CN114237229B - Unstructured road work vehicle path planning method based on empirical path fitting - Google Patents
Unstructured road work vehicle path planning method based on empirical path fitting Download PDFInfo
- Publication number
- CN114237229B CN114237229B CN202111420539.9A CN202111420539A CN114237229B CN 114237229 B CN114237229 B CN 114237229B CN 202111420539 A CN202111420539 A CN 202111420539A CN 114237229 B CN114237229 B CN 114237229B
- Authority
- CN
- China
- Prior art keywords
- path
- point
- planning
- local
- loading
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000013598 vector Substances 0.000 claims abstract description 91
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 238000000926 separation method Methods 0.000 claims description 73
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 230000002441 reversible effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 6
- 230000009467 reduction Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012216 screening 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application discloses an unstructured road work vehicle path planning method based on empirical path fitting, comprising the following steps: determining a path planning point on the artificial annular experience path and tangential direction vectors of the path planning point based on the artificial annular experience path and the set loading/unloading point; calculating a local path plan between the loading/unloading point M and the path planning point according to the loading/unloading point, the path planning point and the tangential direction vector; calculating and selecting a local path plan corresponding to a minimum value in the maximum curvature values of each local path plan, and recording the local path plan as an optimal local path; and calculating and selecting an optimal local path corresponding to the minimum value in the evaluation values of the optimal local paths corresponding to the path planning points and the artificial annular experience path to form the optimal planning path. Through the technical scheme in the application, the implementation difficulty of the path planning of the unstructured road operation vehicle is reduced, and the operation efficiency of the automatic driving of the operation vehicle is improved.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to an unstructured road work vehicle path planning method based on empirical path fitting.
Background
In recent years, the automatic driving technology is rapidly developed, and particularly, various automatic driving technologies are continuously developed in the traffic scene of a structured road such as an urban highway. However, the popularity of the automatic driving technology on the structured road is temporarily difficult, and the main appearance is that the traffic scene contains a large number of other traffic participants such as manned vehicles, pedestrians, bicycles and the like, so that the perception and decision algorithm difficulty and complexity of the automatic driving automobile are high, and the actual running effect is poor.
In contrast, for unstructured roads, in particular traffic scenes in which routes such as factories, wharfs, warehouses, worksites, etc. are relatively fixed, scenes are relatively single and there are no other traffic participants, the automatic driving operation generally has the following features:
firstly, an automatic driving vehicle usually bears a round trip transportation task in a warehouse, a wharf, a factory or a construction site, and the same batch of operation routes are relatively fixed;
second, temporary obstacle avoidance behavior in autopilot trajectory planning may be disregarded because there are no other traffic participants in the closed environment.
In the prior art, the following problems generally exist in the automatic driving scheme under the unstructured road traffic scene in the enclosed environment:
1. the path planning of the working vehicle still follows an automatic driving scheme suitable for the structured road in the scene, and the automatic driving scheme of the structured road depends on a high-precision map and complex fusion perception positioning information, so that the hardware and service cost is too high; when the unstructured road work vehicle path is planned, each transportation operation needs to re-plan the route according to the whole flow, and temporarily adjust the route for a plurality of times according to the action information of the real-time traffic participants, so that a large amount of sensors and computing resources are consumed, and the manual experience path which is easy to provide in the scene cannot be utilized.
2. The route planning result obtained by the existing route planning method only usually considers total distance, total time and the like, and is insufficient in consideration of factors such as transportation cost, route safety degree, transportation operation efficiency and the like of transportation operation under an unstructured road scene in a closed environment.
3. Although the routes of the same batch of work of the work vehicle in the unstructured road scene in the enclosed environment are relatively fixed, the positions of the loading/unloading points of the work vehicle are changed along with the successive transportation and the carrying of cargoes, but the existing automatic driving scheme is not considered. In addition, the steering vector of the loading/unloading point has great influence on the convenience degree of loading and unloading goods and the driving route during the return, for example, the steering vector of the steering point is not convenient for unloading the goods, and the steering vector of the steering point also needs to be reversed to drive out during the return, thereby increasing the complexity of operation and lowering the operation efficiency, and the existing automatic driving scheme is not considered seriously.
Disclosure of Invention
The purpose of the present application is: at least one problem that exists when the existing automatic driving scheme is adopted in unstructured road work vehicle path planning is solved.
The technical scheme of the application is as follows: provided is an unstructured road work vehicle path planning method based on empirical path fitting, the method comprising: step 1, based on artificial annular experience path p ref Determining a path planning point and tangential direction vectors of the path planning point on the artificial annular experience path with the set loading/unloading point M, wherein the path planning point at least comprises a separation point and a confluence point, and the tangential direction vectors at least comprise a separation tangential direction vector and a confluence tangential direction vector; step 2, calculating a local path plan between the loading/unloading point M and the path planning point according to the loading/unloading point M, the path planning point and the tangential direction vector; step 3, sequentially calculating the maximum curvature value of each local path plan, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and marking the local path plan as the optimal local path; and 4, calculating the evaluation value of the optimal local path corresponding to each path planning point, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular experience path to form the optimal planning path.
In any of the above technical solutions, further, in step 1, specifically includes: step 1.1, calculating an artificial annular experience path p ref The closest point to the loading/unloading point M is referred to as the path reference point B 0 (x B0 ，y B0 ) The method comprises the steps of carrying out a first treatment on the surface of the Step 1.2, based on Path reference Point B 0 (x B0 ，y B0 ) And a set mileage interval Deltad, in the artificial annular experience path p ref Sequentially selecting separation points and junction points at equal intervals along the forward direction and the reverse direction, forming a separation point group by the path reference points and the separation points, and forming a junction point group by the junction points; step 1.3, obtaining a separation Point group { B } i I=0, 1,2, each point B in n i In the artificial annular experience path p ref The tangential direction vector is referred to as the separation tangential direction vector
Step 1.4, obtaining a meeting point group { B' i I = 1,2,..' i In the artificial annular experience path p ref The tangential direction vector on the two lines is referred to as the converging tangential direction vector
In any of the above solutions, further, step 1 further includes: selecting an orientation in which the work vehicle is parked at the loading/unloading point M, the process comprising in particular: step a, determining an initial head orientation vector based on the vertical direction of the line between the stacking reference point C (x C ，y C ) Manual annular empirical path p for presetting cargo stacking site distance ref The position of the furthest point; step B, based on the path reference point B 0 (x B0 ，y B0 ) Corresponding separation tangential direction vector
Selecting the vector +.>
The direction vector having an included angle smaller than 90 ° is referred to as the head direction vector, which is the direction in which the work vehicle is stopped at the loading/unloading point M.
In any of the above solutions, further, the local path planning includes an outgoing local path planning and a return local path planning, and the specific process of the outgoing local path planning in step 2 includes: step 2.1, determining the separation points B respectively i For the end point to separate tangential direction vectors
First ray l as exit direction Bi And head direction vector reverse direction ∈of loading/unloading point M as an end point>
A second ray l as an outgoing direction M And calculates a first ray l Bi And a second ray l M Intersection point P between i (x Pi ，y Pi ) Wherein the headstock orientation vector is the orientation of the work vehicle at the loading/unloading point M; step 2.2, when determining the intersection point P i Exist and intersect P i From separation point B i Is less than or equal to the distance threshold, or the intersection point P i Exist and intersect P i When the distance from the loading/unloading point M is smaller than or equal to the distance threshold value, calculating a first ray l according to a first alternative point formula Bi First alternative control point and second ray l M A second alternative control point on the first ray l is calculated according to a second alternative point formula if the first alternative control point is not the second alternative control point Bi First alternative control point and second ray l M A second alternative control point thereon; step 2.3, selecting a first alternative control point B corresponding to the same control point sequence number ij With a second alternative control point M ij Performing local path fitting, and determining a corresponding outgoing local path plan p ij 。
In any of the above technical solutions, further, the local path planning includes an outgoing local path planning and a return local path planning, and the calculating process of the maximum curvature value of the outgoing local path planning specifically includes:
calculating each outgoing local path plan p ij Is of the curvature kappa of (a) ij (t B ) Curvature κ ij (t B ) The calculation formula of (2) is as follows:
wherein y is pij ″(t B ) Planning p for outgoing local paths ij Second derivative of the ordinate function of x pij ′(t B ) Planning p for outgoing local paths ij First derivative of abscissa function of (x) pij ″(t B ) To go to a local pathDiameter plan p ij Second derivative of abscissa function of (y), y pij ′(t B ) Planning p for outgoing local paths ij First derivative of the ordinate function of t B Is a definition domain;
by means of extremum, the curvature kappa can be obtained ij (t B ) In the definition field t B ∈[0，1]A maximum curvature value within.
In any of the above technical solutions, further, the local path planning includes an outgoing local path planning and a return local path planning, and the method for forming an optimal planned path of the outgoing local path planning part specifically includes: step 4.1, calculating the optimal local path p of each outgoing path i Angle delta of the total direction change of (2) i The method comprises the steps of carrying out a first treatment on the surface of the Step 4.2, calculating the optimal local path p of each outgoing path i Mileage distance ratio r of (2) i The method comprises the steps of carrying out a first treatment on the surface of the Step 4.3, calculating the optimal local path p of each outgoing path i Path deviation degree b of (2) i The method comprises the steps of carrying out a first treatment on the surface of the Step 4.4, calculating the optimal local path p of each outgoing path i Evaluation value E of (2) i Wherein the evaluation value E i The calculation formula of (2) is as follows:
E i ＝c 1 max κ i +c 2 δ i +c 3 r i +c 4 b i
wherein, c 1 、c 2 、c 3 、c 4 Respectively, to the maximum curvature value max kappa i Angle delta of change of total direction i Mileage distance ratio r i Weight coefficient b of degree of path deviation i ；
Step 4.5, selecting a Cheng Zuiyou local path p corresponding to the minimum value in the evaluation values i As the final partial path p of the trip de Go to final local path p de The optimal planning path for the travel direction is formed at a separation point corresponding to the artificial annular experience path.
The beneficial effects of this application are:
according to the technical scheme, the artificial annular experience path and the loading/unloading points which are manually set are fitted according to a certain preset rule, and an optimal planning path is formed by selecting an optimal path and the artificial annular experience path from all curves according to the preset rule, so that the path planning of the unstructured road operation vehicle is realized, the difficulty in realizing the path planning of the unstructured road operation vehicle is reduced, the operation efficiency of automatic driving of the operation vehicle is improved, and the method has the following beneficial effects:
1. the implementation difficulty of the path planning of the working vehicle is reduced, each planned path can be determined in advance, the surrounding environment sensing is not required to be carried out by adopting a complex sensing sensor, and the off-line planning of the path of the working vehicle is realized;
2. each time the planned path is finely adjusted based on the manually set manual annular experience path and loading/unloading points, the safety and the rationality of the planned path can be ensured, the calculated amount is small, the hardware requirement is reduced, and the method is convenient to realize on a working vehicle working on an unstructured road;
3. the head orientation vector of the working vehicle during loading/unloading can be finely adjusted according to the specific position of the loading/unloading point, so that side loading/unloading is realized; the operation of driving the working vehicle is convenient, and the head orientation vector of the working vehicle does not need to be adjusted through a return stroke after loading/unloading;
4. the planned path direction smoothly transits without abrupt change, and meets the kinematic constraint of the actual vehicle.
5. The calculation and selection of the planned path fully considers the curvature of the route, the transportation distance, the deviation degree from the empirical route and the like, and optimizes the cost and efficiency of the round trip transportation operation while ensuring the accuracy of the loading/unloading points.
Drawings
The advantages of the foregoing and/or additional aspects of the present application will become apparent and readily appreciated from the description of the embodiments, taken in conjunction with the accompanying drawings, wherein:
FIG. 1 is a schematic flow chart diagram of an unstructured road work vehicle path planning method based on empirical path fitting according to one embodiment of the present application;
FIG. 2 is a schematic diagram of separation and junction selection according to one embodiment of the present application;
FIG. 3 is a schematic diagram of local path plan control point selection with intersection restriction according to one embodiment of the present application;
FIG. 4 is a schematic diagram of non-intersection limiting case local path planning control point selection according to one embodiment of the present application;
FIG. 5 is a schematic diagram of local path planning screening according to one embodiment of the present application;
FIG. 6 is a schematic diagram of the final partial path selection of the outbound and inbound paths according to one embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced otherwise than as described herein, and thus the scope of the present application is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the present embodiment provides an unstructured road work vehicle path planning method based on empirical path fitting, including:
step 1, based on artificial annular experience path p ref Determining a path planning point and tangential direction vectors of the path planning point on the artificial annular experience path with the set loading/unloading point M, wherein the path planning point at least comprises a separation point and a confluence point, and the tangential direction vectors at least comprise a separation tangential direction vector and a confluence tangential direction vector;
specifically, a manual annular empirical path p is set ref The method comprises the following steps:
p ref ＝[x ref (t)，y ref (t)]，t∈[0，1]
wherein x is ref (t) an artificial circular experience Path p ref Is the abscissa function of y ref (t) an artificial annulusEmpirical path p ref T is a position parameter satisfying t.epsilon.0, 1]。
The curve curvature is smoothly changed due to the fact that the vehicle is an experienced path of manual driving and is limited by the kinematic characteristics of the vehicle, so that the abscissa function x ref (t) and ordinate function y ref (t) continuous and derivative continuous.
It should be noted that, the starting point and the ending point of the artificial annular experience path are coincident at the origin O of coordinates, namely, the following is satisfied:
it should be noted that, each time the transporting operation, the loading/unloading point M is slightly changed with the gradual unloading or stacking of the goods, and the head direction vector most convenient for the operation
Changes may also occur.
Setting the loading/unloading point as M (x) M ，y M ) The steering vector of the work vehicle when the work vehicle is parked at the loading/unloading point M is
Wherein x is M 、y M The abscissa and ordinate of the loading/unloading point M, respectively,/->
Is a plane vector pointing to the head orientation vector of the desired vehicle when it is parked at the loading/unloading point M.
Wherein the abscissa of the loading/unloading point M and the head orientation vector of the working vehicle during the parking of the loading/unloading point M
Can be manually adjusted according to the carrying condition of the current goods, can also be determined according to the relative relation between the loading/unloading point M and the stacking reference point C, and is specifically adjustedThe method comprises the following steps:
as shown in fig. 1, stacking reference point C (x C ，y C ) Manual endless empirical path p for a stack of goods or for a desired place of stacking of goods ref The position of the furthest point, x C 、y C Respectively, its abscissa and ordinate. When loading the goods at the loading/unloading point M, loading is performed in the order from the near to the far, the loading/unloading point M gradually approaching the stacking reference point C; when unloading the load, the loading/unloading points M are progressively further from the stacking reference point C, in order from far to near.
When the loading/unloading point M is determined, the head of the working vehicle is directed to a vector
Perpendicular to the line between the loading/unloading point M and the stacking reference point C. Thus, the head orientation vector->
Can be arbitrarily specified on the premise of satisfying the following relation:
x vM (x C -x M )+y vM (y C -y M )＝0
when goods are piled up in a circular or nearly circular footprint, the method is as defined above
The side loading/unloading can be realized by realizing that the cargo stack is positioned at one side of the vehicle, the operation is convenient in the mode, and the head orientation vector does not need to be adjusted by the return stroke after loading/unloading.
The above-mentioned set artificial annular empirical path p ref Selecting and separating a plurality of separating points and junction points to form a separating point group { B } i I=0, 1,2,..n } and meeting point group { B }. i I=1, 2,..n }, and each separation point B is obtained i In the artificial annular experience path p ref The upper tangential direction vector is denoted as a separation tangential direction vector, and all the separation tangential direction vectors can be combined into a separation tangential direction vector
Each junction B' i In the artificial annular experience path p ref The upper tangential direction vector is denoted as a converging tangential direction vector, and all converging tangential direction vectors may constitute a converging tangential direction vector +.>
In the present embodiment, when i=0, the corresponding separation point B 0 Is a path reference point.
Wherein n is the number of set separation points and junction points. Separation point B i Indicating that the vehicle is moving from the origin O point to the loading/unloading point M at the separation point B i Off artificial loop empirical path p ref Adopting the position points of the new path of the local planning; likewise, junction B' i Indicating that the vehicle is at the junction B 'during the return from the loading/unloading point M to the origin of coordinates O' i Import artificial torus empirical path p ref Is a position point of the (c).
As shown in fig. 2, this embodiment further shows an implementation manner of determining a path planning point and a tangential direction vector of the path planning point, where the method includes:
step 1.1, calculating an artificial annular experience path p ref The closest point to the loading/unloading point M is referred to as the path reference point B 0 (x B0 ，y B0 ) The abscissa and the ordinate are x respectively B0 、y B0 。
Specifically, for the loading/unloading point M and the artificial loop empirical path p ref Distance function d of (2) M (t) obtaining extremum, setting distance function d M (t) the value of the argument position parameter at the minimum value is t dmin Thus the abscissa x B0 Y, ordinate B0 The calculation formula of (2) is as follows:
wherein the distance function d M The formula of (t) is:
wherein x is ref (t) is an abscissa function, y ref (t) is an ordinate function, t is a position parameter, x M 、y M The abscissa and ordinate of the loading/unloading point M, respectively.
Step 1.2, based on Path reference Point B 0 (x B0 ，y B0 ) And a set mileage interval Deltad, in the artificial annular experience path p ref And sequentially selecting separation points and junction points at equal intervals along the positive and negative directions, forming a separation point group by the path reference points and the separation points, and forming a junction point group by the junction points.
Specifically, the method for selecting the separation point and the junction point is the same, and taking the separation point as an example, the forward running direction of the vehicle is set as the forward direction, and the backward running direction of the vehicle is set as the reverse direction.
At the path reference point B 0 Along artificial circular empirical path p ref Sequentially selecting n position points as separation points according to equal mileage intervals delta d in the opposite direction of vehicle running, and sequentially marking as B 1 ，B 2 ，...，B i ，...，B n Along with the path reference point B 0 Together form a separation point group { B ] i I=0, 1,2,..n }. Wherein the separation point B i Is respectively marked as x on the abscissa and the ordinate of (2) Bi 、y Bi N is the set number of separation points, Δd is the set mileage interval, and therefore, the separation point B is the alternative i Is selected to satisfy the following equation:
wherein x is ref ′(t)、y ref 't' is the abscissa function x respectively ref (t) ordinate functionNumber y ref (t) derivative. t is t i For separation point B i In the artificial annular experience path p ref The value of the position parameter t is recorded as a separation position parameter t i The method meets the following conditions:
by numerically solving the above equation, the separation position parameter t can be recursively obtained i To obtain the value of the separation point group { B }, and i i=0, 1,2, n, the abscissa of each split point.
Setting the junction point to be B 'in turn' 1 ，B′ 2 ，...，B′ i ，…，B′ n Form the meeting point group { B' i I=1, 2,..n }, where junction B' i The abscissa and ordinate of (2) are respectively marked as x' Bi 、y′ Bi 。
Note that the junction does not include the path reference point B 0 。
Step 1.3, obtaining a separation Point group { B } i I=0, 1,2, each point B in n i In the artificial annular experience path p ref The tangential direction vector is referred to as the separation tangential direction vector
Wherein the tangential direction vector is split>
Is in a direction approaching the loading/unloading point M.
Step 1.4, obtaining a meeting point group { B' i I = 1,2,..' i In the artificial annular experience path p ref The tangential direction vector on the two lines is referred to as the converging tangential direction vector
Wherein the tangential vector is converged>
Is the direction of principle loading/unloading point M.
In the present embodiment, the tangential direction vector is separated
Corresponding to artificial annular empirical path p ref Upper separation point B i Tangential direction at (2) converging tangential direction vector +.>
Corresponding to artificial annular empirical path p ref Upper meeting point B' i Tangential direction of the part.
In particular, the tangential direction vector is separated
From separation element x vi 、y vi Composition, in the form of corresponding coordinates, of separating element x vi 、y vi The calculation formula of (2) is as follows:
similarly, the tangential vector is converged
The medium junction element x' vi 、y′ vi The calculation formula of (2) is as follows:
wherein x is ref ′(t i )、y ref ′(t i ) Respectively the abscissa function x ref (t) ordinate function y ref Derivative of (t), t' i Is the confluence point B' i In the artificial annular experience path p ref The value of the position parameter t.
On the basis of the above embodiment, the present embodiment also relates to a process of selecting an orientation in which the working vehicle is parked at the loading/unloading point M, which specifically includes:
step A, determining an initial headstock orientation vector based on the vertical direction of the connecting line between the stacking reference point C and the loading/unloading point M
Wherein stacking reference point C (x C ，y C ) Manual annular empirical path p for presetting cargo stacking site distance ref The position of the furthest point;
step B, based on the path reference point B 0 (x B0 ，y B0 ) Corresponding separation tangential direction vector
Selecting the vector +.>
The direction vector having an included angle smaller than 90 ° is referred to as the head direction vector, which is the direction in which the work vehicle is stopped at the loading/unloading point M.
Specifically, the vertical direction of the line between the stacking reference point C and the loading/unloading point M includes two directions, and thus, the initial head orientation vector
And a path reference point B 0 (x B0 ，y B0 ) Corresponding separation tangential direction vector->
The included angle between the two steering angles can be divided into two cases of more than 90 degrees and less than or equal to 90 degrees, so that the local path planning is relatively easy, the operation that the operation vehicle is required to complete a large-angle steering operation is avoided, and therefore, an initial head orientation vector is selected>
Vector of middle and separation tangential direction->
The direction vector with an included angle smaller than 90 DEG is named as the head direction vector +.>
So that the head orientation vector of the finally selected working vehicle when it is parked at the loading/unloading point M +.>
And a separation tangential direction vector->
At an acute angle.
And 2, calculating a local path plan between the loading/unloading point M and the path planning point according to the loading/unloading point M, the path planning point and the tangential direction vector, wherein the local path plan comprises an outgoing local path plan and a return local path plan.
Specifically, for each of the separation points B determined in the above embodiment i Meeting point B' i M times of local path planning are needed to obtain an outgoing local path planning and a return local path planning, and then an optimal local path is selected.
Note that the calculation modes of the forward local path planning and the return local path planning are the same, and the separation point B is now pointed at i The path plan to Cheng Jubu of (c) is illustrated as an example.
Step 2.1, determining the separation points B respectively i For the end point to separate tangential direction vectors
First ray l as exit direction Bi Taking loading/unloading point M as an end point, and taking the headstock as a vector reverse direction- & lt/EN & gt>
A second ray l as an outgoing direction M And calculates a first ray l Bi And a second ray l M Intersection point P between i (x Pi ，y Pi ) Wherein x is Pi 、y Pi Respectively are intersection points P i And the abscissa and ordinate of (c). />
Specifically, first ray l is first of all Bi And a second ray l M Expressed in the form of the following parametric equation:
t is in 1 、t 2 Respectively the first rays l Bi And a second ray l M And satisfies t 1 ≥0，t 2 ≥0。
Then, the parameters t of the ray equation are obtained simultaneously 1 、t 2 Is defined by the equation:
[x Bi ，y Bi ]+t 1 [x vi ，y vi ]＝[x M ，y M ]-t 2 [x vM ，y vM ]
solving the equation to obtain the ray equation parameter t 1 、t 2 Is then brought back to the first ray l Bi Or a second ray l M The intersection point P can be obtained in the parameter equation of (1) i Transverse and longitudinal of (2) coordinate x Pi 、y Pi ：
It should be noted that when the above equation is not solved or t cannot be satisfied at the same time 1 Not less than 0 and t 2 When not less than 0, the intersection point P is indicated i The dots are not present.
Step 2.2, when determining the intersection point P i Exist and intersect P i From separation point B i Is less than or equal to a distance threshold, or,
intersection point P i Exist and intersect P i When the distance from the loading/unloading point M is smaller than or equal to the distance threshold value, calculating a first ray l according to a first alternative point formula Bi First alternative control point and second ray l M A second alternative control point on the first ray l is calculated according to a second alternative point formula if the first alternative control point is not the second alternative control point Bi First alternative control point and second ray l M A second alternative control point on the display.
Specifically, if the intersection point P i Exists, calculate the intersection point P i To separation point B i Is a first distance |P i B i I and intersection P i Second distance |P to loading/unloading point M i M| and the corresponding calculation formula is as follows:
judging the first distance |P i B i I or second distance |p i Whether M| satisfies |P i B i mDeltal or P i M is less than or equal to mDeltal, wherein mDeltal is a set distance threshold, M is the number of alternative control points, and Deltal is a set distance interval of the alternative control points.
If so, the situation is referred to as an intersection limitation situation, otherwise, the situation is referred to as a non-intersection limitation situation.
In the first ray l Bi Selecting m first alternative control points to form and separate points B i Corresponding first alternative control point group { B ij I j=1, 2,., m }; in the second ray l M Selecting m second alternative control points to form and separate points B i Corresponding second alternative control point group { M } ij I j=1, 2,..m }. First alternative control Point B ij Is respectively marked as x on the abscissa and the ordinate of (2) Bij 、y Bij A second alternative control point M ij Is respectively marked as x on the abscissa and the ordinate of (2) Mij 、y Mij 。
As shown in FIG. 3, in the case of intersection limitation, the first alternative controlPoint B ij Second alternative control point M ij Is calculated from the first candidate point formula:
where j is the control point number, j=1, 2. In the case of intersection limitation, the mth first alternative control point Bim and the mth second alternative control point M im With the intersection point P i And (5) overlapping.
As shown in FIG. 4, in the non-intersection limiting case, a first alternative control point B ij Second alternative control point M ij Is calculated from the second alternative point formula:
step 2.3, selecting a first alternative control point B corresponding to the same control point sequence number ij With a second alternative control point M ij Performing local path fitting by adopting a third-order Bezier curve method, and determining a corresponding outgoing local path plan p ij 。
Specifically, after traversing all values of the control point sequence number j, the slave separation point B can be obtained i Out-of-path partial path planning p to loading/unloading point M ij Can form a set { p } of local paths of going-through ij |j＝1，2，...，m}。
The fitting of the going local path planning can adopt a third-order Bezier curve method. The method comprises the following steps: select separation point B i (x Bi ，y Bi ) As a starting pointA start point, a j-th first alternative control point B ij (x Bij ，y Bij ) And a second alternative control point M ij (x Mij ，y Mij ) Load/unload point M (x M ，y M ) As an ending point, performing third-order Bezier curve fitting, wherein the fitting formula is as follows:
wherein x is pij (t B ) Planning p for outgoing local paths ij Is the abscissa function of y pij (t B ) Planning p for outgoing local paths ij Is the ordinate function of t B Planning p for outgoing local paths ij Position parameter of (c) satisfies t B ∈[0，1]。
Through the curve fitting, the planned local path curve is smooth and the curvature is continuously changed; p is p ij At B i Tangential direction and empirical path p ref At B i The tangential directions of the positions are the same, so that seamless smooth transition from the experience path to the planning path is realized; p is p ij Tangential direction at point M and
the same meets the parking direction requirement of the loading/unloading point M, and also enables seamless smooth transition of the forward path planning and the return path planning.
And step 3, sequentially calculating the maximum curvature value of each local path plan, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and recording the local path plan as the optimal local path.
Specifically, as shown in FIG. 5, taking the path of Cheng Jubu as an example, at the separation point B i Set of partial paths { p } going to load/unload point M ij Selecting a curve with the smallest value in the maximum curvature values as a separation point B from the values of I j=1, 2 i A partial path p to Cheng Zuiyou separating the load/unload point M i 。
At each of the outbound officesPart path planning p ij Is of the curvature kappa of (a) ij (t B ) When the method is used, the corresponding calculation formula is as follows:
wherein y is pij ″(t B ) Planning p for outgoing local paths ij Second derivative of the ordinate function of x pij ′(t B ) Planning p for outgoing local paths ij First derivative of abscissa function of (x) pij ″(t B ) Planning p for outgoing local paths ij Second derivative of abscissa function of (y), y pij ′(t B ) Planning p for outgoing local paths ij First derivative of the ordinate function of t B Is a definition domain;
by means of extremum, the curvature kappa can be obtained ij (t B ) In the definition field t B ∈[0，1]Maximum curvature value max kappa in ij 。
Thus, for the outbound local path group { p } ij Each of the outgoing partial path plans p in j=1, 2 ij The maximum curvature value max kappa can be obtained ij And is composed of separation point B i Maximum set of curvatures { max kappa for partial path group of forward travel to load/unload point M ij I j=1, 2,..m }. Selecting the minimum value of min { max kappa } from the set ij The local path planning curve corresponding to the i j=1, 2, & gt, m } can be used as the optimal local path p i Simultaneously recording the optimal local path p i Maximum value of curvature max kappa of curve i 。
Since the vehicle is limited by the geometry and kinematics of the vehicle while traveling, there is a minimum turning radius. Therefore, in order to facilitate the steering of the vehicle and improve the transverse control margin, a curve with the smallest maximum curvature is selected as the separation point B i Local path p of de-Cheng Zuiyou i 。
The above steps are aimed at the separation point B i For example, the outbound local path of (c). When aiming at the meeting pointB′ i When the local path of the return journey is planned, only the separation point B in the embodiment is needed i The path planning to the loading/unloading point M is changed from the loading/unloading point M to the junction point B' i Is required to be planned by the local path of the network; thus, after the above-described process, a junction B ' from the junction B ' can be obtained ' i Return optimum local path p 'of junction' i 。
And 4, calculating the evaluation value of the optimal local path corresponding to each path planning point, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular experience path to form the optimal planning path.
As shown in FIG. 6, a local path set { p } is obtained by removing Cheng Zuiyou through the above process i I=0, 1,2,..n } and the maximum set of curvatures { maxκ for each outgoing partial path plan i I=0, 1,2,..n }, and a return optimal local path set { p }' i I=1, 2,..n } and the corresponding maximum curvature set { maxκ }' i I=1, 2,..n }. Therefore, one out-going final local path p needs to be selected from n+1 out-going optimal local paths de Selecting a final local path p 'of the return from the n return optimal local path sets' re 。
To go to the final local path p ij For example, the above process specifically includes:
step 4.1, calculating the optimal local path p of each outgoing path i Angle delta of the total direction change of (2) i The formula is:
where s is the local path p to Cheng Zuiyou i Natural parameters of (i.e. s=p) i (t B )，κ i (s) is a local path p of Cheng Zuiyou with natural parameter s as argument i In calculating the intermediate curvature k i (s) in the case of the local path p, the local path p can be removed Cheng Zuiyou according to the natural parameter s i Obtaining intermediate parameter t by inverse function of (2) B I.e.
Bringing the curvature kappa back into the above ij (t B ) In the calculation formula of (2), the intermediate curvature kappa can be obtained i (s)。
Step 4.2, calculating the optimal local path p of each outgoing path i Mileage distance ratio r of (2) i Wherein, the mileage is compared with r i Defined as the local path p to Cheng Zuiyou i Curve length s i From its end point (separation point B) i Point to load/unload point M) linear distance d i Ratio of (2), namely:
r i ＝s i /d i
wherein x is pi (t B ) To go Cheng Zuiyou local path p i Is the abscissa function of y pi (t B ) To go Cheng Zuiyou local path p i Is a function of the ordinate of (c).
Step 4.3, calculating the optimal local path p of each outgoing path i Path deviation degree b of (2) i The corresponding calculation formula is:
b i ＝∫ 0 1 h i (t B )dt B
in the formula, h i (t B ) Representing the local path p to Cheng Zuiyou i The upper position parameter is the intermediate parameter t B The location point in time and the artificial loop empirical path p ref The distance between the corresponding position points is calculated as follows:
wherein t is r To and go Cheng Zuiyou local path p i The upper position parameter is the intermediate parameter t B An artificial annular empirical path p corresponding to the position point of (2) ref The position parameter of the upper position point is calculated by the following formula:
t r ＝t i +(t 0 -t i )t B
wherein t is 0 And t i Respectively are the path reference points B 0 From separation point B i In the artificial annular experience path p ref And a location parameter thereon.
Step 4.4, calculating the optimal local path p of each outgoing path i Evaluation value E of (2) i Wherein the evaluation value E i Calculated from the following evaluation functions:
E i ＝c 1 max κ i +c 2 δ i +c 3 r i +c 4 b i
wherein, c 1 、c 2 、c 3 、c 4 The weight coefficients of the maximum curvature value, the total direction change angle, the mileage distance ratio and the path deviation degree can be set and adjusted according to the actual running effect of the vehicle.
Evaluation value E of the above type i First item c of (2) 1 max κ i Reflects the local path p of the de-Cheng Zuiyou i To influence the steering angle during vehicle tracking; if the curvature is too large, the steering angle of the front wheel of the vehicle is too large, and even the range of the physical structure is exceeded; thus, this reduction contributes to vehicle steering control and improves the tracking performance and stability of the vehicle.
Second item c 2 δ i Reflects the local path p of the de-Cheng Zuiyou i The total direction change angle of the vehicle is influenced when the vehicle seeks; the overlarge angle of the total direction change indicates that the vehicle turns frequently and has large angle when running, and the vehicle walks a lot of curved roads; therefore, the reduction of the term is beneficial to steering control of the vehicle, reduction of the driving mileage of the vehicle and improvement of the transportation efficiency and economy.
Third item c 3 r i Reflects the local path p of the de-Cheng Zuiyou i The ratio of the driving mileage of the vehicle to the head-to-tail linear distance is directly determined; thus, this reduction contributes to an improvement in transportation efficiency and economy.
Fourth item c 4 b i Reflects the local path p of the de-Cheng Zuiyou i Compared with the artificial annular experience path p ref Degree of deviation of (2); and artificial circular empirical path p ref Too large deviation will lead to a decrease in driving safety; therefore, the reduction of the term contributes to improvement of safety and rationality of running of the vehicle.
Step 4.5, selecting a Cheng Zuiyou local path p corresponding to the minimum value in the evaluation values i As the final partial path p of the trip de The final partial path p of the trip de The optimal planning path for the travel direction is formed at a separation point corresponding to the artificial annular experience path.
Note that the return final local path p' re The selection process of (2) is the same as the above process, but it should be noted that the calculated position parameter t in step 4.3 is required r The formula of (2) is changed to:
t r ＝t 0 +(t′ i -t 0 )t B
by the method for planning the path of the unstructured road operation vehicle based on the empirical path fitting, the implementation difficulty of the path planning of the unstructured road operation vehicle is reduced, the operation efficiency of automatic driving of the operation vehicle is improved, and the rationality of the path planning is improved.
The technical scheme of the application is described in detail above with reference to the accompanying drawings, and the application provides an unstructured road work vehicle path planning method based on empirical path fitting, which comprises the following steps: step 1, determining a path planning point and tangential direction vectors of the path planning point on an artificial annular experience path based on the artificial annular experience path and a set loading/unloading point, wherein the path planning point at least comprises a separation point and a convergence point, and the tangential direction vectors at least comprise a separation tangential direction vector and a convergence tangential direction vector; step 2, calculating a local path plan between the loading/unloading point M and the path planning point according to the loading/unloading point, the path planning point and the tangential direction vector; step 3, sequentially calculating the maximum curvature value of each local path plan, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and marking the local path plan as the optimal local path; and 4, calculating the evaluation value of the optimal local path corresponding to each path planning point according to the maximum curvature value, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular experience path to form the optimal planning path. Through the technical scheme in the application, the implementation difficulty of the path planning of the unstructured road operation vehicle is reduced, and the operation efficiency of the automatic driving of the operation vehicle is improved.
The steps in the present application may be sequentially adjusted, combined, and pruned according to actual requirements.
The units in the device can be combined, divided and pruned according to actual requirements.
Although the present application is disclosed in detail with reference to the accompanying drawings, it is to be understood that such descriptions are merely illustrative and are not intended to limit the application of the present application. The scope of the present application is defined by the appended claims and may include various modifications, alterations, and equivalents to the invention without departing from the scope and spirit of the application.
Claims (6)
1. An unstructured road work vehicle path planning method based on empirical path fitting, which is characterized by comprising the following steps:
step 1, based on artificial annular experience path p ref Determining a path planning point on the artificial annular experience path and tangential direction vectors of the path planning point with a set loading/unloading point M, wherein the path planning point at least comprises a separation point and a convergence point, and the tangential direction vectors at least comprise a separation tangential direction vector and a convergence tangential direction vector;
step 2, calculating a local path plan between the loading/unloading point M and the path planning point according to the loading/unloading point M, the path planning point and the tangential direction vector;
step 3, sequentially calculating the maximum curvature value of each local path plan, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and marking the local path plan as an optimal local path;
and 4, calculating the evaluation value of the optimal local path corresponding to each path planning point, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular experience path to form the optimal planning path.
2. The method for planning an unstructured road working vehicle path based on empirical path fitting according to claim 1, wherein in step 1, the method specifically comprises:
step 1.1, calculating the artificial annular experience path p ref The closest point to the loading/unloading point M is referred to as the path reference point B 0 (x B0 ，y B0 )；
Step 1.2, based on the path reference point B 0 (x B0 ，y B0 ) And a set mileage interval Deltad, in the artificial annular empirical path p ref Sequentially selecting the separation points and the junction points at equal intervals along the forward direction and the reverse direction, forming a separation point group by the path reference points and the separation points, and forming a junction point group by the junction points;
step 1.3, obtaining the separation point group { B } i I=0, 1,2, each point B in n i In the artificial annular empirical path p ref The tangential direction vector on the upper surface is denoted as the separation tangential direction vector
Step 1.4, obtaining the meeting point group { B' i I = 1,2,..' i In the artificial annular empirical path p ref The tangential vector on the above is denoted as the converging tangential vector v' l 。
3. The method for unstructured road work vehicle path planning based on empirical path fitting according to claim 2, wherein said step 1 further comprises: selecting an orientation in which the work vehicle is parked at the loading/unloading point M, the process comprising in particular:
step A, determining an initial headstock orientation vector based on the vertical direction of the connecting line between the stacking reference point C and the loading/unloading point M,
wherein the stacking reference point C (x C ，y C ) To preset the distance between the goods stacking places and the manual annular experience path p ref The position of the furthest point;
step B, based on the path reference point B 0 (x B0 ，y B0 ) Corresponding separation tangential direction vector
Selecting the vector +.>
The direction vector with the included angle smaller than 90 degrees is called a head direction vector, wherein the head direction vector is the direction that the working vehicle stops at the loading/unloading point M.
4. An unstructured road work vehicle path planning method based on empirical path fitting according to claim 1, wherein said local path planning comprises an outgoing local path planning and a return local path planning, and said specific procedure of outgoing local path planning in step 2 comprises:
step 2.1, determining the separation point B i As an end point, with the separated tangential direction vector
First ray l as exit direction Bi And +.o. in the opposite direction of the head direction vector with the loading/unloading point M as the end point>
A second ray l as an outgoing direction M And calculates the first ray l Bi And the second ray l M Intersection point P between i (x Pi ，y Pi ) Wherein the head orientation vector is the orientation in which the work vehicle is parked at the loading/unloading point M;
step 2.2, when determining the intersection point P i Exists and the intersection point P i From said separation point B i Is less than or equal to a distance threshold, or,
the intersection point P i Exists and the intersection point P i When the distance from the loading/unloading point M is less than or equal to the distance threshold,
calculating a first ray l according to a first candidate point formula Bi First alternative control point and second ray l M A second alternative control point on the upper surface,
otherwise, calculating the first ray l according to the second alternative point formula Bi First alternative control point and second ray l M A second alternative control point thereon;
step 2.3, selecting a first alternative control point B corresponding to the same control point sequence number ij With a second alternative control point M ij Performing local path fitting, and determining a corresponding outgoing local path plan p ij 。
5. An unstructured road work vehicle path planning method based on empirical path fitting according to claim 1, wherein the local path planning comprises an outgoing local path planning and a return local path planning, and the calculation process of the maximum curvature value of the outgoing local path planning specifically comprises:
calculating each outgoing local path plan p ij Is of the curvature kappa of (a) ij (t B ) Said curvature κ ij (t B ) The calculation formula of (2) is as follows:
wherein y is pij ″(t B ) Planning p for outgoing local paths ij Second derivative of the ordinate function of x pij ′(t B ) Planning p for outgoing local paths ij First derivative of abscissa function of (x) pij ″(t B ) Planning p for outgoing local paths ij Second derivative of abscissa function of (y), y pij ′(t B ) Planning p for outgoing local paths ij First derivative of the ordinate function of t B Is a definition domain;
by means of extremum, the curvature kappa can be obtained ij (t B ) In the definition field t B ∈[0，1]A maximum curvature value within.
6. An unstructured road work vehicle path planning method based on empirical path fitting according to claim 5, wherein said local path planning comprises an outgoing local path planning and a return local path planning, and said method of composing an optimal planned path for said outgoing local path planning section comprises:
step 4.1, calculating the optimal local path p of each outgoing path i Angle delta of the total direction change of (2) i ；
Step 4.2, calculating the optimal local path p of each outgoing path i Mileage distance ratio r of (2) i ；
Step 4.3, calculating the optimal local path p of each outgoing path i Path deviation degree b of (2) i ；
Step 4.4, calculating the optimal local path p of each outgoing path i Evaluation value E of (2) i Wherein the evaluation value E i The calculation formula of (2) is as follows:
E i ＝c 1 max κ i +c 2 δ i +c 3 r i +c 4 b i
wherein, c 1 、c 2 、c 3 、c 4 Respectively for the maximum curvesValue max kappa i Said total direction change angle delta i The mileage distance ratio r i A weight coefficient b of the degree of path deviation i ；
Step 4.5, selecting a Cheng Zuiyou local path p corresponding to the minimum value in the evaluation values i As the final partial path p of the trip de The final partial path p of the trip de And the optimal planning path for the going direction is formed at a corresponding separation point with the artificial annular experience path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111420539.9A CN114237229B (en) | 2021-11-26 | 2021-11-26 | Unstructured road work vehicle path planning method based on empirical path fitting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111420539.9A CN114237229B (en) | 2021-11-26 | 2021-11-26 | Unstructured road work vehicle path planning method based on empirical path fitting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114237229A CN114237229A (en) | 2022-03-25 |
| CN114237229B true CN114237229B (en) | 2023-06-13 |
Family
ID=80751326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111420539.9A Active CN114237229B (en) | 2021-11-26 | 2021-11-26 | Unstructured road work vehicle path planning method based on empirical path fitting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114237229B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114839983B (en) * | 2022-04-25 | 2024-01-16 | 北京斯年智驾科技有限公司 | Automatic driving path planning method based on map connection relation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR1066157A (en) * | 1951-06-15 | 1954-06-02 | Improvements in processes and devices for the extrusion of plastics | |
| US9804603B1 (en) * | 2015-03-18 | 2017-10-31 | Ag Leader Technology | Curved path approximation in vehicle guidance systems and methods |
| CN108088456A (en) * | 2017-12-21 | 2018-05-29 | 北京工业大学 | A kind of automatic driving vehicle local paths planning method with time consistency |
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
| CN111289008A (en) * | 2020-04-28 | 2020-06-16 | 南京维思科汽车科技有限公司 | Local path planning algorithm for unmanned vehicle |
| CN111998867A (en) * | 2020-08-26 | 2020-11-27 | 上海汽车集团股份有限公司 | Vehicle path planning method and device |
| CN111998864A (en) * | 2020-08-11 | 2020-11-27 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
| CN112362074A (en) * | 2020-10-30 | 2021-02-12 | 重庆邮电大学 | Intelligent vehicle local path planning method under structured environment |
| WO2021135728A1 (en) * | 2019-12-30 | 2021-07-08 | 郑州宇通客车股份有限公司 | Determination method and device for collision prediction of autonomous vehicle |
-
2021
- 2021-11-26 CN CN202111420539.9A patent/CN114237229B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR1066157A (en) * | 1951-06-15 | 1954-06-02 | Improvements in processes and devices for the extrusion of plastics | |
| US9804603B1 (en) * | 2015-03-18 | 2017-10-31 | Ag Leader Technology | Curved path approximation in vehicle guidance systems and methods |
| CN108088456A (en) * | 2017-12-21 | 2018-05-29 | 北京工业大学 | A kind of automatic driving vehicle local paths planning method with time consistency |
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
| WO2021135728A1 (en) * | 2019-12-30 | 2021-07-08 | 郑州宇通客车股份有限公司 | Determination method and device for collision prediction of autonomous vehicle |
| CN111289008A (en) * | 2020-04-28 | 2020-06-16 | 南京维思科汽车科技有限公司 | Local path planning algorithm for unmanned vehicle |
| CN111998864A (en) * | 2020-08-11 | 2020-11-27 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
| CN111998867A (en) * | 2020-08-26 | 2020-11-27 | 上海汽车集团股份有限公司 | Vehicle path planning method and device |
| CN112362074A (en) * | 2020-10-30 | 2021-02-12 | 重庆邮电大学 | Intelligent vehicle local path planning method under structured environment |
Non-Patent Citations (1)
| Title |
|---|
| 面向低速自动驾驶车辆的避障规划研究;肖宏宇;付志强;陈慧勇;;同济大学学报(自然科学版)(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114237229A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11460311B2 (en) | Path planning method, system and device for autonomous driving | |
| CN110749333B (en) | Unmanned vehicle motion planning method based on multi-objective optimization | |
| CN111307152B (en) | Reverse generation planning method for autonomous parking path | |
| González et al. | Continuous curvature planning with obstacle avoidance capabilities in urban scenarios | |
| CN110766220A (en) | Local path planning method for structured road | |
| CN113932823A (en) | Unmanned multi-target-point track parallel planning method based on semantic road map | |
| CN110361013B (en) | Path planning system and method for vehicle model | |
| CN113916246A (en) | Unmanned obstacle avoidance path planning method and system | |
| US11142188B2 (en) | Action-based reference systems for vehicle control | |
| CN113721637B (en) | Intelligent vehicle dynamic obstacle avoidance path continuous planning method and system and storage medium | |
| US20210197819A1 (en) | Vehicle control to join route | |
| CN113619603B (en) | Method for planning turning track of double-stage automatic driving vehicle | |
| CN114237229B (en) | Unstructured road work vehicle path planning method based on empirical path fitting | |
| Hosseini et al. | Interactive path planning for teleoperated road vehicles in urban environments | |
| CN111003027A (en) | Unmanned mine car safety monitoring method and system | |
| CN111896004A (en) | Narrow passage vehicle track planning method and system | |
| CN113419534A (en) | Bezier curve-based steering road section path planning method | |
| CN115520218A (en) | Four-point turning track planning method for automatic driving vehicle | |
| CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
| CN115116220A (en) | Unmanned multi-vehicle cooperative control method for loading and unloading scene of mining area | |
| CN116465427B (en) | Intelligent vehicle lane changing obstacle avoidance path planning method based on space-time risk quantification | |
| Nagasaka et al. | Towards safe, smooth, and stable path planning for on-road autonomous driving under uncertainty | |
| Changhao et al. | An autonomous vehicle motion planning method based on dynamic programming | |
| WO2021138475A1 (en) | Vehicle control to join and depart a route | |
| CN113815645B (en) | Automatic driving behavior decision system and motion planning method suitable for annular intersection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |