A parking trajectory determination method, device, equipment and medium

By connecting the target search node and parking target point with continuous curvature and smooth preset type curve, the problem of discontinuous and non-smooth path curvature in the Hybrid A* algorithm is solved, and parking trajectory that conforms to the vehicle kinematics laws is generated, which reduces the Calculate the load.

CN118514695BActive Publication Date: 2024-11-12IMOTION AUTOMOTIVE TECH (SUZHOU) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410986445.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

The existing automatic parking trajectory planning algorithms, especially the Hybrid A* algorithm, generate path curvatures are discontinuous and non-smooth, require secondary optimization processing, and have high requirements for computing resources, and cannot fully comply with the laws of vehicle kinematics.

Method used

The target search node and parking target point are connected by a continuous and smooth curvature curve to generate a continuous and smooth curvature search curve, thereby determining the parking trajectory, avoiding the trajectory smoothing optimization process and reducing the calculation load.

Benefits of technology

It realizes continuous and smooth parking trajectory generation, conforms to vehicle kinematics laws, saves computing resources, and improves algorithm efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118514695B_ABST
    Figure CN118514695B_ABST
Patent Text Reader

Abstract

The present application discloses a parking trajectory determination method, device, equipment and medium, which relates to the field of vehicle driving, including: starting a search from a parking starting point based on different search parameters to obtain a number of target search nodes whose distance to obstacles is not less than a preset distance; connecting the target search nodes and parking target points based on a preset type curve with continuous and smooth curvature to obtain a search curve, and determining a target search curve that meets preset conditions from each search curve; determining a parking trajectory based on a curve between the parking starting point and the target search node corresponding to the target search curve and the target search curve. The present application connects the target search node and the parking target point using a preset type curve with continuous and smooth curvature, so that the curvature of the connected search curve is continuous and smooth, which conforms to the kinematic law of the vehicle, and can avoid secondary optimization of trajectory smoothness, thereby saving computing power.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle driving, and in particular to a parking trajectory determination method, device, equipment and medium. Background Art

[0002] The current automatic parking trajectory planning algorithms are mainly divided into two types: traditional geometric algorithms and Hybrid A* algorithms. Among them, the traditional geometric algorithm is mainly based on the trajectory calculation of the finite paradigm. Taking the parking in a vertical parking space as an example, it is generally planned from the end point, and the starting point is connected by a straight line and a roundabout. Usually, only a single path can be generated. The Hybrid A* algorithm connects the starting point and the end point by searching + RS curves. Although multiple paths can be generated, the curvature of the straight line and arc, and the connection between arcs on the generated path are discontinuous, and the curvature of the generated path is not smooth. It is usually necessary to use a secondary optimization method to smooth the trajectory. Not only does it require high computing power, but the generated path cannot be guaranteed to comply with the vehicle kinematics. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a parking trajectory determination method, device, equipment and medium, which can connect the target search node and the parking target point based on a preset type curve with continuous and smooth curvature, so that the curvature of the connected search curve is continuous and smooth, which conforms to the vehicle kinematics law, and can avoid secondary optimization of trajectory smoothing, thereby saving computing power. The specific scheme is as follows:

[0004] In a first aspect, the present application provides a parking trajectory determination method, comprising:

[0005] Starting a search from a parking start point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance;

[0006] The target search node and the parking target point are connected based on a preset type curve to obtain a search curve, and a target search curve that meets a preset condition is determined from each of the search curves; the preset type curve is a curve with continuous and smooth curvature;

[0007] The parking trajectory is determined based on a parking curve and the target search curve; the parking curve is a curve from the parking starting point to the target search node corresponding to the target search curve.

[0008] Optionally, the searching is started from a parking starting point based on different search parameters to obtain a number of target search nodes, including:

[0009] The search is started from a parking start point using different gears and based on different search curvatures and search lengths to obtain a number of target search nodes according to arcs and clothoids.

[0010] Optionally, the searching is started from a parking starting point based on different search parameters to obtain a number of target search nodes, including:

[0011] Starting the search from the parking start point based on different search parameters to obtain a number of initial search nodes;

[0012] Determine a rear axle point of the vehicle based on the initial search node, and determine a vehicle profile corresponding to the initial search node based on the rear axle point of the vehicle and a vehicle heading angle corresponding to the initial search node;

[0013] A target search node is determined from the plurality of initial search nodes, wherein the minimum distance between the vehicle profile and the obstacle is not less than a preset distance.

[0014] Optionally, the method further includes:

[0015] A target search parameter when searching from the parking start point to a target search node corresponding to the target search curve is determined, and the parking curve is determined based on the target search parameter.

[0016] Optionally, the connecting the target search node and the parking target point based on a preset type curve includes:

[0017] The target search node and the parking target point are connected based on the CC curve and the HC curve.

[0018] Optionally, determining a target search curve that meets a preset condition from the search curves includes:

[0019] A target search curve having the shortest travel time and a distance between the search curve and the obstacle not less than the preset distance is determined from the search curves.

[0020] Optionally, the determining, from the search curves, a target search curve having a minimum travel time and a distance between the search curve and the obstacle not less than a preset distance includes:

[0021] Determine the travel time corresponding to each of the search curves;

[0022] triggering a search curve selection operation to select a current search curve from the search curves according to the order of the travel time from small to large;

[0023] The current search curve is interpolated. If the distances between a number of interpolation points on the current search curve and the obstacle are not less than the preset distance, the current search curve is determined as the target search curve, and the search curve selection operation is terminated.

[0024] Optionally, the determining the travel time corresponding to each of the search curves includes:

[0025] Determine a first time based on the number of gear shifts and the gear shift time corresponding to the search curve, and determine a second time based on the track length and the driving speed corresponding to the search curve;

[0026] The travel time corresponding to the search curve is determined based on the first time and the second time.

[0027] In a second aspect, the present application provides a parking trajectory determination device, comprising:

[0028] A search node acquisition module, used to start searching from a parking starting point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance;

[0029] A search curve determination module, used for connecting the target search node and the parking target point based on a preset type curve to obtain a search curve, and determining a target search curve that meets a preset condition from each of the search curves; the preset type curve is a curve with continuous and smooth curvature;

[0030] The parking trajectory determination module is used to determine the parking trajectory based on the parking curve and the target search curve; the parking curve is a curve from the parking starting point to the target search node corresponding to the target search curve.

[0031] In a third aspect, the present application provides an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned parking trajectory determination method.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the aforementioned parking trajectory determination method when executed by a processor.

[0035] In the present application, the search is started from the parking starting point based on different search parameters to obtain several target search nodes; wherein the distance between the target search node and the obstacle is not less than the preset distance; the target search node and the parking target point are connected based on a preset type curve to obtain a search curve, and a target search curve that meets the preset conditions is determined from each of the search curves; the preset type curve is a curve with continuous and smooth curvature; the parking trajectory is determined based on the parking curve and the target search curve; the parking curve is a curve from the parking starting point to the target search node corresponding to the target search curve. It can be seen that the present application starts the search from the parking starting point based on different search parameters, so that multiple search curves can be obtained according to several search nodes, and the applicability to different scenarios can be improved through multiple search curves; and the present application uses a preset type curve with continuous and smooth curvature to connect the target search node and the parking target point, so that the curvature of the connected search curve is continuous and smooth, which conforms to the kinematic law of the vehicle, and compared with the RS curve, the present application can avoid the secondary optimization of trajectory smoothing, thereby reducing the computing power required to determine the parking trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A flow chart of a parking trajectory determination method disclosed in this application;

[0038] Figure 2 A schematic diagram of a parking scenario disclosed in this application;

[0039] Figure 3 A schematic diagram of a search node disclosed in this application;

[0040] Figure 4 A parking schematic diagram for a specific scenario disclosed in this application;

[0041] Figure 5 A parking trajectory determination flow chart disclosed in this application;

[0042] Figure 6 A schematic diagram of the structure of a parking trajectory determination device disclosed in this application;

[0043] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The current traditional geometric algorithm can usually only generate a single path, and the curvature of the path generated by the Hybrid A* algorithm is not smooth and discontinuous at the junction, and the path usually needs to be optimized twice to make the trajectory smooth. To this end, the present application provides a parking trajectory determination method, which connects the target search node and the parking target point by using a preset type curve with continuous and smooth curvature, so that the curvature of the connected search curve is continuous and smooth, which conforms to the vehicle kinematics law, and can avoid secondary optimization of trajectory smoothness, thereby saving computing power.

[0046] See also Figure 1 As shown, an embodiment of the present invention discloses a parking trajectory determination method, comprising:

[0047] Step S11, starting the search from the parking starting point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance.

[0048] In this embodiment, the parking start point, parking target point, obstacle information, parking space type corresponding to the parking target point, and parking restriction area corresponding to the parking space type are obtained in advance from the vehicle decision end. The parking space type includes but is not limited to horizontal parking space, vertical parking space, inclined parking space, etc. In addition, the parking start point can be the rear axle point of the vehicle when the vehicle searches for a parking space during the automatic parking process, or the rear axle point of the vehicle when the vehicle receives a parking instruction for the parking space; the parking target point can be the rear axle point of the vehicle when the vehicle is assumed to be completely parked in the parking space, or it can be a point at a certain distance forward from the midpoint of the rear parking space line of the parking space, which needs to ensure that the vehicle can be completely parked in the parking space.

[0049] It should be noted that both the parking start point and the parking target point correspond to a vehicle heading angle, and the vehicle heading angle can be used to determine the direction of the vehicle at that position. Figure 2For example, the small rectangular box with solid lines is the starting position of the vehicle, the rear axle point of the vehicle at this time is the parking starting point, the small rectangular box with dotted lines is the parking space, the point at a certain distance forward from the midpoint of the rear parking space line of the parking space is the parking target point, the asterisk is the obstacle, and the large rectangular box outside is the parking restricted area. The purpose of this embodiment is to find the optimal parking trajectory with continuous and smooth curvature from the parking starting point to the parking target point while bypassing obstacles.

[0050] Specifically, after obtaining the parking starting point and obstacle information, the search starts from the parking starting point based on different search parameters to obtain a number of target search nodes whose distances to the obstacles are not less than a preset distance; wherein the search node can be defined as the rear axle point of the vehicle. That is, the distance between the target search node and each obstacle is greater than or equal to the preset distance. The preset distance can be set by the user according to actual needs, for example, it can be set to 20 centimeters, which is not limited here.

[0051] According to one embodiment, different search parameters may include different gears, different search curvatures, and different search lengths; wherein different gears include forward gears and reverse gears. Therefore, for the target search node, different gears, different search curvatures, and different search lengths may be used to start the search from the parking start point, and the arc and clothoid methods may be used to calculate a number of target search nodes that can be reached and whose distance from the obstacle is not less than a preset distance; and all target search nodes may also be saved in the target node set.

[0052] Among them, for the arc, taking any search curvature among different search curvatures as an example, any search curvature is determined as the starting curvature and the ending curvature of the arc, using different gears and different search lengths and based on the starting curvature and the ending curvature of the arc, the arc is searched from the parking starting point to obtain several target search nodes. That is, the curvature change rate of the arc is 0, and the curvature corresponding to any point on the arc is any search curvature.

[0053] Among them, for the clothoid, taking any search curvature among different search curvatures as an example, any search curvature is determined as the termination curvature of the clothoid, and the starting curvature of the clothoid is determined based on the preset curvature; wherein the preset curvature is generally set to 0; that is, the starting curvature of the clothoid is generally 0, and the ending curvature is any search curvature. Then, using different gears and different search lengths and based on the starting curvature and ending curvature of the clothoid, search is performed from the parking starting point according to the clothoid to obtain several target search nodes. It should be noted that for the clothoid, the curvature change rate = (termination curvature - starting curvature) / search length, so when the search length is different, the curvature change rate of the corresponding clothoid is also different.

[0054] Furthermore, the search may be started from the parking start point in the parking restriction area corresponding to the parking space type of the parking target point based on different search parameters, thereby obtaining several target search nodes whose distance to the obstacle is not less than a preset distance.

[0055] How to obtain a number of target search nodes whose distances from obstacles are not less than a preset distance may specifically include: Figure 3 As shown, the search is first started from the parking starting point based on different search parameters, and several initial search nodes that can be reached are calculated based on arcs and clothoids; wherein the different search parameters include different gears (forward gear and reverse gear), different search curvatures and different search lengths. At the same time, all initial search nodes can also be saved in the initial node set. Afterwards, for each initial search node, it is necessary to determine the rear axle point of the vehicle based on the initial search node, for example, the initial search node can be directly determined as the rear axle point of the vehicle; then, the vehicle contour corresponding to the initial search node is determined based on the rear axle point of the vehicle and the vehicle heading angle corresponding to the initial search node, so as to determine the target search node from several initial search nodes where the minimum distance between the vehicle contour and the obstacle is not less than the preset distance. That is, if the minimum distance between the vehicle contour and the obstacle is less than the preset distance, it is considered that the vehicle will collide with the obstacle when it is at the initial search node corresponding to the vehicle contour.

[0056] Step S12: Connect the target search node and the parking target point based on a preset type curve to obtain a search curve, and determine a target search curve that meets preset conditions from each of the search curves; the preset type curve is a curve with continuous and smooth curvature.

[0057] In this embodiment, for all target search nodes, each target search node is determined as a starting point in turn, and the parking target point is determined as an end point, and each target search node is connected to the parking target point using a preset type curve with continuous and smooth curvature, so as to obtain a plurality of search curves; at the same time, all search curves can also be saved in the first curve set. Among them, the preset type curve with continuous and smooth curvature can use an HC curve and a CC curve, that is, each target search node is connected to the parking target point based on the HC curve and the CC curve, so as to obtain a plurality of search curves.

[0058] Further, after obtaining a plurality of search curves, it is necessary to determine a target search curve that meets a preset condition from the plurality of search curves. The preset condition is a condition constructed based on the travel time and the obstacle distance. Therefore, the target search curve can be a search curve with the shortest travel time and a distance from the obstacle not less than the preset distance among the plurality of search curves. That is, a target search curve with the shortest travel time and a distance from the search curve to the obstacle not less than the preset distance is determined from the plurality of search curves.

[0059] Specifically, after obtaining several search curves, the driving time corresponding to each search curve is determined, and the search curve selection operation is triggered to select the current search curve from the several search curves in order of driving time from small to large. Then the current search curve is interpolated. If the distance between several interpolation points on the current search curve and the obstacle is not less than the preset distance, the current search curve is determined as the target search curve, and the search curve selection operation is terminated. It should be noted that the search nodes and the interpolation points on the search curve all correspond to the vehicle heading angle.

[0060] Among them, for the driving time corresponding to each search curve, the first time is first determined based on the number of gear shifts and the gear shift time corresponding to the search curve, wherein the gear shift time is the time required for one gear shift, and the second time is determined based on the track length and driving speed corresponding to the search curve; then the driving time corresponding to the search curve is determined based on the first time and the second time. That is, driving time t = number of gear shifts × gear shift time + track length / driving speed.

[0061] Among them, for the search curve selection operation, specifically, several search curves are first sorted according to the order of driving time from small to large to obtain the sorted search curve, and the second curve set is determined based on the sorted search curve; that is, the curves in the second curve set are sorted according to the order of driving time from small to large, and the first curve in the second curve set is the curve with the shortest driving time. The first curve in the second curve set is determined as the current search curve, and the current search curve is interpolated at equal intervals. If the distance between one or more interpolation points on the current search curve and the obstacle is less than the preset distance, the next curve in the second curve set is determined as the new current search curve, and the operation of performing the equal interval interpolation on the current search curve is jumped again, until the distance between several interpolation points on the current search curve and the obstacle is not less than the preset distance, at which time the current search curve is determined as the target search curve. That is, if the vehicle travels along the target search curve, the vehicle will not collide with the obstacle.

[0062] According to one embodiment, for the distance between the interpolation point on the current search curve and the obstacle, the vehicle rear axle point is first determined based on the interpolation point on the current search curve. For example, the interpolation point on the current search curve can be directly determined as the vehicle rear axle point; then the vehicle contour corresponding to the interpolation point is determined based on the vehicle rear axle point and the vehicle heading angle corresponding to the interpolation point, so as to calculate the distance between the vehicle contour and the obstacle. At this time, the distance between the vehicle contour and the obstacle is the distance between the interpolation point and the obstacle.

[0063] Step S13, determining a parking trajectory based on a parking curve and the target search curve; the parking curve is a curve from the parking start point to a target search node corresponding to the target search curve.

[0064] In this embodiment, after determining the target search curve, it is also necessary to combine the parking curve from the parking start point to the target search node corresponding to the target search curve, so as to obtain a complete parking trajectory, and send the complete parking trajectory to the vehicle control end in the data format of the horizontal and vertical control interface, and the vehicle control end controls the vehicle to automatically drive from the parking start point to the parking target point according to the parking trajectory, so as to park the vehicle in the parking space. In addition, the parking trajectory can also be displayed on a display screen so that the driver and passengers can intuitively see the parking trajectory, thereby improving the user experience.

[0065] Among them, for the parking curve from the parking starting point to the target search node corresponding to the target search curve, the target search parameters and the target search method (arc or clothoid) when searching from the parking starting point to the target search node corresponding to the target search curve can be determined first, wherein the target search parameters include gear (forward gear or reverse gear), search curvature and search length; then the parking curve from the parking starting point to the target search node corresponding to the target search curve is determined using the target search parameters and based on the target search method.

[0066] It can be seen that the present application starts the search from the parking starting point based on different search parameters, so that multiple search curves can be obtained according to several search nodes. The applicability to different scenarios can be improved through multiple search curves; and the present application connects the target search node and the parking target point by using a preset type curve with continuous and smooth curvature, so that the curvature of the connected search curve is continuous and smooth, which conforms to the kinematic laws of the vehicle, and compared with the use of RS curve, the present application can avoid the secondary optimization of trajectory smoothing, thereby reducing the computing power required to determine the parking trajectory.

[0067] Take the parking lot scenario as an example, see Figure 4 and Figure 5 As shown, an embodiment of the present invention discloses a parking trajectory determination method, comprising:

[0068] Figure 4 The rectangles with slashes in the figure represent pillars, and the solid rectangles represent other vehicles. Both rectangles represent obstacle information. Figure 4 The arrow in the middle indicates the direction of vehicle travel. Figure 4 The hollow solid rectangle in the figure represents the current position of the vehicle. The current rear axle point of the vehicle is used as the parking starting point, and the midpoint of the rear parking space line of the available parking space is a certain distance forward as the parking target point. Figure 4 The hollow dashed rectangle in represents the posture of the vehicle after it is parked in the parking space along the determined parking trajectory.

[0069] After obtaining the parking start point, parking target point and obstacle information, set the current search curvature K to the opposite of the maximum allowable curvature of the vehicle, and set the current search length S to 0, and then determine whether the current search curvature is greater than the maximum allowable curvature of the vehicle. If the current search curvature is not greater than the maximum allowable curvature of the vehicle, update the current search curvature based on the search curvature step dk, and determine whether the current search length is greater than the calibrated search length Sc. If the current search length is not greater than the calibrated search length, update the current search length based on the search length step ds, and use the current search curvature and the current search length in the forward gear and reverse gear respectively, use arcs and clothoids to search for nodes forward or backward, and add the search nodes to the node set A, and then return to the step of determining whether the current search length is greater than the calibrated search length, until the current search length is greater than the calibrated search length, and then reset the current search length to 0, and return to the step of determining whether the current search curvature is greater than the maximum allowable curvature of the vehicle, until the current search curvature is greater than the maximum allowable curvature of the vehicle, at which time the complete node set A can be obtained.

[0070] Traverse the search nodes in node set A, and determine whether the distance between the traversed search node and the obstacle is less than the preset distance. If the distance between the search node and the obstacle is not less than the preset distance, put the search node into node set B, and determine whether the traversal of node set A is complete. If the traversal of node set A is not complete, return to the step of traversing the search nodes in node set A until the traversal of node set A is complete to obtain the complete node set B. If the distance between the search node and the obstacle is less than the preset distance, jump to the step of determining whether the traversal of node set A is complete.

[0071] Traverse the search nodes in node set B, and use the traversed search nodes as the starting point and the parking target point as the end point. Use the HC curve and CC curve to connect the search nodes and the parking target point to obtain a search curve with continuous and smooth curvature, and add the search curve to the curve set C, and then determine whether the traversal of node set B is complete. If the traversal of node set B is not complete, return to the step of traversing the search nodes in node set B until the traversal of node set B is complete to obtain a complete curve set C.

[0072] For each search curve in the curve set C, the travel time corresponding to each search curve is calculated, and all search curves are reordered in ascending order of travel time to obtain the curve set D. That is, the first curve in the curve set D is the curve with the smallest travel time, and the last curve in the curve set D is the curve with the largest travel time.

[0073] Traverse the search curve in the curve set D in a forward and backward order, and determine whether the distance between the traversed search curve and the obstacle is less than the preset distance. If the distance between the search curve and the obstacle is less than the preset distance, determine whether the curve set D has been traversed. If the curve set D has been traversed, it indicates that the trajectory calculation has failed; if the curve set D has not been traversed, return to the step of traversing the search curve in the curve set D in a forward and backward order. If the distance between the search curve and the obstacle is not less than the preset distance, it indicates that the trajectory calculation is successful, and the complete parking trajectory is determined based on the curve between the parking starting point and the search node corresponding to the search curve and the search curve. The complete parking trajectory is then sent to the vehicle control end in the data format of the horizontal and vertical control interface, and the vehicle control end controls the vehicle to automatically drive from the parking starting point to the parking target point according to the parking trajectory, so that the vehicle is automatically parked in the parking space, such as Figure 4 As shown in the hollow dashed rectangle in .

[0074] It can be seen that the present application starts the search from the parking starting point based on different search curvatures, different search lengths and different vehicle gears, thereby obtaining multiple search curves according to a number of search nodes whose distances to obstacles are not less than a preset distance. The applicability to different scenarios can be improved through multiple search curves; and, the present application connects the target search node and the parking target point by using CC curves and HC curves, so that the curvature of the connected search curve is continuous and smooth, which conforms to the vehicle kinematics law, and relative to the use of RS curves, the present application can avoid secondary optimization of trajectory smoothing, thereby reducing the computing power required to determine the parking trajectory.

[0075] See also Figure 6 As shown, an embodiment of the present invention discloses a parking trajectory determination device, comprising:

[0076] A search node acquisition module 11 is used to start searching from a parking start point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance;

[0077] A search curve determination module 12 is used to connect the target search node and the parking target point based on a preset type curve to obtain a search curve, and determine a target search curve that meets a preset condition from each of the search curves; the preset type curve is a curve with continuous and smooth curvature;

[0078] The parking trajectory determination module 13 is used to determine the parking trajectory based on the parking curve and the target search curve; the parking curve is a curve from the parking start point to the target search node corresponding to the target search curve.

[0079] It can be seen that the present application starts the search from the parking starting point based on different search parameters, so that multiple search curves can be obtained according to several search nodes. The applicability to different scenarios can be improved through multiple search curves; and the present application connects the target search node and the parking target point by using a preset type curve with continuous and smooth curvature, so that the curvature of the connected search curve is continuous and smooth, which conforms to the kinematic laws of the vehicle, and compared with the use of RS curve, the present application can avoid the secondary optimization of trajectory smoothing, thereby reducing the computing power required to determine the parking trajectory.

[0080] In some specific embodiments, the search node acquisition module 11 includes:

[0081] The search node acquisition unit is used to start searching from a parking start point using different gears and based on different search curvatures and search lengths, so as to obtain a number of target search nodes according to arcs and clothoids.

[0082] In some specific embodiments, the search node acquisition module 11 includes:

[0083] An initial node acquisition unit, used to start searching from a parking start point based on different search parameters to obtain a number of initial search nodes;

[0084] A vehicle profile determination unit, configured to determine a rear axle point of a vehicle based on the initial search node, and determine a vehicle profile corresponding to the initial search node based on the rear axle point of the vehicle and a vehicle heading angle corresponding to the initial search node;

[0085] The target node determination unit is used to determine a target search node from the initial search nodes, where the minimum distance between the vehicle profile and the obstacle is not less than a preset distance.

[0086] In some specific embodiments, the parking trajectory determination device further includes:

[0087] The parking curve determining unit is used to determine a target search parameter when searching from the parking starting point to a target search node corresponding to the target search curve, and determine the parking curve based on the target search parameter.

[0088] In some specific embodiments, the search curve determination module 12 includes:

[0089] A node connection unit is used to connect the target search node and the parking target point based on the CC curve and the HC curve.

[0090] In some specific embodiments, the search curve determination module 12 includes:

[0091] A search curve determining unit is used to determine, from the search curves, a target search curve whose travel time is the shortest and whose distance between the search curve and the obstacle is not less than the preset distance.

[0092] In some specific embodiments, the search curve determination unit includes:

[0093] A driving time determination unit, used to determine the driving time corresponding to each of the search curves;

[0094] A search curve selection unit, used to trigger a search curve selection operation to select a current search curve from the search curves according to the order of the travel time from small to large;

[0095] The search curve interpolation unit is used to interpolate the current search curve. If the distance between a number of interpolation points on the current search curve and the obstacle is not less than the preset distance, the current search curve is determined as the target search curve and the search curve selection operation is ended.

[0096] In some specific embodiments, the travel time determination unit includes:

[0097] A first time determination unit, configured to determine a first time based on the number of gear shifts and the gear shift time corresponding to the search curve;

[0098] A second time determination unit, configured to determine a second time based on a track length corresponding to the search curve and a driving speed;

[0099] A third time determination unit is configured to determine a travel time corresponding to the search curve based on the first time and the second time.

[0100] Furthermore, the present application also discloses an electronic device. Figure 7This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0101] Figure 7 The structure diagram of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the parking trajectory determination method disclosed in any of the above embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0102] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0103] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0104] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and may be Windows Server, Netware, Unix, Linux, etc. In addition to computer programs that can be used to complete the parking trajectory determination method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0105] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the parking trajectory determination method disclosed above. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, and will not be repeated here.

[0106] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0107] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0109] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0110] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A parking trajectory determination method, characterized in that: include: Starting a search from a parking start point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance; The target search node and the parking target point are connected based on a preset type curve to obtain a search curve, and a target search curve that meets a preset condition is determined from each of the search curves; the preset type curve is a curve with continuous and smooth curvature; Determining a parking trajectory based on a parking curve and the target search curve; the parking curve is a curve from the parking start point to a target search node corresponding to the target search curve; The search is started from the parking starting point based on different search parameters to obtain several target search nodes, including: Using different gears and based on different search curvatures and different search lengths, the search is started from a parking start point to obtain a number of target search nodes according to arcs and clothoids; The search is started from the parking starting point based on different search parameters to obtain several target search nodes, including: Starting the search from the parking start point based on different search parameters to obtain a number of initial search nodes; Determine a rear axle point of the vehicle based on the initial search node, and determine a vehicle profile corresponding to the initial search node based on the rear axle point of the vehicle and a vehicle heading angle corresponding to the initial search node; A target search node is determined from the plurality of initial search nodes, wherein the minimum distance between the vehicle profile and the obstacle is not less than a preset distance.

2. The parking trajectory determination method according to claim 1, characterized in that: Also includes: A target search parameter when searching from the parking start point to a target search node corresponding to the target search curve is determined, and the parking curve is determined based on the target search parameter.

3. The parking trajectory determination method according to claim 1, characterized in that: The connecting the target search node and the parking target point based on a preset type curve includes: The target search node and the parking target point are connected based on the CC curve and the HC curve.

4. The parking trajectory determination method according to any one of claims 1 to 3, characterized in that: The step of determining a target search curve that meets a preset condition from each of the search curves includes: A target search curve having the shortest travel time and a distance between the search curve and the obstacle not less than the preset distance is determined from the search curves.

5. The parking trajectory determination method according to claim 4, characterized in that: The step of determining a target search curve from the search curves, wherein the travel time is the shortest and the distance between the search curve and the obstacle is not less than the preset distance, comprises: Determine the travel time corresponding to each of the search curves; triggering a search curve selection operation to select a current search curve from the search curves according to the order of the travel time from small to large; The current search curve is interpolated. If the distances between a number of interpolation points on the current search curve and the obstacle are not less than the preset distance, the current search curve is determined as the target search curve, and the search curve selection operation is terminated.

6. The parking trajectory determination method according to claim 5, characterized in that: The determining of the travel time corresponding to each of the search curves includes: Determine a first time based on the number of gear shifts and the gear shift time corresponding to the search curve, and determine a second time based on the track length and the driving speed corresponding to the search curve; The travel time corresponding to the search curve is determined based on the first time and the second time.

7. A parking trajectory determination device, characterized in that: include: A search node acquisition module, used to start searching from a parking starting point based on different search parameters to obtain a number of target search nodes; the distance between the target search node and the obstacle is not less than a preset distance; A search curve determination module, used for connecting the target search node and the parking target point based on a preset type curve to obtain a search curve, and determining a target search curve that meets a preset condition from each of the search curves; the preset type curve is a curve with continuous and smooth curvature; A parking trajectory determination module, configured to determine a parking trajectory based on a parking curve and the target search curve; the parking curve is a curve from the parking start point to a target search node corresponding to the target search curve; The search node acquisition module is specifically used to: start the search from the parking start point using different gears and based on different search curvatures and different search lengths, so as to obtain a number of target search nodes according to arcs and clothoids; Among them, the search node acquisition module is specifically used to: start searching from a parking starting point based on different search parameters to obtain a number of initial search nodes; determine the rear axle point of the vehicle based on the initial search node, and determine the vehicle contour corresponding to the initial search node based on the rear axle point of the vehicle and the vehicle heading angle corresponding to the initial search node; determine a target search node from the several initial search nodes, where the minimum distance between the vehicle contour and the obstacle is not less than a preset distance.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the parking trajectory determination method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the parking trajectory determination method according to any one of claims 1 to 6.