Parking path processing method and device, electronic equipment and storage medium

Abstract

The invention relates to a parking path processing method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a driving action sequence based on the driving action of a vehicle in an initial parking path, dividing the initial parking path into a plurality of sub-paths according to the driving action sequence, and performing clothoid optimization processing on the arc path in the plurality of sub-paths to generate an optimized sub-path, and determining a final parking path according to the linear path in the plurality of sub-paths and the optimized sub-path. Therefore, the control precision can be improved, in-situ steering of the tires is effectively avoided, and abrasion of the tires in the parking process is reduced.

Description

Technical Field

[0001] This application relates to the technical field of automatic parking, and particularly to a parking path processing method, apparatus, electronic device, and storage medium. Background Art

[0002] With the continuous development of intelligent vehicle technology, automatic parking has become an indispensable part of intelligent vehicle autonomous driving. Among them, parking path planning plays the most important role. The existing parking path planning methods generally include geometric methods and search methods.

[0003] However, whether it is a geometric method or a search method, a parking path is obtained by combining straight lines and arcs. There are often sudden changes in curvature at the joints of arc - straight line or arc - arc, resulting in poor control effects and the situation of the tire turning in place. Summary of the Invention

[0004] This application provides a parking path processing method, apparatus, electronic device, and storage medium, which can improve control accuracy, effectively avoid the tire turning in place, and reduce tire wear during parking.

[0005] In a first aspect, this application provides a parking path processing method, including:

[0006] Obtain the initial parking path of the vehicle, and determine the driving action sequence of the initial parking path, where the driving action sequence includes the driving actions corresponding to each path node in the initial parking path;

[0007] Divide the initial parking path into multiple sub - paths according to the driving action sequence;

[0008] Perform clothoid optimization processing on the arc paths in the multiple sub - paths to generate optimized sub - paths;

[0009] Determine the final parking path according to the straight - line paths and the optimized sub - paths in the multiple sub - paths.

[0010] In a second aspect, an embodiment of this application provides a parking path processing apparatus, including:

[0011] A driving action determination module, configured to obtain the initial parking path of the vehicle, and determine the driving action sequence of the initial parking path, where the driving action sequence includes the driving actions corresponding to each path node in the initial parking path;

[0012] A sub - path division module, configured to divide the initial parking path into multiple sub - paths according to the driving action sequence;

[0013] A sub-path processing module, configured to perform clothoid optimization processing on the arc paths in the multiple sub-paths to generate optimized sub-paths;

[0014] A final parking path determination module, configured to determine a final parking path according to the straight-line paths and the optimized sub-paths in the multiple sub-paths.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0016] A memory, configured to store a computer program;

[0017] A processor, configured to execute the computer program stored in the memory, and when the computer program is executed, implement the method provided by the embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and characterized in that when the computer program is executed by a processor, the method provided by the embodiment of the present application is implemented.

[0019] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art: In the method provided by the embodiments of the present application, a driving action sequence is determined based on the driving actions of the vehicle in the initial parking path, the initial parking path is divided into multiple sub-paths according to the driving action sequence, clothoid optimization processing is performed on the arc paths in the multiple sub-paths to generate optimized sub-paths, and a final parking path is determined according to the straight-line paths and the optimized sub-paths in the multiple sub-paths. Specifically, the arc paths in the above multiple sub-paths are processed into the form of a clothoid-arc-clothoid with continuous curvature, and the final parking path is determined in combination with the straight-line part in the initial parking path. Thereby, the control accuracy can be improved, the in-situ steering of the tires can be effectively avoided, the wear of the tires during the parking process can be reduced, and this is a post-processing operation step for the initial parking path, which does not affect the front-end planning of the initial parking path, can be decoupled from the front-end planning algorithm of the initial parking path, and is compatible with any front-end planning algorithm of the combination of arcs and straight lines, with strong compatibility. Description of the Drawings

[0020] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present application and used together with the description to explain the principles of the present application.

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0022] One or more embodiments are illustrated by way of example in the accompanying drawings corresponding thereto. These illustrative descriptions do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements, unless otherwise stated, and the drawings in the figures do not constitute a scale limitation.

[0023] Figure 1 is a schematic diagram of a parking scenario;

[0024] Figure 2 is Figure 1 a schematic diagram of the path curvature change of a parking scenario shown in;

[0025] Figure 3 is a schematic diagram of another parking scenario;

[0026] Figure 4 is Figure 3 a schematic diagram of the path curvature change of another parking scenario shown in;

[0027] Figure 5 is a schematic diagram of a clothoid;

[0028] Figure 6 is a flowchart of a parking path processing method provided by an embodiment of the present application;

[0029] Figure 7 is Figure 1 a schematic diagram of the final parking path obtained after processing the initial parking path shown in;

[0030] Figure 8 is Figure 7 a schematic diagram of the path curvature change of the final parking path shown in;

[0031] Figure 9 is Figure 3 a schematic diagram of the final parking path obtained after processing the initial parking path shown in;

[0032] Figure 10 is Figure 9 a schematic diagram of the path curvature change of the final parking path shown in;

[0033] Figure 11 is a flowchart of a method for determining a driving action sequence of an initial parking path provided by an embodiment of the present application;

[0034] Figure 12 is a flowchart of a method for determining an arc path in a plurality of sub-paths in an initial parking path according to the curvature of each path node in the initial parking path provided by an embodiment of the present application;

[0035] Figure 13It is a flowchart of a method for dividing an initial parking path into multiple sub-paths according to a driving action sequence provided by an embodiment of the present application;

[0036] Figure 14 It is a flowchart of a method for performing clothoid optimization processing on circular arc paths in multiple sub-paths to generate optimized sub-paths provided by an embodiment of the present application;

[0037] Figure 15 It is a schematic diagram of the processing process of the circular arc path in the initial parking path;

[0038] Figure 16 It is a flowchart of a method for performing a symmetry operation on a target curve based on the connection line between the midpoint of a target circular arc and a target intersection point to obtain an optimized sub-path including a first clothoid - target circular arc - second clothoid provided by an embodiment of the present application;

[0039] Figure 17 It is a flowchart for processing the circular arc path in the initial parking path;

[0040] Figure 18 It is a structural block diagram of a parking path processing device provided by an embodiment of the present application;

[0041] Figure 19 It is a structural block diagram of an electronic device provided by an embodiment of the present application. Specific embodiments

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0043] The following disclosure provides many different embodiments or examples for implementing different structures of the present application. To simplify the disclosure of the present application, the components and settings of specific examples are described below. Of course, they are only examples and are not intended to limit the present application. In addition, the present application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0044] See Figure 1 , Figure 1 is a schematic diagram of a parking scenario. As Figure 1As shown, the vehicle starts from point A, moves forward along the straight path AB to point B, then moves forward along the arc path BC with a fixed turning radius to the left to point C, switches to reverse gear at point C, then moves along the arc path CD to point D, and finally moves along the straight path DE to point E to complete parking.

[0045] The above parking path consists of the straight path AB, the arc path BC, the arc path CD, and the straight path DE. The curve of the path curvature k with respect to the path length s is as Figure 2 shown. Among them, in the above parking path, at the connection of the arc path BC and the arc path CD, that is, at point C, the curvature changes suddenly, which is likely to cause poor control effect and there is a situation where the tire turns in place.

[0046] See Figure 3 , Figure 3 is a schematic diagram of another parking scenario. As Figure 3 shown, the vehicle starts from point A, moves forward along the straight path AB to point B, then moves backward along the arc path BC with a fixed turning radius to the right to point C, maintains reverse gear at point C, and then moves along the straight path CD to point D to complete parking.

[0047] The above parking path consists of the straight path AB, the arc path BC, and the straight path CD. The curve of the path curvature k with respect to the path length s is as Figure 4 shown. Among them, in the above parking path, at the connection of the arc path and the straight path, that is, at point B, the curvature changes suddenly, which is likely to cause poor control effect and there is a situation where the tire turns in place.

[0048] The above scenarios are only examples, and other scenarios are similar and will not be elaborated here.

[0049] To solve the technical problems of poor control effect caused by sudden curvature changes in the parking path in the prior art and the situation where the tire turns in place, the present application provides a parking path processing method, device, electronic device, and storage medium. By using a clothoid to process the arc path in the parking path, the parking path can be transformed into a path with continuous curvature, improving the control accuracy, effectively avoiding the in-place turning of the tire, and reducing the wear of the tire during parking. Among them, the clothoid can refer to the solid line part in Figure 5 , O0 is the starting point with a curvature of 0, and it extends with a variable curvature to the point (x t , y t ). At this time, the minimum turning radius R of the vehicle is reached min , and the instantaneous center of the circle is o t (x ot , y ot ). At this time, the path length traveled is L min . Among them, the formula of the clothoid curve is:

[0050] A 2 = RL

[0051] Wherein, L is the arc length, R is the turning radius at the arc length of L, and A characterizes the curvature characteristics of the clothoid curve.

[0052] Figure 6 It is a flowchart of a parking path processing method provided by an embodiment of the present application. As Figure 6 shown, the method includes the following steps:

[0053] Step 601: Obtain the initial parking path of the vehicle and determine the driving action sequence of the initial parking path.

[0054] In the technical solution of the embodiment of the present application, the initial parking path may be a parking path planned by a geometric algorithm in the early stage. The initial parking path usually includes an arc path part and / or a straight path part. For example, as Figure 1 shown, the initial parking path includes a straight path AB, an arc path BC, an arc path CD, and a straight path DE. As Figure 3 shown, the initial parking path includes a straight path AB, an arc path BC, and a straight path CD.

[0055] The driving action sequence of the initial parking path includes the driving actions corresponding to each path node in the initial parking path. Among them, the driving action corresponding to the path node refers to the driving-related actions at the path node during parking, including but not limited to gear shifting actions, direction adjustment actions, etc. For example, in Figure 1 the shown scenario, the driving action corresponding to path node A is: forward gear, the driving action corresponding to path node B is: forward gear and turn left, the driving action corresponding to path node C is: reverse gear and turn right, and the driving action corresponding to path node D is: reverse gear and straighten the direction. In Figure 3 the shown scenario, the driving action corresponding to path node A is forward gear, the driving action corresponding to path node B is: reverse gear and turn right, and the driving action corresponding to path node C is: reverse gear and straighten the direction.

[0056] Specifically, how to determine the driving action sequence of the initial parking path will be described in detail in the relevant embodiments below, and will not be elaborated here first.

[0057] Step 602: Divide the initial parking path into multiple sub-paths according to the driving action sequence.

[0058] In the technical solution of the embodiment of the present application, a multi-step parking path refers to a driving path that requires gear shifting and / or steering during the parking process. Specifically, if any of the following conditions is met throughout the parking process, the parking path is regarded as a "multi-step parking path": the reverse gear and the forward gear need to be alternately used throughout the process, and the entire parking process cannot be completed with only one reverse gear or only one forward gear; at least two steering actions need to be performed during the parking process, such as "forward - steering - reverse - steering again". For example, Figure 1 and Figure 3 The parking paths in the shown scenarios are all multi-step parking paths, where Figure 1 and Figure 3 In the shown scenarios, the reverse gear and the forward gear are alternately used throughout the parking path, and there are direction steering actions during the parking process.

[0059] For the case where the initial parking path is a multi-step parking path, according to the driving action sequence, the initial parking path is divided into multiple sub-paths. Among them, based on the above description, it can be known that the above driving action sequence includes the driving actions corresponding to different path nodes in the initial parking path. Then, dividing the initial parking path into multiple sub-paths according to the driving action sequence is to divide the entire initial parking path according to the driving actions corresponding to different path nodes in the initial parking path, and divide the entire initial parking path into multiple sub-paths. In addition, the above multiple sub-paths may include straight-line paths, arc paths, curved paths, etc., and the embodiments of the present application do not limit this. Specifically, how to divide the sub-paths according to the driving actions of different path nodes will be described in detail in the relevant embodiments below and will not be elaborated here.

[0060] Step 603: Perform clothoid optimization processing on the arc paths in the multiple sub-paths to generate optimized sub-paths.

[0061] Based on the relevant description of the above step 602, it can be known that the entire initial parking path is divided into multiple sub-paths, where the sub-paths can be straight-line paths or arc paths. Since there is no situation of steering the steering wheel or tires when the vehicle is driving in a straight-line path, the curvature in the case of a straight-line path is a fixed value, and there is no situation of sudden curvature change. For example, refer to Figure 4 , for Figure 3 A schematic diagram of the path curvature change in another parking scenario shown, the curvature from point A to point B in the figure is 0, and there is no sudden curvature change in the straight-line path AB. While the curvature of the arc path will change suddenly. For example, refer to Figure 2 , for Figure 1 A schematic diagram of the path curvature change in a parking scenario shown, the curvature at point B in the figure suddenly changes from 0 to A curvature mutation occurs at point B, and there is a curvature mutation in the arc path BC. Therefore, in the embodiment of the present application, the arc paths in the multiple sub-paths obtained after division are optimized by a clothoid curve to generate optimized sub-paths. Among them, the above-mentioned optimized sub-path refers to a path whose curvature does not mutate after being optimized by a clothoid curve.

[0062] In this embodiment, the following processing is performed for each sub-path: According to the curvature of each path node in the sub-path, the arc path in the sub-path is determined. Specifically, it can be determined whether the current sub-path is an arc path according to whether the curvature of each path node has mutated.

[0063] For example, as Figure 1 and Figure 2 shown, in the initial parking path A - B - C - D, the curvatures at points B and C both mutate, and the curvatures at points C and D also both mutate. Therefore, it can be determined that the arc paths in the initial parking path A - B - C - D include the arc path BC and the arc path CD. As Figure 3 and Figure 4 shown, in the initial parking path A - B - C - D, the curvatures at points B and C both mutate. Therefore, it can be determined that the arc path in the initial parking path A - B - C - D includes the arc path BC. The above are just simple examples. Specifically, how to determine the arc paths in the multiple sub-paths of the initial parking path according to the curvature of each path node will be explained in detail in the relevant embodiments below and will not be elaborated here first.

[0064] It can be seen from this that for the case where the initial parking path is a multi-step parking path, regarding the initial parking path as a whole to determine the arc path in the initial parking path does not mean that there is only one arc path in the initial parking path. In fact, there are also cases where there are two or more arc paths.

[0065] In the technical solution of the embodiment of the present application, after determining that a certain sub-path is an arc path, the arc paths in the multiple sub-paths can be optimized by a clothoid curve to generate optimized sub-paths. Specifically, the places where the curvature mutates in the arc paths in the multiple sub-paths are optimized into the form of a clothoid curve to generate the optimized sub-paths.

[0066] Specifically, the arc paths in the multiple sub-paths are processed into a combination of a first clothoid curve - target arc - second clothoid curve to generate optimized sub-paths. Among them, the first endpoint of the first clothoid curve is the first endpoint of the arc path, and the instantaneous radius of the first clothoid curve at the second endpoint is equal to the radius of the target arc; the first clothoid curve and the second clothoid curve are symmetric about the connection line between the midpoint of the target arc and the center of the circle where the target arc is located.

[0067] The above first endpoint can be the starting point, and the corresponding second endpoint is the ending point. Or the above first endpoint can be the ending point, and the corresponding second endpoint is the starting point. For the convenience of calculation, it can be considered that the first endpoint is the starting point and the second endpoint is the ending point.

[0068] Specifically, for each arc path, the first endpoint of the arc path can be used as the first endpoint of the first clothoid. By means of a calculation method, the second endpoint of the second clothoid is continuously explored until the second endpoint of the second clothoid is determined. Specifically, the second endpoint of the second clothoid can be continuously explored through the comparison relationship between the instantaneous radius of the first clothoid at the second endpoint and the radius of the target arc until the instantaneous radius of the first clothoid at the second endpoint is equal to the radius of the target arc. The second endpoint of the first clothoid in this case is used as the second endpoint of the first clothoid that really needs to be found. After determining the second endpoint of the first clothoid, the first clothoid is determined. By using a calculation method, the midpoint of the target arc can be calculated. In the target arc, the arc from the second endpoint of the first clothoid to this midpoint can be used as the first arc. The combined curve formed by the first clothoid and the first arc is symmetrically operated based on the connection line between the midpoint of the target arc and the center of the circle where the target arc is located, to obtain a second arc symmetric to the first arc and a second clothoid symmetric to the first clothoid. Thus, the first clothoid, the first arc, the second arc, and the second clothoid are combined to obtain a combination of the first clothoid - target arc - second clothoid. Among them, the first arc and the second arc are combined to form the target arc.

[0069] Step 604: Determine the final parking path according to the straight-line paths and optimized sub-paths in the multiple sub-paths.

[0070] In the technical solution of the embodiment of the present application, a complete initial parking path can be divided into multiple sub-paths, and the multiple sub-paths can be straight-line paths or arc paths. Based on the description of the above step 603, it can be known that the arc paths in the multiple sub-paths in the embodiment of the present application are processed by clothoid optimization, and optimized sub-paths are generated. Then, the generated optimized sub-paths are used to replace the arc sub-paths in the initial path, to obtain the finally processed parking path without curvature mutation, that is, the final parking path is determined according to the straight-line paths and optimized sub-paths in the multiple sub-paths.

[0071] Specifically, the final parking path is determined according to the optimized sub-path, that is, the combination of the first clothoid - target arc - second clothoid and the straight-line path part in the initial parking path. Each arc path corresponds to a combination of the first clothoid - target arc - second clothoid. In the initial parking path, each arc path is replaced with the corresponding combination of the first clothoid - target arc - second clothoid to obtain the final parking path. Exemplarily, as Figure 7 shown Figure 7 corresponds to Figure 1 The final multi-step parking path obtained after processing the multi-step parking path in Figure 1 can be the solid line part formed by ABCD, where the dotted line part is the Figure 1 arc path part in the initial multi-step parking path in Figure 7 After processing the arc path part in the initial multi-step parking path in Figure 8 shown, the curvatures of points A, B, C, and D in the final multi-step parking path in are continuous. As shown in the schematic diagram of the curvature change of the processed multi-step parking path in shown, the curvature of the processed multi-step parking path gradually increases from 0 at point B to and then gradually decreases from to 0 at point C. Then the curvature gradually decreases from 0 at point C to Figure 8 and then gradually increases from Figure 7 to 0 at point D, achieving curvature continuity at the geometric connection points. Figure 8 The solid line part in corresponds to the curvature change of the solid line part of the processed multi-step parking path in shown, and the dotted line part in is the curvature of the arc segment from point B to point C and the curvature of the arc segment from point C to point D of the initial multi-step parking path before processing. It can be seen that the curvature of the arc segment from point B to point C and the curvature of the arc segment from point C to point D of the multi-step parking path before processing remain unchanged, and the curvature at point C undergoes a sudden change. However, for the arc segment from point B to point C of the processed multi-step parking path, the curvature gradually increases from 0 to and then gradually decreases to 0, and the curvature from point C to point D gradually decreases from 0 to

[0072] and then gradually increases to 0. The curvature is continuous and no sudden change occurs, and there is no problem of sudden change in curvature. Figure 9 Similarly, Figure 3 is a schematic diagram of the parking path with continuous curvature obtained after processing the initial parking path in Figure 9 shown, and the dotted line part in Figure 3The arc segment BC in the initial parking path, Figure 9 The solid line part in Figure 3 is the final parking path with continuous curvature obtained after processing the initial parking path in Figure 10 For Figure 9 Figure showing the curvature change corresponding to the final parking path of the solid line part in

[0073] For example, assume that a complete initial path A - B - C - D includes multiple sub - paths, namely: straight - line path AB, arc path BC, arc path CD, and straight - line path DE. After performing clothoid optimization on the arc path BC and the arc path CD, optimized sub - paths B1C1 and optimized sub - path C1D1 are generated. Then the final parking path is the complete parking path composed of the straight - line path AB, the optimized sub - path B1C1, the optimized sub - path C1D1, and the straight - line path DE, and there is no curvature mutation in the finally optimized parking path.

[0074] The technical solution provided by the embodiment of the present application is as follows: By obtaining the initial parking path of the vehicle, determining the driving action sequence of the initial parking path, splitting the initial parking path into multiple sub - paths according to the driving action sequence, performing clothoid optimization on the arc paths in the multiple sub - paths to generate optimized sub - paths, and determining the final parking path according to the straight - line paths and the optimized sub - paths in the multiple sub - paths. Specifically, the arc paths in the multiple sub - paths are processed into a combination of a first clothoid - target arc - second clothoid. Each arc path in the multiple sub - paths can be processed into a curve with continuous curvature. Specifically, by taking the first endpoint of the first clothoid as the first endpoint of the arc path, and making the instantaneous radius of the first clothoid at the second endpoint equal to the radius of the target arc, the first clothoid and the target arc can be made to have continuous curvature at the second endpoint of the first clothoid. Through the second clothoid symmetric to the first clothoid, the connection point between the target arc and the second clothoid can be made to have continuous curvature, ensuring that the combination of the first clothoid - target arc - second clothoid formed by each arc has continuous curvature. Thus, the parking path can be transformed into a path with continuous curvature, improving the control accuracy, effectively avoiding the in - place steering of the tires, and reducing the wear of the tires during the parking process.

[0075] In the prior art, in the post - processing solution for the parking path, most methods use numerical optimization to obtain a parking path with continuous curvature. However, since this method involves solving non - linear optimization problems, the solution efficiency is low, it is difficult to implement in engineering, and usually, when planning the initial parking path at the front - end, it is necessary to model non - linear problems. Therefore, the path planning of the initial parking path at the front - end and the back - end processing cannot be well decoupled. The technical solution provided in this application is a post - processing of the initial parking path, which does not affect the planning of the initial parking path at the front - end, can be decoupled from the planning algorithm of the initial parking path at the front - end, is compatible with any front - end planning algorithm composed of arcs and straight lines, has strong compatibility, and does not change the positions of the endpoints of any arc path in the initial parking path, can maintain the gear - shifting points of the initial parking path planned at the front - end, and is consistent with the front - end decision - making, with high reliability.

[0076] Figure 11 It is a flowchart of a method for determining a driving action sequence of an initial parking path and determining whether the current initial parking path is a multi - step parking path provided by an embodiment of the present application. Figure 11 The process shown in Figure 6 Based on the process shown in, this process includes the following steps:

[0077] Step 1101: Obtain the path parameters of each path node in the initial parking path. The path parameters include coordinate information and heading angle.

[0078] In one embodiment, the coordinate information of the path node refers to the abscissa and ordinate of the path node in the absolute coordinate system, which means that each path node in the initial parking path has a clear position description information relative to a certain fixed reference point. In addition to the coordinate information, the heading angle is also one of the key information, and the heading angle describes the driving direction of the vehicle at each path node.

[0079] When planning the initial parking path through a path planning algorithm, such as a geometric algorithm, the coordinate information and heading angle of each path node will be determined to ensure that the vehicle can park smoothly along this path.

[0080] Step 1102: For each path node in the initial parking path, based on the path parameters of the path node and the path parameters of its next path node, determine the moving direction angle of the next path node relative to the path node.

[0081] Step 1103: For each path node in the initial parking path, determine the driving gear corresponding to the path node based on the moving direction angle corresponding to the path node.

[0082] As an alternative implementation, for each path node in the initial parking path, determining the driving gear corresponding to the path node based on the moving direction angle corresponding to the path node includes:

[0083] Determining the driving gear corresponding to the path node based on the following formula:

[0084]

[0085] where S i is the driving gear corresponding to the i-th path node, 1 represents reverse gear, and 0 represents forward gear;

[0086] θ r is the moving direction angle, x i and y i are the abscissa and ordinate of the i-th path node respectively, and x i+1 and y i+1 are the abscissa and ordinate of the (i + 1)-th path node respectively.

[0087] Step 1104: Sort the driving gears corresponding to the multiple path nodes in the order of the path nodes to obtain the driving action sequence of the initial parking path.

[0088] As an alternative implementation, sorting the driving gears corresponding to the multiple path nodes in the order of the path nodes to obtain the driving action sequence. In the case where the driving gears of all path nodes in the entire driving action sequence are not the same, it is determined that the initial parking path is a multi-step parking path. Among them, the driving gears include forward gear and reverse gear.

[0089] As another alternative implementation, it is also possible to determine whether the driving gears of every two adjacent path nodes are the same through formula calculation. In the case where the driving gears of every two adjacent path nodes are not the same, it means that the driving gears of all path nodes in the entire parking path are not the same, that is, the vehicle needs to shift gears throughout the process when parking using this parking path.

[0090] Specifically, in the case where the following formula holds, it is determined that the driving gears of all path nodes in the initial parking path are not the same:

[0091]

[0092] where N is the number of path nodes, and S i+1 is the driving gear corresponding to the (i + 1)-th path node.

[0093] The calculation logic of the above formula (2) is: by |S i - S i+1Determine the consistency of the gear actions of every two adjacent path nodes according to the calculation method, where, |S i -S i+1 | = 1 means that the gear actions of two adjacent path nodes are different. Then, determine the consistency of the gear actions of all path nodes throughout the journey by calculating the cumulative sum of the calculation results of the consistency of the gear actions of every two adjacent path nodes. Among them, if It means that the gear actions of all path nodes throughout the parking path are inconsistent, that is, the gear actions throughout the parking path are inconsistent and there is a gear shifting behavior.

[0094] For example, referring to Figure 1 The initial parking path in the shown scenario, this parking path includes path node A, path node B, path node C, and path node D. Among them, the driving gear of path node A is the forward gear, that is, S A = 0; the driving gear of path node B is the forward gear, that is, S B = 0; the driving gear of path node C is the reverse gear, that is, S C = 1; the driving gear of path node D is the reverse gear, that is, S C = 1; the driving gears of these path nodes can all be determined based on their respective moving direction angles according to the above formula (1), which will not be elaborated here. Therefore, the driving action sequence of the parking path ABCD segment composed of the above path nodes A, B, C, and D is {S A = 0, S B = 0, S C = 1}, calculate the consistency of the gear actions between any two adjacent nodes based on the above formula (2): |S A -S B | = 0, |S B -S C | = 1, |S A -S B | + |S B -S C | = 1, obtain the result by calculating the cumulative sum of the calculation results of the consistency of the gear actions of two adjacent path nodes, which is 1. This means that the gear actions of all path nodes throughout the journey are inconsistent and there is a gear shifting behavior. It can be seen that Figure 1 The driving gear throughout the corresponding initial parking path is not consistent and there is a gear shifting behavior. Therefore, it can be determined that this initial parking path is a multi-step parking path.

[0095] Referring to Figure 3 The initial parking path in the shown scenario, this parking path includes path node A, path node B, path node C, and path node D. Among them, the driving gear of path node A is the forward gear 0, that is, S A= 0; The driving gear of path node B is reverse gear 1, i.e., S B = 1; The driving gear of path node C is reverse gear 1, i.e., S C = 1; The driving gears of these path nodes can all be determined based on the above formula (1) according to their respective moving direction angles, which will not be elaborated here. Therefore, the driving action sequence of the parking path section ABCD composed of the above path node A, path node B, path node C, and path node D is {S A = 0, S B = 1, S C = 1}, and based on the above formula (2), calculate the consistency of the gear actions between any two adjacent nodes: |S A - S B | = 1, |S B - S C | = 0, |S A - S B | + |S B - S C | = 1. By calculating the cumulative sum of the calculation results of the gear action consistency between adjacent path nodes, the result is 1, which means that the gear actions of all path nodes throughout the process are inconsistent and there is a gear shifting behavior. It can be seen that Figure 3 In the corresponding initial parking path, the driving gears throughout the whole process are not consistent and there is a gear shifting behavior. Therefore, it can be determined that this initial parking path is a multi-step parking path.

[0096] By determining the driving gear of the vehicle under this path node based on the moving direction angle of the vehicle in the initial parking path, and determining the driving action sequence of the initial parking path according to the driving gear of the vehicle under each path node, it is convenient for the vehicle to quickly identify the current parking path, and further post-process the current parking path to obtain a final parking path with continuous curvature, improving the control of the vehicle steering wheel during parking, avoiding tire wear, and at the same time avoiding the vehicle deviating from the parking path. In addition, further determine whether the initial parking path is a multi-step parking path according to the driving action sequence, and the calculation method is simple. When the current parking path is a multi-step parking path, it is determined that the driving gears of the whole process of the current initial path remain consistent and will not change, which is convenient for controlling the vehicle, avoiding the situation that the vehicle cannot park based on the current initial parking path due to gear problems, and at the same time avoiding vehicle out of control and improving the stability of intelligent parking.

[0097] Figure 12 is a flowchart of a method for determining the arc path in multiple sub-paths in the initial parking path according to the curvature of each path node in the initial parking path, that is, determining the arc path section in the initial parking path according to the curvature of different path nodes, Figure 12 The process shown in Figure 6Based on the process shown, the process includes the following steps:

[0098] Step 1201: For non - the first path node in the initial parking path, determine whether the curvature of the path node and the curvature of its previous path node satisfy a preset equality condition.

[0099] Step 1202: In the case where the curvature of the path node and the curvature of its previous path node do not satisfy the equality condition, determine the path node as a curvature mutation point.

[0100] In the technical solution of the embodiment of the present application, the preset equality condition does not mean that the curvatures are exactly the same, but allows a certain difference in the curvatures of two adjacent path nodes, as long as this difference is within an acceptable range. That is to say, the preset equality condition is actually a tolerance range used to determine whether the curvatures of two adjacent nodes are "close enough" to maintain the smoothness of the path.

[0101] Based on this, as an optional implementation manner, it can be determined whether the curvatures of adjacent path nodes satisfy the preset equality condition by judging whether the absolute value of the difference in curvatures of adjacent path nodes exceeds a set threshold. Among them, if the absolute value of the difference in curvatures of adjacent path nodes exceeds the set threshold, it means that the preset equality condition is not satisfied; if the absolute value of the difference in curvatures of adjacent path nodes does not exceed the set threshold, it means that the preset equality condition is satisfied.

[0102] Further, based on the above description, in the case where the curvature of the path node and the curvature of its previous path node do not satisfy the equality condition, determine the path node as a curvature mutation point.

[0103] For example, Figure 1 in the shown scenario, referring to Figure 2 the curvature change diagram of the initial parking path shown, it can be known that the curvature of path node C in path segment BC is while the curvature of path node C in path segment CD is Thus, it can be seen that the absolute value of the difference in curvatures of path node C in path segment BC and path segment CD is Assume the preset threshold is Then it shows that the absolute value of the difference in curvatures of path node C in path segment BC and path segment CD exceeds the set threshold, which means that the difference in curvatures of path node C in path segment BC and path segment CD is very large and not "close enough", so path node C is determined as a curvature mutation point.

[0104] Figure 3 in the shown scenario, referring to Figure 4From the graph showing the curvature change of the initial parking path, it can be seen that the curvature of path node B in path segment AB is 0, while the curvature of path node B in path segment BC is The absolute value of the difference in curvature between path node B in path segment AB and path segment BC is Assume the preset threshold is If the absolute value of the difference in curvature between path node B in path segment AB and path segment BC exceeds the set threshold, it indicates that the difference in curvature between path node B in path segment AB and path segment BC is very large and not "sufficiently close", then path node B is determined as a curvature mutation point.

[0105] Step 1203: Determine the non - straight path segment between the curvature mutation point and its adjacent path nodes as the arc path in the initial parking path.

[0106] The initial parking path includes but is not limited to curves, straight lines, etc. When the curvature mutation point in the initial parking path is determined, the path segment composed of the path nodes adjacent to the curvature mutation point is not necessarily a curve and may also be a straight line. Therefore, the non - straight path segment between the curvature mutation point and its adjacent path nodes is determined as the arc path in the initial parking path.

[0107] Refer to Figure 1 the scenario shown. Based on the above steps, it is determined that Figure 1 path node C shown in is the curvature mutation point. There are two path nodes adjacent to path node C: path node B and path node D. Moreover, the path segment BC composed of path node B and path node C is a curved path segment, and the path segment CD composed of path node C and path node D is also a curved path segment. Therefore, the path segments BC and CD are determined as the arc paths in the initial parking path.

[0108] Refer to Figure 3 the scenario shown below. Based on the above steps, it is determined that Figure 3 path node B shown in is the curvature mutation point. There are two path nodes adjacent to path node B: path node A and path node C. However, the path segment AB composed of path node B and path node A is a straight path segment. Therefore, the path segment BC composed of path node B and path node C is determined as the arc path in the initial parking path.

[0109] Through Figure 12 the process shown, the curvature mutation point is determined according to the curvature of the path nodes, and the arc path that needs to be processed is found based on the curvature mutation point. This method can help the vehicle quickly find the arc path that needs to be processed and improve the vehicle's processing efficiency for the arc path.

[0110] Figure 13It is a flowchart of a method provided by an embodiment of the present application for dividing an initial parking path into multiple sub-paths according to a driving action sequence. Figure 13 The process shown Figure 6 On the basis of the process shown, mainly includes the following steps:

[0111] Step 1301: Sequentially traverse the non-first path nodes in the initial parking path.

[0112] Step 1302: When it is determined that the driving action changes for the currently traversed path node compared to its previous path node, determine the currently traversed path node as the target path node.

[0113] Step 1303: Divide the initial parking path into multiple sub-paths with the target path node as the division point.

[0114] Regarding the above steps 1301 - 1303, the following is a unified description:

[0115] In the technical solution provided by the embodiment of the present application, sequentially traverse the non-first path nodes in the initial parking path. When it is determined that the driving action changes for the currently traversed path node compared to its previous path node, determine the currently traversed path node as the target path node.

[0116] Specifically, the driving action of the current path node compared to the previous path node can be determined in the following two ways. The first way: Determine the steering wheel angles corresponding to the currently traversed path node and its previous path node respectively. When it is determined that the steering wheel angles corresponding to the currently traversed path node and its previous path node are inconsistent, determine that the driving action changes for the currently traversed path node compared to its previous path node. The second way: Determine the driving gears corresponding to the currently traversed path node and its previous path node respectively. When it is determined that the driving gears corresponding to the currently traversed path node and its previous path node are inconsistent, determine that the driving action changes for the currently traversed path node compared to its previous path node. In addition, the driving action of the current path node compared to the previous path node can also be judged by other ways, and the embodiment of the present application does not limit this.

[0117] In the embodiments of the present application, the target path node can be determined by comparing the steering wheel angles or driving gears of the current path node and one of its path nodes respectively according to the steering wheel angle or driving gear of the current path node and one of its path nodes. If the steering wheel angle of the current path node changes compared with the previous path node, it is determined that the current path node is the target path node. Similarly, if the driving gear of the current path node changes compared with the previous path node, it is determined that the current path node is the target path node. Finally, according to the determined target path nodes, the initial parking path is divided into multiple sub-paths.

[0118] Specifically, the steering wheel angle of the path node can be determined in the following way: Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and heading angle; Based on the path parameters of the path node and its previous path node respectively, determine the rate of change of the heading angle of the path node relative to its previous path node; According to the rate of change of the heading angle, the wheelbase of the vehicle, and the set parking speed, determine the steering wheel angle of the path node.

[0119] Among them, the above path parameters include coordinate information and heading angle. Determine the coordinate information and heading angle corresponding to the current path node and the previous path node respectively, and determine the rate of change of the heading angle of the current path node relative to its previous path node according to the coordinate information and heading angle. The rate of change of the heading angle can be calculated based on the following formula (3):

[0120]

[0121] In the above formula (3), ω is the rate of change of the heading angle, and are the heading angles of the current path node and its previous path node respectively, and Δt is the time difference.

[0122] Based on the rate of change of the heading angle calculated according to the above formula (3), the steering wheel angle of the current path node can be determined based on the following formula (4):

[0123]

[0124] In the above formula (4), ω is the rate of change of the heading angle, v is the set parking speed, and l is the wheelbase of the vehicle. Among them, the above set parking speed can be obtained based on the following formula (5):

[0125]

[0126] In the above formula (5), v is the set parking speed, x1 and x2 are the abscissas of the current path node and its previous path node respectively, y1 and y2 are the ordinates of the current path node and its previous path node respectively, and Δt is the time difference.

[0127] Specifically, the driving gear corresponding to the path node can be determined in the following manner: Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and heading angle; Based on the path parameters of the path node and its previous path node respectively, determine the moving direction angle of the path node relative to its previous path node; Based on the moving direction angle, determine the driving gear corresponding to the path node.

[0128] For example, the current driving gear can be determined as a forward gear or a reverse gear according to the magnitude of the moving direction angle. When the moving direction angle is less than a certain threshold, it indicates that the driving gear of the current path node is a forward gear. When the moving direction angle is greater than a certain threshold, it indicates that the driving gear of the current path node is a reverse gear. Reference can be made to the relevant description of formula (1) in the above related embodiments. In addition, the current driving gear of the path node can also be determined by other means using the moving direction angle, and the embodiments of the present application do not limit this.

[0129] In the embodiments of the present application, by comparing the driving actions of the current path node and the previous path node, it is determined whether the current path node is a target node. According to the target path node, the initial path is divided into multiple sub-paths, which is simple to operate. By comparing the driving actions of adjacent nodes to divide the initial path, the accuracy of the division can be ensured, the division efficiency can be improved, and it is helpful for subsequent optimization of the initial path.

[0130] Figure 14 It is a flowchart of a method for performing clothoid optimization processing on circular arc paths in multiple sub-paths to generate optimized sub-paths, that is, a flowchart of a method for processing circular arc paths in each sub-path into optimized sub-paths including a first clothoid - target circular arc - second clothoid. Figure 14 The process shown in Figure 6 On the basis of the process shown, this process includes the following steps:

[0131] Step 1401: For the circular arc paths in multiple sub-paths, determine the center of the circle where the circular arc path is located and determine the target line passing through the center of the circle where the circular arc path is located and the target midpoint, where the target midpoint is the midpoint of the line segment formed by the two endpoints of the circular arc path.

[0132] As an optional implementation manner, determining the center of the circle where the circular arc path is located includes: Determining the center of the circle where the circular arc path is located based on the following formula:

[0133]

[0134] where x c and y cThey are respectively the abscissa and ordinate of the center of the circle where the arc path is located; x1, y1, and θ1 are respectively the abscissa, ordinate, and heading angle of the first endpoint of the arc path; x2, y2, and θ2 are respectively the ordinates of the second endpoint of the arc path. Among them, for reference Figure 12 For illustration, the center of the circle where the arc path is located is determined according to the two endpoints of the arc path. As Figure 12 shown, the two endpoints on the arc path are p1(x1, y1, θ1) and p2(x2, y2, θ2) respectively; For the arc path to be processed, calculate the center c(x of the circle where the arc path is located according to the above formula (1) c , y c ). It should be noted that when calculating the coordinates of the center of the circle where the arc path is located, for the convenience of calculation, the coordinate system can be converted first, converting the absolute coordinate system to a coordinate system with the first endpoint p1(x1, y1, θ1) of the arc path as the vertex, and then performing the calculation. As Figure 12 shown, the target midpoint is the midpoint of the line segment formed by the two endpoints of the arc path , that is, the midpoint of the line segment p1p2, which is point m. The target line passing through the center c point of the circle where the arc path is located and the target midpoint m point is the line cm.

[0135] Step 1402: Use the first endpoint of the arc path as the first endpoint of the first clothoid.

[0136] For illustration, as Figure 15 shown, the first endpoint (point p1) of the arc path Figure 15 is used as the first endpoint of the first clothoid.

[0137] Step 1403: Preset the arc length of the first clothoid as the current preset arc length, and determine the initial second endpoint of the first clothoid based on the current preset arc length.

[0138] As an optional implementation manner, determining the initial second endpoint of the first clothoid based on the current preset arc length includes: determining the initial second endpoint of the first clothoid based on the following formula:

[0139]

[0140] where x, y, and θ are respectively the abscissa, ordinate, and heading angle of the initial second endpoint of the first clothoid in the coordinate system with the first endpoint of the arc path as the vertex;

[0141] where A is the parameter of the first clothoid, where

[0142] Among them, V max is the maximum vehicle speed during parking, D max is the maximum steering wheel angle, O max is the maximum angular speed of rotation, s′ ∈ [0, L min , is the currently preset arc length, R min is the minimum turning radius.

[0143] Refer to Figure 15 for illustration. As Figure 15 shown, the other endpoint of the first clothoid curve with the currently preset arc length s′ is point c1, which serves as the initial second endpoint of the first clothoid curve. Among them, as Figure 15 shown, the first clothoid curve is the solid curve from point p1 to point c1. The coordinates and the course angle θ of the initial second endpoint c1 of the first clothoid curve can be calculated through the above formula (7). A characterizes the curvature property of the first clothoid curve and can be calculated through the above formula (8).

[0144] Step 1404: Determine the intersection point of the normal line passing through the initial second endpoint and the target line, and use it as the target intersection point, and determine the length between the target intersection point and the initial second endpoint as the radius of the target arc.

[0145] Refer to Figure 15 for illustration. As Figure 15 shown, the intersection point of the normal line passing through the initial second endpoint (point c1) and the target line (line cm) is point o, that is, the target intersection point is point o. The length between the target intersection point and the initial second endpoint is the length from point o to point c1, that is, the length of line segment oc1. The length of oc1 is actually the radius R of the target arc (the arc from c1 to c2, and the coordinates of point c2 are unknown at this time) cc .

[0146] As an alternative implementation, determining the intersection point of the normal line passing through the initial second endpoint and the target line includes: determining the intersection point of the normal line of the initial second endpoint and the target line based on the following formula:

[0147]

[0148] Among them, x o , y o are respectively the abscissa and ordinate of the target intersection point in the coordinate system with the first endpoint of the arc path as the vertex;

[0149] Among them,

[0150] Among them, k s is the slope of the target line; x m , y mare the abscissa and ordinate of the target midpoint in the coordinate system with the first endpoint of the arc path as the vertex; x c and y c are the abscissa and ordinate of the center of the circle where the arc path is located in the coordinate system with the first endpoint of the arc path as the vertex, respectively.

[0151] As an optional implementation manner, determining the length between the target intersection point and the initial second endpoint includes: determining the length between the target intersection point and the initial second endpoint based on the following formula:

[0152]

[0153] where R cc is the length between the target intersection point and the initial second endpoint, serving as the radius of the target arc; x o and y o are the abscissa and ordinate of the target intersection point in the coordinate system with the first endpoint of the arc path as the vertex, respectively, and x and y are the abscissa and ordinate of the initial second endpoint in the coordinate system with the first endpoint of the arc path as the vertex, respectively.

[0154] where the reference Figure 15 , k s is the slope of the straight line cm, which can be calculated through the above formula (10), that is, calculated through the coordinates of point c and point m; the coordinates of the intersection point (point o) of the normal line passing through the initial second endpoint (point c1) and the target straight line (cm) can be calculated through the above formula (9), and the length of oc1, R cc can be calculated through the above formula (11), which is the radius of the target arc c1c2. It should be noted that at this time, the first endpoint c1 of the target arc is determined, and the second endpoint c2 of the target arc has not been determined yet. Here, c2 is introduced for the convenience of expression and understanding, and the coordinates of c2 are not introduced in the calculation of the above formula.

[0155] Step 1405: Determine whether the radius of the target arc is equal to the instantaneous radius of the first clothoid at the initial second endpoint.

[0156] In the technical solution of the embodiment of the present application, in step 1405, by determining whether the difference between the radius of the target arc and the instantaneous radius of the first clothoid at the initial second endpoint is less than a preset error value. If so, it is determined that the two meet the equal condition; if not, it is determined that the two do not meet the equal condition. This preset threshold can be obtained according to the test data during the actual operation of the vehicle.

[0157] In the technical solution of the embodiment of the present application, if it is determined that the radius of the target arc does not meet the equal condition with the instantaneous radius at the initial second end point of the first clothoid, execute 1406; if it meets the equal condition, execute 1407.

[0158] In an alternative embodiment, it is determined whether the radius of the target arc meets the equal condition with the instantaneous radius based on the following formula:

[0159]

[0160] wherein, R cc is the radius of the target arc, ε is a preset error value, and r c is the instantaneous radius.

[0161] Refer to Figure 15 for illustration. As shown in Figure 15 , when the radius of the target arc c1c2 (the length of the line segment oc1, R cc ) meets the equal condition with the instantaneous radius r c of the first clothoid p1c1 at the point c1, it indicates that the curvature of the first clothoid p1c1 and the target arc c1c2 is continuous at the point c1. Therefore, it is necessary to determine whether the radius of the target arc c1c2 meets the equal condition with the instantaneous radius r c of the first clothoid p1c1 at the point c1, so as to understand whether the curvature of the first clothoid p1c1 and the target arc c1c2 is continuous at the point c1.

[0162] Step 1406: Change the current preset arc length, use the changed arc length as the current preset arc length, and return to step 1403.

[0163] Step 1407: Use the last initial second end point as the second end point of the first clothoid.

[0164] As an alternative embodiment, the bisection method can be used to change the current preset arc length, return to step 1403, and repeat steps 1403 - 1405. Use the last initial second end point as the second end point of the first clothoid. The specific method of using the bisection method to change the current preset arc length is to divide the current preset arc length into two parts. According to the comparison result of the target length and the instantaneous radius, determine whether to select the changed arc length in the first half or the second half of the current preset arc length. After determining the changed arc length, return to step 1403 until the radius of the target arc meets the equal condition with the instantaneous radius. Refer to Figure 15 , as shown in Figure 15 , when the length of the line segment oc1 meets the equal condition with the instantaneous radius r cUnder the condition of meeting the equality, the obtained c1 point at this time is used as the second endpoint of the final first clothoid curve.

[0165] Step 1408: Determine the midpoint of the target arc; wherein, the center of the circle where the target arc is located is the target intersection point, and the first endpoint of the target arc is the second endpoint of the first clothoid curve.

[0166] As an alternative implementation, determining the midpoint of the target arc includes: determining the midpoint of the target arc based on the following formula:

[0167]

[0168] where α is the semi-central angle of the target arc; x h , y h and θ h are respectively the abscissa, ordinate and course angle of the midpoint of the target arc in the coordinate system with the first endpoint of the arc path as the vertex; is the vector from the target intersection point to the target midpoint, is the vector from the target intersection point to the second endpoint of the first clothoid curve.

[0169] Refer to Figure 15 for illustration. By continuously determining the second endpoint of the first clothoid curve p1c1, the finally obtained c1 point is used as the second endpoint of the first clothoid curve. The first endpoint of the target arc c1c2 is the second endpoint of the first clothoid curve p1c1, that is, the c1 point. The center of the circle where the target arc c1c2 is located is the o point, the radius of the circle is the line segment oc1, and the h point is the midpoint of the target arc.

[0170] Calculate the midpoint of the target arc c1c2 through the above formula (13), is is α is the semi-central angle of the target arc c1c2.

[0171] Step 1409: Symmetrically operate the target curve based on the connection line between the midpoint of the target arc and the target intersection point to obtain the combination of the first clothoid curve - target arc - second clothoid curve; wherein, the target curve is a curve obtained by combining the first clothoid curve and the first arc based on the first endpoint of the first clothoid curve and the second endpoint of the first clothoid curve; the first arc is the arc between the second endpoint of the first clothoid curve and the midpoint of the target arc in the target arc.

[0172] Refer to Figure 15 for illustration. As Figure 15As shown, the target curve is the curve p1c1h formed by the first clothoid p1c1 and the first circular arc c1h. By performing a symmetry operation on the curve p1c1h based on the line segment oh, a combination of the first clothoid - target circular arc - second clothoid can be obtained, thereby converting the circular arc path into the curve p1c1hc2p2.

[0173] Figure 16 is a flowchart of a method provided by an embodiment of the present application for performing a symmetry operation on a target curve based on the line connecting the midpoint of a target circular arc to a target intersection point to obtain an optimized sub - path including a first clothoid - target circular arc - second clothoid, Figure 16 The process shown in Figure 14 Based on the process shown, the method includes the following steps:

[0174] Step 1601: Determine the symmetric point of the second endpoint of the first clothoid symmetric with respect to the target symmetry line; wherein, the target symmetry line is the line connecting the midpoint of the target circular arc to the target intersection point.

[0175] As an optional implementation manner, determining the symmetric point of the second endpoint of the first clothoid symmetric with respect to the target symmetry line includes:

[0176] Determine the symmetric point based on the following formula:

[0177]

[0178] wherein, and are respectively the abscissa and ordinate of the symmetric point in the coordinate system with the first endpoint of the circular arc path as the vertex. Among them, in the above formula (14), d x 、d y and l are intermediate quantities in the calculation process. Referring to Figure 10 , the symmetric point of the second endpoint c1 of the first clothoid p1c1 symmetric with respect to the target symmetry line oh is c2. The coordinates of the symmetric point c2 can be calculated through the above formula (14). In the present application, calculating the symmetric point c2 first is to find the segmentation point of the target circular arc and the second clothoid, so as to make the symmetry operation more efficient.

[0179] Step 1602: Determine the second clothoid of the first clothoid symmetric with respect to the target symmetry line between the symmetric point and the second endpoint of the circular arc path.

[0180] Step 1603: Determine the second circular arc of the first circular arc symmetric with respect to the target symmetry line between the midpoint of the target circular arc and the symmetric point.

[0181] Step 1604: The first clothoid, the first circular arc, the second circular arc, and the second clothoid form a combination of the first clothoid - target circular arc - second clothoid.

[0182] A unified description is given for Steps 1602 - 1604. In Step 1602, discrete points are selected on the first clothoid, these discrete points are symmetric with respect to the target symmetry line to find the corresponding symmetric points, and the symmetric point of the second endpoint of the first clothoid, the symmetric points corresponding to these discrete points, and the second endpoint of the circular arc path are connected in sequence to obtain the second clothoid. Refer to Figure 15 , discrete points are selected on the first clothoid p1c1, these discrete points are symmetric with respect to the line segment oh to obtain a series of corresponding symmetric points, and the points c2, this series of symmetric points corresponding to these discrete points, and the point p2 are connected in sequence to obtain the second clothoid c2p2.

[0183] In Step 1603, discrete points are selected on the first circular arc, these discrete points are symmetric with respect to the target symmetric point to find the corresponding symmetric points, and the midpoint of the target circular arc, the symmetric points corresponding to these discrete points, and the symmetric point of the second endpoint of the first clothoid are connected in sequence to obtain the second circular arc. Refer to Figure 15 , discrete points are selected on the first circular arc c1h, these discrete points are symmetric with respect to the line segment oh to obtain a series of corresponding symmetric points; the points h, this series of symmetric points corresponding to these discrete points, and the point c2 are connected in sequence to obtain the second circular arc hc2.

[0184] In Step 1604, refer to Figure 15 , the first clothoid p1c1, the first circular arc c1h, the second circular arc hc2, and the second clothoid c2p2 are used to obtain the curve p1c1hc2p2, that is, the combination of the first clothoid - target circular arc - second clothoid.

[0185] Among them, the process of processing the circular arc path in the initial parking path provided in this embodiment can be referred to Figure 17 , and the electronic device obtains the final parking path by executing the Figure 17 shown process.

[0186] The technical solution provided in the embodiment of the present application processes each circular arc path in the initial parking path through a geometric algorithm to obtain a curve with continuous curvature. By using the geometric algorithm, the calculation efficiency is high, the practicability is strong, and it is suitable for engineering implementation.

[0187] Figure 18 is a structural block diagram of a parking path processing device provided in the embodiment of the present application, as Figure 18 shown, including:

[0188] The driving action determination module 110 is configured to obtain the initial parking path of the vehicle and determine the driving action sequence of the initial parking path, where the driving action sequence includes the driving actions corresponding to each path node in the initial parking path;

[0189] The sub-path division module 120 is configured to divide the initial parking path into multiple sub-paths according to the driving action sequence;

[0190] The sub-path processing module 130 is configured to perform clothoid optimization processing on the arc paths in the multiple sub-paths to generate optimized sub-paths;

[0191] The final parking path determination module 140 is configured to determine the final parking path according to the straight-line paths and the optimized sub-paths in the multiple sub-paths.

[0192] In a possible implementation manner, the driving action determination module 110 includes:

[0193] The path traversal unit is configured to sequentially traverse the non-first path nodes in the initial parking path;

[0194] The target path node determination unit is configured to determine the currently traversed path node as the target path node when it is determined that the driving action changes for the currently traversed path node compared to its previous path node;

[0195] The sub-path division unit is configured to divide the initial parking path into multiple sub-paths with the target path node as the division point.

[0196] In a possible implementation manner, the target path node determination unit includes:

[0197] The steering wheel angle determination sub-unit is configured to determine the steering wheel angles corresponding to the currently traversed path node and its previous path node respectively;

[0198] The steering wheel angle judgment sub-unit is configured to determine that the driving action changes for the currently traversed path node compared to its previous path node when it is determined that the steering wheel angles corresponding to the currently traversed path node and its previous path node are inconsistent.

[0199] In a possible implementation manner, the target path node determination unit includes:

[0200] The driving gear determination sub-unit is configured to determine the driving gears corresponding to the currently traversed path node and its previous path node respectively;

[0201] A driving gear determination sub - unit, configured to determine that a driving action changes for the currently traversed path node compared to its previous path node when it is determined that the driving gears corresponding to the currently traversed path node and its previous path node are inconsistent.

[0202] In a possible implementation, a steering wheel angle determination sub - unit is configured to:

[0203] Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and a heading angle;

[0204] Based on the path parameters of the path node and its previous path node respectively, determine the rate of change of the heading angle of the path node relative to its previous path node;

[0205] According to the rate of change of the heading angle, the wheelbase of the vehicle, and a set parking speed, determine the steering wheel angle of the path node.

[0206] In a possible implementation, a driving gear determination sub - unit is configured to:

[0207] Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and a heading angle;

[0208] Based on the path parameters of the path node and its previous path node respectively, determine the moving direction angle of the path node relative to its previous path node;

[0209] Based on the moving direction angle, determine the driving gear corresponding to the path node.

[0210] In a possible implementation, the sub - path processing module 130 includes:

[0211] A first determination unit, configured to, for the circular arc path among the multiple sub - paths, determine the center of the circle where the circular arc path is located and determine a target straight line passing through the center of the circle where the circular arc path is located and a target mid - point, where the target mid - point is the mid - point of the line segment formed by the two endpoints of the circular arc path;

[0212] A second determination unit, configured to use the first endpoint of the circular arc path as the first endpoint of a first clothoid curve, and preset the arc length of the first clothoid curve as the current preset arc length, and determine the initial second endpoint of the first clothoid curve based on the current preset arc length;

[0213] A third determination unit, configured to determine the intersection point of the normal line passing through the initial second endpoint and the target straight line as the target intersection point, and determine the length between the target intersection point and the initial second endpoint as the radius of the target circular arc;

[0214] A judgment unit, configured to judge whether the radius of the target arc is equal to the instantaneous radius of the first clothoid at the initial second endpoint;

[0215] A return unit, configured to, if not, change the current preset arc length, use the changed arc length as the current preset arc length, return the operation of setting the arc length of the first clothoid as the current preset arc length, and determine the initial second endpoint of the first clothoid based on the current preset arc length until the radius of the target arc is equal to the instantaneous radius, and use the last initial second endpoint as the second endpoint of the first clothoid;

[0216] A fourth determination unit, configured to determine the midpoint of the target arc; wherein, the center of the circle where the target arc is located is the target intersection point, and the first endpoint of the target arc is the second endpoint of the first clothoid;

[0217] A symmetry unit, configured to perform a symmetry operation on the target curve based on the connection line between the midpoint of the target arc and the target intersection point to obtain an optimized sub-path including a first clothoid - target arc - second clothoid; wherein, the target curve is a curve obtained by combining a first clothoid and a first arc based on the first endpoint of the first clothoid and the second endpoint of the first clothoid; the first arc is an arc between the second endpoint of the first clothoid and the midpoint of the target arc in the target arc.

[0218] In a possible implementation manner, the symmetry unit is specifically configured to:

[0219] Determine the symmetric point of the second endpoint of the first clothoid symmetric about the target symmetry line; wherein, the target symmetry line is the connection line between the midpoint of the target arc and the target intersection point;

[0220] Determine the second clothoid of the first clothoid symmetric about the target symmetry line between the symmetric point and the second endpoint of the arc path;

[0221] Determine the second arc of the first arc symmetric about the target symmetry line between the midpoint of the target arc and the symmetric point;

[0222] The first clothoid, the first arc, the second arc, and the second clothoid form an optimized sub-path including a first clothoid - target arc - second clothoid.

[0223] In a possible implementation manner, the determining the symmetric point of the second endpoint of the first clothoid symmetric about the target symmetry line includes:

[0224] The symmetric point is determined based on the following formula:

[0225]

[0226] where and are the abscissa and ordinate of the symmetric point, respectively, in the coordinate system with the first endpoint of the arc path as the vertex.

[0227] As Figure 19 shown, an embodiment of the present application provides an electronic device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114. Among them, the processor 111, the communication interface 112, and the memory 113 complete mutual communication through the communication bus 114.

[0228] The memory 113 is used to store a computer program.

[0229] In an embodiment of the present application, when the processor 111 executes the program stored on the memory 113, it implements the parking path processing method provided by any one of the foregoing method embodiments, including:

[0230] Obtain the initial parking path of the vehicle and determine the driving action sequence of the initial parking path. The driving action sequence includes the driving actions corresponding to each path node in the initial parking path.

[0231] Divide the initial parking path into multiple sub-paths according to the driving action sequence.

[0232] Perform clothoid optimization processing on the arc paths in the multiple sub-paths to generate optimized sub-paths.

[0233] Determine the final parking path according to the straight-line paths and the optimized sub-paths in the multiple sub-paths.

[0234] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the parking path processing method provided by any one of the foregoing method embodiments.

[0235] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0236] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the relevant technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0237] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, as used herein, the singular forms "a", "an", and "the" may also include the plural forms. The terms "include", "comprise", "contain", and "have" are inclusive and thus specify the presence of the stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or their combinations. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the particular order described or illustrated, unless the order of performance is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0238] The above are only the specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A parking path processing method, characterized in that, Including: Obtain an initial parking path of a vehicle, and determine a driving action sequence of the initial parking path, where the driving action sequence includes driving actions corresponding to each path node in the initial parking path; Divide the initial parking path into multiple sub-paths according to the driving action sequence; Perform clothoid curve optimization processing on circular arc paths in the multiple sub-paths to generate optimized sub-paths; Determine a final parking path according to straight-line paths and the optimized sub-paths in the multiple sub-paths.

2. The method according to claim 1, characterized in that The dividing the initial parking path into multiple sub-paths according to the driving action sequence includes: Traverse non-first path nodes in the initial parking path sequentially; When it is determined that the driving action changes for the currently traversed path node compared to its previous path node, determine the currently traversed path node as a target path node; Divide the initial parking path into multiple sub-paths with the target path node as a dividing point.

3. The method according to claim 2, wherein The determining that the driving action changes for the currently traversed path node compared to its previous path node includes: Determine the steering wheel angles corresponding to the currently traversed path node and its previous path node respectively; When it is determined that the steering wheel angles corresponding to the currently traversed path node and its previous path node are inconsistent, determine that the driving action changes for the currently traversed path node compared to its previous path node.

4. The method according to claim 2, wherein The determining that the driving action changes for the currently traversed path node compared to its previous path node includes: Determine the driving gears corresponding to the currently traversed path node and its previous path node respectively; When it is determined that the driving gears corresponding to the currently traversed path node and its previous path node are inconsistent, determine that the driving action changes for the currently traversed path node compared to its previous path node.

5. The method according to claim 3, wherein Determining the steering wheel angle corresponding to the path node includes: Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and heading angle; Based on the path parameters of the path node and its previous path node respectively, determine the heading angle change rate of the path node relative to its previous path node; Determine the steering wheel angle of the path node according to the heading angle change rate, the wheelbase of the vehicle, and a set parking speed.

6. The method according to claim 4, wherein Determining the driving gear corresponding to the path node includes: Obtain the path parameters of the path node and its previous path node respectively, where the path parameters include coordinate information and heading angle; Based on the path parameters of the path node and its previous path node respectively, determine the moving direction angle of the path node relative to its previous path node; Determine the driving gear corresponding to the path node based on the moving direction angle.

7. The method according to claim 1, characterized in that, The performing clothoid curve optimization processing on circular arc paths in the multiple sub-paths to generate optimized sub-paths includes: For the circular arc path among the multiple sub-paths, determine the center of the circle where the circular arc path is located and determine the target line passing through the center of the circle where the circular arc path is located and the target midpoint, where the target midpoint is the midpoint of the line segment formed by the two endpoints of the circular arc path; Take the first endpoint of the circular arc path as the first endpoint of the first clothoid, and preset the arc length of the first clothoid as the current preset arc length, and determine the initial second endpoint of the first clothoid based on the current preset arc length; Determine the intersection point of the normal line passing through the initial second endpoint and the target line, and use it as the target intersection point, and determine the length between the target intersection point and the initial second endpoint as the radius of the target circular arc; Judge whether the radius of the target circular arc is equal to the instantaneous radius of the first clothoid at the initial second endpoint; If not, change the current preset arc length, use the changed arc length as the current preset arc length, and return to the operation of presetting the arc length of the first clothoid as the current preset arc length and determining the initial second endpoint of the first clothoid based on the current preset arc length until the radius of the target circular arc is equal to the instantaneous radius, and use the last initial second endpoint as the second endpoint of the first clothoid; Determine the midpoint of the target circular arc; where the center of the circle where the target circular arc is located is the target intersection point, and the first endpoint of the target circular arc is the second endpoint of the first clothoid; Perform a symmetry operation on the target curve based on the connection line between the midpoint of the target circular arc and the target intersection point to obtain an optimized sub-path including a first clothoid - target circular arc - second clothoid; where the target curve is a curve formed by combining a first clothoid and a first circular arc obtained based on the first endpoint and the second endpoint of the first clothoid; the first circular arc is the circular arc between the second endpoint of the first clothoid and the midpoint of the target circular arc in the target circular arc.

8. The method according to claim 7, wherein The operation of performing a symmetry operation on the target curve based on the connection line between the midpoint of the target circular arc and the target intersection point to obtain an optimized sub-path including a first clothoid - target circular arc - second clothoid includes: Determine the symmetric point of the second endpoint of the first clothoid symmetric about the target symmetry line; where the target symmetry line is the connection line between the midpoint of the target circular arc and the target intersection point; Determine the second clothoid obtained by symmetrically transforming the first clothoid based on the target symmetry line between the symmetric point and the second endpoint of the circular arc path; Determine the second circular arc obtained by symmetrically transforming the first circular arc based on the target symmetry line between the midpoint of the target circular arc and the symmetric point; The first clothoid, the first circular arc, the second circular arc, and the second clothoid form an optimized sub-path including a first clothoid - target circular arc - second clothoid.

9. The method according to claim 8, characterized in that, The operation of determining the symmetric point of the second endpoint of the first clothoid symmetric about the target symmetry line includes: Determine the symmetric point based on the following formula: wherein, and are respectively the abscissa and ordinate of the symmetric point in a coordinate system with the first endpoint of the arc path as the vertex.

10. A parking path processing device, characterized in that, Including: A driving action determination module, configured to obtain an initial parking path of a vehicle and determine a driving action sequence of the initial parking path, where the driving action sequence includes driving actions corresponding to each path node in the initial parking path; A path division module, configured to divide the initial parking path into a plurality of sub-paths according to the driving action sequence; A sub-path processing module, configured to perform clothoid optimization processing on circular arc paths in the plurality of sub-paths to generate optimized sub-paths; A final parking path determination module, configured to determine a final parking path according to straight-line paths and the optimized sub-paths in the plurality of sub-paths.

11. An electronic device, characterized in that, Comprising: A memory, configured to store a computer program; A processor, configured to execute the computer program stored in the memory, and when the computer program is executed, implement the method according to any one of claims 1-9 above.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1-9 above is implemented.

Images