CN116360426A - Global path planning method, system, medium and equipment for automatic driving of vehicle - Google Patents
Global path planning method, system, medium and equipment for automatic driving of vehicle Download PDFInfo
- Publication number
- CN116360426A CN116360426A CN202310190314.1A CN202310190314A CN116360426A CN 116360426 A CN116360426 A CN 116360426A CN 202310190314 A CN202310190314 A CN 202310190314A CN 116360426 A CN116360426 A CN 116360426A
- Authority
- CN
- China
- Prior art keywords
- track
- global
- point
- path
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000005070 sampling Methods 0.000 claims abstract description 28
- 238000009499 grossing Methods 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims description 31
- 238000012952 Resampling Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 description 17
- 230000001133 acceleration Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application relates to a vehicle automatic driving global path planning method, a system, a medium and equipment, wherein the method comprises the following steps: acquiring the current vehicle position and the target point position, and planning a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points; dynamically smoothing the global reference track points to obtain a continuous reference path; sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling, and generating a dynamic feasible track cluster; calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function; and selecting the track with the minimum total cost value as the optimal running track of the current vehicle. By adopting the embodiment of the application, the optimal running path which can run can be planned for the automatic driving vehicle to run.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a global path planning method, a global path planning system, a global path planning medium and global path planning equipment for automatic driving of a vehicle.
Background
The automatic driving technology relies on the cooperation of computer vision, radar, monitoring device, global positioning system, etc. to make the motor vehicle realize automatic driving without active operation of human. Autonomous vehicles use various computer systems to move the vehicle from one location to another. Since the automatic driving technology does not need a human to drive the motor vehicle, driving errors of the human can be avoided in theory, traffic accidents can be reduced, and transportation efficiency of a road can be improved, so that the automatic driving technology is increasingly paid attention.
At present, the traditional automatic driving technology executes driving operation according to the collected road condition information and navigation information and preset driving rules in an automatic driving mode, however, the traditional automatic driving technology cannot plan optimal path driving when facing complex and diverse traffic road environments.
Disclosure of Invention
In order to plan an optimal running path for an automatic driving vehicle, the application provides a method, a system, a medium and equipment for planning the global path for the automatic driving of the vehicle.
In a first aspect of the present application, a global path planning method for automatic driving of a vehicle is provided, and the following technical scheme is adopted: acquiring the current vehicle position and the target point position, and planning a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points;
Dynamically smoothing the global reference track points to obtain a continuous reference path;
sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling, and generating a dynamic feasible track cluster;
calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function;
and selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
By adopting the technical scheme, the global reference track point from the vehicle position to the target point position is dynamically smoothed to obtain a stable continuous reference path with small fluctuation, the multi-dimensional state quantity of the continuous reference path is sampled based on transverse and longitudinal decoupling to obtain a dynamic feasible track cluster containing each dimensional information, the total cost value of each track in the dynamic feasible track cluster is calculated, the track with the minimum total cost value is selected as the optimal running track, and a smooth optimal running path with the minimum cost value can be planned for the automatic driving vehicle.
Optionally, before the dynamically smoothing the global reference track point to obtain a continuous reference path, the method further includes: and carrying out secondary resampling on the global reference point track by adopting a preset secondary resampling interval value to obtain a secondary resampled global reference track point. The step of dynamically smoothing the global reference track point to obtain a continuous reference path includes: and carrying out dynamic smoothing treatment on the twice resampled global reference track point to obtain a continuous reference path.
By adopting the technical scheme, the global reference point track is resampled for the second time by adopting the resampling interval value for the second time, so that the global reference track point is more accurate, the fluctuation of the vehicle in the automatic driving process is smaller, and the riding comfort of passengers is improved.
Optionally, the dynamically smoothing the twice resampled global reference track point to obtain a continuous reference path includes: traversing the secondary resampled global reference track point, searching a track point nearest to the current vehicle position, and intercepting all tracks from the nearest track point to the target point position as a local track set; calculating the track length of each track point in the local track set, and establishing a coordinate pair set of the track length and the corresponding track point; polynomial fitting calculation is carried out on each coordinate pair set to obtain each fitting result interpolation; and calculating coordinates of each track in each local track set and corresponding track length according to the fitting result interpolation to form a continuous reference path.
By adopting the technical scheme, the track point closest to the current vehicle position is taken as the starting point of the vehicle, all tracks from the closest track point to the position of the target point are taken as local reference tracks, and the local reference tracks are dynamically smoothed to obtain continuous reference paths with continuous and smooth paths.
Optionally, the sampling calculation is performed on the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling, and a dynamic feasible track cluster is generated, which includes: respectively acquiring longitudinal multi-dimensional state quantity and transverse multi-dimensional state quantity of the current vehicle position and the target point position in the continuous reference path; according to the longitudinal multi-dimensional state quantity and the transverse multi-dimensional state quantity, a plurality of groups of longitudinal polynomial equations and a plurality of groups of transverse polynomial equations are obtained through calculation; and obtaining a plurality of dynamic feasible track clusters according to the plurality of sets of longitudinal polynomial equations and the plurality of sets of transverse polynomial equations.
By adopting the technical scheme, a plurality of groups of transverse and longitudinal polynomial equations are calculated according to the longitudinal multi-dimensional state quantity and the transverse multi-dimensional state quantity of the known vehicle position and the target point position, so as to obtain a plurality of dynamic feasible track clusters according to the plurality of groups of transverse and longitudinal polynomial equations.
Optionally, obtaining a plurality of dynamic feasible track clusters according to the plurality of sets of longitudinal polynomial equations and the plurality of sets of transverse polynomial equations includes: selecting a set of longitudinal polynomial equations, calculating each parameter value in the set of longitudinal polynomial equations, and substituting one parameter value into a set of transverse polynomial equations to obtain a transverse point set; converting the transverse point set into a dynamic feasible track according to a Cartesian coordinate system; traversing the other sets of longitudinal polynomial equations and the other sets of transverse polynomial equations in sequence, and executing the steps to obtain a plurality of dynamic feasible track clusters.
By adopting the technical scheme, one parameter value calculated by a set of longitudinal polynomial equations is brought into a set of transverse polynomial equations to obtain a transverse point set, the transverse point set is converted into a dynamic feasible track under a Cartesian coordinate system, and the rest transverse and longitudinal polynomial equations are traversed in sequence according to the method to obtain a plurality of dynamic feasible track clusters.
Optionally, the calculating the total cost value of each track in the dynamically feasible track cluster according to a preset cost function includes: acquiring multi-dimensional information of each track in a plurality of dynamic feasible track clusters; calculating the child value corresponding to each piece of dimension information respectively; calculating the total cost value of each track according to the offspring value and the cost function; the cost function is: f=w 1 f 1 +W 2 f 2 +W 3 f 3 +…+W n f n Wherein F is the total cost value of any track A in a plurality of dynamic feasible track clusters, and W is n For the cost weight coefficient of track A in the nth dimension, the f n Is the child value of trace a in the nth dimension.
By adopting the technical scheme, the feasible tracks of the dynamic track comprise multidimensional information of each track, the child value corresponding to each dimensional information is calculated respectively, and then the total cost value of each track is calculated according to the cost function, so that the optimal path is screened according to the total cost value of each track.
Optionally, before calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function, the method further includes: acquiring track point information in each track in the dynamic feasible track cluster; judging whether target tracks with the multi-dimensional state quantity larger than the corresponding multi-dimensional state standard quantity exist in the track point information or not; if the target track exists in each track, deleting the target track from the dynamic feasible track cluster; and if the target track does not exist in each track, the target track is reserved.
By adopting the technical scheme, the target track with the multi-dimensional state quantity larger than the corresponding multi-dimensional state standard quantity in the dynamic feasible track cluster is deleted, the unqualified track is subjected to preliminary screening, and the subsequent calculated quantity is reduced.
In a second aspect of the present application there is provided a vehicle autopilot global path planning system, the system comprising: the global path planning module is used for acquiring the current vehicle position and the target point position, and planning a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points;
The path smoothing processing module is used for carrying out dynamic smoothing processing on the global reference track points to obtain a continuous reference path; the dynamic feasible track cluster acquisition module is used for sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling and generating a dynamic feasible track cluster;
the cost value calculation module is used for calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function; and the optimal path selection module is used for selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
In a third aspect the present application provides a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the above-described method steps.
In a fourth aspect of the present application, there is provided an electronic device comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.
In summary, the present application includes at least one of the following beneficial technical effects:
1. dynamically smoothing global reference track points from a vehicle position to a target point position to obtain a stable and small-fluctuation continuous reference path, sampling multi-dimensional state quantities of the continuous reference path based on transverse and longitudinal decoupling to obtain dynamic feasible track clusters containing dimensional information, calculating the total cost value of each track in the dynamic feasible track clusters, selecting the track with the minimum total cost value as an optimal running track, and planning a smooth and optimal running path with the minimum cost value for an automatic driving vehicle; 2. and the global reference point track is resampled for the second time by adopting the resampling interval value for the second time, so that the global reference track point is more accurate, the fluctuation of the vehicle in the automatic driving process is smaller, and the riding comfort of passengers is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a global path planning method for automatic driving of a vehicle according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of a global path planning system for vehicle autonomous driving according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 1. a global path planning module; 2. a path smoothing module; 3. a track cluster acquisition module; 4. a cost value calculation module; 5. an optimal path selection module; 1000. an electronic device; 1001. a processor; 1002. a communication bus; 1003. a user interface; 1004. a network interface; 1005. a memory.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.
In the description of embodiments of the present application, words such as "exemplary," "such as" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "illustrative," "such as" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "illustratively," "such as" or "for example," etc., is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, the term "and/or" is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a alone, B alone, and both A and B. In addition, unless otherwise indicated, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
The following embodiments may be combined with each other, and may not be described in detail in some embodiments for the same or similar probability or process.
Step 10: and acquiring the current vehicle position and the target point position, and planning a global reference track from the vehicle position to the target point position in a preset electronic map.
A global reference path is understood in the present embodiment to be the entire path from the current position of the vehicle to the target point position.
Specifically, the computer device obtains a current vehicle position and a target point position, where the target point position may be an end point position to be reached by the vehicle. The computer device plans a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points. The computer device may be a vehicle-mounted terminal on a vehicle in the embodiment of the present application.
Step 20: and carrying out dynamic smoothing treatment on the global reference track points to obtain a continuous reference path.
The global reference track points can be discrete points in the global reference track in the embodiment of the application, and as the connecting line of the global reference track points has a meandering condition, the global reference track points are dynamically smoothed, so that the track is smoother, the occurrence of vehicle shake caused by track meandering of a vehicle is reduced, and the riding comfort of passengers is further improved.
On the basis of the foregoing embodiments, as an optional embodiment, the step of dynamically smoothing the global reference track point to obtain a continuous reference path further includes the following steps:
step 201: and carrying out secondary resampling on the global reference track by adopting a preset secondary resampling interval value to obtain a secondary resampled global reference track point.
The secondary resampling may be, in the embodiment of the present application, subsampling the track points on the global reference track.
For example, the preset secondary resampling interval value in the embodiment of the present application may be set to 0.5 m, and the global reference track is equally divided every 0.5 m, so as to obtain secondary resampled global reference track points, where each track point is sequentially provided with a number, for example, the number of the first track point on one reference track is 1, and the number of the 100 th track point is 100. The track point interval in the reference track can be set to be more accurate by carrying out secondary resampling on the global reference track, and the reference track is smoother, so that shake generated when the vehicle is controlled to run is smaller, and meanwhile, when the vehicle needs to park between two track points, the vehicle can be controlled to park accurately in a smaller interval more accurately.
Step 202: traversing the global reference track point of the secondary resampling, searching the track point nearest to the current vehicle position, and intercepting all tracks from the nearest track point to the target point position as a local track set.
Specifically, the computer equipment sequentially traverses the global reference track points which are resampled for the second time, searches the track point closest to the current vehicle position, takes the closest track point as the starting point of the vehicle, intercepts all tracks from the closest track point to the target point position as a local track set, and can directly carry out smoothing processing on the local track set from the closest track point to the target point position.
In another possible embodiment, the computer device traverses the global reference track points resampled for the second time in sequence, searches the track point closest to the current vehicle position, acquires the number of the track point, intercepts all tracks between the number and the target point with the preset point length before the number as a local track set, the preset point length can be determined in a self-defined mode according to the vehicle speed, and the preset point length can be set longer as the vehicle speed is faster. The track which is driven and has a certain distance in the advancing direction of the vehicle can be smoothly processed.
For example, the computer device searches the track point closest to the current vehicle position for 100, and the preset point length is 500, intercepts the track from the track point with the number 100 to the track point with the number 600 as a local track, when the vehicle runs fast to the tail end of the local track, that is, takes the track point with the number 600 as the closest track point, intercepts the track from the track point with the number 600 to the track point with the number 1100 as the local track, and so on, and performs smoothing processing on the local track in real time when the vehicle runs.
Step 203: and calculating the track length of each track point in the local track set, and establishing a coordinate pair set of the track length and the corresponding track point.
Specifically, the computer device traverses the twice resampled local track points in sequence, takes the track point closest to the current vehicle as the first track point, and the track length S of the track point 1 And (3) for 0, sequentially calculating Euclidean distances between two adjacent track points, and accumulating and storing to obtain the track length S of each track point in the local track set. For example, if the Euclidean distance between every two track points is 0.5, the track length S of the second track point 2 Track length S of the third track point is 0.5 3 Track length S of the fourth track point is 1 4 1.5. Establishing each track pointAbscissa and track length X i -S i Coordinate pair set between them, and establishing ordinate of each track point and track length Y i -S i A set of coordinate pairs in between.
Step 204: polynomial fitting calculation is carried out on each coordinate pair set to obtain interpolation of each fitting result; and (3) interpolating according to the fitting result, and calculating the coordinates of each track in each local track set and the corresponding track length to form a continuous reference path.
Specifically, the computer equipment pair X i -S i Coordinate pair set between and Y i -S i Respectively performing polynomial fitting calculation on the coordinate pair sets; according to the interpolation of the polynomial fitting calculation result, the abscissa and the ordinate of the track point corresponding to the track length after each secondary resampling are calculated to form a group of coordinate pairs (X i ，Y i ，S i ) And sequentially reading and storing each group of pairs, and forming a continuous reference path according to each group of pairs, so that dynamic smoothing of local tracks can be realized.
Step 30: and sampling and calculating the multi-dimensional state quantity in the continuous reference path based on the transverse and longitudinal decoupling, and generating a dynamic feasible track cluster.
In the embodiment of the present application, the dynamic feasible track clusters may be multiple dynamic feasible tracks after dynamic smoothing processing, where each dynamic feasible track includes multidimensional information of each track point.
Based on the above embodiments, as an optional embodiment, the step of sampling and calculating the multi-dimensional state quantity in the continuous reference path based on the transverse and longitudinal decoupling and generating the dynamic feasible track cluster further includes the following steps: step 301: longitudinal multi-dimensional state quantities of the current vehicle position and the target point position in the continuous reference path are obtained, and a plurality of groups of longitudinal polynomial equations are obtained through calculation;
specifically, the longitudinal multi-dimensional state quantity includes, but is not limited to, displacement, speed, acceleration, and time in the embodiment of the present application, and the lateral multi-dimensional state quantity includes, but is not limited to, lateral offset, yaw rate, heading angle, and displacement in the embodiment of the present application.
Further, the longitudinal multi-dimensional state quantity and the lateral multi-dimensional state quantity of the current vehicle position are known to be determined, and the longitudinal multi-dimensional state quantity and the lateral multi-dimensional state quantity of the target point position are preset desired values.
Further, the longitudinal speed is sampled for a plurality of times to obtain the speed sampling times, the speed difference between the initial speed of the current vehicle position and the expected speed of the target point position is calculated, the speed sampling interval can be calculated by dividing the speed difference by the speed sampling times, and the speed interval from the initial speed to the expected speed is divided into m parts by the speed sampling interval. And sampling the longitudinal time to obtain a time interval between the initial time of the current vehicle position and the expected time of the target point position, dividing the time interval by the speed sampling times to calculate a time sampling interval, and dividing the time interval between the initial time and the expected time into n times by using the time sampling interval.
For example, a longitudinal fourth-order polynomial equation about time-displacement is established, the longitudinal multi-dimensional state quantity of the current vehicle position, that is, the initial displacement, the initial velocity, the initial acceleration and the initial time, the desired longitudinal multi-dimensional state quantity of the target point position, that is, the final velocity, the final acceleration and the final time, are taken, a set of longitudinal fourth-order polynomial equations can be solved through six known longitudinal dimension state quantities, and similarly, a set of m×n longitudinal polynomial equations can be calculated.
Step 302: acquiring transverse multi-dimensional state quantities of the current vehicle position and the target point position in a continuous reference path, and calculating to obtain a plurality of groups of transverse polynomial equations;
specifically, the longitudinal velocity and the corresponding longitudinal time of the set of longitudinal fourth-order polynomial equations in step 301 are obtained, the longitudinal displacement is obtained according to the longitudinal time, and the longitudinal displacement is used as the displacement constraint of transverse sampling, and the total m×n displacement constraints are taken as the total.
Further, the transverse offset is sampled for a plurality of times to obtain transverse offset sampling times, a transverse offset interval of the initial transverse offset of the current vehicle position and the expected transverse offset of the target point position is calculated, and the transverse offset interval is divided into h parts according to the transverse offset sampling times.
By way of example, taking the displacement constraint and the corresponding lateral offset, establishing a lateral penta-polynomial equation between displacement and lateral offset, taking the lateral multi-dimensional state quantities of the current vehicle position, namely, the initial lateral offset, the initial heading angle, the initial yaw rate and the initial displacement, taking the expected lateral multi-dimensional state quantities of the target point position, namely, the final lateral offset, the final heading angle, the final yaw rate and the final displacement, solving a set of lateral penta-polynomial equations through six known lateral dimension state quantities, and so on, and calculating h sets of lateral multi-polynomial equations with each displacement constraint and h lateral offset constraints.
Step 303: and obtaining a plurality of dynamic feasible track clusters according to the plurality of sets of longitudinal polynomial equations and the plurality of sets of transverse polynomial equations.
Specifically, a set of longitudinal polynomial equations is taken, and a longitudinal point set containing information of various longitudinal multi-dimensions can be calculated according to different order derivatives, wherein the longitudinal point set comprises displacement, speed, acceleration and time, for example, the longitudinal fourth-order polynomial equation is as follows: s=a 1 t 4 +a 2 t 3 +a 3 t 2 +a 4 t+a 5 The velocity can be found by taking the first derivative of the original Cheng Qiu for a known amount of time and the second derivative of the original equation can be found by finding the acceleration. And taking the obtained displacement as a constraint value to a group of transverse polynomial equations, and calculating a transverse point set containing the transverse multi-dimensional information according to different order derivatives, wherein the transverse point set comprises transverse offset, course angle, yaw rate and displacement. And (3) displaying a track by using the displacement and the transverse offset in the transverse multidimensional information under the freset coordinate system, and converting the transverse point set under the Cartesian coordinate system according to the coordinate conversion mode before the freset coordinate system and the Cartesian coordinate system, so as to obtain the track expressed by coordinates.
Further, according to the method, a plurality of groups of transverse and longitudinal polynomials are sequentially traversed, and n.times.m.times.h initial sampling track clusters can be obtained. And sequentially traversing each initial sampling track cluster, judging whether a target track with the multi-dimensional state quantity larger than the corresponding multi-dimensional state standard quantity exists in each track point information, deleting the target track from the initial sampling track cluster if the target track exists in the initial sampling track cluster, and reserving the target track into the initial sampling track cluster if the target track does not exist in the initial sampling track cluster, so as to finally obtain a plurality of dynamic feasible track clusters.
Step 40: and calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function.
On the basis of the foregoing embodiments, as an optional embodiment, the step of calculating the total cost value of each track in the dynamically feasible track cluster according to a preset cost function further includes the following steps:
step 401: and acquiring track point information in each track in the dynamic feasible track cluster.
Specifically, the dynamic feasible track cluster comprises a plurality of dynamic feasible tracks, each dynamic feasible track is composed of a plurality of track points, and each track point comprises, but is not limited to, coordinates at the moment of the track point, a reference course angle, a reference speed, a reference acceleration, a reference gear, a reference curvature, a reference lateral offset and a reference yaw rate. The target parameters of each track point are determined according to the actual performance and the actual riding requirement of each vehicle, and the target parameters include, but are not limited to, a target planning course angle, a target speed, a target acceleration, a target gear, a target curvature, a target transverse offset, a target yaw rate and the like.
Step 402: and calculating the child value corresponding to each dimension information.
Illustratively, the computer device traverses each track point in the dynamic feasible track in turn, calculates the child value of the speed dimension, calculates the absolute value of the speed difference value between the reference speed and the target speed of each track point, and accumulates the absolute value of the speed difference value of each track point as the child value of the speed of the track. And calculating the child value of the gear dimension, wherein the previous gear cost value is low, the backward gear cost value is high, and the gear value of each track point is accumulated to be used as the gear child value of the track. And calculating the value of the offspring of the acceleration dimension, and calculating the mean error of the reference acceleration of each track point, wherein the larger the mean error is, the larger the fluctuation of the acceleration is, and the larger the cost value is at the moment. Calculating the value of the child of the curvature dimension, calculating the absolute value of the reference curvature of each track point, and accumulating the absolute value of the curvature of each point on each track as the value of the child of the curvature, wherein the larger the curvature is, the smaller the turning radius is, and the larger the value of the child of the curvature is. And calculating the child value of the track deviation dimension, calculating the lateral offset between each track point and the nearest track point on the reference track, and accumulating the lateral offset of each track point on each track to be used as the child value of the track deviation. And calculating the child value of the yaw rate, and calculating the mean error of the reference yaw rate of each track point, wherein the larger the mean error is, the larger the fluctuation of the yaw rate is, and the larger the cost value is. And calculating the value of the offspring close to the end point dimension, and calculating the distance from the end point of each track to the position of the target point as the value of the offspring close to the end point.
Step 403: and calculating the total cost value of each track according to the offspring value and the cost function.
Specifically, the total cost value of each track is calculated according to the offspring value and a cost function, wherein the cost function is as follows:
F＝W 1 f 1 +W 2 f 2 +W 3 f 3 +…+W n f n
wherein F is the total cost value, W, of any track A in a plurality of dynamic feasible track clusters n For the cost weight coefficient of the track A in the nth dimension, f n Is the child value of trace a in the nth dimension.
The cost weight coefficient of each dimension can be set automatically according to actual conditions. In another possible embodiment, other cost functions may be selected according to the requirements. Multiplying the child value of each dimension by the corresponding cost weight coefficient, and accumulating to obtain the total cost value of each track.
Step 50: and selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
Specifically, a track with the smallest total cost value is selected from the total cost values of all tracks to be used as the optimal running track of the current vehicle, and the optimal running track is sent to the vehicle-mounted terminal to enable the vehicle to run according to the optimal running track, and the optimal running track has the characteristics of smoothness, small fluctuation, small time cost, low collision risk and the like, so that the riding comfort of passengers on the vehicle is further improved.
The following are device embodiments of the present application, which may be used to perform method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
Referring to fig. 2, a global path planning system for vehicle automatic driving according to an embodiment of the present application may include: the system comprises a global path planning module 1, a path smoothing module 2, a track cluster acquisition module 3, a cost value calculation module 4 and an optimal path selection module 5, wherein:
the global path planning module 1 is used for acquiring the current vehicle position and the target point position, and planning a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points;
the path smoothing processing module 2 is used for dynamically smoothing the global reference track points to obtain a continuous reference path; the track cluster acquisition module 3 is used for sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling and generating a dynamic feasible track cluster;
the cost value calculation module 4 is used for calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function; and the optimal path selection module 5 is used for selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
On the basis of the above embodiments, as an alternative embodiment, the vehicle autopilot global path planning system may further include: and the secondary resampling module and the track primary screening module.
The secondary resampling module is used for carrying out secondary resampling on the global reference point track by adopting a preset secondary resampling interval value to obtain a secondary resampled global reference track point;
the track primary screening module is used for taking track point information in each track in the dynamic feasible track cluster; judging whether target tracks with the multi-dimensional state quantity larger than the corresponding multi-dimensional state standard quantity exist in the track point information or not; if the target track exists in each track, deleting the target track from the dynamic feasible track cluster; and if the target track does not exist in each track, the target track is reserved.
In the system provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the system and method embodiments provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the system and method embodiments are detailed in the method embodiments, which are not repeated herein.
The embodiment of the application further provides a computer storage medium, where the computer storage medium may store a plurality of instructions, where the instructions are adapted to be loaded by a processor and execute the method for planning a global path for vehicle automatic driving according to the embodiment shown in the foregoing, and a specific execution process may be referred to a specific description of the embodiment shown in fig. 1, and reference is made to fig. 3 for a detailed description herein. As shown in fig. 3, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, at least one communication bus 1002.
Wherein the communication bus 1002 is used to enable connected communication between these components.
The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire server 1000 using various interfaces and lines, and performs various functions of the server 1000 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 1001 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 1001 and may be implemented by a single chip.
The Memory 1005 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory 1005 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like referred to in the above respective method embodiments. The memory 1005 may also optionally be at least one storage device located remotely from the processor 1001. As shown in fig. 3, an operating system, a network communication module, a user interface module, and an application program of a method of vehicle autopilot global path planning may be included in a memory 1005 as a computer storage medium.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
In the electronic device 1000 shown in fig. 3, the user interface 1003 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke the application program in the memory 1005 storing a vehicle autopilot global path planning method that, when executed by the one or more processors, causes the electronic device to perform the method as described in one or more of the embodiments above.
An electronic device readable storage medium, wherein the electronic device readable storage medium stores instructions. When executed by one or more processors, cause an electronic device to perform the method as described in one or more of the embodiments above.
It will be clear to a person skilled in the art that the solution of the present application may be implemented by means of software and/or hardware. "Unit" and "module" in this specification refer to software and/or hardware capable of performing a specific function, either alone or in combination with other components, such as Field programmable gate arrays (Field-ProgrammaBLE Gate Array, FPGAs), integrated circuits (Integrated Circuit, ICs), etc.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be performed by hardware associated with a program that is stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. A method for global path planning for automatic driving of a vehicle, applied to a computer device, the method comprising: acquiring the current vehicle position and the target point position, and planning a global reference track from the vehicle position to the target point position in a preset electronic map, wherein the global reference track consists of global reference track points;
Dynamically smoothing the global reference track points to obtain a continuous reference path;
sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling, and generating a dynamic feasible track cluster;
calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function;
and selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
2. The method for planning an automatic global path for driving a vehicle according to claim 1, further comprising, before said dynamically smoothing said global reference trajectory point to obtain a continuous reference path:
performing secondary resampling on the global reference point track by adopting a preset secondary resampling interval value to obtain a secondary resampled global reference track point;
the step of dynamically smoothing the global reference track point to obtain a continuous reference path includes:
and carrying out dynamic smoothing treatment on the twice resampled global reference track point to obtain a continuous reference path.
3. The method for planning an automatic global path for driving a vehicle according to claim 2, wherein the dynamically smoothing the twice resampled global reference trajectory point to obtain a continuous reference path comprises:
Traversing the secondary resampled global reference track point, searching a track point nearest to the current vehicle position, and intercepting all tracks from the nearest track point to the target point position as a local track set;
calculating the track length of each track point in the local track set, and establishing a coordinate pair set of the track length and the corresponding track point;
polynomial fitting calculation is carried out on each coordinate pair set to obtain each fitting result interpolation;
and calculating coordinates of each track in each local track set and corresponding track length according to the fitting result interpolation to form a continuous reference path.
4. The method for vehicle autopilot global path planning of claim 1 wherein said sampling the multi-dimensional state quantities in the continuous reference path based on lateral-longitudinal decoupling and generating a dynamically viable track cluster comprises:
respectively acquiring longitudinal multi-dimensional state quantity and transverse multi-dimensional state quantity of the current vehicle position and the target point position in the continuous reference path;
according to the longitudinal multi-dimensional state quantity and the transverse multi-dimensional state quantity, a plurality of groups of longitudinal polynomial equations and a plurality of groups of transverse polynomial equations are obtained through calculation;
And obtaining a plurality of dynamic feasible track clusters according to the plurality of sets of longitudinal polynomial equations and the plurality of sets of transverse polynomial equations.
5. The method of claim 4, wherein obtaining a plurality of dynamically viable track clusters from the plurality of sets of longitudinal polynomial equations and the plurality of sets of transverse polynomial equations comprises:
selecting a set of longitudinal polynomial equations, calculating each parameter value in the set of longitudinal polynomial equations, and substituting one parameter value into a set of transverse polynomial equations to obtain a transverse point set;
converting the transverse point set into a dynamic feasible track according to a Cartesian coordinate system;
traversing the other sets of longitudinal polynomial equations and the other sets of transverse polynomial equations in sequence, and executing the steps to obtain a plurality of dynamic feasible track clusters.
6. The method for planning an automatic global path for driving a vehicle according to claim 1, wherein the calculating the total cost value of each track in the dynamically viable track cluster according to a preset cost function comprises:
acquiring multi-dimensional information of each track in a plurality of dynamic feasible track clusters;
calculating the child value corresponding to each piece of dimension information respectively;
Calculating the total cost value of each track according to the offspring value and the cost function;
the cost function is:
F＝W 1 f 1 +W 2 f 2 +W 3 f 3 +…+W n f n
wherein F is the total cost value of any track A in a plurality of dynamic feasible track clusters, and W is n For the cost weight coefficient of track A in the nth dimension, the f n Is the child value of trace a in the nth dimension.
7. The method for planning an automatic global path for driving a vehicle according to claim 1, wherein before calculating the total cost value of each track in the dynamically viable track cluster according to a preset cost function, the method further comprises:
acquiring track point information in each track in the dynamic feasible track cluster;
judging whether target tracks with the multi-dimensional state quantity larger than the corresponding multi-dimensional state standard quantity exist in the track point information or not; if the target track exists in each track, deleting the target track from the dynamic feasible track cluster;
and if the target track does not exist in each track, the target track is reserved.
8. A vehicle autopilot global path planning system, the system comprising:
the global path planning module (1) is used for acquiring the current vehicle position and the target point position, and planning a global reference path from the vehicle position to the target point position in a preset electronic map, wherein the global reference path consists of global reference track points;
The path smoothing processing module (2) is used for dynamically smoothing the global reference track points to obtain a continuous reference path; the track cluster acquisition module (3) is used for sampling and calculating the multi-dimensional state quantity in the continuous reference path based on transverse and longitudinal decoupling and generating a dynamic feasible track cluster;
the cost value calculation module (4) is used for calculating the total cost value of each track in the dynamic feasible track cluster according to a preset cost function;
and the optimal path selection module (5) is used for selecting the track with the minimum total cost value as the optimal running track of the current vehicle.
9. A computer readable storage medium storing instructions which, when executed, perform the method steps of any one of claims 1 to 7.
10. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310190314.1A CN116360426A (en) | 2023-02-24 | 2023-02-24 | Global path planning method, system, medium and equipment for automatic driving of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310190314.1A CN116360426A (en) | 2023-02-24 | 2023-02-24 | Global path planning method, system, medium and equipment for automatic driving of vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116360426A true CN116360426A (en) | 2023-06-30 |
Family
ID=86917961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310190314.1A Pending CN116360426A (en) | 2023-02-24 | 2023-02-24 | Global path planning method, system, medium and equipment for automatic driving of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116360426A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117311368A (en) * | 2023-11-23 | 2023-12-29 | 武汉光昱明晟智能科技有限公司 | Automatic pre-marking robot system and operation method thereof |
| CN117555340A (en) * | 2024-01-12 | 2024-02-13 | 北京集度科技有限公司 | Path planning method and related device |
-
2023
- 2023-02-24 CN CN202310190314.1A patent/CN116360426A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117311368A (en) * | 2023-11-23 | 2023-12-29 | 武汉光昱明晟智能科技有限公司 | Automatic pre-marking robot system and operation method thereof |
| CN117311368B (en) * | 2023-11-23 | 2024-04-09 | 武汉光昱明晟智能科技有限公司 | Automatic pre-marking robot system and operation method thereof |
| CN117555340A (en) * | 2024-01-12 | 2024-02-13 | 北京集度科技有限公司 | Path planning method and related device |
| CN117555340B (en) * | 2024-01-12 | 2024-04-09 | 北京集度科技有限公司 | Path planning method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116360426A (en) | Global path planning method, system, medium and equipment for automatic driving of vehicle | |
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| US20190079528A1 (en) | Dynamic programming and gradient descent based decision and planning for autonomous driving vehicles | |
| CN110276834B (en) | Construction method of laser point cloud map, terminal and readable storage medium | |
| WO2022056770A1 (en) | Path planning method and path planning apparatus | |
| JP7103161B2 (en) | Map information system | |
| WO2022088104A1 (en) | Method and apparatus for determining point cloud set corresponding to target object | |
| CN112256037B (en) | Control method and device applied to automatic driving, electronic equipment and medium | |
| CN110288154A (en) | Speed predicting method, device, equipment and medium | |
| US20230342520A1 (en) | Traffic simulation conversion method and apparatus, and computer device and storage medium | |
| CN111260092A (en) | System and method for predicting object arrival times | |
| CN113494917A (en) | Map construction method and system, method for making navigation strategy and storage medium | |
| CN109814568B (en) | Method and device for generating speed track of unmanned vehicle and storage medium | |
| CN113050660B (en) | Error compensation method, error compensation device, computer equipment and storage medium | |
| CN113033925B (en) | Apparatus, electronic device, and medium for controlling travel of autonomous vehicle | |
| CN116088538B (en) | Vehicle track information generation method, device, equipment and computer readable medium | |
| CN113885496B (en) | Intelligent driving simulation sensor model and intelligent driving simulation method | |
| CN113269168B (en) | Obstacle data processing method and device, electronic equipment and computer readable medium | |
| CN113320544B (en) | Vehicle driving behavior planning method and device, electronic equipment and storage medium | |
| CN115583254A (en) | Path planning method, device and equipment and automatic driving vehicle | |
| CN114419758A (en) | Vehicle following distance calculation method and device, vehicle and storage medium | |
| CN113119999A (en) | Method, apparatus, device, medium, and program product for determining automatic driving characteristics | |
| CN113432618A (en) | Trajectory generation method and apparatus, computing device and computer-readable storage medium | |
| CN115123227A (en) | Lane changing decision method and device and vehicle | |
| CN111928870A (en) | Method and device for planning driving route, computing equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |