CN114237229A - Unstructured road operation vehicle path planning method based on empirical path fitting - Google Patents
Unstructured road operation vehicle path planning method based on empirical path fitting Download PDFInfo
- Publication number
- CN114237229A CN114237229A CN202111420539.9A CN202111420539A CN114237229A CN 114237229 A CN114237229 A CN 114237229A CN 202111420539 A CN202111420539 A CN 202111420539A CN 114237229 A CN114237229 A CN 114237229A
- Authority
- CN
- China
- Prior art keywords
- path
- point
- planning
- local
- local path
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000013598 vector Substances 0.000 claims abstract description 99
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000000926 separation method Methods 0.000 claims description 70
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 9
- 230000036961 partial effect Effects 0.000 claims description 6
- 230000002829 reductive effect Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 6
- 230000009467 reduction Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- UELITFHSCLAHKR-UHFFFAOYSA-N acibenzolar-S-methyl Chemical compound CSC(=O)C1=CC=CC2=C1SN=N2 UELITFHSCLAHKR-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000002441 reversible effect 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
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000284 resting effect Effects 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 operation vehicle path planning method based on empirical path fitting, which comprises the following steps: determining a path planning point on the artificial annular experience path and a tangential direction vector 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 plan point according to the loading/unloading point, the path plan point and the tangential direction vector; calculating and selecting a local path plan corresponding to the minimum value in the maximum curvature values of all local path plans, and recording the local path plan as an optimal local path; and calculating and selecting the optimal local path and the artificial annular empirical path corresponding to the minimum value in the evaluation values of the optimal local paths corresponding to the path planning points to form the optimal planning path. Through the technical scheme in the application, the difficulty in realizing the path planning of the unstructured road operation vehicle is reduced, and the operation efficiency of 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 operation vehicle path planning method based on empirical path fitting.
Background
In recent years, the automatic driving technology has been rapidly developed, and particularly, in a traffic scene of a structured road such as an urban highway, various automatic driving technologies are continuously developed. However, the popularization of the automatic driving technology on such a structured road is still difficult for a while, and the main point is that a large number of other traffic participants such as manned vehicles, pedestrians, bicycles and the like are included in such a traffic scene, so that the difficulty and complexity of perception and decision algorithm of the automatic driving automobile are high, and the actual operation effect is poor.
In contrast, for unstructured roads, particularly traffic scenes where the routes of a factory floor, a dock, a warehouse, a construction site, etc. are relatively fixed, the scene is relatively single, and there are no other traffic participants, the automatic driving operation generally has the following features:
firstly, whether in a warehouse, a dock, a factory or a construction site, the automatic driving vehicle generally undertakes a round-trip transportation task, and the same batch of operation routes are relatively fixed;
secondly, as no other traffic participants exist in the closed environment, the temporary obstacle avoidance behavior in the automatic driving track planning can be disregarded.
In the prior art, the following problems generally exist in an automatic driving scheme under an unstructured road traffic scene in a closed environment:
1. the path planning of the operation vehicle in such a scene still follows an automatic driving scheme suitable for the structured road, the automatic driving scheme of the structured road mostly depends on a high-precision map and complex fusion perception and positioning information, and the hardware and service cost is too high; and when the route of the unstructured road operation vehicle is planned, the route is required to be re-planned according to the full flow in each transportation operation, and the route is temporarily adjusted for multiple times according to the action information of real-time traffic participants, so that a large amount of sensors and computing resources are consumed, and the manual experience route which is easy to provide in the scene cannot be utilized.
2. The path planning result obtained by the existing path planning method only considers the total distance, the total time and the like, and the factors of transportation cost, route safety degree, transportation operation efficiency and the like which are concerned by transportation operation under the unstructured road scene in a closed environment are not considered sufficiently.
3. Although the routes of the same batch of operation of the working vehicles in the unstructured road scene in the closed environment are relatively fixed, the positions of the loading/unloading points of the working vehicles are changed along with the successive transportation and carrying of cargos, but the existing automatic driving scheme does not give consideration. Moreover, the direction vector of the head of the loading/unloading point has great influence on the convenience of loading and unloading goods and the driving route during return, for example, the direction vector of the head of the loading/unloading point points to the goods, which is not convenient for unloading the goods, and the head of the loading/unloading point can be driven out only by backing up the car during return, so that the complexity of operation is increased and the operation efficiency is low, and the existing automatic driving scheme is not considered emphatically.
Disclosure of Invention
The purpose of this application lies in: at least one problem that exists when the existing automatic driving scheme is adopted in the path planning of the unstructured road operation vehicle is solved.
The technical scheme of the application is as follows: an unstructured road work vehicle path planning method based on empirical path fitting is provided, and comprises the following steps: step 1, based on artificial annular experience path prefDetermining a path planning point and a tangential direction vector of the path planning point on the artificial annular empirical path 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 vector at least comprises 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 plan point according to the loading/unloading point M, the path plan point and the tangential direction vector; step 3, calculating the maximum curvature values of all local path plans in sequence, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and recording the local path plan as an optimal local path; and 4, calculating evaluation values of the optimal local paths corresponding to the path planning points, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular empirical path to form the optimal planning path.
In any one of the above technical solutions, further, in step 1, the method specifically includes: step 1.1, calculating the artificial ringEmpirical path prefThe point at the upper position closest to the loading/unloading point M is designated as the path reference point B0(xB0,yB0) (ii) a Step 1.2, based on path reference point B0(xB0,yB0) And a set mileage interval Δ d in the artificial loop empirical path prefSequentially 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 { BiEach point B in | i ═ 0, 1, 2,.. times, n }iOn an artificial circular empirical path prefThe above tangential direction vector is recorded as a separate tangential direction vectorStep 1.4, obtaining a meeting point group { B'iEach point B' of 1, 2.iOn an artificial circular empirical path prefThe above tangential direction vector is recorded as a converging tangential direction vector
In any one of the above technical solutions, further, step 1 further includes: selecting an orientation for the work vehicle to stop at the loading/unloading point M, the process comprising: step A, determining an initial head orientation vector based on the vertical direction of a connecting line between a stacking reference point C and a loading/unloading point M, wherein the stacking reference point C (x)C,yC) Artificial circular empirical path p for preset distance between goods stacking placesrefThe location of the farthest point; step B, based on the path reference point B0(xB0,yB0) Corresponding separation tangent direction vectorSelecting the vector of the initial headstock orientation vector and the direction of the separation tangentThe direction vector between which the included angle is less than 90 degrees is taken as the heading vector of the vehicle headWherein the heading orientation vector is the orientation of the work vehicle at the loading/unloading point M.
In any one of the above technical solutions, further, the local path planning includes an outbound local path planning and a return local path planning, and the specific process of the outbound local path planning in step 2 includes: step 2.1, determine respectively to separate point BiAs end points, to separate tangential direction vectorsFirst ray l in the emergent directionBiAnd the opposite direction of the locomotive direction vector with the loading/unloading point M as the end pointSecond ray l in the emergent directionMAnd calculating a first ray lBiAnd a second ray lMPoint of intersection P betweeni(xPi,yPi) Wherein the heading vector is the heading for the work vehicle to stop at the loading/unloading point M; step 2.2, when the intersection point P is judgediExists and intersect point PiAnd separation point BiIs less than or equal to a distance threshold, or the intersection point PiExists and intersect point PiWhen the distance from the loading/unloading point M is less than or equal to the distance threshold value, calculating a first ray l according to a first alternative point formulaBiFirst alternative control point and second ray lMThe second alternative control point of (c), otherwise, the first ray l is calculated according to the second alternative point formulaBiFirst alternative control point and second ray lMA second alternative control point; step 2.3, selecting a first alternative control point B corresponding to the same control point serial numberijWith the second alternative control point MijPerforming local path fitting to determine a corresponding trip local path plan pij。
In any one of the above technical solutions, further, the local path planning includes an outbound local path planning and a return local path planning, and the calculation process of the maximum curvature value of the outbound local path planning specifically includes:
calculating each outbound local path plan pijCurvature k ofij(tB) Curvature kappaij(tB) The calculation formula of (2) is as follows:
in the formula, ypij″(tB) Planning p for outbound local pathijSecond derivative of the ordinate function, xpij′(tB) Planning p for outbound local pathijFirst derivative of the abscissa function, xpij″(tB) Planning p for outbound local pathijSecond derivative of the abscissa function of (a), ypij′(tB) Planning p for outbound local pathijFirst derivative of the ordinate function of, tBTo define a domain;
by way of extremum, the curvature κ may be obtainedij(tB) In the definition domain tB∈[0,1]The maximum curvature value of the inner.
In any one of the above technical solutions, further, the local path planning includes an outbound local path planning and a return local path planning, and the method for forming the optimal planned path of the outbound local path planning section specifically includes: step 4.1, calculating the optimal local path p of each journeyiTotal direction change angle delta ofi(ii) a Step 4.2, calculating the optimal local path p of each journeyiDistance ratio r ofi(ii) a Step 4.3, calculating the optimal local path p of each journeyiDegree of deviation of path bi(ii) a Step 4.4, calculating the optimal local path p of each journeyiEvaluation value E ofiWherein, the evaluation value EiThe calculation formula of (2) is as follows:
Ei=c1 max κi+c2δi+c3ri+c4bi
in the formula, c1、c2、c3、c4Respectively for the maximum curvature value max κiTotal direction change angle deltaiDistance ratio riWeight coefficient b of the degree of deviation of the pathi;
Step 4.5, selecting the optimal local path p of the journey to which the minimum value in the evaluation values correspondsiAs final partial path p of outbounddeFinal local path p of outbounddeAnd the optimal planning path is used for forming an optimal planning path in the outbound direction at a corresponding separation point with the artificial annular empirical path.
The beneficial effect of this application is:
the technical scheme in the application is that the artificial annular experience path set for people and the loading/unloading point are fitted according to a certain preset rule, and an optimal path and the artificial annular experience path are selected from all curves according to the preset rule to form an optimal planning path, so that the path planning of the unstructured road operation vehicle is realized, the realization 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 method has the following advantages:
1. the difficulty in realizing path planning of the working vehicle is reduced, the path planned each time 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 planned path is finely adjusted based on an artificial annular experience path and a loading/unloading point which are set manually, so that the safety and reasonability 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 an operating vehicle operating on an unstructured road;
3. the direction vector of the head of the working vehicle during loading/unloading can be finely adjusted according to the specific position of the loading/unloading point, so that lateral loading/unloading is realized; the direction vector of the head of the working vehicle does not need to be adjusted in a return stroke after loading/unloading while the driving operation of the working vehicle is facilitated;
4. the planning path direction smoothly transits without sudden 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 the cost and the efficiency of the back-and-forth transportation operation are optimized while the accuracy of loading/unloading points is ensured.
Drawings
The advantages of the above and/or additional aspects of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of a method for unstructured road work vehicle path planning 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 planning control point selection with intersection constraints according to an embodiment of the present application;
FIG. 4 is a schematic diagram of non-intersection-limited case local path planning control point selection according to an embodiment of the present application;
FIG. 5 is a schematic diagram of local path planning screening according to an embodiment of the present application;
fig. 6 is a schematic diagram of selection of a outbound final local path and an inbound final local path according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the present application can be more clearly understood, the present application will be described in further detail with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
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 in other ways than those described herein, and therefore the scope of the present application is not limited by the specific embodiments disclosed below.
As shown in fig. 1, the present embodiment provides an unstructured road operation vehicle path planning method based on empirical path fitting, including:
step 1, based on artificial annular experience roadDiameter prefDetermining a path planning point and a tangential direction vector of the path planning point on the artificial annular empirical path 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 vector at least comprises a separation tangential direction vector and a convergence tangential direction vector;
specifically, an artificial loop empirical path p is setrefComprises the following steps:
pref=[xref(t),yref(t)],t∈[0,1]
in the formula, xref(t) is an artificial circular empirical path prefAbscissa function of (a), yref(t) is an artificial circular empirical path prefT is a position parameter, and satisfies the condition that t belongs to [0, 1 ]]。
The curve curvature changes smoothly due to the fact that the curve is an empirical path of manual driving and is limited by the kinematic characteristics of the vehicle, and therefore the abscissa function xref(t) and the ordinate function yref(t) is continuous and the derivative is continuous.
It should be noted that the start point and the end point of the artificial circular empirical path coincide at the coordinate origin O, that is, the following are satisfied:
it should be noted that, in each transportation operation, as the goods are gradually emptied or stacked, the loading/unloading point M changes slightly, and the direction vector of the head most convenient for the operation is the vectorVariations will also occur.
Setting the load/unload point to M (x)M,yM) The heading vector of the work vehicle at the loading/unloading point M isWherein x isM、yMRespectively the abscissa and ordinate of the loading/unloading point M,is a planar vector pointing to the heading vector of the desired vehicle when resting at the loading/unloading point M.
Wherein, the horizontal and vertical coordinates of the loading/unloading point M and the direction vector of the head of the working vehicle when the loading/unloading point M is parkedThe method can be manually adjusted according to the current carrying condition of the goods, and can also be determined according to the relative relation between the loading/unloading point M and the stacking reference point C, and the specific adjustment method is as follows:
as shown in FIG. 1, the stacking reference point C (x)C,yC) For stacks of goods or desired goods stacking places from an artificial circular empirical path prefPosition of the farthest point, xC、yCRespectively the abscissa and ordinate thereof. Loading is performed in the order from the near to the far when the goods are loaded at the loading/unloading point M, which gradually approaches the stacking reference point C; when unloading the goods, loading is performed in the order from far to near, with the loading/unloading point M gradually moving away from the stacking reference point C.
After the loading/unloading point M is determined, the direction vector of the head of the working vehicle is enabledPerpendicular to the line between the loading/unloading point M and the stacking reference point C. Thus, the heading vectorThe following relationship can be arbitrarily specified:
xvM(xC-xM)+yvM(yC-yM)=0
when the goods are piled up in a circular or approximately circular land occupation manner, the goods are specified according to the methodThe cargo pile can be positioned at one side of the vehicle, so that the lateral loading/unloading can be realized, the operation is convenient, and the orientation vector of the head of the vehicle does not need to be adjusted in the return stroke after the loading/unloading.
In the above-mentioned set artificial circular experience path prefA plurality of separation points and confluence points are selected and separated to form a separation point group { BiI | -0, 1, 2.. n } and a meeting point set { B'iI 1, 2.., n }, and each separation point B is acquirediOn an artificial circular empirical path prefThe upper tangential direction vector is recorded as a separation tangential direction vector, and all the separation tangential direction vectors can be combined into a separation tangential direction vectorAnd each meeting point B'iOn an artificial circular empirical path prefThe upper tangent direction vector is recorded as a converging tangent direction vector, and all converging tangent direction vectors can form a converging tangent direction vector
In the present embodiment, when i is 0, the corresponding separation point B is0Is a path reference point.
Wherein n is the number of the set separation points and the set convergence points. Separation point BiIndicating that the vehicle is moving from the origin of coordinates O to the loading/unloading point M, at the separation point BiDeparture from artificial circular empirical path prefAdopting the position points of the new path of the local planning; likewise, meeting Point B'iIndicating that the vehicle is at a merging point B 'during the process of returning to the origin of coordinates O from the load/unload point M'iMerging into artificial circular experience path prefThe position point of (a).
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 prefUpper and loading/unloading point M being most distantThe near position point is taken as a path reference point B0(xB0,yB0) The abscissa and ordinate are x respectivelyB0、yB0。
Specifically, for the M point of loading/unloading and the artificial circular empirical path prefDistance function d ofM(t) obtaining an extremum and setting a distance function dM(t) the value of the independent variable position parameter when the minimum value is taken as tdminThus the abscissa xB0Ordinate yB0The calculation formula of (2) is as follows:
wherein the distance function dMThe formula of (t) is:
in the formula, xref(t) is a function of the abscissa, yref(t) is a function of the ordinate, t is a position parameter, xM、yMRespectively the abscissa and ordinate of the loading/unloading point M.
Step 1.2, based on path reference point B0(xB0,yB0) And a set mileage interval Δ d in the artificial loop empirical path prefAnd sequentially selecting the separation points and the merging points at equal intervals along the positive direction and the negative direction, forming a separation point group by the path reference points and the separation points, and forming a merging point group by the merging points.
Specifically, the method for selecting the separation point and the merging point is the same, and taking the selection of the separation point as an example, the forward driving direction of the vehicle is set as a forward direction, and the backward driving direction of the vehicle is set as a reverse direction.
At path reference point B0Following an artificial circular empirical path prefSequentially selecting n position points as separation points in the opposite direction of the running of the vehicle according to the equal mileage interval delta d, and sequentially marking as B1,B2,...,Bi,...,BnTogether with a path reference point B0Together form a separation point group { BiI ═ 0, 1, 2,. and n }. Wherein the separation point BiThe abscissa and the ordinate are respectively denoted as xBi、yBiN is the set number of separation points and Δ d is the set mileage interval, so the alternative separation point BiSatisfies the following equation:
in the formula, xref′(t)、yref' (t) are respectively abscissa functions xref(t), ordinate function yref(t) derivative of (t). t is tiIs a separation point BiOn an artificial circular empirical path prefThe value of the above position parameter t is recorded as the separation position parameter tiSatisfies the following conditions:
by numerically solving the above equation, the separation position parameter t can be recursively obtainediTo find a separation point group { B }iI ═ 0, 1, 2,. and n } the abscissa and ordinate of each separation point.
Set merging point and sequentially record as B'1,B′2,...,B′i,…,B′nConstitute a meeting point group { B'i1, 2., n }, where meeting point B'iThe abscissa and the ordinate of (a) are x'Bi、y′Bi。
It should be noted that the merging point does not include the path reference point B0。
Step 1.3, obtaining a separation point group { BiEach point B in | i ═ 0, 1, 2,.. times, n }iOn an artificial circular empirical path prefThe above tangential direction vector is recorded as a separate tangential direction vectorWherein the vector of the tangent direction is separatedIs the direction close to the loading/unloading point M.
Step 1.4, obtaining a meeting point group { B'iEach point B' of 1, 2.iOn an artificial circular empirical path prefThe above tangential direction vector is recorded as a converging tangential direction vectorWherein the vector of the converging tangential directionIs the direction of the principle loading/unloading point M.
In this embodiment, the vector of the tangential direction is separatedCorresponding artificial circular empirical path prefUpper separation point BiTangential direction of the point, converging tangential direction vectorCorresponding artificial circular empirical path prefUpper merging point B'iIn the tangential direction of (c).
In particular, separating tangential vectorsBy separation of element xvi、yviComposition, in the form of respective coordinates, separating the elements xvi、yviThe calculation formula of (2) is as follows:
by the same token, converging the tangential direction vectorMedium confluence element x'vi、y′viThe calculation formula of (2) is as follows:
in the formula, xref′(ti)、yref′(ti) Respectively as a function of the abscissa xref(t), ordinate function yrefDerivative of (t), t'iIs a confluence point B'iOn an artificial circular empirical path prefThe value of the position parameter t.
On the basis of the above-described embodiment, the present embodiment further relates to a process for selecting an orientation of a work vehicle parked at a loading/unloading point M, the process specifically including:
step A, determining an initial head orientation vector based on the vertical direction of a connecting line between a stacking reference point C and a loading/unloading point MWherein the stacking reference point C (x)C,yC) Artificial circular empirical path p for preset distance between goods stacking placesrefThe location of the farthest point;
step B, based on the path reference point B0(xB0,yB0) Corresponding separation tangent direction vectorSelecting the vector of the initial headstock orientation vector and the direction of the separation tangentThe direction vector between which the angle is smaller than 90 ° is taken as the heading vector, wherein the heading vector is the direction in which the work vehicle stops at the loading/unloading point M.
In particular, the vertical direction to the line between the stacking reference point C and the loading/unloading point M includes two directions, and therefore the initial head orientation vectorAnd a path reference point B0(xB0,yB0) Corresponding separation tangent direction vectorThe included angle between the two can be divided into two conditions of more than 90 degrees and less than or equal to 90 degrees, in order to make the local path planning relatively easy and avoid the operation vehicle from completing a steering operation with a large angle, therefore, the initial head orientation vector is selectedVector of neutral and separated tangent directionThe direction vector between which the included angle is less than 90 degrees is taken as the heading vector of the vehicle headSo that the finally selected heading vector of the work vehicle when it is parked at M points of the loading/unloading pointAnd the vector of the separation tangent directionAt an acute angle.
And 2, calculating a local path plan between the loading/unloading point M and the path plan point according to the loading/unloading point M, the path plan point and the tangential direction vector, wherein the local path plan comprises an outbound local path plan and a return local path plan.
Specifically, each separation point B determined for the above embodimentiAnd confluence point B'iAnd performing local path planning for m times to obtain a go-route local path planning and a return-route local path planning, and further selecting an optimal local path.
It should be noted that the outbound local pathThe path plan and the return local path plan are calculated in the same way, now for the split point BiThe round-trip partial path planning of (1) is explained as an example.
Step 2.1, determine respectively to separate point BiAs end points, to separate tangential direction vectorsFirst ray l in the emergent directionBiAnd the loading/unloading point M is used as the end point, and the direction of the headstock vector is reversed-Second ray l in the emergent directionMAnd calculating a first ray lBiAnd a second ray lMPoint of intersection P betweeni(xPi,yPi) Wherein x isPi、yPiAre respectively an intersection point PiThe abscissa and the ordinate of (a).
Specifically, first, the first ray l isBiAnd a second ray lMExpressed in the form of parametric equations:
in the formula t1、t2Are respectively the first ray lBiAnd a second ray lMAnd satisfies t1≥0,t2≥0。
Then simultaneously obtaining the parameter t related to the ray equation1、t2The equation of (c):
[xBi,yBi]+t1[xvi,yvi]=[xM,yM]-t2[xvM,yvM]
solving the above equation to obtain the ray equation parameter t1、t2Is then brought back to the first ray lBiOr a second ray lMIn the parameter equation of (2), the intersection point P can be obtainediAbscissa and ordinate x ofPi、yPi:
It should be noted that when the above equation is not solved, or t cannot be satisfied simultaneously1T is not less than 02When the value is more than or equal to 0, the intersection point P is indicatediThe dots are not present.
Step 2.2, when the intersection point P is judgediExists and intersect point PiAnd separation point BiIs less than or equal to a distance threshold, or,
intersection point PiExists and intersect point PiWhen the distance from the loading/unloading point M is less than or equal to the distance threshold value, calculating a first ray l according to a first alternative point formulaBiFirst alternative control point and second ray lMThe second alternative control point of (c), otherwise, the first ray l is calculated according to the second alternative point formulaBiFirst alternative control point and second ray lMThe second alternative control point of (c).
Specifically, if the point of intersection PiExistence, calculation of the intersection point PiTo the separation point BiFirst distance | PiBiI and intersection point PiSecond distance | P to Loading/unloading Point MiM, the corresponding calculation formula is as follows:
determine the first distance | PiBiOr second distance | PiWhether M | satisfies | P |iBiM delta l or | P | < oriAnd M is less than or equal to M delta l, wherein M delta l is a set distance threshold value, M is the number of the alternative control points, and delta l is the set distance interval of the alternative control points.
If so, the situation is recorded as an intersection limit situation, otherwise, the situation is recorded as a non-intersection limit situation.
In the first ray lBiSelecting m first alternative control points, forming and dividingDeparture point BiCorresponding first set of alternative control points { Bij1, 2.·, m }; in the second ray lMM second alternative control points are selected to form and separate a point BiCorresponding second set of alternative control points { M }ij1, 2.. multidot.m.. First alternative control Point BijThe abscissa and the ordinate are respectively denoted as xBij、yBijSecond alternative control point MijThe abscissa and the ordinate are respectively denoted as xMij、yMij。
As shown in FIG. 3, in the intersection limit case, the first alternative control point BijSecond alternative control point MijThe horizontal and vertical coordinates of the point are respectively calculated by a first alternative point formula:
where j is a control point number, and j is 1, 2. Under the condition of intersection point limitation, the mth first candidate control point Bim and the mth second candidate control point MimAnd point of intersection PiAnd (4) overlapping.
As shown in FIG. 4, in the non-intersection limiting case, the first alternate control point BijSecond alternative control point MijThe horizontal and vertical coordinates of the point are respectively calculated by a second alternative point formula:
step 2.3, selecting a first alternative control point B corresponding to the same control point serial numberijWith the second alternative control point MijBy using third orderBezier curve fitting to determine corresponding trip local path plan pij。
Specifically, after traversing all values of the control point sequence number j, the slave split point B can be obtainediOutbound local path plan p to load/unload point MijA set of outbound local paths { p } may be formedij|j=1,2,...,m}。
The fitting of the forward local path planning can adopt a third-order Bezier curve method. The method specifically comprises the following steps: selecting a separation point Bi(xBi,yBi) As a starting point, the jth first candidate control point Bij(xBij,yBij) And a second alternative control point Mij(xMij,yMij) A loading/unloading point M (x)M,yM) And as the termination point, performing third-order Bezier curve fitting, wherein the fitting formula is as follows:
in the formula, xpij(tB) Planning p for outbound local pathijAbscissa function of (a), ypij(tB) Planning p for outbound local pathijOrdinate function of tBPlanning p for outbound local pathijSatisfies tB∈[0,1]。
Through the curve fitting, the planned local path curve is smooth and the curvature is continuously changed; p is a radical ofijIn BiTangential direction of the point and the empirical path prefIn BiThe tangential directions of the positions are the same, and seamless smooth transition from the empirical path to the planned path is realized; p is a radical ofijTangential direction at point M andsimilarly, the requirement of the loading/unloading point M on the parking direction is met, and the forward planning path and the backward planning path are in seamless smooth transition.
And 3, sequentially calculating the maximum curvature values of the local path plans, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and recording the local path plan as an optimal local path.
Specifically, as shown in FIG. 5, the outbound partial path is planned, for example, at a point B away from the split pointiSet of outbound local paths to load/unload point M pijSelecting one curve with the minimum value from the maximum curvature values as a curve from a separation point BiSeparating the optimal local path p of the journey to the loading/unloading point Mi。
In the calculation of each outbound local path plan pijCurvature k ofij(tB) The corresponding calculation formula is as follows:
in the formula, ypij″(tB) Planning p for outbound local pathijSecond derivative of the ordinate function, xpij′(tB) Planning p for outbound local pathijFirst derivative of the abscissa function, xpij″(tB) Planning p for outbound local pathijSecond derivative of the abscissa function of (a), ypij′(tB) Planning p for outbound local pathijFirst derivative of the ordinate function of, tBTo define a domain;
by way of extremum, the curvature κ may be obtainedij(tB) In the definition domain tB∈[0,1]Inner maximum curvature value max κij。
Thus, for the outbound local path set { pijEach outbound local path plan p in 1, 2ijCan obtain the maximum curvature value max kijAnd constitute a point of departure BiSet of maximum curvatures { max κ k } for outbound local path set to load/unload point Mij1, 2.. multidot.m.. The minimum value in the set, min { max κ is selectedijThe local path planning curve corresponding to 1, 2.. and m } can be used as the optimal path planning curveLocal path piSimultaneously recording the optimal local path piMaximum curvature value max κ of curvei。
There is a minimum turning radius as the vehicle is constrained by the geometry and kinematics of the vehicle while traveling. Therefore, in order to facilitate the steering of the vehicle and improve the lateral control margin, the curve with the minimum maximum curvature is selected as the separation point BiProcessing the separated optimal local path pi。
The above steps are directed to the separation point BiThe outbound local path of (2) is exemplary. When to meeting Point B'iWhen the return local path planning is carried out, only the separation point B in the embodiment is needediRoute planning to load/unload point M is changed from load/unload point M to merge point B'iLocal path planning is carried out; thus, after the above process, the slave junction B 'can be obtained'iOf a merged return optimal local path p'i。
And 4, calculating evaluation values of the optimal local paths corresponding to the path planning points, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular empirical path to form the optimal planning path.
As shown in FIG. 6, through the above process, the optimal local path set { p for the path is obtainediI ═ 0, 1, 2,.., n } with the maximum curvature set { max κ for each traversal local path planiI | -0, 1, 2,. ·, n }, and a return-trip-optimal local path set { p'i1, 2.. n } is associated with a corresponding maximum curvature set { max κ'i1, 2. Therefore, it is necessary to select a final local path p of the outbound path from the n +1 optimal local paths of the outbound pathdeSelecting a return final local path p 'from the n return optimal local path sets're。
By the final local path p of the round tripijThe selection of the method is taken as an example, and the process specifically comprises the following steps:
step 4.1, calculating the optimal local path p of each journeyiTotal direction change angle delta ofiThe formula is as follows:
where s is the optimal local path p for the journeyiI.e. s ═ pi(tB),κi(s) is the optimal local path p of the journey with the natural parameter s as argumentiIn calculating the intermediate curvature ki(s) first, according to the natural parameter s, go to the optimal local path piObtaining the intermediate parameter t by the inverse function ofBI.e. byThen brought into the curvature kij(tB) In the calculation formula (c), the intermediate curvature k is obtainedi(s)。
Step 4.2, calculating the optimal local path p of each journeyiDistance ratio r ofiWherein the mileage-to-distance ratio riDefining an optimal local path p for the journeyiLength of curve siFrom its end point (separation point B)iPoint to loading/unloading point M) linear distance diThe ratio of (a) to (b), namely:
ri=si/di
in the formula, xpi(tB) Optimizing a local path p for a journeyiAbscissa function of (a), ypi(tB) Optimizing a local path p for a journeyiIs measured in the same manner as the ordinate function of (c).
Step 4.3, calculating the optimal local path p of each journeyiDegree of deviation of path biThe corresponding calculation formula is:
bi=∫0 1hi(tB)dtB
in the formula, hi(tB) Representing the optimal local path p of the journeyiThe upper position parameter is an intermediate parameter tBThe position point of the time and the artificial circular experience path prefThe distance of the upper corresponding position point is calculated by the following formula:
in the formula, trOptimizing a local path p for and-goiThe upper position parameter is an intermediate parameter tBThe position point of (a) corresponds to the artificial circular empirical path prefThe position parameter of the upper position point is calculated by the following formula:
tr=ti+(t0-ti)tB
in the formula, t0And tiRespectively as path reference points B0And separation point BiOn an artificial circular empirical path prefA position parameter of (a).
Step 4.4, calculating the optimal local path p of each journeyiEvaluation value E ofiWherein, the evaluation value EiCalculated from the following merit function:
Ei=c1 max κi+c2δi+c3ri+c4bi
in the formula, c1、c2、c3、c4The weight coefficients of the maximum curvature value, the total direction change angle, the mileage-to-distance ratio and the route deviation degree can be set and adjusted according to the actual driving effect of the vehicle.
Evaluation value E of the above equationiThe first item of (1)1 max κiReflects the optimal local path p of the journeyiThe maximum curvature of the steering wheel influences the steering angle of the vehicle during tracking; if the curvature is too large, the steering angle of the front wheel of the vehicle is too large and even exceeds the physical structure range; therefore, the temperature of the molten metal is controlled,this reduction facilitates vehicle steering control and improves vehicle tracking performance and stability.
Second item c2δiReflects the optimal local path p of the journeyiThe total direction change angle of the vehicle influences the steering angle and the driving mileage of the vehicle during tracking; the change angle of the total direction is too large, which indicates that the vehicle turns frequently and has a large angle when running, and the vehicle walks many curved roads; therefore, the reduction of the term is beneficial to vehicle steering control, reduces the driving range of the vehicle and improves the transportation efficiency and the economical efficiency.
Third item c3riReflects the optimal local path p of the journeyiThe ratio of the driving mileage to the head-tail straight line distance directly determines the driving mileage of the vehicle; thus, this reduction contributes to improved transport efficiency and economy.
Fourth item c4biReflects the optimal local path p of the journeyiComparing with artificial circular empirical path prefThe degree of deviation of; and an artificial circular empirical path prefToo large deviation will result in reduced driving safety; therefore, the reduction of the term contributes to improvement of safety and rationality of vehicle running.
Step 4.5, selecting the optimal local path p of the journey to which the minimum value in the evaluation values correspondsiAs final partial path p of outbounddeThe final local path p of the round tripdeAnd the optimal planning path is used for forming an optimal planning path in the outbound direction at a corresponding separation point with the artificial annular empirical path.
Note that the return final partial path p'reThe selection process is the same as the above process, but it should be noted that the position parameter t is calculated in step 4.3rThe formula of (1) is changed into:
tr=t0+(t′i-t0)tB
by the method for planning the path of the unstructured road operation vehicle based on 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 reasonability of the path planning is improved.
The technical scheme of the application is described in detail in the above with reference to the accompanying drawings, and the application provides an unstructured road operation vehicle path planning method based on empirical path fitting, and the method comprises the following steps: step 1, determining a path planning point and a tangential direction vector of the path planning point on an artificial annular empirical path based on the artificial annular empirical 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 vector at least comprises 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 plan point according to the loading/unloading point, the path plan point and the tangential direction vector; step 3, calculating the maximum curvature values of all local path plans in sequence, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and recording the local path plan as an optimal local path; and 4, calculating evaluation values of the optimal local paths corresponding to the path planning points according to the maximum curvature values, and selecting the optimal local paths corresponding to the minimum values in the evaluation values and the artificial annular empirical paths to form the optimal planning paths. Through the technical scheme in the application, the difficulty in realizing the path planning of the unstructured road operation vehicle is reduced, and the operation efficiency of automatic driving of the operation vehicle is improved.
The steps in the present application may be sequentially adjusted, combined, and subtracted according to actual requirements.
The units in the device can be merged, divided and deleted according to actual requirements.
Although the present application has been disclosed in detail with reference to the accompanying drawings, it is to be understood that such description is merely illustrative and not restrictive of the application of the present application. The scope of the present application is defined by the appended claims and may include various modifications, adaptations, and equivalents of the invention without departing from the scope and spirit of the application.
Claims (6)
1. The unstructured road operation vehicle path planning method based on empirical path fitting is characterized by comprising the following steps:
step 1, based on artificial annular experience path prefDetermining a path planning point on the artificial circular empirical path and a tangential direction vector 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 vector at least comprises 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 plan point according to the loading/unloading point M, the path plan point and the tangential direction vector;
step 3, calculating the maximum curvature values of all local path plans in sequence, selecting the local path plan corresponding to the minimum value in the maximum curvature values, and recording the local path plan as an optimal local path;
and 4, calculating evaluation values of the optimal local paths corresponding to the path planning points, and selecting the optimal local path corresponding to the minimum value in the evaluation values and the artificial annular empirical path to form the optimal planning path.
2. The unstructured road work vehicle path planning method based on empirical path fitting according to claim 1, characterized in that the step 1 specifically comprises:
step 1.1, calculating the artificial annular experience path prefThe point on the path closest to the loading/unloading point M is designated as the path reference point B0(xB0,yB0);
Step 1.2, based on the path reference point B0(xB0,yB0) And a set mileage interval Δ d at the artificial loop empirical path prefSequentially selecting the separation points and the merging points at equal intervals along the forward direction and the backward direction, forming a separation point group by the path reference points and the separation points, and forming a merging point group by the merging points;
step 1.3, obtaining the separation point group { BiEach point B in | i ═ 0, 1, 2,.. times, n }iIn the artificial circular empirical path prefThe above tangential direction vector is recorded as the separated tangential direction vector
Step 1.4, obtaining the meeting point group { B'iEach point B' of 1, 2.iIn the artificial circular empirical path prefThe above tangential direction vector is recorded as the merged tangential direction vector v'l。
3. The method for unstructured road work vehicle path planning based on empirical path fitting according to claim 2, characterized in that the step 1 further comprises: selecting an orientation for the work vehicle to stop at the loading/unloading point M, which process comprises:
step A, determining an initial head orientation vector based on the vertical direction of a connecting line between a stacking reference point C and the loading/unloading point M,
wherein the stacking reference point C (x)C,yC) The distance from the artificial circular empirical path p to the preset goods stacking placerefThe location of the farthest point;
step B, based on the path reference point B0(xB0,yB0) Corresponding separation tangent direction vectorSelecting the vector in the initial headstock orientation vector and the direction of the separation tangentThe direction vector between which the angle is smaller than 90 ° is denoted as the heading vector, wherein the heading vector is the direction in which the work vehicle stops at the loading/unloading point M.
4. The unstructured road work vehicle path planning method based on empirical path fitting according to claim 1, characterized in that the local path planning comprises an outbound local path planning and a return local path planning, and the specific process of the outbound local path planning in the step 2 comprises:
step 2.1, determining the separation point B respectivelyiVector at the separation tangent direction as end pointFirst ray l in the emergent directionBiAnd the direction opposite to the direction vector of the head with the loading/unloading point M as an end pointSecond ray l in the emergent directionMAnd calculating said first ray lBiAnd the second ray lMPoint of intersection P betweeni(xPi,yPi) Wherein the nose orientation vector is the orientation of the work vehicle at the loading/unloading point M;
step 2.2, when the intersection point P is judgediExists and the intersection point PiAnd the separation point BiIs less than or equal to a distance threshold, or,
the point of intersection PiExists and the intersection point PiWhen 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 alternative point formulaBiFirst alternative control point and second ray lMThe second alternative control point of (a) above,
otherwise, calculating the first ray l according to the second alternative point formulaBiFirst alternative control point and second ray lMA second alternative control point;
step 2.3, selecting a first alternative control point B corresponding to the same control point serial numberijWith the second alternative control point MijPerforming local path fitting to determine a corresponding trip local path plan pij。
5. The method for unstructured road work vehicle path planning based on empirical path fitting according to claim 1, characterized in that the local path planning comprises an outbound local path planning and a return local path planning, and the calculation process of the maximum curvature value of the outbound local path planning specifically comprises:
calculating each outbound local path plan pijCurvature k ofij(tB) The curvature kappaij(tB) The calculation formula of (2) is as follows:
in the formula, ypij″(tB) Planning p for outbound local pathijSecond derivative of the ordinate function, xpij′(tB) Planning p for outbound local pathijFirst derivative of the abscissa function, xpij″(tB) Planning p for outbound local pathijSecond derivative of the abscissa function of (a), ypij′(tB) Planning p for outbound local pathijFirst derivative of the ordinate function of, tBTo define a domain;
by way of extremum, the curvature κ may be obtainedij(tB) In the definition domain tB∈[0,1]The maximum curvature value of the inner.
6. The method for planning the path of the unstructured road work vehicle based on empirical path fitting according to claim 5, characterized in that the local path planning comprises an outbound local path planning and a return local path planning, and the method for forming the optimal planned path of the outbound local path planning part specifically comprises:
step 4.1, calculating the optimal local path p of each journeyiTotal direction change angle delta ofi;
Step 4.2, calculating the optimal local path p of each journeyiDistance ratio r ofi;
Step 4.3, calculating each stripLocal path p with optimal pathiDegree of deviation of path bi;
Step 4.4, calculating the optimal local path p of each journeyiEvaluation value E ofiWherein the evaluation value EiThe calculation formula of (2) is as follows:
Ei=c1 max κi+c2δi+c3ri+c4bi
in the formula, c1、c2、c3、c4Respectively for said maximum curvature value max κiThe total direction change angle δiThe mileage-to-distance ratio riWeighting factor b of the degree of deviation of the pathi;
Step 4.5, selecting the optimal local path p of the journey-going corresponding to the minimum value in the evaluation valuesiAs final partial path p of outbounddeSaid outbound final local path pdeAnd the optimal planning path in the outbound direction is formed at the corresponding separation point of the artificial annular empirical 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 true CN114237229A (en) | 2022-03-25 |
CN114237229B 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) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114839983A (en) * | 2022-04-25 | 2022-08-02 | 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 |
---|
肖宏宇;付志强;陈慧勇;: "面向低速自动驾驶车辆的避障规划研究", 同济大学学报(自然科学版), no. 1 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114839983A (en) * | 2022-04-25 | 2022-08-02 | 北京斯年智驾科技有限公司 | Automatic driving path planning method based on map connection relation |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN114237229B (en) | 2023-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113932823A (en) | Unmanned multi-target-point track parallel planning method based on semantic road map | |
CN110749333B (en) | Unmanned vehicle motion planning method based on multi-objective optimization | |
US11460311B2 (en) | Path planning method, system and device for autonomous driving | |
CN113916246B (en) | Unmanned obstacle avoidance path planning method and system | |
González et al. | Continuous curvature planning with obstacle avoidance capabilities in urban scenarios | |
Banzhaf et al. | The future of parking: A survey on automated valet parking with an outlook on high density parking | |
CN110361013B (en) | Path planning system and method for vehicle model | |
CN110766220A (en) | Local path planning method for structured road | |
US11142188B2 (en) | Action-based reference systems for vehicle control | |
CN111003027B (en) | Unmanned mine car safety monitoring method and system | |
US20210197819A1 (en) | Vehicle control to join route | |
CN115116220B (en) | Unmanned multi-vehicle cooperative control method for mining area loading and unloading scene | |
CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
CN113670305A (en) | Parking trajectory generation method and device, computer equipment and storage medium | |
CN115520218A (en) | Four-point turning track planning method for automatic driving vehicle | |
CN115079702A (en) | Intelligent vehicle planning method and system under mixed road scene | |
CN114237229A (en) | Unstructured road operation vehicle path planning method based on empirical path fitting | |
CN117141489B (en) | Intelligent vehicle track layered planning method based on minimum action quantity principle | |
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 | |
CN114265374B (en) | AGV (automatic guided vehicle) cargo access system and method for van truck | |
CN115871709A (en) | Method, device, equipment, medium and vehicle for planning station-entering track of automatic driving vehicle | |
CN115416656A (en) | Automatic driving lane changing method, device and medium based on multi-target track planning | |
CN113867357B (en) | Low-delay path planning algorithm for industrial vehicle |
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 |