CN115657675A - Vehicle motion path generation method and system and storage medium - Google Patents
Vehicle motion path generation method and system and storage medium Download PDFInfo
- Publication number
- CN115657675A CN115657675A CN202211320109.4A CN202211320109A CN115657675A CN 115657675 A CN115657675 A CN 115657675A CN 202211320109 A CN202211320109 A CN 202211320109A CN 115657675 A CN115657675 A CN 115657675A
- Authority
- CN
- China
- Prior art keywords
- point
- neighborhood
- vehicle
- determining
- cost function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Navigation (AREA)
Abstract
The application discloses a vehicle motion path generation method, a vehicle motion path generation system and a storage medium. The method comprises the following steps: acquiring a starting point pose of a starting point and an end point pose of an end point of a vehicle, wherein the starting point pose comprises a starting point coordinate and a starting point orientation, and the end point pose comprises an end point coordinate and an end point orientation; acquiring a map near the vehicle, wherein the range of the map covers the starting point and the end point; searching and determining a first child node near the starting point based on the cost function; determining a vehicle movement path of the vehicle in the map based on at least the first child node; wherein the cost function is determined based on the start point coordinates, the start point orientation, the end point coordinates, the end point orientation, and a number of direction changes of a neighborhood point. The method considers the direction of the starting point and the ending point and the direction change cost calculation of the path in the cost function, can avoid excessive steering of vehicles in parking, provides a more ideal and reasonable vehicle movement path, and can reduce the search time.
Description
Technical Field
The present disclosure relates to the field of automatic driving technologies, and in particular, to a method, a system, and a storage medium for generating a vehicle movement path.
Background
Planning in an automatic driving product is an extremely important link, and path planning is one of key modules for intelligent driving. The path planning is responsible for generating a path for the vehicle to run stably, the quality of the path generation has great influence on the automatic driving function, performance and safety, and the colored path planning can even become a differential selling point of the vehicle, such as better automatic parking effect.
In the prior art, a mainstream scheme for vehicle path planning, such as parking path planning, is to use a hybrid a star (Astar) algorithm to complete path planning according to a start point location, an end point location, and a cost function. However, the prior art method for path planning based on the hybrid a-x algorithm has the following problems: firstly, in a parking scene, the planned path requires that the change of the yaw angle of the locomotive is as small as possible; however, the hybrid a-x algorithm does not consider the influence of the change of the yaw angle of the locomotive on the search in the search process. Too fast a change in the nose angle will affect the effect of the downstream controller following the planned path, resulting in the vehicle running out of the lane or other serious conditions. Secondly, the method for path planning based on the hybrid A-x algorithm does not consider the difference between the yaw angle of the current sub-node in the planned path and the terminal yaw angle of the vehicle motion path, so that the search time is too long, and the timeliness of path planning is affected.
Disclosure of Invention
In view of the above, the present application provides a method, a system and a storage medium for generating a vehicle motion path, which consider the direction of a starting point and a destination and the cost of the change of direction of the path in a cost function, so as to avoid excessive steering of the vehicle during parking, provide a more ideal and reasonable vehicle motion path, and reduce the search time.
In order to solve the above technical problem, a first aspect of the present application provides a vehicle movement path generating method, including: acquiring a starting point pose of a starting point and an end point pose of an end point of a vehicle, wherein the starting point pose comprises a starting point coordinate and a starting point orientation, and the end point pose comprises an end point coordinate and an end point orientation; acquiring a map near the vehicle, wherein the range of the map covers the starting point and the end point; searching and determining a first child node near the starting point based on the cost function; determining a vehicle movement path of the vehicle in the map based on at least the first child node; wherein the cost function is determined based on the start point coordinate, the start point orientation, the end point coordinate, the end point orientation, and a number of direction changes of a neighborhood point, and the neighborhood point of the start point includes the first child node. .
According to a preferred embodiment of the present application, the searching for determining the first child node near the starting point further includes: determining a plurality of the neighborhood points in the vicinity of the starting point; calculating the cost of each neighborhood point based on the cost function; and determining the neighborhood point with the minimum cost as the first child node.
According to a preferred embodiment of the present application, the determining the vehicle movement path of the vehicle in the map based on at least the first child node further comprises: determining a plurality of the neighborhood points in the vicinity of the first child node; judging whether the terminal point falls into the plurality of neighborhood points; if so, ending the search, and determining the vehicle motion path based on the starting point, the first child node and the end point; if not, continuing to search and determining the second child node.
According to a preferred embodiment of the present application, the determining the second child node includes: determining a plurality of the neighborhood points in the vicinity of the first child node; calculating the cost of each neighborhood point based on the cost function; determining the neighborhood point with the minimum cost as the second child node; the method further comprises the following steps: for the neighborhood point of each child node, judging whether the end point falls into the neighborhood point, if so, determining the vehicle motion path based on the starting point, the child nodes and the end point; if not, repeating the searching process until the end point is found.
According to a preferred embodiment of the present application, the determining a plurality of the neighborhood points includes: determining eight neighborhood points around the father node in a style of a nine-square grid; wherein the parent node is the searched point of the child node.
According to a preferred embodiment of the present application, the determining the vehicle movement path includes: determining a curve among a plurality of sections of adjacent points based on a preset curve model, wherein the adjacent points are two path points which are adjacent in sequence; determining the vehicle motion path based on the multi-segment curve.
According to a preferred embodiment of the present application, the cost function includes a first cost function, a second cost function, and a third cost function; wherein the first cost function is determined based on the origin point and the neighborhood point; the second cost function is determined based on the neighborhood point and the endpoint; the third cost function is determined based on the direction change times of the neighborhood points.
According to a preferred embodiment of the present application, the cost function further includes a judgment constraint term, and the judgment constraint term includes a threshold value of the direction change times.
According to a preferred embodiment of the present application, the method further comprises discarding the child node when the number of direction changes of the child node exceeds the threshold.
According to a preferred embodiment of the present application, the first cost function is:
cost 1 ＝k 1 *d s +k 2 *δ yaw_s
wherein d is s Is the distance, δ, of the neighborhood point from the origin point yaw_s Is the angular difference, k, of the directions of the neighborhood point and the origin point 1 、k 2 Are respectively d s Weight sum δ of yaw_s The weight of (c).
According to a preferred embodiment of the present application, the second cost function is:
cost 2 ＝k 3 *d e +k 4 *δ yaw_e
wherein d is e Is the distance, δ, of the neighborhood point to the end point yaw_e Is the angular difference, k, of the directions of the neighborhood point and the end point 3 、k 4 Are respectively d e Weight sum δ of yaw_e The weight of (c).
According to a preferred embodiment of the present application, the third cost function is:
cost 3 ＝k 5 *N
wherein N is the number of direction changes of the neighborhood point, k 5 Is the weight of N.
In order to solve the above technical problem, a second aspect of the present application provides a vehicle movement path generation system, including a memory for storing a computer program; a processor for loading and executing the computer program to implement the method of vehicle motion path generation as provided in the first aspect of the present application.
In order to solve the above technical problem, a third aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method for vehicle motion path generation as provided in the first aspect of the present application.
According to the method, the system and the storage medium for generating the vehicle motion path, the direction change of the vehicle in the generated vehicle motion path is less, and the adverse effect caused by too much or too fast direction change of the vehicle is effectively avoided; in addition, the times of changing the movement direction of the child nodes are introduced into the cost function, the path planning is ensured to obviously face the end point direction of the path, and the searching time of the path nodes is effectively reduced.
Drawings
In order to make the technical problems solved, technical means adopted and technical effects achieved by the embodiments in the present application clearer, specific embodiments of the embodiments in the present application will be described in detail below with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only for exemplary embodiments of the present application and that those skilled in the art will be able to derive from them other embodiments without the exercise of inventive faculty.
Fig. 1A and 1B are schematic views of a vehicle parking according to the present application.
Fig. 2 is a flowchart illustrating steps of a vehicle movement path generation method according to the present application.
Fig. 3 is a framework flowchart of a vehicle movement path generation method provided in accordance with the present application.
Fig. 4A and 4B are schematic diagrams of search determination neighborhood points according to the present application.
Fig. 5 is a schematic diagram of a framework of a vehicle motion path generation system provided in accordance with the present application.
Detailed Description
Exemplary embodiments of the present application will now be described more fully hereinafter with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.
Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in any suitable manner in one or more other embodiments while remaining within the technical spirit of the embodiments of the present application.
The described features, structures, characteristics, or other details of the embodiments of the present application are intended to provide a sufficient understanding of the embodiments for one skilled in the art in the description of the specific embodiments. One skilled in the relevant art will recognize, however, that the embodiments of the present application can be practiced without one or more of the specific features, structures, characteristics, or other details.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the embodiments of the present application.
The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.
Path planning is a very important function of current automatic driving vehicles or auxiliary driving vehicles, and is particularly embodied in some scenarios that can realize full automatic driving at short distance, such as automatic parking and the like. Automatic parking enables a vehicle to park into a parking space completely autonomously. The application provides a vehicle movement path generation method and system, which can reduce the calculation amount of path generation and accelerate the vehicle movement path generation, thereby providing good riding experience for drivers and passengers.
The vehicle motion path generation method and system provided by the application can be applied to automatic driving vehicles. The autonomous vehicle includes a vehicle that implements a full autonomous driving function, a partial autonomous driving function, or an auxiliary driving function. For example, under the standard of SAE driving automation hierarchy, there may be vehicles of L1 to L5 classes. Autonomous vehicles are equipped with computing devices, such as domain controllers and the like, for receiving or processing various types of data of the vehicle itself or sensed surroundings. The vehicle motion path generation method provided by the application can be applied to the computing device, and the vehicle motion path generation system provided by the application can be the computing device or a part of the system contained in the computing device.
Fig. 1A and 1B show an example of parking an autonomous vehicle according to the present application. The vehicle is initially at P as shown in FIG. 1A s At a position (starting point), hereThe vehicles have a corresponding pose, i.e. origin pose, comprising origin coordinates (x) s ,y s ) And starting point orientation j s . And the vehicle needs to park to P e At a location (endpoint), the vehicle at the endpoint has an expected pose, i.e., endpoint pose, including endpoint coordinates (x) e ,y e ) And starting point orientation j e . That is, the vehicle is driven from P if necessary s Parking at position P e Position, then a slave P is required s Position to P e Vehicle movement path of a location. As shown in FIG. 1B, the vehicle may generate a vehicle movement path based on at least one path point P 1 To generate. Of course, more waypoints, such as P, may be included based on the actual situation 2 ，…，P n And the like. Thus, a P is obtained s -P 1 -P 2 -…-P n -…-P e The vehicle can run to the terminal according to the vehicle motion path and meet the vehicle pose requirement of the terminal. For example, when the vehicle is automatically parked, the vehicle can be driven to the parking position P according to the movement path e And the orientation of the vehicle is consistent with that of the parking space.
The vehicle movement path generation method provided by the present application is further described below with reference to fig. 2. The method comprises steps S100-S400. For convenience of understanding, the following description will first be made on each type of dot, and detailed description will not be provided in the following specific steps.
Starting point and end point: respectively, a starting point for the vehicle to park and an end point for the target to reach.
And (4) parent node: the searched point when each step of search is carried out comprises a starting point.
And (3) child nodes: the point determined by the search when each step of search is performed includes an end point, and also includes a first child node, a second child node, and the like.
Neighborhood points: the points around the parent node at each search step include the child nodes determined by the search step.
Path point: all the points which are passed through on the moving path of the vehicle comprise a starting point, each middle child node and an end point.
The steps are specifically realized as follows.
Step S100: and acquiring the starting point pose of the starting point and the end point pose of the end point of the vehicle.
The starting point pose comprises a starting point coordinate and a starting point orientation, and the end point pose comprises an end point coordinate and an end point orientation. As previously described, referring to FIG. 1A, the starting point pose may include (x) s ,y s ) And j s And the end pose may include (x) e ,y e ) And j e 。
The coordinates of the starting point of the vehicle may be acquired by a positioning sensor on the vehicle, such as a GPS or the like. The orientation of the origin may be obtained by inertial sensors on the vehicle, such as the IMU or the like. The coordinates and orientation of the vehicle's endpoint are then determined by the vehicle's decision. For example, the vehicle determines the coordinates of the parking space and the desired orientation of the vehicle to park in the space by determining the surrounding parking space in which the vehicle may park. The parking space in which parking is possible can be determined by the vehicle's own sensing system, or by map data or the like. The orientation in which the vehicle is parked may then be determined based on the shape of the parking space, etc. Of course, the coordinates and orientation of the endpoint may also be obtained through other sensing or decision-making forms, which are not limited in this application.
Step S200: and acquiring a map near the vehicle, wherein the range of the map covers the starting point and the end point.
The map near the vehicle may be stored in the vehicle in advance, or may be a map acquired on-line in real time. The map is required to cover the starting point and the ending point of parking, that is, the vehicle at least needs to acquire a local map as a range where the vehicle movement path is generated. The map may be a normal two-dimensional map or a high-precision map. In another embodiment, the map around the vehicle may also be an instant three-dimensional reconstructed map based on a vehicle-mounted sensing system (such as a camera, a lidar, etc.), that is, no additional map data is needed. When the map is an instant three-dimensional reconstruction map, the starting point pose and the end point pose can be relative poses acquired based on the vehicle-mounted sensing system correspondingly.
The acquired map near the vehicle can be used as a reference for the starting point, the end point and the poses of the sub-nodes to be described later, and a necessary reference basis is provided for the generation of the motion path of the vehicle.
Step S300: based on the cost function, searching and determining a first child node near the starting point.
Step S300 of the present application will be specifically described below with reference to fig. 4A and 4B. In the application, starting from the starting point, a series of child nodes are searched until the end point is found, so that the vehicle motion path is generated.
Referring to FIG. 4A, one embodiment of searching for a determined child node is illustrated. For parent node P i Determining to correspond to the parent node P based on a cost function i The child node of (1). Specifically, the parent node P is first determined i Surrounding plurality of neighborhood points P ij . Then, according to the cost function, each neighborhood point P in the neighborhood is determined ij And determining the neighborhood point with the minimum cost as the child node determined by searching. Wherein, the father node P i Is a starting point P s Then, the child node determined by the search is the first child node.
The number, distribution and distance of the neighborhood points of the parent node can be set according to actual needs, namely, each neighborhood point P ij And parent node P i There is a pre-set change in direction and distance. In one embodiment, eight neighborhood points P around a parent node may be determined in the form of a nine-square grid i1 ～P i8 The eight directions of north, northeast, east, southeast, south, southwest, west and northwest of the father node are respectively indicated. Of course, the eight neighborhood points may also refer to other different directions, which is not limited in this application.
In one embodiment, the cost function of determining the child node from the parent node search may include a first cost function, a second cost function, and a third cost function.
A first cost function is determined based on the starting point and the neighborhood point. This cost function characterizes the cost of the change of the neighborhood point relative to the starting point. In one approach, the first cost function is:
cost 1 ＝k 1 *d s +k 2 *δ yaw_s
wherein d is s Is the distance, δ, of the neighborhood point from the origin point yaw_s Is the angular difference, k, of the directions of the neighborhood point and the origin point 1 、k 2 Are respectively d s Weight sum δ of yaw_s The weight of (c).
In calculating the first cost, the coordinates and direction of each neighborhood point may be determined based on the coordinate orientation of the parent node and a pre-set setting. The distance between the neighborhood point and the starting point can be Euclidean distance, namely, the real distance of the neighborhood point relative to the starting point is reflected. Weight k 1 、k 2 Can be set according to the actual engineering requirements.
A second cost function is determined based on the neighborhood point and the endpoint. This cost function characterizes the cost of the change of the neighborhood point relative to the endpoint. In one approach, the second cost function is:
cost 2 ＝k 3 *d e +k 4 *δ yaw_e
wherein d is e Is the distance, δ, of the neighborhood point from the end point yaw_e Is the angular difference, k, of the directions of the neighborhood point and the end point 3 、k 4 Are respectively d e Weight sum δ of yaw_e The weight of (c).
Calculating the second price may be performed similarly to calculating the first price. Weight k 3 、k 4 Can be set according to the actual engineering requirements.
The third cost function is determined based on the number of direction changes of the neighborhood points. This cost function characterizes the degree of directional change of the vehicle in the path of motion of the vehicle. In one approach, the second cost function is:
cost 3 ＝k 5 *N
wherein N is the number of direction changes of the neighborhood point, k 5 Is the weight of N.
Referring to FIG. 4B, for a parent node P i Neighborhood point P of ij Search determination results inA child node P i+1 Thereafter, the method can continue to be directed to the child node P i+1 Neighborhood point P of (i+1)j A search is conducted to determine the next child node. At this time, the child node P i+1 It becomes the parent node for the next search. Further, for each child node P i+1 All exist with its parent node P i As indicated by the arrows in fig. 4B. Likewise, the neighborhood points for each parent node also have this relative orientation. Thus, for the child node P i+1 Neighborhood point P of (parent node of next search) (i+1)j When it is associated with the child node P i+1 Relative direction of the child node P i+1 And the parent node P of the previous stage i When the relative direction of the neighboring point changes, 1 is added to the direction change times of the neighboring point. The relative direction changes, and the standard of the change can be determined according to actual needs. For example, a relative orientation change of more than 90 ° may be considered to be a "change" and the count incremented by 1, or some other orientation change criterion. The basic direction change number is zero from the starting point. Furthermore, for each step of search, the determined child node adds 1 to the direction change number of its parent node or remains unchanged.
Weight k of number of direction changes N 5 Relating to the parking scene. For example, when the parking scene is a narrow space, the number of directional changes of expected parking may be large, and the weight k may be adjusted accordingly 5 。
In this way, by calculating the first cost, the second cost and the third cost using three cost functions for each neighborhood point of the parent node, the neighborhood point with the smallest cost can be found as the child node determined by the search.
According to the method and the device, the plurality of cost functions are set, and parameters of the starting point, the end point and the direction change times are covered, so that the path points in the vehicle motion path are better searched and determined, the angle change of the vehicle in parking is as small as possible, and the vehicle can run along the vehicle motion path by a downstream controller conveniently.
In another embodiment, the cost function may further include a judgment constraint term on the basis of the aforementioned three cost functions. The judgment constraint term is a threshold value of the number of direction changes. That is, an upper limit, i.e., the maximum number of direction changes, may be set in the cost function for the number of direction changes. If the direction change times of the child nodes determined by one father node through the three cost functions exceeds the upper limit, the child nodes are abandoned and rollback is carried out. The fallback may be to the parent node or a fallback multi-step search. If the search is a multi-step search, the number of steps for backspacing can be determined according to actual needs.
In this way, by setting the judgment constraint item, it is possible to prevent the vehicle moving path from being an undesired path due to excessive vehicle direction change in the vehicle moving path generation.
Step S400: determining a vehicle movement path of the vehicle in the map based on at least the first child node.
In step S300, after the starting point is searched for by the cost function in one step, the first child node is determined to be obtained. Further, according to at least the first child node, a vehicle movement path of the vehicle in the map can be determined.
Referring to fig. 3, specifically, it is first determined whether the neighborhood point of the first child node includes an end point. If so, the search for the path may be terminated, and the vehicle movement path may be output based on the first child node. If not, further searching is needed to determine the next child node, and the same judgment is carried out. And circulating the steps until the destination is found, stopping searching, obtaining a series of sub nodes, and outputting a vehicle motion path based on the series of sub nodes.
In the output vehicle movement path, a tail child node, namely a child node before the terminal point, can be obtained first; and then, reversely checking the parent node of the child node according to the child node, and reversely checking the parent node of the higher level until a certain parent node can not inquire the parent node of the higher level, namely the starting point, stopping inquiring, further adding all inquired path points into the path array, completing the linkage of the path points, and outputting the path array. Of course, the output vehicle movement path may also be added to the path array in the process of determining the child node in each step of searching, and the determined child nodes are added down to the end point in a step-by-step manner, so as to output the path array.
After all waypoints in the path array have been determined, the path of motion of the vehicle can be determined from the waypoints. Specifically, a curve between adjacent points may be determined according to a preset curve model, where the adjacent points are two sequentially adjacent path points, such as a parent node and a child node determined by searching the parent node; and then after curves are obtained for every two adjacent points, a final global vehicle motion path can be determined. The curve model may be a Spiral curve, a Bezier curve, a Cubic curve, etc., which is not limited in the present application.
According to the vehicle motion path generation method, the change of the vehicle direction in the vehicle motion path can be further considered in the traditional mixed A-algorithm, the situation that the downstream control system is difficult to control the vehicle to realize the path due to overlarge change of the path direction is avoided, meanwhile, the search process can be accelerated, and the path generation efficiency is improved.
Referring to fig. 5, the present application further provides a system for vehicle motion path generation. The system 10 comprises a memory 11 and a processor 12, the memory 11 being adapted to store a computer program, the processor 12 being adapted to perform the method of vehicle movement path generation as provided herein as described above when the computer program is executed by said processor 12.
Another embodiment of the present application also provides a computer readable storage medium storing one or more programs which, when executed by a processor, implement the method for generating a vehicle motion path provided by the present application as described above.
Those skilled in the art will appreciate that all or part of the steps to implement the above embodiments are implemented as programs executed by data processing apparatuses (including computers), i.e., computer programs. When the computer program is executed, the above method provided by the application can be realized. Also, the computer program may be stored in a computer-readable storage medium, i.e., a computer-readable storage medium, which may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a magnetic disk, an optical disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing such as a storage array of multiple storage media, e.g., a magnetic disk or tape storage array. The computer program, when executed by one or more data processing devices, enables the computer-readable storage medium to implement the above-described methods of the present application. Further, the storage medium is not limited to a centralized storage, but may be a distributed storage, such as a cloud storage based on cloud computing. It should be appreciated that in the foregoing description of exemplary embodiments of the present application, various features of the present application are sometimes described in a single embodiment or with reference to a single figure, in order to streamline the application and assist those skilled in the art in understanding various aspects of the present application. However, the present application should not be construed that the features included in the exemplary embodiments are all the essential technical features of the present patent claims.
Further, those skilled in the art will readily appreciate that the exemplary embodiments described herein may be implemented in software, or in combination with hardware as necessary. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a data processing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present application. The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable storage medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the C language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
Thus, the present application may be embodied as a method, system, electronic device, or computer-readable storage medium that executes a computer program. Some or all of the functions of the present application may be implemented in practice using general purpose data processing devices such as microprocessors or Digital Signal Processors (DSPs).
It should be understood that the modules, units, components, and the like included in the device of one embodiment of the present application may be adaptively changed to be provided in a device different from the embodiment. The different modules, units or components comprised by the apparatus of an embodiment may be combined into one module, unit or component or may be divided into a plurality of sub-modules, sub-units or sub-components. The modules, units or components in the embodiments of the present application may be implemented in hardware, may be implemented in software running on one or more processors, or may be implemented in a combination thereof.
The above-mentioned embodiments are further described in detail for the purpose of illustrating the invention, and it should be understood that the above-mentioned embodiments are only illustrative of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
In summary, the present application may be implemented as a method, apparatus, system, or computer-readable storage medium that executes a computer program. Some or all of the functions of the present application may be implemented in practice using general purpose data processing devices such as microprocessors or Digital Signal Processors (DSPs). The foregoing detailed description of the embodiments, and the objects, technical solutions and advantages of the embodiments of the present application have been described in further detail, and it should be understood that the embodiments of the present application are not inherently related to any particular computer, virtual device or electronic system, and that various general-purpose devices may implement the embodiments of the present application. The above description is only exemplary of the embodiments of the present application and should not be construed as limiting the embodiments of the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the embodiments of the present application.
Claims (14)
1. A vehicle movement path generation method characterized by comprising:
acquiring a starting point pose of a starting point and an end point pose of an end point of a vehicle, wherein the starting point pose comprises a starting point coordinate and a starting point orientation, and the end point pose comprises an end point coordinate and an end point orientation;
acquiring a map near the vehicle, wherein the range of the map covers the starting point and the end point;
searching and determining a first child node near the starting point based on the cost function;
determining a vehicle movement path of the vehicle in the map based on at least the first child node;
wherein the cost function is determined based on the start point coordinate, the start point orientation, the end point coordinate, the end point orientation, and a number of direction changes of a neighborhood point, and the neighborhood point of the start point includes the first child node.
2. The method of claim 1, wherein the searching determines a first child node near the origin, further comprising:
determining a plurality of the neighborhood points in the vicinity of the origin point;
calculating the cost of each neighborhood point based on the cost function;
and determining the neighborhood point with the minimum cost as the first child node.
3. The method of claim 1, wherein the determining the vehicle movement path of the vehicle in the map based at least on the first child node further comprises:
determining a plurality of the neighborhood points in the vicinity of the first child node;
judging whether the end point falls into the plurality of neighborhood points;
if so, ending the search, and determining the vehicle motion path based on the starting point, the first child node and the end point;
if not, continuing searching and determining the second child node.
4. The method of claim 3, wherein the determining a second child node comprises:
determining a plurality of the neighborhood points in the vicinity of the first child node;
calculating the cost of each neighborhood point based on the cost function;
determining the neighborhood point with the minimum cost as the second child node;
the method further comprises the following steps:
for the neighborhood point of each child node, judging whether the end point falls into the neighborhood point, if so, determining the vehicle motion path based on the starting point, the child nodes and the end point; if not, repeating the searching process until the end point is found.
5. The method of any of claims 2-4, wherein said determining a plurality of said neighborhood points comprises:
determining eight neighborhood points around the father node in a style of a nine-square grid;
wherein the parent node is the searched point of the child node.
6. The method of any one of claims 1-4, wherein said determining the vehicle motion path comprises:
determining a curve among a plurality of sections of adjacent points based on a preset curve model, wherein the adjacent points are two path points which are adjacent in sequence;
determining the vehicle motion path based on the multi-segment curve.
7. The method of any of claims 2-4, wherein the cost function comprises a first cost function, a second cost function, and a third cost function; wherein the content of the first and second substances,
the first cost function is determined based on the starting point and the neighborhood point;
the second cost function is determined based on the neighborhood point and the endpoint;
the third cost function is determined based on the direction change times of the neighborhood points.
8. The method of claim 7, wherein the cost function further comprises a predicate constraint term comprising a threshold of the number of direction changes.
9. The method of claim 8, further comprising:
and when the direction change times of the child nodes exceed the threshold value, discarding the child nodes.
10. The method of claim 7, wherein the first cost function is:
cost 1 ＝k 1 *d s +k 2 *δ yaw_s
wherein, d s Is the distance, δ, of the neighborhood point from the origin point yaw_s Is the angular difference, k, of the directions of the neighborhood point and the origin point 1 、k 2 Are respectively d s Weight sum δ of yaw_s The weight of (c).
11. The method of claim 7, wherein the second cost function is:
cost 2 ＝k 3 *d e +k 4 *δ yaw_e
wherein d is e Is the distance, δ, of the neighborhood point from the end point yaw_e Is the angular difference, k, of the directions of the neighborhood point and the end point 3 、k 4 Are respectively d e Weight sum δ of yaw_e The weight of (c).
12. The method of claim 7, wherein the third cost function is:
cost 3 ＝k 5 *N
wherein N is the number of direction changes of the neighborhood point, k 5 Is the weight of N.
13. A vehicle motion path generation system, comprising:
a memory for storing a computer program;
a processor for loading and executing the computer program to implement the vehicle motion path generation method according to any one of claims 1 to 12.
14. A computer readable storage medium, wherein the computer readable storage medium stores one or more computer programs which, when executed by a processor, implement the vehicle motion path generation method of any one of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211320109.4A CN115657675A (en) | 2022-10-26 | 2022-10-26 | Vehicle motion path generation method and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211320109.4A CN115657675A (en) | 2022-10-26 | 2022-10-26 | Vehicle motion path generation method and system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115657675A true CN115657675A (en) | 2023-01-31 |
Family
ID=84990675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211320109.4A Pending CN115657675A (en) | 2022-10-26 | 2022-10-26 | Vehicle motion path generation method and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115657675A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117537841A (en) * | 2023-12-08 | 2024-02-09 | 北京斯年智驾科技有限公司 | Reversing path generation method and system for automatic driving vehicle |
-
2022
- 2022-10-26 CN CN202211320109.4A patent/CN115657675A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117537841A (en) * | 2023-12-08 | 2024-02-09 | 北京斯年智驾科技有限公司 | Reversing path generation method and system for automatic driving vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109540142B (en) | Robot positioning navigation method and device, and computing equipment | |
| WO2021180035A1 (en) | Parking path planning method and apparatus, vehicle, and storage medium | |
| US20160375901A1 (en) | System and Method for Controlling Semi-Autonomous Vehicles | |
| CN111750886A (en) | Local path planning method and device | |
| WO2022056770A1 (en) | Path planning method and path planning apparatus | |
| CN109885058B (en) | Driving track planning method and device, electronic equipment and storage medium | |
| CN112394725B (en) | Prediction and reaction field of view based planning for autopilot | |
| CN115123310B (en) | Unmanned vehicle obstacle avoidance local path planning method, equipment and storage medium | |
| CN111795699A (en) | Unmanned vehicle path planning method and device and computer readable storage medium | |
| Bertolazzi et al. | Efficient re-planning for robotic cars | |
| CN112327826A (en) | Path planning method, device, equipment and medium | |
| CN115657675A (en) | Vehicle motion path generation method and system and storage medium | |
| US11435200B2 (en) | Autonomous vehicle routing with local and general routes | |
| Malayjerdi et al. | Practical path planning techniques in overtaking for autonomous shuttles | |
| CN111332279A (en) | Parking path generation method and device | |
| Stević et al. | Development of ADAS perception applications in ROS and" Software-In-the-Loop" validation with CARLA simulator | |
| CN115014380A (en) | Parking path planning method and device, electronic device and storage medium | |
| CN115615449A (en) | Path planning method, device, equipment and storage medium | |
| CN112379692B (en) | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium | |
| CN111984032B (en) | Unmanned plane path planning method and device, electronic equipment and storage medium | |
| CN115097826A (en) | Vehicle turning track planning method and device | |
| CN113790725B (en) | Path planning method, path planning device, storage medium and mobile device | |
| CN109917794B (en) | Global path planning method and device | |
| Björnberg | Shared control for vehicle teleoperation with a virtual environment interface | |
| Yoon et al. | Shape-Aware and G 2 Continuous Path Planning Based on Bidirectional Hybrid A∗ for Car-Like Vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |