value of the Voronoi potential energy along the pose direction of the second candidate pose point, the Voronoi potential energy integrated value on the path from the second candidate pose point to the target parking pose point, and the pose direction difference value between the intermediate pose point and the second candidate pose point.
And then, the equipment obtains the driving cost value of the candidate pose point according to the obtained driving cost value parameters and a preset weighting strategy.
In one embodiment, if the driving cost of a second candidate pose point r is f, the driving cost f of the second candidate pose point r can be calculated by using the following formula:
f＝w 1 f 1 +w 2 f 2 +w 3 f 3 +w 4 f 4
w 1-w 4 are four non-negative weight constants, f 1-f 4 are respectively a Voronoi potential energy value of the second candidate pose point, a gradient value of the Voronoi potential energy along the pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point, and values of w 1-w 4 can be selected to be proper values according to specific requirements and are not less than 0.
And the larger f is, the larger the running cost value of the second candidate pose point in the actual planning is.
In one embodiment, step 2015 may specifically include:
step 2015a, for each second candidate pose point, obtaining a driving cost parameter of the second candidate pose point.
The driving cost parameter comprises one or more of a Voronoi potential energy value of the second candidate pose point, a gradient value of the Voronoi potential energy along the pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point.
And step 2015b, determining the driving cost value of the second candidate pose point according to the acquired driving cost parameter of the second candidate pose point.
In one embodiment, the apparatus may directly take one of a Voronoi potential energy value of the second candidate pose point, a gradient value of Voronoi potential energy along a pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point as the travel cost value of the second candidate pose point.
In one embodiment, the device may select two or more of the Voronoi potential energy value of the second candidate pose point, the gradient value of the Voronoi potential energy along the pose direction of the second candidate pose point, the Voronoi potential energy integrated value on the path from the second candidate pose point to the target parking pose point, and the pose direction difference value between the intermediate pose point and the second candidate pose point, perform weighted calculation according to actual needs, and obtain the travel cost value of the second candidate pose point.
Fig. 4 is a schematic flow chart of a parking path planning method according to an embodiment of the present invention.
1. Firstly, determining a current pose point and a target pose point to which a vehicle with a planned path runs, and initializing an open set to be the current pose point and a closed set to be null.
2. And selecting the second candidate pose point with the minimum current running cost value as a collision-free pose point from the second candidate pose point set.
3. And judging whether the open set is empty, if so, indicating that all the pose points of the current map are searched, and failing to search the path if no collision-free parking path is searched. If not, continue to step 4.
4. And in the open set, taking the pose point with the minimum total cost f as an intermediate pose point.
5. And determining whether the middle pose point and the collision-free pose point have collision-free paths or not. If the target parking position point exists, path planning is successful, and a final parking path is produced according to a collision-free path from the current position point to the middle position point, a collision-free path from the middle position point to the collision-free position point and a collision-free path from the collision-free position point to the target parking position point. If not, continue to step 6.
6. And determining and selecting an adjacent pose point of the middle pose points according to a kinematic formula.
7. And (6) judging whether a collision-free path exists in the path from the middle pose point to the adjacent pose point, if not, returning to the step 6, and re-selecting one adjacent pose point. If there is a collision-free path, continue to step 8.
8. And judging whether the adjacent pose point is in the closed set or not. If the temporary pose point is in the closed set, the adjacent pose point is traversed, correlation calculation is not needed to be carried out on the adjacent pose point again, and a return value step 6 is carried out to select an adjacent pose point again; if the adjacent pose point is not in the close set, the step 9 is continuously executed.
9. And calculating the motion cost g from the current pose point to the adjacent pose point according to the motion cost from the current pose point to the intermediate pose point and the motion cost from the intermediate pose point to the adjacent pose point.
10. And judging whether the adjacent pose point is in an open set or not. If yes, executing step 11; if not, step 13 is performed.
11. And judging the motion cost g of the adjacent pose point and the motion cost g of the adjacent pose point stored in the opening set. And if the motion cost g of the adjacent pose point is not less than the motion cost g of the adjacent pose point stored in the opening set, directly returning to the step 2. If the motion cost g of the adjacent pose point is less than the motion cost g of the adjacent pose point saved in the opening set, step 12 is executed.
12. And updating the motion cost g of the adjacent pose point in the opening set, the parent node of the adjacent pose point and the total cost f of the adjacent pose point, and returning to the step 2.
13. And calculating the heuristic cost h of the adjacent pose point, calculating the total cost f of the adjacent pose point according to the motion cost g and the heuristic cost h of the adjacent pose point, recording the father node of the adjacent pose point as an intermediate pose point, and adding the adjacent pose point into the open set. And returning to the step 2.
The above is a detailed description of the parking path planning method in the present application, and it should be understood that, although the steps in the flowcharts according to the embodiments described above are sequentially shown according to the arrow, the steps are not necessarily sequentially executed according to the order indicated by the arrow. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a parking path planning device for implementing the above-mentioned parking path planning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the parking path planning device provided below can refer to the limitations on the parking path planning method in the above description, and are not described herein again.
In one embodiment, as shown in fig. 5, there is provided a parking path planning apparatus including: an obtaining module 501, a determining module 503 and a generating module 505, wherein:
an obtaining module 501, configured to obtain collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
a determining module 503, configured to determine whether there is a collision-free path from the intermediate pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
a generating module 505, configured to generate a parking path according to a collision-free path from the current pose point to the intermediate pose point, a collision-free path from the intermediate pose point to the collision-free pose point, and a collision-free path from the collision-free pose point to the target parking pose point, if any.
In one embodiment, the parking path planning apparatus further includes:
an updating module 507 (not shown in the figure) configured to, if no collision-free path exists between the intermediate pose point and the collision-free pose point, re-determine the intermediate pose point according to the path search policy, and invoke the determining module 503.
In one embodiment, the obtaining module 501 specifically includes a selecting submodule 5011 (not shown in the figure) and a screening submodule 5013 (not shown in the figure), wherein,
the selecting submodule 5011 is used for determining a plurality of first candidate pose points in a preset region where the target parking pose points belong according to a preset pose point selecting strategy;
the screening submodule 5013 is configured to, for each first candidate pose point, regard the first candidate pose point as a collision-free pose point when there is a collision-free path from the first candidate pose point to the target parking pose point.
In one embodiment, the above-mentioned selection sub-module 5011 specifically includes a position point determination sub-unit 5011a (not shown in the figure) and a pose point determination sub-unit 5011b (not shown in the figure), wherein,
a location point determining subunit 5011a, configured to determine a plurality of location points in the preset area based on a preset location selection policy;
a pose point determining subunit 5011b, configured to determine, based on a preset pose angle, a pose point corresponding to each position point as a first candidate pose point.
In one embodiment, the obtaining module 501 specifically includes a first candidate pose point determining submodule 501a (not shown), a second candidate pose point determining submodule 501b (not shown), a driving cost value determining submodule 501c (not shown), and a collision-free pose point determining submodule 501d (not shown), wherein,
the first candidate pose point determining sub-module 501a is configured to determine, in a preset area to which the target parking pose point belongs, a plurality of first candidate pose points according to a preset pose point selection strategy;
a second candidate pose point determining sub-module 501b configured to, for each first candidate pose point, regard the first candidate pose point as a second candidate pose point when there is a collision-free path from the first candidate pose point to the target parking pose point;
a driving cost value determination submodule 501c configured to determine, for each second candidate pose point, a driving cost value for driving the second candidate pose point to the target parking pose point;
and a collision-free pose point determining submodule 501d configured to take the second candidate pose point with the smallest travel cost value as the collision-free pose point.
In one embodiment, the driving cost value determination submodule 501c is specifically configured to:
for each second candidate pose point, acquiring a running cost parameter of the second candidate pose point: wherein the driving cost parameter comprises one or more of a Voronoi potential energy value of the second candidate pose point, a gradient value of the Voronoi potential energy along a pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point;
and determining the driving cost value of the second candidate pose point according to the acquired driving cost parameter of the second candidate pose point.
The modules in the parking path planning apparatus may be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a parking path planning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, the scope of the present disclosure should be considered as being described in the present application.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (10)
1. A method for planning a parking path, the method comprising:
acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
determining whether a collision-free path exists from the middle pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if so, generating a parking path according to a collision-free path from the current pose point to the middle pose point, a collision-free path from the middle pose point to the collision-free pose point and a collision-free path from the collision-free pose point to the target parking pose point.
2. The method of claim 1, further comprising:
and if no collision path exists from the middle pose point to the collision-free pose point, re-determining the middle pose point according to the path search strategy, and executing the step of determining whether the collision-free path exists from the middle pose point to the collision-free pose point.
3. The method according to claim 1, wherein the acquiring collision-free pose points within a preset region to which the target parking pose points belong comprises:
determining a plurality of first candidate pose points by a preset pose point selection strategy in a preset area to which the target parking pose point belongs;
for each first candidate pose point, taking the first candidate pose point as a collision-free pose point if there is a collision-free path from the first candidate pose point to the target parking pose point.
4. The method according to claim 3, wherein the determining a plurality of first candidate pose points with a preset pose point selection strategy in a preset area to which the target parking pose point belongs comprises:
determining a plurality of position points in the preset area based on a preset position selection strategy;
and determining a pose point corresponding to each position point based on a preset pose angle as a first candidate pose point.
5. The method according to claim 1, wherein the acquiring collision-free pose points within a preset area to which the target parking pose point belongs comprises:
in a preset area where the target parking pose points belong, determining a plurality of first candidate pose points by a preset pose point selection strategy;
for each first candidate pose point, taking the first candidate pose point as a second candidate pose point when a collision-free path exists from the first candidate pose point to the target parking pose point;
for each second candidate pose point, determining a driving cost value of the second candidate pose point to drive to the target parking pose point;
and taking the second candidate pose point with the minimum driving cost value as a collision-free pose point.
6. The method of claim 5, wherein the determining, for each second candidate pose point, a travel cost value for the candidate pose point to travel to the target parking pose point comprises:
for each second candidate pose point, acquiring a running cost parameter of the second candidate pose point: wherein the driving cost parameter comprises one or more of a Voronoi potential energy value of the second candidate pose point, a gradient value of the Voronoi potential energy along a pose direction of the second candidate pose point, a Voronoi potential energy integrated value on a path from the second candidate pose point to the target parking pose point, and a pose direction difference value between the intermediate pose point and the second candidate pose point;
and determining the driving cost value of the second candidate pose point according to the acquired driving cost parameter of the second candidate pose point.
7. A parking path planning apparatus, characterized by comprising:
the acquisition module is used for acquiring collision-free pose points in a preset area to which the target parking pose points belong; the collision-free pose point is a pose point having a collision-free path with the target parking pose point;
a determining module, configured to determine whether a collision-free path exists from the intermediate pose point to the collision-free pose point; the intermediate pose point is a pose point between the current pose point and the target parking pose point determined according to a preset path search strategy;
and if the collision-free path exists, generating a parking path according to the collision-free path from the current pose point to the middle pose point, the collision-free path from the middle pose point to the collision-free pose point and the collision-free path from the collision-free pose point to the target parking pose point.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210823970.6A CN115195706A (en) | 2022-07-14 | 2022-07-14 | Parking path planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210823970.6A CN115195706A (en) | 2022-07-14 | 2022-07-14 | Parking path planning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115195706A true CN115195706A (en) | 2022-10-18 |
Family
ID=83579163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210823970.6A Pending CN115195706A (en) | 2022-07-14 | 2022-07-14 | Parking path planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115195706A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220063663A1 (en) * | 2020-08-26 | 2022-03-03 | Motional Ad Llc | Conditional motion predictions |
| CN117622114A (en) * | 2023-10-19 | 2024-03-01 | 镁佳(北京)科技有限公司 | Parking path planning method and device, computer equipment and storage medium |
-
2022
- 2022-07-14 CN CN202210823970.6A patent/CN115195706A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220063663A1 (en) * | 2020-08-26 | 2022-03-03 | Motional Ad Llc | Conditional motion predictions |
| US11814075B2 (en) * | 2020-08-26 | 2023-11-14 | Motional Ad Llc | Conditional motion predictions |
| CN117622114A (en) * | 2023-10-19 | 2024-03-01 | 镁佳(北京)科技有限公司 | Parking path planning method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111504325B (en) | Global path planning method based on weighted A-algorithm of enlarged search neighborhood | |
| CN115195706A (en) | Parking path planning method and device | |
| Zhang et al. | Autonomous land vehicle path planning algorithm based on improved heuristic function of A-Star | |
| CN112783169B (en) | Path planning method, path planning equipment and computer readable storage medium | |
| Jan et al. | An $\bm {O (n\log n)} $ Shortest Path Algorithm Based on Delaunay Triangulation | |
| CN110319837A (en) | Indoor complex condition path planning method for service robot | |
| CN111460234B (en) | Graph query method, device, electronic equipment and computer readable storage medium | |
| Zhang et al. | Rapid path planning algorithm for mobile robot in dynamic environment | |
| CN114281084B (en) | Intelligent vehicle global path planning method based on improved A-algorithm | |
| CN115218916A (en) | Safety path planning method and device | |
| CN113063430A (en) | Unmanned vehicle path planning method, client and server | |
| CN115390565A (en) | Unmanned ship dynamic path planning method and system based on improved D-star algorithm | |
| Sarmiento et al. | An efficient strategy for rapidly finding an object in a polygonal world | |
| Wu et al. | A maximal ordered ego-clique based approach for prevalent co-location pattern mining | |
| Chen et al. | Region coverage path planning of multiple disconnected convex polygons based on simulated annealing algorithm | |
| Wang et al. | A partitioning-based approach for robot path planning problems | |
| Qiao et al. | A sampling-based multi-tree fusion algorithm for frontier detection | |
| CN115195705A (en) | Bidirectional planning method and device for parking path and computer equipment | |
| Shen et al. | Fast path planning for underwater robots by combining goal-biased Gaussian sampling with focused optimal search | |
| CN110503234A (en) | A kind of method, system and the equipment of logistics transportation scheduling | |
| CN113119995B (en) | Path searching method and device, equipment and storage medium | |
| Tang et al. | Hexagon-based generalized Voronoi diagrams generation for path planning of intelligent agents | |
| CN113741484A (en) | Path planning method, system and medium based on probability model | |
| Qin et al. | Dynamic detection of topological information from grid-based generalized Voronoi diagrams | |
| Monfared et al. | Generalized intelligent Water Drops algorithm by fuzzy local search and intersection operators on partitioning graph for path planning problem |
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 |